diff --git a/.github/workflows/pre-commit.yml b/.github/workflows/pre-commit.yml index 74f7da19a..ac125bba5 100644 --- a/.github/workflows/pre-commit.yml +++ b/.github/workflows/pre-commit.yml @@ -53,7 +53,7 @@ jobs: working-directory: src/llama_stack_ui - name: Install pre-commit - run: python -m pip install pre-commit + run: python -m pip install 'pre-commit>=4.4.0' - name: Cache pre-commit uses: actions/cache@0057852bfaa89a56745cba8c7296529d2fc39830 # v4 diff --git a/.github/workflows/python-build-test.yml b/.github/workflows/python-build-test.yml index c605a30c3..b58f4eb69 100644 --- a/.github/workflows/python-build-test.yml +++ b/.github/workflows/python-build-test.yml @@ -30,13 +30,16 @@ jobs: activate-environment: true version: 0.7.6 - - name: Build Llama Stack package - run: | - uv build + - name: Build Llama Stack API package + working-directory: src/llama_stack_api + run: uv build - - name: Install Llama Stack package + - name: Build Llama Stack package + run: uv build + + - name: Install Llama Stack package (with api stubs from local build) run: | - uv pip install dist/*.whl + uv pip install --find-links src/llama_stack_api/dist dist/*.whl - name: Verify Llama Stack package run: | diff --git a/.pre-commit-config.yaml b/.pre-commit-config.yaml index 42cd2f5ce..c60440173 100644 --- a/.pre-commit-config.yaml +++ b/.pre-commit-config.yaml @@ -1,5 +1,5 @@ exclude: 'build/' - +minimum_pre_commit_version: 4.4.0 default_language_version: python: python3.12 node: "22" @@ -42,7 +42,7 @@ repos: hooks: - id: ruff args: [ --fix ] - exclude: ^src/llama_stack/strong_typing/.*$ + exclude: ^(src/llama_stack_api/strong_typing/.*)$ - id: ruff-format - repo: https://github.com/adamchainz/blacken-docs diff --git a/client-sdks/stainless/openapi.yml b/client-sdks/stainless/openapi.yml index 1be4af6c9..d0813de4d 100644 --- a/client-sdks/stainless/openapi.yml +++ b/client-sdks/stainless/openapi.yml @@ -998,6 +998,39 @@ paths: description: List models using the OpenAI API. parameters: [] deprecated: false + post: + responses: + '200': + description: A Model. + content: + application/json: + schema: + $ref: '#/components/schemas/Model' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Models + summary: Register model. + description: >- + Register model. + + Register a model. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterModelRequest' + required: true + deprecated: true /v1/models/{model_id}: get: responses: @@ -1032,6 +1065,36 @@ paths: schema: type: string deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Models + summary: Unregister model. + description: >- + Unregister model. + + Unregister a model. + parameters: + - name: model_id + in: path + description: >- + The identifier of the model to unregister. + required: true + schema: + type: string + deprecated: true /v1/moderations: post: responses: @@ -1662,6 +1725,32 @@ paths: description: List all scoring functions. parameters: [] deprecated: false + post: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ScoringFunctions + summary: Register a scoring function. + description: Register a scoring function. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterScoringFunctionRequest' + required: true + deprecated: true /v1/scoring-functions/{scoring_fn_id}: get: responses: @@ -1693,6 +1782,33 @@ paths: schema: type: string deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ScoringFunctions + summary: Unregister a scoring function. + description: Unregister a scoring function. + parameters: + - name: scoring_fn_id + in: path + description: >- + The ID of the scoring function to unregister. + required: true + schema: + type: string + deprecated: true /v1/scoring/score: post: responses: @@ -1781,6 +1897,36 @@ paths: description: List all shields. parameters: [] deprecated: false + post: + responses: + '200': + description: A Shield. + content: + application/json: + schema: + $ref: '#/components/schemas/Shield' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Shields + summary: Register a shield. + description: Register a shield. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterShieldRequest' + required: true + deprecated: true /v1/shields/{identifier}: get: responses: @@ -1812,6 +1958,33 @@ paths: schema: type: string deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Shields + summary: Unregister a shield. + description: Unregister a shield. + parameters: + - name: identifier + in: path + description: >- + The identifier of the shield to unregister. + required: true + schema: + type: string + deprecated: true /v1/tool-runtime/invoke: post: responses: @@ -1881,6 +2054,13 @@ paths: required: false schema: $ref: '#/components/schemas/URL' + - name: authorization + in: query + description: >- + (Optional) OAuth access token for authenticating with the MCP server. + required: false + schema: + type: string deprecated: false /v1/toolgroups: get: @@ -1907,6 +2087,32 @@ paths: description: List tool groups with optional provider. parameters: [] deprecated: false + post: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolGroups + summary: Register a tool group. + description: Register a tool group. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterToolGroupRequest' + required: true + deprecated: true /v1/toolgroups/{toolgroup_id}: get: responses: @@ -1938,6 +2144,32 @@ paths: schema: type: string deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolGroups + summary: Unregister a tool group. + description: Unregister a tool group. + parameters: + - name: toolgroup_id + in: path + description: The ID of the tool group to unregister. + required: true + schema: + type: string + deprecated: true /v1/tools: get: responses: @@ -6898,6 +7130,10 @@ components: - type: object description: >- (Optional) HTTP headers to include when connecting to the server + authorization: + type: string + description: >- + (Optional) OAuth access token for authenticating with the MCP server require_approval: oneOf: - type: string @@ -9082,6 +9318,10 @@ components: - type: object description: >- A dictionary of arguments to pass to the tool. + authorization: + type: string + description: >- + (Optional) OAuth access token for authenticating with the MCP server. additionalProperties: false required: - tool_name @@ -11420,6 +11660,152 @@ components: - hyperparam_search_config - logger_config title: SupervisedFineTuneRequest + RegisterModelRequest: + type: object + properties: + model_id: + type: string + description: The identifier of the model to register. + provider_model_id: + type: string + description: >- + The identifier of the model in the provider. + provider_id: + type: string + description: The identifier of the provider. + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: Any additional metadata for this model. + model_type: + $ref: '#/components/schemas/ModelType' + description: The type of model to register. + additionalProperties: false + required: + - model_id + title: RegisterModelRequest + ParamType: + oneOf: + - $ref: '#/components/schemas/StringType' + - $ref: '#/components/schemas/NumberType' + - $ref: '#/components/schemas/BooleanType' + - $ref: '#/components/schemas/ArrayType' + - $ref: '#/components/schemas/ObjectType' + - $ref: '#/components/schemas/JsonType' + - $ref: '#/components/schemas/UnionType' + - $ref: '#/components/schemas/ChatCompletionInputType' + - $ref: '#/components/schemas/CompletionInputType' + discriminator: + propertyName: type + mapping: + string: '#/components/schemas/StringType' + number: '#/components/schemas/NumberType' + boolean: '#/components/schemas/BooleanType' + array: '#/components/schemas/ArrayType' + object: '#/components/schemas/ObjectType' + json: '#/components/schemas/JsonType' + union: '#/components/schemas/UnionType' + chat_completion_input: '#/components/schemas/ChatCompletionInputType' + completion_input: '#/components/schemas/CompletionInputType' + RegisterScoringFunctionRequest: + type: object + properties: + scoring_fn_id: + type: string + description: >- + The ID of the scoring function to register. + description: + type: string + description: The description of the scoring function. + return_type: + $ref: '#/components/schemas/ParamType' + description: The return type of the scoring function. + provider_scoring_fn_id: + type: string + description: >- + The ID of the provider scoring function to use for the scoring function. + provider_id: + type: string + description: >- + The ID of the provider to use for the scoring function. + params: + $ref: '#/components/schemas/ScoringFnParams' + description: >- + The parameters for the scoring function for benchmark eval, these can + be overridden for app eval. + additionalProperties: false + required: + - scoring_fn_id + - description + - return_type + title: RegisterScoringFunctionRequest + RegisterShieldRequest: + type: object + properties: + shield_id: + type: string + description: >- + The identifier of the shield to register. + provider_shield_id: + type: string + description: >- + The identifier of the shield in the provider. + provider_id: + type: string + description: The identifier of the provider. + params: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The parameters of the shield. + additionalProperties: false + required: + - shield_id + title: RegisterShieldRequest + RegisterToolGroupRequest: + type: object + properties: + toolgroup_id: + type: string + description: The ID of the tool group to register. + provider_id: + type: string + description: >- + The ID of the provider to use for the tool group. + mcp_endpoint: + $ref: '#/components/schemas/URL' + description: >- + The MCP endpoint to use for the tool group. + args: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + A dictionary of arguments to pass to the tool group. + additionalProperties: false + required: + - toolgroup_id + - provider_id + title: RegisterToolGroupRequest DataSource: oneOf: - $ref: '#/components/schemas/URIDataSource' diff --git a/docs/docs/api-deprecated/index.mdx b/docs/docs/api-deprecated/index.mdx new file mode 100644 index 000000000..0da357e30 --- /dev/null +++ b/docs/docs/api-deprecated/index.mdx @@ -0,0 +1,62 @@ +--- +title: Deprecated APIs +description: Legacy APIs that are being phased out +sidebar_label: Deprecated +sidebar_position: 1 +--- + +# Deprecated APIs + +This section contains APIs that are being phased out in favor of newer, more standardized implementations. These APIs are maintained for backward compatibility but are not recommended for new projects. + +:::warning Deprecation Notice +These APIs are deprecated and will be removed in future versions. Please migrate to the recommended alternatives listed below. +::: + +## Migration Guide + +When using deprecated APIs, please refer to the migration guides provided for each API to understand how to transition to the supported alternatives. + +## Deprecated API List + +### Legacy Inference APIs +Some older inference endpoints that have been superseded by the standardized Inference API. + +**Migration Path:** Use the [Inference API](../api/) instead. + +### Legacy Vector Operations +Older vector database operations that have been replaced by the Vector IO API. + +**Migration Path:** Use the [Vector IO API](../api/) instead. + +### Legacy File Operations +Older file management endpoints that have been replaced by the Files API. + +**Migration Path:** Use the [Files API](../api/) instead. + +## Support Timeline + +Deprecated APIs will be supported according to the following timeline: + +- **Current Version**: Full support with deprecation warnings +- **Next Major Version**: Limited support with migration notices +- **Following Major Version**: Removal of deprecated APIs + +## Getting Help + +If you need assistance migrating from deprecated APIs: + +1. Check the specific migration guides for each API +2. Review the [API Reference](../api/) for current alternatives +3. Consult the [Community Forums](https://github.com/llamastack/llama-stack/discussions) for migration support +4. Open an issue on GitHub for specific migration questions + +## Contributing + +If you find issues with deprecated APIs or have suggestions for improving the migration process, please contribute by: + +1. Opening an issue describing the problem +2. Submitting a pull request with improvements +3. Updating migration documentation + +For more information on contributing, see our [Contributing Guide](../contributing/). diff --git a/docs/docs/api-experimental/index.mdx b/docs/docs/api-experimental/index.mdx new file mode 100644 index 000000000..adbd64582 --- /dev/null +++ b/docs/docs/api-experimental/index.mdx @@ -0,0 +1,128 @@ +--- +title: Experimental APIs +description: APIs in development with limited support +sidebar_label: Experimental +sidebar_position: 1 +--- + +# Experimental APIs + +This section contains APIs that are currently in development and may have limited support or stability. These APIs are available for testing and feedback but should not be used in production environments. + +:::warning Experimental Notice +These APIs are experimental and may change without notice. Use with caution and provide feedback to help improve them. +::: + +## Current Experimental APIs + +### Batch Inference API +Run inference on a dataset of inputs in batch mode for improved efficiency. + +**Status:** In Development +**Provider Support:** Limited +**Use Case:** Large-scale inference operations + +**Features:** +- Batch processing of multiple inputs +- Optimized resource utilization +- Progress tracking and monitoring + +### Batch Agents API +Run agentic workflows on a dataset of inputs in batch mode. + +**Status:** In Development +**Provider Support:** Limited +**Use Case:** Large-scale agent operations + +**Features:** +- Batch agent execution +- Parallel processing capabilities +- Result aggregation and analysis + +### Synthetic Data Generation API +Generate synthetic data for model development and testing. + +**Status:** Early Development +**Provider Support:** Very Limited +**Use Case:** Training data augmentation + +**Features:** +- Automated data generation +- Quality control mechanisms +- Customizable generation parameters + +### Batches API (OpenAI-compatible) +OpenAI-compatible batch management for inference operations. + +**Status:** In Development +**Provider Support:** Limited +**Use Case:** OpenAI batch processing compatibility + +**Features:** +- OpenAI batch API compatibility +- Job scheduling and management +- Status tracking and monitoring + +## Getting Started with Experimental APIs + +### Prerequisites +- Llama Stack server running with experimental features enabled +- Appropriate provider configurations +- Understanding of API limitations + +### Configuration +Experimental APIs may require special configuration flags or provider settings. Check the specific API documentation for setup requirements. + +### Usage Guidelines +1. **Testing Only**: Use experimental APIs for testing and development only +2. **Monitor Changes**: Watch for updates and breaking changes +3. **Provide Feedback**: Report issues and suggest improvements +4. **Backup Data**: Always backup important data when using experimental features + +## Feedback and Contribution + +We encourage feedback on experimental APIs to help improve them: + +### Reporting Issues +- Use GitHub issues with the "experimental" label +- Include detailed error messages and reproduction steps +- Specify the API version and provider being used + +### Feature Requests +- Submit feature requests through GitHub discussions +- Provide use cases and expected behavior +- Consider contributing implementations + +### Testing +- Test experimental APIs in your environment +- Report performance issues and optimization opportunities +- Share success stories and use cases + +## Migration to Stable APIs + +As experimental APIs mature, they will be moved to the stable API section. When this happens: + +1. **Announcement**: We'll announce the promotion in release notes +2. **Migration Guide**: Detailed migration instructions will be provided +3. **Deprecation Timeline**: Experimental versions will be deprecated with notice +4. **Support**: Full support will be available for stable versions + +## Provider Support + +Experimental APIs may have limited provider support. Check the specific API documentation for: + +- Supported providers +- Configuration requirements +- Known limitations +- Performance characteristics + +## Roadmap + +Experimental APIs are part of our ongoing development roadmap: + +- **Q1 2024**: Batch Inference API stabilization +- **Q2 2024**: Batch Agents API improvements +- **Q3 2024**: Synthetic Data Generation API expansion +- **Q4 2024**: Batches API full OpenAI compatibility + +For the latest updates, follow our [GitHub releases](https://github.com/llamastack/llama-stack/releases) and [roadmap discussions](https://github.com/llamastack/llama-stack/discussions). diff --git a/docs/docs/api-openai/index.mdx b/docs/docs/api-openai/index.mdx new file mode 100644 index 000000000..99f3edaa7 --- /dev/null +++ b/docs/docs/api-openai/index.mdx @@ -0,0 +1,287 @@ +--- +title: OpenAI API Compatibility +description: OpenAI-compatible APIs and features in Llama Stack +sidebar_label: OpenAI Compatibility +sidebar_position: 1 +--- + +# OpenAI API Compatibility + +Llama Stack provides comprehensive OpenAI API compatibility, allowing you to use existing OpenAI API clients and tools with Llama Stack providers. This compatibility layer ensures seamless migration and interoperability. + +## Overview + +OpenAI API compatibility in Llama Stack includes: + +- **OpenAI-compatible endpoints** for all major APIs +- **Request/response format compatibility** with OpenAI standards +- **Authentication and authorization** using OpenAI-style API keys +- **Error handling** with OpenAI-compatible error codes and messages +- **Rate limiting** and usage tracking compatible with OpenAI patterns + +## Supported OpenAI APIs + +### Chat Completions API +OpenAI-compatible chat completions for conversational AI applications. + +**Endpoint:** `/v1/chat/completions` +**Compatibility:** Full OpenAI API compatibility +**Providers:** All inference providers + +**Features:** +- Message-based conversations +- System prompts and user messages +- Function calling support +- Streaming responses +- Temperature and other parameter controls + +### Completions API +OpenAI-compatible text completions for general text generation. + +**Endpoint:** `/v1/completions` +**Compatibility:** Full OpenAI API compatibility +**Providers:** All inference providers + +**Features:** +- Text completion generation +- Prompt engineering support +- Customizable parameters +- Batch processing capabilities + +### Embeddings API +OpenAI-compatible embeddings for vector operations. + +**Endpoint:** `/v1/embeddings` +**Compatibility:** Full OpenAI API compatibility +**Providers:** All embedding providers + +**Features:** +- Text embedding generation +- Multiple embedding models +- Batch embedding processing +- Vector similarity operations + +### Files API +OpenAI-compatible file management for document processing. + +**Endpoint:** `/v1/files` +**Compatibility:** Full OpenAI API compatibility +**Providers:** Local Filesystem, S3 + +**Features:** +- File upload and management +- Document processing +- File metadata tracking +- Secure file access + +### Vector Store Files API +OpenAI-compatible vector store file operations for RAG applications. + +**Endpoint:** `/v1/vector_stores/{vector_store_id}/files` +**Compatibility:** Full OpenAI API compatibility +**Providers:** FAISS, SQLite-vec, Milvus, ChromaDB, Qdrant, Weaviate, Postgres (PGVector) + +**Features:** +- Automatic document processing +- Vector store integration +- File chunking and indexing +- Search and retrieval operations + +### Batches API +OpenAI-compatible batch processing for large-scale operations. + +**Endpoint:** `/v1/batches` +**Compatibility:** OpenAI API compatibility (experimental) +**Providers:** Limited support + +**Features:** +- Batch job creation and management +- Progress tracking +- Result retrieval +- Error handling + +## Migration from OpenAI + +### Step 1: Update API Endpoint +Change your API endpoint from OpenAI to your Llama Stack server: + +```python +# Before (OpenAI) +import openai +client = openai.OpenAI(api_key="your-openai-key") + +# After (Llama Stack) +import openai +client = openai.OpenAI( + api_key="your-llama-stack-key", + base_url="http://localhost:8000/v1" # Your Llama Stack server +) +``` + +### Step 2: Configure Providers +Set up your preferred providers in the Llama Stack configuration: + +```yaml +# stack-config.yaml +inference: + providers: + - name: "meta-reference" + type: "inline" + model: "llama-3.1-8b" +``` + +### Step 3: Test Compatibility +Verify that your existing code works with Llama Stack: + +```python +# Test chat completions +response = client.chat.completions.create( + model="llama-3.1-8b", + messages=[ + {"role": "user", "content": "Hello, world!"} + ] +) +print(response.choices[0].message.content) +``` + +## Provider-Specific Features + +### Meta Reference Provider +- Full OpenAI API compatibility +- Local model execution +- Custom model support + +### Remote Providers +- OpenAI API compatibility +- Cloud-based execution +- Scalable infrastructure + +### Vector Store Providers +- OpenAI vector store API compatibility +- Automatic document processing +- Advanced search capabilities + +## Authentication + +Llama Stack supports OpenAI-style authentication: + +### API Key Authentication +```python +client = openai.OpenAI( + api_key="your-api-key", + base_url="http://localhost:8000/v1" +) +``` + +### Environment Variables +```bash +export OPENAI_API_KEY="your-api-key" +export OPENAI_BASE_URL="http://localhost:8000/v1" +``` + +## Error Handling + +Llama Stack provides OpenAI-compatible error responses: + +```python +try: + response = client.chat.completions.create(...) +except openai.APIError as e: + print(f"API Error: {e}") +except openai.RateLimitError as e: + print(f"Rate Limit Error: {e}") +except openai.APIConnectionError as e: + print(f"Connection Error: {e}") +``` + +## Rate Limiting + +OpenAI-compatible rate limiting is supported: + +- **Requests per minute** limits +- **Tokens per minute** limits +- **Concurrent request** limits +- **Usage tracking** and monitoring + +## Monitoring and Observability + +Track your API usage with OpenAI-compatible monitoring: + +- **Request/response logging** +- **Usage metrics** and analytics +- **Performance monitoring** +- **Error tracking** and alerting + +## Best Practices + +### 1. Provider Selection +Choose providers based on your requirements: +- **Local development**: Meta Reference, Ollama +- **Production**: Cloud providers (Fireworks, Together, NVIDIA) +- **Specialized use cases**: Custom providers + +### 2. Model Configuration +Configure models for optimal performance: +- **Model selection** based on task requirements +- **Parameter tuning** for specific use cases +- **Resource allocation** for performance + +### 3. Error Handling +Implement robust error handling: +- **Retry logic** for transient failures +- **Fallback providers** for high availability +- **Monitoring** and alerting for issues + +### 4. Security +Follow security best practices: +- **API key management** and rotation +- **Access control** and authorization +- **Data privacy** and compliance + +## Implementation Examples + +For detailed code examples and implementation guides, see our [OpenAI Implementation Guide](../providers/openai.mdx). + +## Known Limitations + +### Responses API Limitations +The Responses API is still in active development. For detailed information about current limitations and implementation status, see our [OpenAI Responses API Limitations](../providers/openai_responses_limitations.mdx). + +## Troubleshooting + +### Common Issues + +**Connection Errors** +- Verify server is running +- Check network connectivity +- Validate API endpoint URL + +**Authentication Errors** +- Verify API key is correct +- Check key permissions +- Ensure proper authentication headers + +**Model Errors** +- Verify model is available +- Check provider configuration +- Validate model parameters + +### Getting Help + +For OpenAI compatibility issues: + +1. **Check Documentation**: Review provider-specific documentation +2. **Community Support**: Ask questions in GitHub discussions +3. **Issue Reporting**: Open GitHub issues for bugs +4. **Professional Support**: Contact support for enterprise issues + +## Roadmap + +Upcoming OpenAI compatibility features: + +- **Enhanced batch processing** support +- **Advanced function calling** capabilities +- **Improved error handling** and diagnostics +- **Performance optimizations** for large-scale deployments + +For the latest updates, follow our [GitHub releases](https://github.com/llamastack/llama-stack/releases) and [roadmap discussions](https://github.com/llamastack/llama-stack/discussions). diff --git a/docs/docs/api/index.mdx b/docs/docs/api/index.mdx new file mode 100644 index 000000000..7088c6c2b --- /dev/null +++ b/docs/docs/api/index.mdx @@ -0,0 +1,144 @@ +--- +title: API Reference +description: Complete reference for Llama Stack APIs +sidebar_label: Overview +sidebar_position: 1 +--- + +# API Reference + +Llama Stack provides a comprehensive set of APIs for building generative AI applications. All APIs follow OpenAI-compatible standards and can be used interchangeably across different providers. + +## Core APIs + +### Inference API +Run inference with Large Language Models (LLMs) and embedding models. + +**Supported Providers:** +- Meta Reference (Single Node) +- Ollama (Single Node) +- Fireworks (Hosted) +- Together (Hosted) +- NVIDIA NIM (Hosted and Single Node) +- vLLM (Hosted and Single Node) +- TGI (Hosted and Single Node) +- AWS Bedrock (Hosted) +- Cerebras (Hosted) +- Groq (Hosted) +- SambaNova (Hosted) +- PyTorch ExecuTorch (On-device iOS, Android) +- OpenAI (Hosted) +- Anthropic (Hosted) +- Gemini (Hosted) +- WatsonX (Hosted) + +### Agents API +Run multi-step agentic workflows with LLMs, including tool usage, memory (RAG), and complex reasoning. + +**Supported Providers:** +- Meta Reference (Single Node) +- Fireworks (Hosted) +- Together (Hosted) +- PyTorch ExecuTorch (On-device iOS) + +### Vector IO API +Perform operations on vector stores, including adding documents, searching, and deleting documents. + +**Supported Providers:** +- FAISS (Single Node) +- SQLite-Vec (Single Node) +- Chroma (Hosted and Single Node) +- Milvus (Hosted and Single Node) +- Postgres (PGVector) (Hosted and Single Node) +- Weaviate (Hosted) +- Qdrant (Hosted and Single Node) + +### Files API (OpenAI-compatible) +Manage file uploads, storage, and retrieval with OpenAI-compatible endpoints. + +**Supported Providers:** +- Local Filesystem (Single Node) +- S3 (Hosted) + +### Vector Store Files API (OpenAI-compatible) +Integrate file operations with vector stores for automatic document processing and search. + +**Supported Providers:** +- FAISS (Single Node) +- SQLite-vec (Single Node) +- Milvus (Single Node) +- ChromaDB (Hosted and Single Node) +- Qdrant (Hosted and Single Node) +- Weaviate (Hosted) +- Postgres (PGVector) (Hosted and Single Node) + +### Safety API +Apply safety policies to outputs at a systems level, not just model level. + +**Supported Providers:** +- Llama Guard (Depends on Inference Provider) +- Prompt Guard (Single Node) +- Code Scanner (Single Node) +- AWS Bedrock (Hosted) + +### Post Training API +Fine-tune models for specific use cases and domains. + +**Supported Providers:** +- Meta Reference (Single Node) +- HuggingFace (Single Node) +- TorchTune (Single Node) +- NVIDIA NEMO (Hosted) + +### Eval API +Generate outputs and perform scoring to evaluate system performance. + +**Supported Providers:** +- Meta Reference (Single Node) +- NVIDIA NEMO (Hosted) + +### Telemetry API +Collect telemetry data from the system for monitoring and observability. + +**Supported Providers:** +- Meta Reference (Single Node) + +### Tool Runtime API +Interact with various tools and protocols to extend LLM capabilities. + +**Supported Providers:** +- Brave Search (Hosted) +- RAG Runtime (Single Node) + +## API Compatibility + +All Llama Stack APIs are designed to be OpenAI-compatible, allowing you to: +- Use existing OpenAI API clients and tools +- Migrate from OpenAI to other providers seamlessly +- Maintain consistent API contracts across different environments + +## Getting Started + +To get started with Llama Stack APIs: + +1. **Choose a Distribution**: Select a pre-configured distribution that matches your environment +2. **Configure Providers**: Set up the providers you want to use for each API +3. **Start the Server**: Launch the Llama Stack server with your configuration +4. **Use the APIs**: Make requests to the API endpoints using your preferred client + +For detailed setup instructions, see our [Getting Started Guide](../getting_started/quickstart). + +## Provider Details + +For complete provider compatibility and setup instructions, see our [Providers Documentation](../providers/). + +## API Stability + +Llama Stack APIs are organized by stability level: +- **[Stable APIs](./index.mdx)** - Production-ready APIs with full support +- **[Experimental APIs](../api-experimental/)** - APIs in development with limited support +- **[Deprecated APIs](../api-deprecated/)** - Legacy APIs being phased out + +## OpenAI Integration + +For specific OpenAI API compatibility features, see our [OpenAI Compatibility Guide](../api-openai/). diff --git a/docs/docs/building_applications/playground.mdx b/docs/docs/building_applications/playground.mdx new file mode 100644 index 000000000..1afb250c4 --- /dev/null +++ b/docs/docs/building_applications/playground.mdx @@ -0,0 +1,87 @@ +--- +title: Admin UI & Chat Playground +description: Web-based admin interface and chat playground for Llama Stack +sidebar_label: Playground +sidebar_position: 10 +--- + +# Admin UI & Chat Playground + +The Llama Stack UI provides a comprehensive web-based admin interface for managing your Llama Stack server, with an integrated chat playground for interactive testing. This admin interface is the primary way to monitor, manage, and debug your Llama Stack applications. + +## Quick Start + +Launch the admin UI with: + +```bash +npx llama-stack-ui +``` + +Then visit `http://localhost:8322` to access the interface. + +## Admin Interface Features + +The Llama Stack UI is organized into three main sections: + +### 🎯 Create +**Chat Playground** - Interactive testing environment +- Real-time chat interface for testing agents and models +- Multi-turn conversations with tool calling support +- Agent SDK integration (will be migrated to Responses API) +- Custom system prompts and model parameter adjustment + +### 📊 Manage +**Logs & Resource Management** - Monitor and manage your stack +- **Responses Logs**: View and analyze agent responses and interactions +- **Chat Completions Logs**: Monitor chat completion requests and responses +- **Vector Stores**: Create, manage, and monitor vector databases for RAG workflows +- **Prompts**: Full CRUD operations for prompt templates and management +- **Files**: Forthcoming file management capabilities + +## Key Capabilities for Application Development + +### Real-time Monitoring +- **Response Tracking**: Monitor all agent responses and tool calls +- **Completion Analysis**: View chat completion performance and patterns +- **Vector Store Activity**: Track RAG operations and document processing +- **Prompt Usage**: Analyze prompt template performance + +### Resource Management +- **Vector Store CRUD**: Create, update, and delete vector databases +- **Prompt Library**: Organize and version control your prompts +- **File Operations**: Manage documents and assets (forthcoming) + +### Interactive Testing +- **Chat Playground**: Test conversational flows before production deployment +- **Agent Prototyping**: Validate agent behaviors and tool integrations + +## Development Workflow Integration + +The admin UI supports your development lifecycle: + +1. **Development**: Use chat playground to prototype and test features +2. **Monitoring**: Track system performance through logs and metrics +3. **Management**: Organize prompts, vector stores, and other resources +4. **Debugging**: Analyze logs to identify and resolve issues + +## Architecture Notes + +- **Current**: Chat playground uses Agents SDK +- **Future**: Migration to Responses API for improved performance and consistency +- **Admin Focus**: Primary emphasis on monitoring, logging, and resource management + +## Getting Started + +1. **Launch the UI**: Run `npx llama-stack-ui` +2. **Explore Logs**: Start with Responses and Chat Completions logs to understand your system activity +3. **Test in Playground**: Use the chat interface to validate your agent configurations +4. **Manage Resources**: Create vector stores and organize prompts through the UI + +For detailed setup and configuration, see the [Llama Stack UI documentation](/docs/distributions/llama_stack_ui). + +## Next Steps + +- Set up your [first agent](/docs/building_applications/agent) +- Implement [RAG functionality](/docs/building_applications/rag) +- Add [evaluation metrics](/docs/building_applications/evals) +- Configure [safety measures](/docs/building_applications/safety) diff --git a/docs/docs/concepts/apis/external.mdx b/docs/docs/concepts/apis/external.mdx index 42819a4ac..005b85647 100644 --- a/docs/docs/concepts/apis/external.mdx +++ b/docs/docs/concepts/apis/external.mdx @@ -58,7 +58,7 @@ External APIs must expose a `available_providers()` function in their module tha ```python # llama_stack_api_weather/api.py -from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec +from llama_stack_api import Api, InlineProviderSpec, ProviderSpec def available_providers() -> list[ProviderSpec]: @@ -79,7 +79,7 @@ A Protocol class like so: # llama_stack_api_weather/api.py from typing import Protocol -from llama_stack.schema_utils import webmethod +from llama_stack_api import webmethod class WeatherAPI(Protocol): @@ -151,13 +151,12 @@ __all__ = ["WeatherAPI", "available_providers"] # llama-stack-api-weather/src/llama_stack_api_weather/weather.py from typing import Protocol -from llama_stack.providers.datatypes import ( +from llama_stack_api import ( Api, ProviderSpec, RemoteProviderSpec, + webmethod, ) -from llama_stack.schema_utils import webmethod - def available_providers() -> list[ProviderSpec]: return [ diff --git a/docs/docs/concepts/apis/index.mdx b/docs/docs/concepts/apis/index.mdx index 7519f6eff..7d12478ed 100644 --- a/docs/docs/concepts/apis/index.mdx +++ b/docs/docs/concepts/apis/index.mdx @@ -7,7 +7,7 @@ sidebar_position: 1 # APIs -A Llama Stack API is described as a collection of REST endpoints. We currently support the following APIs: +A Llama Stack API is described as a collection of REST endpoints following OpenAI API standards. We currently support the following APIs: - **Inference**: run inference with a LLM - **Safety**: apply safety policies to the output at a Systems (not only model) level @@ -16,11 +16,26 @@ A Llama Stack API is described as a collection of REST endpoints. We currently s - **Scoring**: evaluate outputs of the system - **Eval**: generate outputs (via Inference or Agents) and perform scoring - **VectorIO**: perform operations on vector stores, such as adding documents, searching, and deleting documents +- **Files**: manage file uploads, storage, and retrieval +- **Telemetry**: collect telemetry data from the system - **Post Training**: fine-tune a model - **Tool Runtime**: interact with various tools and protocols -- **Responses**: generate responses from an LLM using this OpenAI compatible API. +- **Responses**: generate responses from an LLM We are working on adding a few more APIs to complete the application lifecycle. These will include: - **Batch Inference**: run inference on a dataset of inputs - **Batch Agents**: run agents on a dataset of inputs - **Batches**: OpenAI-compatible batch management for inference + + +## OpenAI API Compatibility +We are working on adding OpenAI API compatibility to Llama Stack. This will allow you to use Llama Stack with OpenAI API clients and tools. + +### File Operations and Vector Store Integration + +The Files API and Vector Store APIs work together through file operations, enabling automatic document processing and search. This integration implements the [OpenAI Vector Store Files API specification](https://platform.openai.com/docs/api-reference/vector-stores-files) and allows you to: +- Upload documents through the Files API +- Automatically process and chunk documents into searchable vectors +- Store processed content in vector databases based on the availability of [our providers](../../providers/index.mdx) +- Search through documents using natural language queries +For detailed information about this integration, see [File Operations and Vector Store Integration](../file_operations_vector_stores.md). diff --git a/docs/docs/concepts/file_operations_vector_stores.mdx b/docs/docs/concepts/file_operations_vector_stores.mdx new file mode 100644 index 000000000..6168ecf9d --- /dev/null +++ b/docs/docs/concepts/file_operations_vector_stores.mdx @@ -0,0 +1,420 @@ +# File Operations and Vector Store Integration + +## Overview + +Llama Stack provides seamless integration between the Files API and Vector Store APIs, enabling you to upload documents and automatically process them into searchable vector embeddings. This integration implements file operations following the [OpenAI Vector Store Files API specification](https://platform.openai.com/docs/api-reference/vector-stores-files). + +## Enhanced Capabilities Beyond OpenAI + +While Llama Stack maintains full compatibility with OpenAI's Vector Store API, it provides several additional capabilities that enhance functionality and flexibility: + +### **Embedding Model Specification** +Unlike OpenAI's vector stores which use a fixed embedding model, Llama Stack allows you to specify which embedding model to use when creating a vector store: + +```python +# Create vector store with specific embedding model +vector_store = client.vector_stores.create( + name="my_documents", + embedding_model="all-MiniLM-L6-v2", # Specify your preferred model + embedding_dimension=384, +) +``` + +### **Advanced Search Modes** +Llama Stack supports multiple search modes beyond basic vector similarity: + +- **Vector Search**: Pure semantic similarity search using embeddings +- **Keyword Search**: Traditional keyword-based search for exact matches +- **Hybrid Search**: Combines both vector and keyword search for optimal results + +```python +# Different search modes +results = await client.vector_stores.search( + vector_store_id=vector_store.id, + query="machine learning algorithms", + search_mode="hybrid", # or "vector", "keyword" + max_num_results=5, +) +``` + +### **Flexible Ranking Options** +For hybrid search, Llama Stack offers configurable ranking strategies: + +- **RRF (Reciprocal Rank Fusion)**: Combines rankings with configurable impact factor +- **Weighted Ranker**: Linear combination of vector and keyword scores with adjustable weights + +```python +# Custom ranking configuration +results = await client.vector_stores.search( + vector_store_id=vector_store.id, + query="neural networks", + search_mode="hybrid", + ranking_options={ + "ranker": {"type": "weighted", "alpha": 0.7} # 70% vector, 30% keyword + }, +) +``` + +### **Provider Selection** +Choose from multiple vector store providers based on your specific needs: + +- **Inline Providers**: FAISS (fast in-memory), SQLite-vec (disk-based), Milvus (high-performance) +- **Remote Providers**: ChromaDB, Qdrant, Weaviate, Postgres (PGVector), Milvus + +```python +# Specify provider when creating vector store +vector_store = client.vector_stores.create( + name="my_documents", provider_id="sqlite-vec" # Choose your preferred provider +) +``` + +## How It Works + +The file operations work through several key components: + +1. **File Upload**: Documents are uploaded through the Files API +2. **Automatic Processing**: Files are automatically chunked and converted to embeddings +3. **Vector Storage**: Chunks are stored in vector databases with metadata +4. **Search & Retrieval**: Users can search through processed documents using natural language + +## Supported Vector Store Providers + +The following vector store providers support file operations: + +### Inline Providers (Single Node) + +- **FAISS**: Fast in-memory vector similarity search +- **SQLite-vec**: Disk-based storage with hybrid search capabilities + +### Remote Providers (Hosted) + +- **ChromaDB**: Vector database with metadata filtering +- **Weaviate**: Vector database with GraphQL interface +- **Postgres (PGVector)**: Vector extensions for PostgreSQL + +### Both Inline & Remote Providers +- **Milvus**: High-performance vector database with advanced indexing +- **Qdrant**: Vector similarity search with payload filtering + +## File Processing Pipeline + +### 1. File Upload + +```python +from llama_stack import LlamaStackClient + +client = LlamaStackClient("http://localhost:8000") + +# Upload a document +with open("document.pdf", "rb") as f: + file_info = await client.files.upload(file=f, purpose="assistants") +``` + +### 2. Attach to Vector Store + +```python +# Create a vector store +vector_store = client.vector_stores.create(name="my_documents") + +# Attach the file to the vector store +file_attach_response = await client.vector_stores.files.create( + vector_store_id=vector_store.id, file_id=file_info.id +) +``` + +### 3. Automatic Processing + +The system automatically: +- Detects the file type and extracts text content +- Splits content into chunks (default: 800 tokens with 400 token overlap) +- Generates embeddings for each chunk +- Stores chunks with metadata in the vector store +- Updates file status to "completed" + +### 4. Search and Retrieval + +```python +# Search through processed documents +search_results = await client.vector_stores.search( + vector_store_id=vector_store.id, + query="What is the main topic discussed?", + max_num_results=5, +) + +# Process results +for result in search_results.data: + print(f"Score: {result.score}") + for content in result.content: + print(f"Content: {content.text}") +``` + +## Supported File Types + +The FileResponse system supports various document formats: + +- **Text Files**: `.txt`, `.md`, `.rst` +- **Documents**: `.pdf`, `.docx`, `.doc` +- **Code**: `.py`, `.js`, `.java`, `.cpp`, etc. +- **Data**: `.json`, `.csv`, `.xml` +- **Web Content**: HTML files + +## Chunking Strategies + +### Default Strategy + +The default chunking strategy uses: +- **Max Chunk Size**: 800 tokens +- **Overlap**: 400 tokens +- **Method**: Semantic boundary detection + +### Custom Chunking + +You can customize chunking when attaching files: + +```python +from llama_stack.apis.vector_io import VectorStoreChunkingStrategy + +# Attach file with custom chunking +file_attach_response = await client.vector_stores.files.create( + vector_store_id=vector_store.id, + file_id=file_info.id, + chunking_strategy=chunking_strategy, +) +``` + +**Note**: While Llama Stack is OpenAI-compatible, it also supports additional options beyond the standard OpenAI API. When creating vector stores, you can specify custom embedding models and embedding dimensions that will be used when processing chunks from attached files. + + +## File Management + +### List Files in Vector Store + +```python +# List all files in a vector store +files = await client.vector_stores.files.list(vector_store_id=vector_store.id) + +for file in files: + print(f"File: {file.filename}, Status: {file.status}") +``` + +### File Status Tracking + +Files go through several statuses: +- **in_progress**: File is being processed +- **completed**: File successfully processed and searchable +- **failed**: Processing failed (check `last_error` for details) +- **cancelled**: Processing was cancelled + +### Retrieve File Content + +```python +# Get chunked content from vector store +content_response = await client.vector_stores.files.retrieve_content( + vector_store_id=vector_store.id, file_id=file_info.id +) + +for chunk in content_response.content: + print(f"Chunk {chunk.metadata.get('chunk_index', 0)}: {chunk.text}") +``` + +## Vector Store Management + +### List Vector Stores + +Retrieve a paginated list of all vector stores: + +```python +# List all vector stores with default pagination +vector_stores = await client.vector_stores.list() + +# Custom pagination and ordering +vector_stores = await client.vector_stores.list( + limit=10, + order="asc", # or "desc" + after="vs_12345678", # cursor-based pagination +) + +for store in vector_stores.data: + print(f"Store: {store.name}, Files: {store.file_counts.total}") + print(f"Created: {store.created_at}, Status: {store.status}") +``` + +### Retrieve Vector Store Details + +Get detailed information about a specific vector store: + +```python +# Get vector store details +store_details = await client.vector_stores.retrieve(vector_store_id="vs_12345678") + +print(f"Name: {store_details.name}") +print(f"Status: {store_details.status}") +print(f"File Counts: {store_details.file_counts}") +print(f"Usage: {store_details.usage_bytes} bytes") +print(f"Created: {store_details.created_at}") +print(f"Metadata: {store_details.metadata}") +``` + +### Update Vector Store + +Modify vector store properties such as name, metadata, or expiration settings: + +```python +# Update vector store name and metadata +updated_store = await client.vector_stores.update( + vector_store_id="vs_12345678", + name="Updated Document Collection", + metadata={ + "description": "Updated collection for research", + "category": "research", + "version": "2.0", + }, +) + +# Set expiration policy +expired_store = await client.vector_stores.update( + vector_store_id="vs_12345678", + expires_after={"anchor": "last_active_at", "days": 30}, +) + +print(f"Updated store: {updated_store.name}") +print(f"Last active: {updated_store.last_active_at}") +``` + +### Delete Vector Store + +Remove a vector store and all its associated data: + +```python +# Delete a vector store +delete_response = await client.vector_stores.delete(vector_store_id="vs_12345678") + +if delete_response.deleted: + print(f"Vector store {delete_response.id} successfully deleted") +else: + print("Failed to delete vector store") +``` + +**Important Notes:** +- Deleting a vector store removes all files, chunks, and embeddings +- This operation cannot be undone +- The underlying vector database is also cleaned up +- Consider backing up important data before deletion + +## Search Capabilities + +### Vector Search + +Pure similarity search using embeddings: + +```python +results = await client.vector_stores.search( + vector_store_id=vector_store.id, + query="machine learning algorithms", + max_num_results=10, +) +``` + +### Filtered Search + +Combine vector search with metadata filtering: + +```python +results = await client.vector_stores.search( + vector_store_id=vector_store.id, + query="machine learning algorithms", + filters={"file_type": "pdf", "upload_date": "2024-01-01"}, + max_num_results=10, +) +``` + +### Hybrid Search + +[SQLite-vec](../providers/vector_io/inline_sqlite-vec.mdx), [pgvector](../providers/vector_io/remote_pgvector.mdx), and [Milvus](../providers/vector_io/inline_milvus.mdx) support combining vector and keyword search. + +## Performance Considerations + +> **Note**: For detailed performance optimization strategies, see [Performance Considerations](../providers/files/openai_file_operations_support.md#performance-considerations) in the provider documentation. + +**Key Points:** +- **Chunk Size**: 400-600 tokens for precision, 800-1200 for context +- **Storage**: Choose provider based on your performance needs +- **Search**: Optimize for your specific use case + +## Error Handling + +> **Note**: For comprehensive troubleshooting and error handling, see [Troubleshooting](../providers/files/openai_file_operations_support.md#troubleshooting) in the provider documentation. + +**Common Issues:** +- File processing failures (format, size limits) +- Search performance optimization +- Storage and memory issues + +## Best Practices + +> **Note**: For detailed best practices and recommendations, see [Best Practices](../providers/files/openai_file_operations_support.md#best-practices) in the provider documentation. + +**Key Recommendations:** +- File organization and naming conventions +- Chunking strategy optimization +- Metadata and monitoring practices +- Regular cleanup and maintenance + +## Integration Examples + +### RAG Application + +```python +# Build a RAG system with file uploads +async def build_rag_system(): + # Create vector store + vector_store = client.vector_stores.create(name="knowledge_base") + + # Upload and process documents + documents = ["doc1.pdf", "doc2.pdf", "doc3.pdf"] + for doc in documents: + with open(doc, "rb") as f: + file_info = await client.files.create(file=f, purpose="assistants") + await client.vector_stores.files.create( + vector_store_id=vector_store.id, file_id=file_info.id + ) + + return vector_store + + +# Query the RAG system +async def query_rag(vector_store_id, question): + results = await client.vector_stores.search( + vector_store_id=vector_store_id, query=question, max_num_results=5 + ) + return results +``` + +### Document Analysis + +```python +# Analyze document content through vector search +async def analyze_document(vector_store_id, file_id): + # Get document content + content = await client.vector_stores.files.retrieve_content( + vector_store_id=vector_store_id, file_id=file_id + ) + + # Search for specific topics + topics = ["introduction", "methodology", "conclusion"] + analysis = {} + + for topic in topics: + results = await client.vector_stores.search( + vector_store_id=vector_store_id, query=topic, max_num_results=3 + ) + analysis[topic] = results.data + + return analysis +``` + +## Next Steps + +- Explore the [Files API documentation](../../providers/files/files.mdx) for detailed API reference +- Check [Vector Store Providers](../providers/vector_io/index.mdx) for specific implementation details +- Review [Getting Started](../getting_started/quickstart.mdx) for quick setup instructions diff --git a/docs/docs/distributions/building_distro.mdx b/docs/docs/distributions/building_distro.mdx index c4a01bf7d..532ffaaf0 100644 --- a/docs/docs/distributions/building_distro.mdx +++ b/docs/docs/distributions/building_distro.mdx @@ -65,7 +65,7 @@ external_providers_dir: /workspace/providers.d Inside `providers.d/custom_ollama/provider.py`, define `get_provider_spec()` so the CLI can discover dependencies: ```python -from llama_stack.providers.datatypes import ProviderSpec +from llama_stack_api.providers.datatypes import ProviderSpec def get_provider_spec() -> ProviderSpec: diff --git a/docs/docs/providers/external/external-providers-guide.mdx b/docs/docs/providers/external/external-providers-guide.mdx index 748fd62c0..dc813c75b 100644 --- a/docs/docs/providers/external/external-providers-guide.mdx +++ b/docs/docs/providers/external/external-providers-guide.mdx @@ -80,7 +80,7 @@ container_image: custom-vector-store:latest # optional All providers must contain a `get_provider_spec` function in their `provider` module. This is a standardized structure that Llama Stack expects and is necessary for getting things such as the config class. The `get_provider_spec` method returns a structure identical to the `adapter`. An example function may look like: ```python -from llama_stack.providers.datatypes import ( +from llama_stack_api.providers.datatypes import ( ProviderSpec, Api, RemoteProviderSpec, diff --git a/docs/docs/providers/files/files.mdx b/docs/docs/providers/files/files.mdx new file mode 100644 index 000000000..095642be3 --- /dev/null +++ b/docs/docs/providers/files/files.mdx @@ -0,0 +1,290 @@ +--- +sidebar_label: Files +title: Files +--- + +## Overview + +The Files API provides file management capabilities for Llama Stack. It allows you to upload, store, retrieve, and manage files that can be used across various endpoints in your application. + +## Features + +- **File Upload**: Upload files with metadata and purpose classification +- **File Management**: List, retrieve, and delete files +- **Content Retrieval**: Access raw file content for processing +- **API Compatibility**: Full compatibility with OpenAI Files API endpoints +- **Flexible Storage**: Support for local filesystem and cloud storage backends + +## API Endpoints + +### Upload File + +**POST** `/v1/openai/v1/files` + +Upload a file that can be used across various endpoints. + +**Request Body:** +- `file`: The file object to be uploaded (multipart form data) +- `purpose`: The intended purpose of the uploaded file + +**Supported Purposes:** +- `batch`: Files for batch operations + +**Response:** +```json +{ + "id": "file-abc123", + "object": "file", + "bytes": 140, + "created_at": 1613779121, + "filename": "mydata.jsonl", + "purpose": "batch" +} +``` + +**Example:** +```python +import requests + +with open("data.jsonl", "rb") as f: + files = {"file": f} + data = {"purpose": "batch"} + response = requests.post( + "http://localhost:8000/v1/openai/v1/files", files=files, data=data + ) + file_info = response.json() +``` + +### List Files + +**GET** `/v1/openai/v1/files` + +Returns a list of files that belong to the user's organization. + +**Query Parameters:** +- `after` (optional): A cursor for pagination +- `limit` (optional): Limit on number of objects (1-10,000, default: 10,000) +- `order` (optional): Sort order by created_at timestamp (`asc` or `desc`, default: `desc`) +- `purpose` (optional): Filter files by purpose + +**Response:** +```json +{ + "object": "list", + "data": [ + { + "id": "file-abc123", + "object": "file", + "bytes": 140, + "created_at": 1613779121, + "filename": "mydata.jsonl", + "purpose": "fine-tune" + } + ], + "has_more": false +} +``` + +**Example:** +```python +import requests + +# List all files +response = requests.get("http://localhost:8000/v1/openai/v1/files") +files = response.json() + +# List files with pagination +response = requests.get( + "http://localhost:8000/v1/openAi/v1/files", + params={"limit": 10, "after": "file-abc123"}, +) +files = response.json() + +# Filter by purpose +response = requests.get( + "http://localhost:8000/v1/openAi/v1/files", params={"purpose": "fine-tune"} +) +files = response.json() +``` + +### Retrieve File + +**GET** `/v1/openAi/v1/files/{file_id}` + +Returns information about a specific file. + +**Path Parameters:** +- `file_id`: The ID of the file to retrieve + +**Response:** +```json +{ + "id": "file-abc123", + "object": "file", + "bytes": 140, + "created_at": 1613779121, + "filename": "mydata.jsonl", + "purpose": "fine-tune" +} +``` + +**Example:** +```python +import requests + +file_id = "file-abc123" +response = requests.get(f"http://localhost:8000/v1/openAi/v1/files/{file_id}") +file_info = response.json() +``` + +### Delete File + +**DELETE** `/v1/openAi/v1/files/{file_id}` + +Delete a file. + +**Path Parameters:** +- `file_id`: The ID of the file to delete + +**Response:** +```json +{ + "id": "file-abc123", + "object": "file", + "deleted": true +} +``` + +**Example:** +```python +import requests + +file_id = "file-abc123" +response = requests.delete(f"http://localhost:8000/v1/openAi/v1/files/{file_id}") +result = response.json() +``` + +### Retrieve File Content + +**GET** `/v1/openAi/v1/files/{file_id}/content` + +Returns the raw file content as a binary response. + +**Path Parameters:** +- `file_id`: The ID of the file to retrieve content from + +**Response:** +Binary file content with appropriate headers: +- `Content-Type`: `application/octet-stream` +- `Content-Disposition`: `attachment; filename="filename"` + +**Example:** +```python +import requests + +file_id = "file-abc123" +response = requests.get(f"http://localhost:8000/v1/openAi/v1/files/{file_id}/content") + +# Save content to file +with open("downloaded_file.jsonl", "wb") as f: + f.write(response.content) + +# Or process content directly +content = response.content +``` + +## Vector Store Integration + +The Files API integrates with Vector Stores to enable document processing and search. For detailed information about this integration, see [File Operations and Vector Store Integration](../concepts/file_operations_vector_stores.md). + +### Vector Store File Operations + +**List Vector Store Files:** +- **GET** `/v1/openAi/v1/vector_stores/{vector_store_id}/files` + +**Retrieve Vector Store File Content:** +- **GET** `/v1/openAi/v1/vector_stores/{vector_store_id}/files/{file_id}/content` + +**Attach File to Vector Store:** +- **POST** `/v1/openAi/v1/vector_stores/{vector_store_id}/files` + +## Error Handling + +The Files API returns standard HTTP status codes and error responses: + +- `400 Bad Request`: Invalid request parameters +- `404 Not Found`: File not found +- `429 Too Many Requests`: Rate limit exceeded +- `500 Internal Server Error`: Server error + +**Error Response Format:** +```json +{ + "error": { + "message": "Error description", + "type": "invalid_request_error", + "code": "file_not_found" + } +} +``` + +## Rate Limits + +The Files API implements rate limiting to ensure fair usage: +- File uploads: 100 files per minute +- File retrievals: 1000 requests per minute +- File deletions: 100 requests per minute + +## Best Practices + +1. **File Organization**: Use descriptive filenames and appropriate purpose classifications +2. **Batch Operations**: For multiple files, consider using batch endpoints when available +3. **Error Handling**: Always check response status codes and handle errors gracefully +4. **Content Types**: Ensure files are uploaded with appropriate content types +5. **Cleanup**: Regularly delete unused files to manage storage costs + +## Integration Examples + +### With Python Client + +```python +from llama_stack import LlamaStackClient + +client = LlamaStackClient("http://localhost:8000") + +# Upload a file +with open("data.jsonl", "rb") as f: + file_info = await client.files.upload(file=f, purpose="fine-tune") + +# List files +files = await client.files.list(purpose="fine-tune") + +# Retrieve file content +content = await client.files.retrieve_content(file_info.id) +``` + +### With cURL + +```bash +# Upload file +curl -X POST http://localhost:8000/v1/openAi/v1/files \ + -F "file=@data.jsonl" \ + -F "purpose=fine-tune" + +# List files +curl http://localhost:8000/v1/openAi/v1/files + +# Download file content +curl http://localhost:8000/v1/openAi/v1/files/file-abc123/content \ + -o downloaded_file.jsonl +``` + +## Provider Support + +The Files API supports multiple storage backends: + +- **Local Filesystem**: Store files on local disk (inline provider) +- **S3**: Store files in AWS S3 or S3-compatible services (remote provider) +- **Custom Backends**: Extensible architecture for custom storage providers + +See the [Files Providers](index.md) documentation for detailed configuration options. diff --git a/docs/docs/providers/files/openai_file_operations_quick_reference.md b/docs/docs/providers/files/openai_file_operations_quick_reference.md new file mode 100644 index 000000000..43e2318e2 --- /dev/null +++ b/docs/docs/providers/files/openai_file_operations_quick_reference.md @@ -0,0 +1,80 @@ +# File Operations Quick Reference + +## Overview + +As of release 0.2.14, Llama Stack provides comprehensive file operations and Vector Store API integration, following the [OpenAI Vector Store Files API specification](https://platform.openai.com/docs/api-reference/vector-stores-files). + +> **Note**: For detailed overview and implementation details, see [Overview](../openai_file_operations_support.md#overview) in the full documentation. + +## Supported Providers + +> **Note**: For complete provider details and features, see [Supported Providers](../openai_file_operations_support.md#supported-providers) in the full documentation. + +**Inline Providers**: FAISS, SQLite-vec, Milvus +**Remote Providers**: ChromaDB, Qdrant, Weaviate, PGVector + +## Quick Start + +### 1. Upload File +```python +file_info = await client.files.upload( + file=open("document.pdf", "rb"), purpose="assistants" +) +``` + +### 2. Create Vector Store +```python +vector_store = client.vector_stores.create(name="my_docs") +``` + +### 3. Attach File +```python +await client.vector_stores.files.create( + vector_store_id=vector_store.id, file_id=file_info.id +) +``` + +### 4. Search +```python +results = await client.vector_stores.search( + vector_store_id=vector_store.id, query="What is the main topic?", max_num_results=5 +) +``` + +## File Processing & Search + +**Processing**: 800 tokens default chunk size, 400 token overlap +**Formats**: PDF, DOCX, TXT, Code files, etc. +**Search**: Vector similarity, Hybrid (SQLite-vec), Filtered with metadata + +## Configuration + +> **Note**: For detailed configuration examples and options, see [Configuration Examples](../openai_file_operations_support.md#configuration-examples) in the full documentation. + +**Basic Setup**: Configure vector_io and files providers in your run.yaml + +## Common Use Cases + +- **RAG Systems**: Document Q&A with file uploads +- **Knowledge Bases**: Searchable document collections +- **Content Analysis**: Document similarity and clustering +- **Research Tools**: Literature review and analysis + +## Performance Tips + +> **Note**: For detailed performance optimization strategies, see [Performance Considerations](../openai_file_operations_support.md#performance-considerations) in the full documentation. + +**Quick Tips**: Choose provider based on your needs (speed vs. storage vs. scalability) + +## Troubleshooting + +> **Note**: For comprehensive troubleshooting, see [Troubleshooting](../openai_file_operations_support.md#troubleshooting) in the full documentation. + +**Quick Fixes**: Check file format compatibility, optimize chunk sizes, monitor storage + +## Resources + +- [Full Documentation](openai_file_operations_support.md) +- [Integration Guide](../concepts/file_operations_vector_stores.md) +- [Files API](files_api.md) +- [Provider Details](../vector_io/index.md) diff --git a/docs/docs/providers/files/openai_file_operations_support.md b/docs/docs/providers/files/openai_file_operations_support.md new file mode 100644 index 000000000..058c994da --- /dev/null +++ b/docs/docs/providers/files/openai_file_operations_support.md @@ -0,0 +1,291 @@ +# File Operations Support in Vector Store Providers + +## Overview + +This document provides a comprehensive overview of file operations and Vector Store API support across all available vector store providers in Llama Stack. As of release 0.2.24, the following providers support full file operations integration. + +## Supported Providers + +### ✅ Full File Operations Support + +The following providers support complete file operations integration, including file upload, automatic processing, and search: + +#### Inline Providers (Single Node) + +| Provider | File Operations | Key Features | +|----------|----------------|--------------| +| **FAISS** | ✅ Full Support | Fast in-memory search, GPU acceleration | +| **SQLite-vec** | ✅ Full Support | Hybrid search, disk-based storage | +| **Milvus** | ✅ Full Support | High-performance, scalable indexing | + +#### Remote Providers (Hosted) + +| Provider | File Operations | Key Features | +|----------|----------------|--------------| +| **ChromaDB** | ✅ Full Support | Metadata filtering, persistent storage | +| **Qdrant** | ✅ Full Support | Payload filtering, advanced search | +| **Weaviate** | ✅ Full Support | GraphQL interface, schema management | +| **Postgres (PGVector)** | ✅ Full Support | SQL integration, ACID compliance | + +### 🔄 Partial Support + +Some providers may support basic vector operations but lack full file operations integration: + +| Provider | Status | Notes | +|----------|--------|-------| +| **Meta Reference** | 🔄 Basic | Core vector operations only | + +## File Operations Features + +All supported providers offer the following file operations capabilities: + +### Core Functionality + +- **File Upload & Processing**: Automatic document ingestion and chunking +- **Vector Storage**: Embedding generation and storage +- **Search & Retrieval**: Semantic search with metadata filtering +- **File Management**: List, retrieve, and manage files in vector stores + +### Advanced Features + +- **Automatic Chunking**: Configurable chunk sizes and overlap +- **Metadata Preservation**: File attributes and chunk metadata +- **Status Tracking**: Monitor file processing progress +- **Error Handling**: Comprehensive error reporting and recovery + +## Implementation Details + +### File Processing Pipeline + +1. **Upload**: File uploaded via Files API +2. **Extraction**: Text content extracted from various formats +3. **Chunking**: Content split into optimal chunks (default: 800 tokens) +4. **Embedding**: Chunks converted to vector embeddings +5. **Storage**: Vectors stored with metadata in vector database +6. **Indexing**: Search index updated for fast retrieval + +### Supported File Formats + +- **Documents**: PDF, DOCX, DOC +- **Text**: TXT, MD, RST +- **Code**: Python, JavaScript, Java, C++, etc. +- **Data**: JSON, CSV, XML +- **Web**: HTML files + +### Chunking Strategies + +- **Default**: 800 tokens with 400 token overlap +- **Custom**: Configurable chunk sizes and overlap +- **Static**: Fixed-size chunks with overlap + +## Provider-Specific Features + +### FAISS + +- **Storage**: In-memory with optional persistence +- **Performance**: Optimized for speed and GPU acceleration +- **Use Case**: High-performance, memory-constrained environments + +### SQLite-vec + +- **Storage**: Disk-based with SQLite backend +- **Search**: Hybrid vector + keyword search +- **Use Case**: Large document collections, frequent updates + +### Milvus + +- **Storage**: Scalable distributed storage +- **Indexing**: Multiple index types (IVF, HNSW) +- **Use Case**: Production deployments, large-scale applications + +### ChromaDB + +- **Storage**: Persistent storage with metadata +- **Filtering**: Advanced metadata filtering +- **Use Case**: Applications requiring rich metadata + +### Qdrant + +- **Storage**: High-performance vector database +- **Filtering**: Payload-based filtering +- **Use Case**: Real-time applications, complex queries + +### Weaviate + +- **Storage**: GraphQL-native vector database +- **Schema**: Flexible schema management +- **Use Case**: Applications requiring complex data relationships + +### Postgres (PGVector) + +- **Storage**: SQL database with vector extensions +- **Integration**: ACID compliance, existing SQL workflows +- **Use Case**: Applications requiring transactional guarantees + +## Configuration Examples + +### Basic Configuration + +```yaml +vector_io: + - provider_id: faiss + provider_type: inline::faiss + config: + kvstore: + type: sqlite + db_path: ~/.llama/faiss_store.db +``` + +### With FileResponse Support + +```yaml +vector_io: + - provider_id: faiss + provider_type: inline::faiss + config: + kvstore: + type: sqlite + db_path: ~/.llama/faiss_store.db + +files: + - provider_id: local-files + provider_type: inline::localfs + config: + storage_dir: ~/.llama/files + metadata_store: + type: sqlite + db_path: ~/.llama/files_metadata.db +``` + +## Usage Examples + +### Python Client + +```python +from llama_stack import LlamaStackClient + +client = LlamaStackClient("http://localhost:8000") + +# Create vector store +vector_store = client.vector_stores.create(name="documents") + +# Upload and process file +with open("document.pdf", "rb") as f: + file_info = await client.files.upload(file=f, purpose="assistants") + +# Attach to vector store +await client.vector_stores.files.create( + vector_store_id=vector_store.id, file_id=file_info.id +) + +# Search +results = await client.vector_stores.search( + vector_store_id=vector_store.id, query="What is the main topic?", max_num_results=5 +) +``` + +### cURL Commands + +```bash +# Upload file +curl -X POST http://localhost:8000/v1/openai/v1/files \ + -F "file=@document.pdf" \ + -F "purpose=assistants" + +# Create vector store +curl -X POST http://localhost:8000/v1/openai/v1/vector_stores \ + -H "Content-Type: application/json" \ + -d '{"name": "documents"}' + +# Attach file to vector store +curl -X POST http://localhost:8000/v1/openai/v1/vector_stores/{store_id}/files \ + -H "Content-Type: application/json" \ + -d '{"file_id": "file-abc123"}' + +# Search vector store +curl -X POST http://localhost:8000/v1/openai/v1/vector_stores/{store_id}/search \ + -H "Content-Type: application/json" \ + -d '{"query": "What is the main topic?", "max_num_results": 5}' +``` + +## Performance Considerations + +### Chunk Size Optimization + +- **Small chunks (400-600 tokens)**: Better precision, more results +- **Large chunks (800-1200 tokens)**: Better context, fewer results +- **Overlap (50%)**: Maintains context between chunks + +### Storage Efficiency + +- **FAISS**: Fastest, but memory-limited +- **SQLite-vec**: Good balance of performance and storage +- **Milvus**: Scalable, production-ready +- **Remote providers**: Managed, but network-dependent + +### Search Performance + +- **Vector search**: Fastest for semantic queries +- **Hybrid search**: Best accuracy (SQLite-vec only) +- **Filtered search**: Fast with metadata constraints + +## Troubleshooting + +### Common Issues + +1. **File Processing Failures** + - Check file format compatibility + - Verify file size limits + - Review error messages in file status + +2. **Search Performance** + - Optimize chunk sizes for your use case + - Use filters to narrow search scope + - Monitor vector store metrics + +3. **Storage Issues** + - Check available disk space + - Verify database permissions + - Monitor memory usage (for in-memory providers) + +### Monitoring + +```python +# Check file processing status +file_status = await client.vector_stores.files.retrieve( + vector_store_id=vector_store.id, file_id=file_info.id +) + +if file_status.status == "failed": + print(f"Error: {file_status.last_error.message}") + +# Monitor vector store health +health = await client.vector_stores.health(vector_store_id=vector_store.id) +print(f"Status: {health.status}") +``` + +## Best Practices + +1. **File Organization**: Use descriptive names and organize by purpose +2. **Chunking Strategy**: Test different sizes for your specific use case +3. **Metadata**: Add relevant attributes for better filtering +4. **Monitoring**: Track processing status and search performance +5. **Cleanup**: Regularly remove unused files to manage storage + +## Future Enhancements + +Planned improvements for file operations support: + +- **Batch Processing**: Process multiple files simultaneously +- **Advanced Chunking**: More sophisticated chunking algorithms +- **Custom Embeddings**: Support for custom embedding models +- **Real-time Updates**: Live file processing and indexing +- **Multi-format Support**: Enhanced file format support + +## Support and Resources + +- **Documentation**: [File Operations and Vector Store Integration](../../concepts/file_operations_vector_stores.mdx) +- **API Reference**: [Files API](files_api.md) +- **Provider Docs**: [Vector Store Providers](../vector_io/index.md) +- **Examples**: [Getting Started](../getting_started/index.md) +- **Community**: [GitHub Discussions](https://github.com/meta-llama/llama-stack/discussions) diff --git a/docs/docs/providers/index.mdx b/docs/docs/providers/index.mdx index bfc16b29a..5c81a57ed 100644 --- a/docs/docs/providers/index.mdx +++ b/docs/docs/providers/index.mdx @@ -22,6 +22,7 @@ Importantly, Llama Stack always strives to provide at least one fully inline pro ## Provider Categories - **[External Providers](external/index.mdx)** - Guide for building and using external providers +- **[OpenAI Compatibility](../api-openai/index.mdx)** - OpenAI API compatibility layer - **[Inference](inference/index.mdx)** - LLM and embedding model providers - **[Agents](agents/index.mdx)** - Agentic system providers - **[DatasetIO](datasetio/index.mdx)** - Dataset and data loader providers @@ -30,6 +31,16 @@ Importantly, Llama Stack always strives to provide at least one fully inline pro - **[Tool Runtime](tool_runtime/index.mdx)** - Tool and protocol providers - **[Files](files/index.mdx)** - File system and storage providers -## Other information about Providers -- **[OpenAI Compatibility](./openai.mdx)** - OpenAI API compatibility layer +## API Documentation + +For comprehensive API documentation and reference: + +- **[API Reference](../api/index.mdx)** - Complete API documentation +- **[Experimental APIs](../api-experimental/index.mdx)** - APIs in development +- **[Deprecated APIs](../api-deprecated/index.mdx)** - Legacy APIs being phased out +- **[OpenAI Compatibility](../api-openai/index.mdx)** - OpenAI API compatibility guide + +## Additional Provider Information + +- **[OpenAI Implementation Guide](./openai.mdx)** - Code examples and implementation details for OpenAI APIs - **[OpenAI-Compatible Responses Limitations](./openai_responses_limitations.mdx)** - Known limitations of the Responses API in Llama Stack diff --git a/docs/docs/providers/openai.mdx b/docs/docs/providers/openai.mdx index 84436e769..c3bb46ecf 100644 --- a/docs/docs/providers/openai.mdx +++ b/docs/docs/providers/openai.mdx @@ -1,9 +1,14 @@ --- -title: OpenAI Compatibility -description: OpenAI API Compatibility -sidebar_label: OpenAI Compatibility -sidebar_position: 1 +title: OpenAI Implementation Guide +description: Code examples and implementation details for OpenAI API compatibility +sidebar_label: OpenAI Implementation +sidebar_position: 2 --- + +# OpenAI Implementation Guide + +This guide provides detailed code examples and implementation details for using OpenAI-compatible APIs with Llama Stack. For a comprehensive overview of OpenAI compatibility features, see our [OpenAI API Compatibility Guide](../api-openai/index.mdx). + ## OpenAI API Compatibility ### Server path @@ -195,3 +200,9 @@ Lines of code unfurl Logic whispers in the dark Art in hidden form ``` + +## Additional Resources + +- **[OpenAI API Compatibility Guide](../api-openai/index.mdx)** - Comprehensive overview of OpenAI compatibility features +- **[OpenAI Responses API Limitations](./openai_responses_limitations.mdx)** - Detailed limitations and known issues +- **[Provider Documentation](../index.mdx)** - Complete provider ecosystem overview diff --git a/docs/docs/providers/vector_io/inline_sqlite-vec.mdx b/docs/docs/providers/vector_io/inline_sqlite-vec.mdx index bfa2f29de..45631dff3 100644 --- a/docs/docs/providers/vector_io/inline_sqlite-vec.mdx +++ b/docs/docs/providers/vector_io/inline_sqlite-vec.mdx @@ -153,7 +153,7 @@ description: | Example using RAGQueryConfig with different search modes: ```python - from llama_stack.apis.tools import RAGQueryConfig, RRFRanker, WeightedRanker + from llama_stack_api import RAGQueryConfig, RRFRanker, WeightedRanker # Vector search config = RAGQueryConfig(mode="vector", max_chunks=5) @@ -358,7 +358,7 @@ Two ranker types are supported: Example using RAGQueryConfig with different search modes: ```python -from llama_stack.apis.tools import RAGQueryConfig, RRFRanker, WeightedRanker +from llama_stack_api import RAGQueryConfig, RRFRanker, WeightedRanker # Vector search config = RAGQueryConfig(mode="vector", max_chunks=5) diff --git a/docs/openapi_generator/generate.py b/docs/openapi_generator/generate.py index 65720df4a..769db32a7 100644 --- a/docs/openapi_generator/generate.py +++ b/docs/openapi_generator/generate.py @@ -16,7 +16,7 @@ import sys import fire import ruamel.yaml as yaml -from llama_stack.apis.version import LLAMA_STACK_API_V1 # noqa: E402 +from llama_stack_api import LLAMA_STACK_API_V1 # noqa: E402 from llama_stack.core.stack import LlamaStack # noqa: E402 from .pyopenapi.options import Options # noqa: E402 diff --git a/docs/openapi_generator/pyopenapi/generator.py b/docs/openapi_generator/pyopenapi/generator.py index 30fc9038d..9b5f76e2a 100644 --- a/docs/openapi_generator/pyopenapi/generator.py +++ b/docs/openapi_generator/pyopenapi/generator.py @@ -16,27 +16,27 @@ from typing import Annotated, Any, Dict, get_args, get_origin, Set, Union from fastapi import UploadFile -from llama_stack.apis.datatypes import Error -from llama_stack.strong_typing.core import JsonType -from llama_stack.strong_typing.docstring import Docstring, parse_type -from llama_stack.strong_typing.inspection import ( +from llama_stack_api import ( + Docstring, + Error, + JsonSchemaGenerator, + JsonType, + Schema, + SchemaOptions, + get_schema_identifier, is_generic_list, is_type_optional, is_type_union, is_unwrapped_body_param, + json_dump_string, + object_to_json, + parse_type, + python_type_to_name, + register_schema, unwrap_generic_list, unwrap_optional_type, unwrap_union_types, ) -from llama_stack.strong_typing.name import python_type_to_name -from llama_stack.strong_typing.schema import ( - get_schema_identifier, - JsonSchemaGenerator, - register_schema, - Schema, - SchemaOptions, -) -from llama_stack.strong_typing.serialization import json_dump_string, object_to_json from pydantic import BaseModel from .operations import ( @@ -979,8 +979,8 @@ class Generator: if deprecated: filtered_operations.append(op) elif self.options.stability_filter == "stainless": - # Include both stable (v1 non-deprecated) and experimental (v1alpha, v1beta) endpoints - if (stability_level == "v1" and not deprecated) or stability_level in ["v1alpha", "v1beta"]: + # Include stable (v1), deprecated (v1 deprecated), and experimental (v1alpha, v1beta) endpoints + if stability_level == "v1" or stability_level in ["v1alpha", "v1beta"]: filtered_operations.append(op) operations = filtered_operations diff --git a/docs/openapi_generator/pyopenapi/operations.py b/docs/openapi_generator/pyopenapi/operations.py index a1c95c7a7..42a554f2c 100644 --- a/docs/openapi_generator/pyopenapi/operations.py +++ b/docs/openapi_generator/pyopenapi/operations.py @@ -11,19 +11,21 @@ import typing from dataclasses import dataclass from typing import Any, Callable, Dict, Iterable, Iterator, List, Optional, Tuple, Union -from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1BETA, LLAMA_STACK_API_V1ALPHA - from termcolor import colored -from llama_stack.strong_typing.inspection import get_signature - from typing import get_origin, get_args from fastapi import UploadFile from fastapi.params import File, Form from typing import Annotated -from llama_stack.schema_utils import ExtraBodyField +from llama_stack_api import ( + ExtraBodyField, + LLAMA_STACK_API_V1, + LLAMA_STACK_API_V1ALPHA, + LLAMA_STACK_API_V1BETA, + get_signature, +) def split_prefix( diff --git a/docs/openapi_generator/pyopenapi/specification.py b/docs/openapi_generator/pyopenapi/specification.py index 90bf54316..bfa35f539 100644 --- a/docs/openapi_generator/pyopenapi/specification.py +++ b/docs/openapi_generator/pyopenapi/specification.py @@ -9,7 +9,7 @@ import enum from dataclasses import dataclass from typing import Any, ClassVar, Dict, List, Optional, Union -from llama_stack.strong_typing.schema import JsonType, Schema, StrictJsonType +from llama_stack_api import JsonType, Schema, StrictJsonType URL = str diff --git a/docs/openapi_generator/pyopenapi/utility.py b/docs/openapi_generator/pyopenapi/utility.py index c1425b250..762249eb8 100644 --- a/docs/openapi_generator/pyopenapi/utility.py +++ b/docs/openapi_generator/pyopenapi/utility.py @@ -11,8 +11,7 @@ from pathlib import Path from typing import Any, List, Optional, TextIO, Union, get_type_hints, get_origin, get_args from pydantic import BaseModel -from llama_stack.strong_typing.schema import object_to_json, StrictJsonType -from llama_stack.strong_typing.inspection import is_unwrapped_body_param +from llama_stack_api import StrictJsonType, is_unwrapped_body_param, object_to_json from llama_stack.core.resolver import api_protocol_map from .generator import Generator @@ -165,12 +164,12 @@ def _validate_api_delete_method_returns_none(method) -> str | None: return "has no return type annotation" return_type = hints['return'] - + # Allow OpenAI endpoints to return response objects since they follow OpenAI specification method_name = getattr(method, '__name__', '') if method_name.__contains__('openai_'): return None - + if return_type is not None and return_type is not type(None): return "does not return None where None is mandatory" diff --git a/docs/static/llama-stack-spec.yaml b/docs/static/llama-stack-spec.yaml index 66eda78c7..759c7501a 100644 --- a/docs/static/llama-stack-spec.yaml +++ b/docs/static/llama-stack-spec.yaml @@ -1878,6 +1878,13 @@ paths: required: false schema: $ref: '#/components/schemas/URL' + - name: authorization + in: query + description: >- + (Optional) OAuth access token for authenticating with the MCP server. + required: false + schema: + type: string deprecated: false /v1/toolgroups: get: @@ -6182,6 +6189,10 @@ components: - type: object description: >- (Optional) HTTP headers to include when connecting to the server + authorization: + type: string + description: >- + (Optional) OAuth access token for authenticating with the MCP server require_approval: oneOf: - type: string @@ -8366,6 +8377,10 @@ components: - type: object description: >- A dictionary of arguments to pass to the tool. + authorization: + type: string + description: >- + (Optional) OAuth access token for authenticating with the MCP server. additionalProperties: false required: - tool_name diff --git a/docs/static/stainless-llama-stack-spec.yaml b/docs/static/stainless-llama-stack-spec.yaml index 1be4af6c9..d0813de4d 100644 --- a/docs/static/stainless-llama-stack-spec.yaml +++ b/docs/static/stainless-llama-stack-spec.yaml @@ -998,6 +998,39 @@ paths: description: List models using the OpenAI API. parameters: [] deprecated: false + post: + responses: + '200': + description: A Model. + content: + application/json: + schema: + $ref: '#/components/schemas/Model' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Models + summary: Register model. + description: >- + Register model. + + Register a model. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterModelRequest' + required: true + deprecated: true /v1/models/{model_id}: get: responses: @@ -1032,6 +1065,36 @@ paths: schema: type: string deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Models + summary: Unregister model. + description: >- + Unregister model. + + Unregister a model. + parameters: + - name: model_id + in: path + description: >- + The identifier of the model to unregister. + required: true + schema: + type: string + deprecated: true /v1/moderations: post: responses: @@ -1662,6 +1725,32 @@ paths: description: List all scoring functions. parameters: [] deprecated: false + post: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ScoringFunctions + summary: Register a scoring function. + description: Register a scoring function. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterScoringFunctionRequest' + required: true + deprecated: true /v1/scoring-functions/{scoring_fn_id}: get: responses: @@ -1693,6 +1782,33 @@ paths: schema: type: string deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ScoringFunctions + summary: Unregister a scoring function. + description: Unregister a scoring function. + parameters: + - name: scoring_fn_id + in: path + description: >- + The ID of the scoring function to unregister. + required: true + schema: + type: string + deprecated: true /v1/scoring/score: post: responses: @@ -1781,6 +1897,36 @@ paths: description: List all shields. parameters: [] deprecated: false + post: + responses: + '200': + description: A Shield. + content: + application/json: + schema: + $ref: '#/components/schemas/Shield' + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Shields + summary: Register a shield. + description: Register a shield. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterShieldRequest' + required: true + deprecated: true /v1/shields/{identifier}: get: responses: @@ -1812,6 +1958,33 @@ paths: schema: type: string deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - Shields + summary: Unregister a shield. + description: Unregister a shield. + parameters: + - name: identifier + in: path + description: >- + The identifier of the shield to unregister. + required: true + schema: + type: string + deprecated: true /v1/tool-runtime/invoke: post: responses: @@ -1881,6 +2054,13 @@ paths: required: false schema: $ref: '#/components/schemas/URL' + - name: authorization + in: query + description: >- + (Optional) OAuth access token for authenticating with the MCP server. + required: false + schema: + type: string deprecated: false /v1/toolgroups: get: @@ -1907,6 +2087,32 @@ paths: description: List tool groups with optional provider. parameters: [] deprecated: false + post: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolGroups + summary: Register a tool group. + description: Register a tool group. + parameters: [] + requestBody: + content: + application/json: + schema: + $ref: '#/components/schemas/RegisterToolGroupRequest' + required: true + deprecated: true /v1/toolgroups/{toolgroup_id}: get: responses: @@ -1938,6 +2144,32 @@ paths: schema: type: string deprecated: false + delete: + responses: + '200': + description: OK + '400': + $ref: '#/components/responses/BadRequest400' + '429': + $ref: >- + #/components/responses/TooManyRequests429 + '500': + $ref: >- + #/components/responses/InternalServerError500 + default: + $ref: '#/components/responses/DefaultError' + tags: + - ToolGroups + summary: Unregister a tool group. + description: Unregister a tool group. + parameters: + - name: toolgroup_id + in: path + description: The ID of the tool group to unregister. + required: true + schema: + type: string + deprecated: true /v1/tools: get: responses: @@ -6898,6 +7130,10 @@ components: - type: object description: >- (Optional) HTTP headers to include when connecting to the server + authorization: + type: string + description: >- + (Optional) OAuth access token for authenticating with the MCP server require_approval: oneOf: - type: string @@ -9082,6 +9318,10 @@ components: - type: object description: >- A dictionary of arguments to pass to the tool. + authorization: + type: string + description: >- + (Optional) OAuth access token for authenticating with the MCP server. additionalProperties: false required: - tool_name @@ -11420,6 +11660,152 @@ components: - hyperparam_search_config - logger_config title: SupervisedFineTuneRequest + RegisterModelRequest: + type: object + properties: + model_id: + type: string + description: The identifier of the model to register. + provider_model_id: + type: string + description: >- + The identifier of the model in the provider. + provider_id: + type: string + description: The identifier of the provider. + metadata: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: Any additional metadata for this model. + model_type: + $ref: '#/components/schemas/ModelType' + description: The type of model to register. + additionalProperties: false + required: + - model_id + title: RegisterModelRequest + ParamType: + oneOf: + - $ref: '#/components/schemas/StringType' + - $ref: '#/components/schemas/NumberType' + - $ref: '#/components/schemas/BooleanType' + - $ref: '#/components/schemas/ArrayType' + - $ref: '#/components/schemas/ObjectType' + - $ref: '#/components/schemas/JsonType' + - $ref: '#/components/schemas/UnionType' + - $ref: '#/components/schemas/ChatCompletionInputType' + - $ref: '#/components/schemas/CompletionInputType' + discriminator: + propertyName: type + mapping: + string: '#/components/schemas/StringType' + number: '#/components/schemas/NumberType' + boolean: '#/components/schemas/BooleanType' + array: '#/components/schemas/ArrayType' + object: '#/components/schemas/ObjectType' + json: '#/components/schemas/JsonType' + union: '#/components/schemas/UnionType' + chat_completion_input: '#/components/schemas/ChatCompletionInputType' + completion_input: '#/components/schemas/CompletionInputType' + RegisterScoringFunctionRequest: + type: object + properties: + scoring_fn_id: + type: string + description: >- + The ID of the scoring function to register. + description: + type: string + description: The description of the scoring function. + return_type: + $ref: '#/components/schemas/ParamType' + description: The return type of the scoring function. + provider_scoring_fn_id: + type: string + description: >- + The ID of the provider scoring function to use for the scoring function. + provider_id: + type: string + description: >- + The ID of the provider to use for the scoring function. + params: + $ref: '#/components/schemas/ScoringFnParams' + description: >- + The parameters for the scoring function for benchmark eval, these can + be overridden for app eval. + additionalProperties: false + required: + - scoring_fn_id + - description + - return_type + title: RegisterScoringFunctionRequest + RegisterShieldRequest: + type: object + properties: + shield_id: + type: string + description: >- + The identifier of the shield to register. + provider_shield_id: + type: string + description: >- + The identifier of the shield in the provider. + provider_id: + type: string + description: The identifier of the provider. + params: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: The parameters of the shield. + additionalProperties: false + required: + - shield_id + title: RegisterShieldRequest + RegisterToolGroupRequest: + type: object + properties: + toolgroup_id: + type: string + description: The ID of the tool group to register. + provider_id: + type: string + description: >- + The ID of the provider to use for the tool group. + mcp_endpoint: + $ref: '#/components/schemas/URL' + description: >- + The MCP endpoint to use for the tool group. + args: + type: object + additionalProperties: + oneOf: + - type: 'null' + - type: boolean + - type: number + - type: string + - type: array + - type: object + description: >- + A dictionary of arguments to pass to the tool group. + additionalProperties: false + required: + - toolgroup_id + - provider_id + title: RegisterToolGroupRequest DataSource: oneOf: - $ref: '#/components/schemas/URIDataSource' diff --git a/pyproject.toml b/pyproject.toml index e6808af8a..f6d28fd03 100644 --- a/pyproject.toml +++ b/pyproject.toml @@ -31,6 +31,7 @@ dependencies = [ "httpx", "jinja2>=3.1.6", "jsonschema", + "llama-stack-api", # API and provider specifications (local dev via tool.uv.sources) "openai>=2.5.0", "prompt-toolkit", "python-dotenv", @@ -49,6 +50,7 @@ dependencies = [ "aiosqlite>=0.21.0", # server - for metadata store "asyncpg", # for metadata store "sqlalchemy[asyncio]>=2.0.41", # server - for conversations + "starlette>=0.49.1", ] [project.optional-dependencies] @@ -69,7 +71,7 @@ dev = [ "black", "ruff", "mypy", - "pre-commit", + "pre-commit>=4.4.0", "ruamel.yaml", # needed for openapi generator ] # Type checking dependencies - includes type stubs and optional runtime dependencies @@ -180,7 +182,7 @@ install-wheel-from-presigned = "llama_stack.cli.scripts.run:install_wheel_from_p [tool.setuptools.packages.find] where = ["src"] -include = ["llama_stack", "llama_stack.*"] +include = ["llama_stack", "llama_stack.*", "llama_stack_api", "llama_stack_api.*"] [[tool.uv.index]] name = "pytorch-cpu" @@ -190,6 +192,7 @@ explicit = true [tool.uv.sources] torch = [{ index = "pytorch-cpu" }] torchvision = [{ index = "pytorch-cpu" }] +llama-stack-api = [{ path = "src/llama_stack_api", editable = true }] [tool.ruff] line-length = 120 @@ -257,7 +260,7 @@ unfixable = [ [tool.mypy] mypy_path = ["src"] -packages = ["llama_stack"] +packages = ["llama_stack", "llama_stack_api"] plugins = ['pydantic.mypy'] disable_error_code = [] warn_return_any = true @@ -282,12 +285,13 @@ exclude = [ "^src/llama_stack/models/llama/llama3/interface\\.py$", "^src/llama_stack/models/llama/llama3/tokenizer\\.py$", "^src/llama_stack/models/llama/llama3/tool_utils\\.py$", - "^src/llama_stack/providers/inline/datasetio/localfs/", - "^src/llama_stack/providers/inline/eval/meta_reference/eval\\.py$", - "^src/llama_stack/providers/inline/inference/meta_reference/inference\\.py$", "^src/llama_stack/models/llama/llama3/generation\\.py$", "^src/llama_stack/models/llama/llama3/multimodal/model\\.py$", "^src/llama_stack/models/llama/llama4/", + "^src/llama_stack/providers/inline/agents/meta_reference/", + "^src/llama_stack/providers/inline/datasetio/localfs/", + "^src/llama_stack/providers/inline/eval/meta_reference/eval\\.py$", + "^src/llama_stack/providers/inline/inference/meta_reference/inference\\.py$", "^src/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers\\.py$", "^src/llama_stack/providers/inline/post_training/common/validator\\.py$", "^src/llama_stack/providers/inline/safety/code_scanner/", @@ -337,7 +341,7 @@ exclude = [ "^src/llama_stack/providers/utils/telemetry/dataset_mixin\\.py$", "^src/llama_stack/providers/utils/telemetry/trace_protocol\\.py$", "^src/llama_stack/providers/utils/telemetry/tracing\\.py$", - "^src/llama_stack/strong_typing/auxiliary\\.py$", + "^src/llama_stack_api/strong_typing/auxiliary\\.py$", "^src/llama_stack/distributions/template\\.py$", ] diff --git a/scripts/generate_prompt_format.py b/scripts/generate_prompt_format.py index 855033f95..381bbc6a7 100755 --- a/scripts/generate_prompt_format.py +++ b/scripts/generate_prompt_format.py @@ -15,10 +15,10 @@ from pathlib import Path import fire -from llama_stack.apis.common.errors import ModelNotFoundError from llama_stack.models.llama.llama3.generation import Llama3 from llama_stack.models.llama.llama4.generation import Llama4 from llama_stack.models.llama.sku_list import resolve_model +from llama_stack_api import ModelNotFoundError THIS_DIR = Path(__file__).parent.resolve() diff --git a/scripts/integration-tests.sh b/scripts/integration-tests.sh index 0951feb14..8b0002125 100755 --- a/scripts/integration-tests.sh +++ b/scripts/integration-tests.sh @@ -162,6 +162,17 @@ if [[ "$COLLECT_ONLY" == false ]]; then export LLAMA_STACK_TEST_STACK_CONFIG_TYPE="library_client" echo "Setting stack config type: library_client" fi + + # Set MCP host for in-process MCP server tests + # - For library client and server mode: localhost (both on same host) + # - For docker mode: host.docker.internal (container needs to reach host) + if [[ "$STACK_CONFIG" == docker:* ]]; then + export LLAMA_STACK_TEST_MCP_HOST="host.docker.internal" + echo "Setting MCP host: host.docker.internal (docker mode)" + else + export LLAMA_STACK_TEST_MCP_HOST="localhost" + echo "Setting MCP host: localhost (library/server mode)" + fi fi SETUP_ENV=$(PYTHONPATH=$THIS_DIR/.. python "$THIS_DIR/get_setup_env.py" --suite "$TEST_SUITE" --setup "$TEST_SETUP" --format bash) @@ -338,6 +349,7 @@ if [[ "$STACK_CONFIG" == *"docker:"* && "$COLLECT_ONLY" == false ]]; then DOCKER_ENV_VARS="" DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e LLAMA_STACK_TEST_INFERENCE_MODE=$INFERENCE_MODE" DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e LLAMA_STACK_TEST_STACK_CONFIG_TYPE=server" + DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e LLAMA_STACK_TEST_MCP_HOST=${LLAMA_STACK_TEST_MCP_HOST:-host.docker.internal}" # Disabled: https://github.com/llamastack/llama-stack/issues/4089 #DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:${COLLECTOR_PORT}" DOCKER_ENV_VARS="$DOCKER_ENV_VARS -e OTEL_METRIC_EXPORT_INTERVAL=200" @@ -371,8 +383,11 @@ if [[ "$STACK_CONFIG" == *"docker:"* && "$COLLECT_ONLY" == false ]]; then # Use regular port mapping instead NETWORK_MODE="" PORT_MAPPINGS="" + ADD_HOST_FLAG="" if [[ "$(uname)" != "Darwin" ]] && [[ "$(uname)" != *"MINGW"* ]]; then NETWORK_MODE="--network host" + # On Linux with host network, also add host.docker.internal mapping for consistency + ADD_HOST_FLAG="--add-host=host.docker.internal:host-gateway" else # On non-Linux (macOS, Windows), need explicit port mappings for both app and telemetry PORT_MAPPINGS="-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT -p $COLLECTOR_PORT:$COLLECTOR_PORT" @@ -381,6 +396,7 @@ if [[ "$STACK_CONFIG" == *"docker:"* && "$COLLECT_ONLY" == false ]]; then docker run -d $NETWORK_MODE --name "$container_name" \ $PORT_MAPPINGS \ + $ADD_HOST_FLAG \ $DOCKER_ENV_VARS \ "$IMAGE_NAME" \ --port $LLAMA_STACK_PORT diff --git a/scripts/provider_codegen.py b/scripts/provider_codegen.py index de79b4d17..d62d626ad 100755 --- a/scripts/provider_codegen.py +++ b/scripts/provider_codegen.py @@ -22,7 +22,7 @@ def get_api_docstring(api_name: str) -> str | None: """Extract docstring from the API protocol class.""" try: # Import the API module dynamically - api_module = __import__(f"llama_stack.apis.{api_name}", fromlist=[api_name.title()]) + api_module = __import__(f"llama_stack_api.{api_name}", fromlist=[api_name.title()]) # Get the main protocol class (usually capitalized API name) protocol_class_name = api_name.title() @@ -83,8 +83,9 @@ def get_config_class_info(config_class_path: str) -> dict[str, Any]: # this string replace is ridiculous field_type = field_type.replace("typing.", "").replace("Optional[", "").replace("]", "") field_type = field_type.replace("Annotated[", "").replace("FieldInfo(", "").replace(")", "") - field_type = field_type.replace("llama_stack.apis.inference.inference.", "") + field_type = field_type.replace("llama_stack_api.inference.", "") field_type = field_type.replace("llama_stack.providers.", "") + field_type = field_type.replace("llama_stack_api.datatypes.", "") default_value = field.default if field.default_factory is not None: diff --git a/src/llama_stack/apis/agents/__init__.py b/src/llama_stack/apis/agents/__init__.py deleted file mode 100644 index 6416b283b..000000000 --- a/src/llama_stack/apis/agents/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .agents import * diff --git a/src/llama_stack/apis/batches/__init__.py b/src/llama_stack/apis/batches/__init__.py deleted file mode 100644 index 9ce7d3d75..000000000 --- a/src/llama_stack/apis/batches/__init__.py +++ /dev/null @@ -1,9 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .batches import Batches, BatchObject, ListBatchesResponse - -__all__ = ["Batches", "BatchObject", "ListBatchesResponse"] diff --git a/src/llama_stack/apis/benchmarks/__init__.py b/src/llama_stack/apis/benchmarks/__init__.py deleted file mode 100644 index 62d1b367c..000000000 --- a/src/llama_stack/apis/benchmarks/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .benchmarks import * diff --git a/src/llama_stack/apis/common/__init__.py b/src/llama_stack/apis/common/__init__.py deleted file mode 100644 index 756f351d8..000000000 --- a/src/llama_stack/apis/common/__init__.py +++ /dev/null @@ -1,5 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. diff --git a/src/llama_stack/apis/conversations/__init__.py b/src/llama_stack/apis/conversations/__init__.py deleted file mode 100644 index b6ddc5999..000000000 --- a/src/llama_stack/apis/conversations/__init__.py +++ /dev/null @@ -1,27 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .conversations import ( - Conversation, - ConversationDeletedResource, - ConversationItem, - ConversationItemCreateRequest, - ConversationItemDeletedResource, - ConversationItemList, - Conversations, - Metadata, -) - -__all__ = [ - "Conversation", - "ConversationDeletedResource", - "ConversationItem", - "ConversationItemCreateRequest", - "ConversationItemDeletedResource", - "ConversationItemList", - "Conversations", - "Metadata", -] diff --git a/src/llama_stack/apis/datasetio/__init__.py b/src/llama_stack/apis/datasetio/__init__.py deleted file mode 100644 index 8c087bfa4..000000000 --- a/src/llama_stack/apis/datasetio/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .datasetio import * diff --git a/src/llama_stack/apis/datasets/__init__.py b/src/llama_stack/apis/datasets/__init__.py deleted file mode 100644 index 9c9a128d2..000000000 --- a/src/llama_stack/apis/datasets/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .datasets import * diff --git a/src/llama_stack/apis/datatypes.py b/src/llama_stack/apis/datatypes.py deleted file mode 100644 index ae01c5dfc..000000000 --- a/src/llama_stack/apis/datatypes.py +++ /dev/null @@ -1,158 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from enum import Enum, EnumMeta - -from pydantic import BaseModel, Field - -from llama_stack.schema_utils import json_schema_type - - -class DynamicApiMeta(EnumMeta): - def __new__(cls, name, bases, namespace): - # Store the original enum values - original_values = {k: v for k, v in namespace.items() if not k.startswith("_")} - - # Create the enum class - cls = super().__new__(cls, name, bases, namespace) - - # Store the original values for reference - cls._original_values = original_values - # Initialize _dynamic_values - cls._dynamic_values = {} - - return cls - - def __call__(cls, value): - try: - return super().__call__(value) - except ValueError as e: - # If this value was already dynamically added, return it - if value in cls._dynamic_values: - return cls._dynamic_values[value] - - # If the value doesn't exist, create a new enum member - # Create a new member name from the value - member_name = value.lower().replace("-", "_") - - # If this member name already exists in the enum, return the existing member - if member_name in cls._member_map_: - return cls._member_map_[member_name] - - # Instead of creating a new member, raise ValueError to force users to use Api.add() to - # register new APIs explicitly - raise ValueError(f"API '{value}' does not exist. Use Api.add() to register new APIs.") from e - - def __iter__(cls): - # Allow iteration over both static and dynamic members - yield from super().__iter__() - if hasattr(cls, "_dynamic_values"): - yield from cls._dynamic_values.values() - - def add(cls, value): - """ - Add a new API to the enum. - Used to register external APIs. - """ - member_name = value.lower().replace("-", "_") - - # If this member name already exists in the enum, return it - if member_name in cls._member_map_: - return cls._member_map_[member_name] - - # Create a new enum member - member = object.__new__(cls) - member._name_ = member_name - member._value_ = value - - # Add it to the enum class - cls._member_map_[member_name] = member - cls._member_names_.append(member_name) - cls._member_type_ = str - - # Store it in our dynamic values - cls._dynamic_values[value] = member - - return member - - -@json_schema_type -class Api(Enum, metaclass=DynamicApiMeta): - """Enumeration of all available APIs in the Llama Stack system. - :cvar providers: Provider management and configuration - :cvar inference: Text generation, chat completions, and embeddings - :cvar safety: Content moderation and safety shields - :cvar agents: Agent orchestration and execution - :cvar batches: Batch processing for asynchronous API requests - :cvar vector_io: Vector database operations and queries - :cvar datasetio: Dataset input/output operations - :cvar scoring: Model output evaluation and scoring - :cvar eval: Model evaluation and benchmarking framework - :cvar post_training: Fine-tuning and model training - :cvar tool_runtime: Tool execution and management - :cvar telemetry: Observability and system monitoring - :cvar models: Model metadata and management - :cvar shields: Safety shield implementations - :cvar datasets: Dataset creation and management - :cvar scoring_functions: Scoring function definitions - :cvar benchmarks: Benchmark suite management - :cvar tool_groups: Tool group organization - :cvar files: File storage and management - :cvar prompts: Prompt versions and management - :cvar inspect: Built-in system inspection and introspection - """ - - providers = "providers" - inference = "inference" - safety = "safety" - agents = "agents" - batches = "batches" - vector_io = "vector_io" - datasetio = "datasetio" - scoring = "scoring" - eval = "eval" - post_training = "post_training" - tool_runtime = "tool_runtime" - - models = "models" - shields = "shields" - vector_stores = "vector_stores" # only used for routing table - datasets = "datasets" - scoring_functions = "scoring_functions" - benchmarks = "benchmarks" - tool_groups = "tool_groups" - files = "files" - prompts = "prompts" - conversations = "conversations" - - # built-in API - inspect = "inspect" - - -@json_schema_type -class Error(BaseModel): - """ - Error response from the API. Roughly follows RFC 7807. - - :param status: HTTP status code - :param title: Error title, a short summary of the error which is invariant for an error type - :param detail: Error detail, a longer human-readable description of the error - :param instance: (Optional) A URL which can be used to retrieve more information about the specific occurrence of the error - """ - - status: int - title: str - detail: str - instance: str | None = None - - -class ExternalApiSpec(BaseModel): - """Specification for an external API implementation.""" - - module: str = Field(..., description="Python module containing the API implementation") - name: str = Field(..., description="Name of the API") - pip_packages: list[str] = Field(default=[], description="List of pip packages to install the API") - protocol: str = Field(..., description="Name of the protocol class for the API") diff --git a/src/llama_stack/apis/eval/__init__.py b/src/llama_stack/apis/eval/__init__.py deleted file mode 100644 index 28a1d6049..000000000 --- a/src/llama_stack/apis/eval/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .eval import * diff --git a/src/llama_stack/apis/files/__init__.py b/src/llama_stack/apis/files/__init__.py deleted file mode 100644 index 189e4de19..000000000 --- a/src/llama_stack/apis/files/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .files import * diff --git a/src/llama_stack/apis/inference/__init__.py b/src/llama_stack/apis/inference/__init__.py deleted file mode 100644 index f0c8783c1..000000000 --- a/src/llama_stack/apis/inference/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .inference import * diff --git a/src/llama_stack/apis/inspect/__init__.py b/src/llama_stack/apis/inspect/__init__.py deleted file mode 100644 index 016937e3d..000000000 --- a/src/llama_stack/apis/inspect/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .inspect import * diff --git a/src/llama_stack/apis/models/__init__.py b/src/llama_stack/apis/models/__init__.py deleted file mode 100644 index ee90106b6..000000000 --- a/src/llama_stack/apis/models/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .models import * diff --git a/src/llama_stack/apis/post_training/__init__.py b/src/llama_stack/apis/post_training/__init__.py deleted file mode 100644 index 695575a30..000000000 --- a/src/llama_stack/apis/post_training/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .post_training import * diff --git a/src/llama_stack/apis/prompts/__init__.py b/src/llama_stack/apis/prompts/__init__.py deleted file mode 100644 index 6070f3450..000000000 --- a/src/llama_stack/apis/prompts/__init__.py +++ /dev/null @@ -1,9 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .prompts import ListPromptsResponse, Prompt, Prompts - -__all__ = ["Prompt", "Prompts", "ListPromptsResponse"] diff --git a/src/llama_stack/apis/providers/__init__.py b/src/llama_stack/apis/providers/__init__.py deleted file mode 100644 index e35e2fe47..000000000 --- a/src/llama_stack/apis/providers/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .providers import * diff --git a/src/llama_stack/apis/safety/__init__.py b/src/llama_stack/apis/safety/__init__.py deleted file mode 100644 index d93bc1355..000000000 --- a/src/llama_stack/apis/safety/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .safety import * diff --git a/src/llama_stack/apis/scoring/__init__.py b/src/llama_stack/apis/scoring/__init__.py deleted file mode 100644 index 624b9e704..000000000 --- a/src/llama_stack/apis/scoring/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .scoring import * diff --git a/src/llama_stack/apis/scoring_functions/__init__.py b/src/llama_stack/apis/scoring_functions/__init__.py deleted file mode 100644 index fc1de0311..000000000 --- a/src/llama_stack/apis/scoring_functions/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .scoring_functions import * diff --git a/src/llama_stack/apis/shields/__init__.py b/src/llama_stack/apis/shields/__init__.py deleted file mode 100644 index 783a4d124..000000000 --- a/src/llama_stack/apis/shields/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .shields import * diff --git a/src/llama_stack/apis/tools/__init__.py b/src/llama_stack/apis/tools/__init__.py deleted file mode 100644 index b25310ecf..000000000 --- a/src/llama_stack/apis/tools/__init__.py +++ /dev/null @@ -1,8 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .rag_tool import * -from .tools import * diff --git a/src/llama_stack/apis/vector_io/__init__.py b/src/llama_stack/apis/vector_io/__init__.py deleted file mode 100644 index 3f4c60805..000000000 --- a/src/llama_stack/apis/vector_io/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .vector_io import * diff --git a/src/llama_stack/apis/vector_stores/__init__.py b/src/llama_stack/apis/vector_stores/__init__.py deleted file mode 100644 index 8fc34058a..000000000 --- a/src/llama_stack/apis/vector_stores/__init__.py +++ /dev/null @@ -1,7 +0,0 @@ -# Copyright (c) Meta Platforms, Inc. and affiliates. -# All rights reserved. -# -# This source code is licensed under the terms described in the LICENSE file in -# the root directory of this source tree. - -from .vector_stores import * diff --git a/src/llama_stack/cli/stack/_list_deps.py b/src/llama_stack/cli/stack/_list_deps.py index 18141be5f..82bef1a4f 100644 --- a/src/llama_stack/cli/stack/_list_deps.py +++ b/src/llama_stack/cli/stack/_list_deps.py @@ -21,7 +21,7 @@ from llama_stack.core.datatypes import ( from llama_stack.core.distribution import get_provider_registry from llama_stack.core.stack import replace_env_vars from llama_stack.log import get_logger -from llama_stack.providers.datatypes import Api +from llama_stack_api import Api TEMPLATES_PATH = Path(__file__).parent.parent.parent / "templates" diff --git a/src/llama_stack/cli/stack/utils.py b/src/llama_stack/cli/stack/utils.py index cc1ca051b..d49b142e0 100644 --- a/src/llama_stack/cli/stack/utils.py +++ b/src/llama_stack/cli/stack/utils.py @@ -32,7 +32,7 @@ from llama_stack.core.storage.datatypes import ( from llama_stack.core.utils.config_dirs import DISTRIBS_BASE_DIR, EXTERNAL_PROVIDERS_DIR from llama_stack.core.utils.dynamic import instantiate_class_type from llama_stack.core.utils.image_types import LlamaStackImageType -from llama_stack.providers.datatypes import Api +from llama_stack_api import Api TEMPLATES_PATH = Path(__file__).parent.parent.parent / "distributions" diff --git a/src/llama_stack/core/build.py b/src/llama_stack/core/build.py index fb3a22109..630b2a47f 100644 --- a/src/llama_stack/core/build.py +++ b/src/llama_stack/core/build.py @@ -13,7 +13,7 @@ from llama_stack.core.datatypes import BuildConfig from llama_stack.core.distribution import get_provider_registry from llama_stack.distributions.template import DistributionTemplate from llama_stack.log import get_logger -from llama_stack.providers.datatypes import Api +from llama_stack_api import Api log = get_logger(name=__name__, category="core") diff --git a/src/llama_stack/core/client.py b/src/llama_stack/core/client.py index 49e01794e..ba935a35e 100644 --- a/src/llama_stack/core/client.py +++ b/src/llama_stack/core/client.py @@ -15,7 +15,7 @@ import httpx from pydantic import BaseModel, parse_obj_as from termcolor import cprint -from llama_stack.providers.datatypes import RemoteProviderConfig +from llama_stack_api import RemoteProviderConfig _CLIENT_CLASSES = {} diff --git a/src/llama_stack/core/configure.py b/src/llama_stack/core/configure.py index 5d4a54184..d738b8a61 100644 --- a/src/llama_stack/core/configure.py +++ b/src/llama_stack/core/configure.py @@ -20,7 +20,7 @@ from llama_stack.core.stack import cast_image_name_to_string, replace_env_vars from llama_stack.core.utils.dynamic import instantiate_class_type from llama_stack.core.utils.prompt_for_config import prompt_for_config from llama_stack.log import get_logger -from llama_stack.providers.datatypes import Api, ProviderSpec +from llama_stack_api import Api, ProviderSpec logger = get_logger(name=__name__, category="core") diff --git a/src/llama_stack/core/conversations/conversations.py b/src/llama_stack/core/conversations/conversations.py index f83834522..4cf5a82ee 100644 --- a/src/llama_stack/core/conversations/conversations.py +++ b/src/llama_stack/core/conversations/conversations.py @@ -10,7 +10,12 @@ from typing import Any, Literal from pydantic import BaseModel, TypeAdapter -from llama_stack.apis.conversations.conversations import ( +from llama_stack.core.datatypes import AccessRule, StackRunConfig +from llama_stack.log import get_logger +from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType +from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore +from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl +from llama_stack_api import ( Conversation, ConversationDeletedResource, ConversationItem, @@ -20,11 +25,6 @@ from llama_stack.apis.conversations.conversations import ( Conversations, Metadata, ) -from llama_stack.core.datatypes import AccessRule, StackRunConfig -from llama_stack.log import get_logger -from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType -from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore -from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl logger = get_logger(name=__name__, category="openai_conversations") diff --git a/src/llama_stack/core/datatypes.py b/src/llama_stack/core/datatypes.py index 2182ea4e5..1e29690ff 100644 --- a/src/llama_stack/core/datatypes.py +++ b/src/llama_stack/core/datatypes.py @@ -11,20 +11,6 @@ from urllib.parse import urlparse from pydantic import BaseModel, Field, field_validator, model_validator -from llama_stack.apis.benchmarks import Benchmark, BenchmarkInput -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Dataset, DatasetInput -from llama_stack.apis.eval import Eval -from llama_stack.apis.inference import Inference -from llama_stack.apis.models import Model, ModelInput -from llama_stack.apis.resource import Resource -from llama_stack.apis.safety import Safety -from llama_stack.apis.scoring import Scoring -from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnInput -from llama_stack.apis.shields import Shield, ShieldInput -from llama_stack.apis.tools import ToolGroup, ToolGroupInput, ToolRuntime -from llama_stack.apis.vector_io import VectorIO -from llama_stack.apis.vector_stores import VectorStore, VectorStoreInput from llama_stack.core.access_control.datatypes import AccessRule from llama_stack.core.storage.datatypes import ( KVStoreReference, @@ -32,7 +18,32 @@ from llama_stack.core.storage.datatypes import ( StorageConfig, ) from llama_stack.log import LoggingConfig -from llama_stack.providers.datatypes import Api, ProviderSpec +from llama_stack_api import ( + Api, + Benchmark, + BenchmarkInput, + Dataset, + DatasetInput, + DatasetIO, + Eval, + Inference, + Model, + ModelInput, + ProviderSpec, + Resource, + Safety, + Scoring, + ScoringFn, + ScoringFnInput, + Shield, + ShieldInput, + ToolGroup, + ToolGroupInput, + ToolRuntime, + VectorIO, + VectorStore, + VectorStoreInput, +) LLAMA_STACK_BUILD_CONFIG_VERSION = 2 LLAMA_STACK_RUN_CONFIG_VERSION = 2 diff --git a/src/llama_stack/core/distribution.py b/src/llama_stack/core/distribution.py index 9be5ffb49..658c75ef2 100644 --- a/src/llama_stack/core/distribution.py +++ b/src/llama_stack/core/distribution.py @@ -15,7 +15,7 @@ from pydantic import BaseModel from llama_stack.core.datatypes import BuildConfig, DistributionSpec from llama_stack.core.external import load_external_apis from llama_stack.log import get_logger -from llama_stack.providers.datatypes import ( +from llama_stack_api import ( Api, InlineProviderSpec, ProviderSpec, diff --git a/src/llama_stack/core/external.py b/src/llama_stack/core/external.py index 12e9824ad..d1a2d6e42 100644 --- a/src/llama_stack/core/external.py +++ b/src/llama_stack/core/external.py @@ -7,9 +7,9 @@ import yaml -from llama_stack.apis.datatypes import Api, ExternalApiSpec from llama_stack.core.datatypes import BuildConfig, StackRunConfig from llama_stack.log import get_logger +from llama_stack_api import Api, ExternalApiSpec logger = get_logger(name=__name__, category="core") diff --git a/src/llama_stack/core/inspect.py b/src/llama_stack/core/inspect.py index 07b51128f..272c9d1bc 100644 --- a/src/llama_stack/core/inspect.py +++ b/src/llama_stack/core/inspect.py @@ -8,17 +8,17 @@ from importlib.metadata import version from pydantic import BaseModel -from llama_stack.apis.inspect import ( +from llama_stack.core.datatypes import StackRunConfig +from llama_stack.core.external import load_external_apis +from llama_stack.core.server.routes import get_all_api_routes +from llama_stack_api import ( HealthInfo, + HealthStatus, Inspect, ListRoutesResponse, RouteInfo, VersionInfo, ) -from llama_stack.core.datatypes import StackRunConfig -from llama_stack.core.external import load_external_apis -from llama_stack.core.server.routes import get_all_api_routes -from llama_stack.providers.datatypes import HealthStatus class DistributionInspectConfig(BaseModel): diff --git a/src/llama_stack/core/library_client.py b/src/llama_stack/core/library_client.py index db990368b..2a224d915 100644 --- a/src/llama_stack/core/library_client.py +++ b/src/llama_stack/core/library_client.py @@ -19,6 +19,8 @@ import httpx import yaml from fastapi import Response as FastAPIResponse +from llama_stack_api import is_unwrapped_body_param + try: from llama_stack_client import ( NOT_GIVEN, @@ -57,7 +59,6 @@ from llama_stack.core.utils.config import redact_sensitive_fields from llama_stack.core.utils.context import preserve_contexts_async_generator from llama_stack.core.utils.exec import in_notebook from llama_stack.log import get_logger, setup_logging -from llama_stack.strong_typing.inspection import is_unwrapped_body_param logger = get_logger(name=__name__, category="core") diff --git a/src/llama_stack/core/prompts/prompts.py b/src/llama_stack/core/prompts/prompts.py index 1a6f38cb5..9f532c1cd 100644 --- a/src/llama_stack/core/prompts/prompts.py +++ b/src/llama_stack/core/prompts/prompts.py @@ -9,9 +9,9 @@ from typing import Any from pydantic import BaseModel -from llama_stack.apis.prompts import ListPromptsResponse, Prompt, Prompts from llama_stack.core.datatypes import StackRunConfig from llama_stack.providers.utils.kvstore import KVStore, kvstore_impl +from llama_stack_api import ListPromptsResponse, Prompt, Prompts class PromptServiceConfig(BaseModel): diff --git a/src/llama_stack/core/providers.py b/src/llama_stack/core/providers.py index 7095ffd18..e3fe3c7b3 100644 --- a/src/llama_stack/core/providers.py +++ b/src/llama_stack/core/providers.py @@ -9,9 +9,8 @@ from typing import Any from pydantic import BaseModel -from llama_stack.apis.providers import ListProvidersResponse, ProviderInfo, Providers from llama_stack.log import get_logger -from llama_stack.providers.datatypes import HealthResponse, HealthStatus +from llama_stack_api import HealthResponse, HealthStatus, ListProvidersResponse, ProviderInfo, Providers from .datatypes import StackRunConfig from .utils.config import redact_sensitive_fields diff --git a/src/llama_stack/core/resolver.py b/src/llama_stack/core/resolver.py index 8bf371fed..6bc32c2d0 100644 --- a/src/llama_stack/core/resolver.py +++ b/src/llama_stack/core/resolver.py @@ -8,29 +8,6 @@ import importlib.metadata import inspect from typing import Any -from llama_stack.apis.agents import Agents -from llama_stack.apis.batches import Batches -from llama_stack.apis.benchmarks import Benchmarks -from llama_stack.apis.conversations import Conversations -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Datasets -from llama_stack.apis.datatypes import ExternalApiSpec -from llama_stack.apis.eval import Eval -from llama_stack.apis.files import Files -from llama_stack.apis.inference import Inference, InferenceProvider -from llama_stack.apis.inspect import Inspect -from llama_stack.apis.models import Models -from llama_stack.apis.post_training import PostTraining -from llama_stack.apis.prompts import Prompts -from llama_stack.apis.providers import Providers as ProvidersAPI -from llama_stack.apis.safety import Safety -from llama_stack.apis.scoring import Scoring -from llama_stack.apis.scoring_functions import ScoringFunctions -from llama_stack.apis.shields import Shields -from llama_stack.apis.tools import ToolGroups, ToolRuntime -from llama_stack.apis.vector_io import VectorIO -from llama_stack.apis.vector_stores import VectorStore -from llama_stack.apis.version import LLAMA_STACK_API_V1ALPHA from llama_stack.core.client import get_client_impl from llama_stack.core.datatypes import ( AccessRule, @@ -44,17 +21,44 @@ from llama_stack.core.external import load_external_apis from llama_stack.core.store import DistributionRegistry from llama_stack.core.utils.dynamic import instantiate_class_type from llama_stack.log import get_logger -from llama_stack.providers.datatypes import ( +from llama_stack_api import ( + LLAMA_STACK_API_V1ALPHA, + Agents, Api, + Batches, + Benchmarks, BenchmarksProtocolPrivate, + Conversations, + DatasetIO, + Datasets, DatasetsProtocolPrivate, + Eval, + ExternalApiSpec, + Files, + Inference, + InferenceProvider, + Inspect, + Models, ModelsProtocolPrivate, + PostTraining, + Prompts, ProviderSpec, RemoteProviderConfig, RemoteProviderSpec, + Safety, + Scoring, + ScoringFunctions, ScoringFunctionsProtocolPrivate, + Shields, ShieldsProtocolPrivate, + ToolGroups, ToolGroupsProtocolPrivate, + ToolRuntime, + VectorIO, + VectorStore, +) +from llama_stack_api import ( + Providers as ProvidersAPI, ) logger = get_logger(name=__name__, category="core") diff --git a/src/llama_stack/core/routers/__init__.py b/src/llama_stack/core/routers/__init__.py index 729d1c9ea..289755bcb 100644 --- a/src/llama_stack/core/routers/__init__.py +++ b/src/llama_stack/core/routers/__init__.py @@ -12,8 +12,8 @@ from llama_stack.core.datatypes import ( ) from llama_stack.core.stack import StackRunConfig from llama_stack.core.store import DistributionRegistry -from llama_stack.providers.datatypes import Api, RoutingTable from llama_stack.providers.utils.inference.inference_store import InferenceStore +from llama_stack_api import Api, RoutingTable async def get_routing_table_impl( diff --git a/src/llama_stack/core/routers/datasets.py b/src/llama_stack/core/routers/datasets.py index 2f1d5f78e..b6a5f3b96 100644 --- a/src/llama_stack/core/routers/datasets.py +++ b/src/llama_stack/core/routers/datasets.py @@ -6,11 +6,8 @@ from typing import Any -from llama_stack.apis.common.responses import PaginatedResponse -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import DatasetPurpose, DataSource from llama_stack.log import get_logger -from llama_stack.providers.datatypes import RoutingTable +from llama_stack_api import DatasetIO, DatasetPurpose, DataSource, PaginatedResponse, RoutingTable logger = get_logger(name=__name__, category="core::routers") diff --git a/src/llama_stack/core/routers/eval_scoring.py b/src/llama_stack/core/routers/eval_scoring.py index ffca81bf0..4d7269180 100644 --- a/src/llama_stack/core/routers/eval_scoring.py +++ b/src/llama_stack/core/routers/eval_scoring.py @@ -6,15 +6,18 @@ from typing import Any -from llama_stack.apis.eval import BenchmarkConfig, Eval, EvaluateResponse, Job -from llama_stack.apis.scoring import ( +from llama_stack.log import get_logger +from llama_stack_api import ( + BenchmarkConfig, + Eval, + EvaluateResponse, + Job, + RoutingTable, ScoreBatchResponse, ScoreResponse, Scoring, ScoringFnParams, ) -from llama_stack.log import get_logger -from llama_stack.providers.datatypes import RoutingTable logger = get_logger(name=__name__, category="core::routers") diff --git a/src/llama_stack/core/routers/inference.py b/src/llama_stack/core/routers/inference.py index d6270d428..719624e86 100644 --- a/src/llama_stack/core/routers/inference.py +++ b/src/llama_stack/core/routers/inference.py @@ -15,13 +15,25 @@ from openai.types.chat import ChatCompletionToolChoiceOptionParam as OpenAIChatC from openai.types.chat import ChatCompletionToolParam as OpenAIChatCompletionToolParam from pydantic import TypeAdapter -from llama_stack.apis.common.errors import ModelNotFoundError, ModelTypeError -from llama_stack.apis.inference import ( +from llama_stack.core.telemetry.telemetry import MetricEvent +from llama_stack.core.telemetry.tracing import enqueue_event, get_current_span +from llama_stack.log import get_logger +from llama_stack.models.llama.llama3.chat_format import ChatFormat +from llama_stack.models.llama.llama3.tokenizer import Tokenizer +from llama_stack.providers.utils.inference.inference_store import InferenceStore +from llama_stack_api import ( + HealthResponse, + HealthStatus, Inference, ListOpenAIChatCompletionResponse, + ModelNotFoundError, + ModelType, + ModelTypeError, OpenAIAssistantMessageParam, OpenAIChatCompletion, OpenAIChatCompletionChunk, + OpenAIChatCompletionContentPartImageParam, + OpenAIChatCompletionContentPartTextParam, OpenAIChatCompletionRequestWithExtraBody, OpenAIChatCompletionToolCall, OpenAIChatCompletionToolCallFunction, @@ -35,19 +47,8 @@ from llama_stack.apis.inference import ( OpenAIMessageParam, Order, RerankResponse, + RoutingTable, ) -from llama_stack.apis.inference.inference import ( - OpenAIChatCompletionContentPartImageParam, - OpenAIChatCompletionContentPartTextParam, -) -from llama_stack.apis.models import ModelType -from llama_stack.core.telemetry.telemetry import MetricEvent -from llama_stack.core.telemetry.tracing import enqueue_event, get_current_span -from llama_stack.log import get_logger -from llama_stack.models.llama.llama3.chat_format import ChatFormat -from llama_stack.models.llama.llama3.tokenizer import Tokenizer -from llama_stack.providers.datatypes import HealthResponse, HealthStatus, RoutingTable -from llama_stack.providers.utils.inference.inference_store import InferenceStore logger = get_logger(name=__name__, category="core::routers") @@ -416,7 +417,7 @@ class InferenceRouter(Inference): prompt_tokens=chunk.usage.prompt_tokens, completion_tokens=chunk.usage.completion_tokens, total_tokens=chunk.usage.total_tokens, - model_id=fully_qualified_model_id, + fully_qualified_model_id=fully_qualified_model_id, provider_id=provider_id, ) for metric in metrics: diff --git a/src/llama_stack/core/routers/safety.py b/src/llama_stack/core/routers/safety.py index e5ff2ada9..2bc99f14f 100644 --- a/src/llama_stack/core/routers/safety.py +++ b/src/llama_stack/core/routers/safety.py @@ -6,13 +6,9 @@ from typing import Any -from llama_stack.apis.inference import OpenAIMessageParam -from llama_stack.apis.safety import RunShieldResponse, Safety -from llama_stack.apis.safety.safety import ModerationObject -from llama_stack.apis.shields import Shield from llama_stack.core.datatypes import SafetyConfig from llama_stack.log import get_logger -from llama_stack.providers.datatypes import RoutingTable +from llama_stack_api import ModerationObject, OpenAIMessageParam, RoutingTable, RunShieldResponse, Safety, Shield logger = get_logger(name=__name__, category="core::routers") diff --git a/src/llama_stack/core/routers/tool_runtime.py b/src/llama_stack/core/routers/tool_runtime.py index fb13d94a4..b387cb657 100644 --- a/src/llama_stack/core/routers/tool_runtime.py +++ b/src/llama_stack/core/routers/tool_runtime.py @@ -6,14 +6,12 @@ from typing import Any -from llama_stack.apis.common.content_types import ( +from llama_stack.log import get_logger +from llama_stack_api import ( URL, -) -from llama_stack.apis.tools import ( ListToolDefsResponse, ToolRuntime, ) -from llama_stack.log import get_logger from ..routing_tables.toolgroups import ToolGroupsRoutingTable @@ -36,16 +34,16 @@ class ToolRuntimeRouter(ToolRuntime): logger.debug("ToolRuntimeRouter.shutdown") pass - async def invoke_tool(self, tool_name: str, kwargs: dict[str, Any]) -> Any: + async def invoke_tool(self, tool_name: str, kwargs: dict[str, Any], authorization: str | None = None) -> Any: logger.debug(f"ToolRuntimeRouter.invoke_tool: {tool_name}") provider = await self.routing_table.get_provider_impl(tool_name) return await provider.invoke_tool( tool_name=tool_name, kwargs=kwargs, + authorization=authorization, ) async def list_runtime_tools( - self, tool_group_id: str | None = None, mcp_endpoint: URL | None = None + self, tool_group_id: str | None = None, mcp_endpoint: URL | None = None, authorization: str | None = None ) -> ListToolDefsResponse: - logger.debug(f"ToolRuntimeRouter.list_runtime_tools: {tool_group_id}") - return await self.routing_table.list_tools(tool_group_id) + return await self.routing_table.list_tools(tool_group_id, authorization=authorization) diff --git a/src/llama_stack/core/routers/vector_io.py b/src/llama_stack/core/routers/vector_io.py index ed5fb8253..5256dda44 100644 --- a/src/llama_stack/core/routers/vector_io.py +++ b/src/llama_stack/core/routers/vector_io.py @@ -10,13 +10,20 @@ from typing import Annotated, Any from fastapi import Body -from llama_stack.apis.common.content_types import InterleavedContent -from llama_stack.apis.models import ModelType -from llama_stack.apis.vector_io import ( +from llama_stack.core.datatypes import VectorStoresConfig +from llama_stack.log import get_logger +from llama_stack_api import ( Chunk, + HealthResponse, + HealthStatus, + InterleavedContent, + ModelNotFoundError, + ModelType, + ModelTypeError, OpenAICreateVectorStoreFileBatchRequestWithExtraBody, OpenAICreateVectorStoreRequestWithExtraBody, QueryChunksResponse, + RoutingTable, SearchRankingOptions, VectorIO, VectorStoreChunkingStrategy, @@ -33,9 +40,6 @@ from llama_stack.apis.vector_io import ( VectorStoreObject, VectorStoreSearchResponsePage, ) -from llama_stack.core.datatypes import VectorStoresConfig -from llama_stack.log import get_logger -from llama_stack.providers.datatypes import HealthResponse, HealthStatus, RoutingTable logger = get_logger(name=__name__, category="core::routers") @@ -122,6 +126,14 @@ class VectorIORouter(VectorIO): if embedding_model is not None and embedding_dimension is None: embedding_dimension = await self._get_embedding_model_dimension(embedding_model) + # Validate that embedding model exists and is of the correct type + if embedding_model is not None: + model = await self.routing_table.get_object_by_identifier("model", embedding_model) + if model is None: + raise ModelNotFoundError(embedding_model) + if model.model_type != ModelType.embedding: + raise ModelTypeError(embedding_model, model.model_type, ModelType.embedding) + # Auto-select provider if not specified if provider_id is None: num_providers = len(self.routing_table.impls_by_provider_id) diff --git a/src/llama_stack/core/routing_tables/benchmarks.py b/src/llama_stack/core/routing_tables/benchmarks.py index 8c87d395d..9037ffe8b 100644 --- a/src/llama_stack/core/routing_tables/benchmarks.py +++ b/src/llama_stack/core/routing_tables/benchmarks.py @@ -6,11 +6,11 @@ from typing import Any -from llama_stack.apis.benchmarks import Benchmark, Benchmarks, ListBenchmarksResponse from llama_stack.core.datatypes import ( BenchmarkWithOwner, ) from llama_stack.log import get_logger +from llama_stack_api import Benchmark, Benchmarks, ListBenchmarksResponse from .common import CommonRoutingTableImpl diff --git a/src/llama_stack/core/routing_tables/common.py b/src/llama_stack/core/routing_tables/common.py index d6faf93c5..a9e3ff95f 100644 --- a/src/llama_stack/core/routing_tables/common.py +++ b/src/llama_stack/core/routing_tables/common.py @@ -6,9 +6,6 @@ from typing import Any -from llama_stack.apis.common.errors import ModelNotFoundError -from llama_stack.apis.models import Model -from llama_stack.apis.resource import ResourceType from llama_stack.core.access_control.access_control import AccessDeniedError, is_action_allowed from llama_stack.core.access_control.datatypes import Action from llama_stack.core.datatypes import ( @@ -21,7 +18,7 @@ from llama_stack.core.datatypes import ( from llama_stack.core.request_headers import get_authenticated_user from llama_stack.core.store import DistributionRegistry from llama_stack.log import get_logger -from llama_stack.providers.datatypes import Api, RoutingTable +from llama_stack_api import Api, Model, ModelNotFoundError, ResourceType, RoutingTable logger = get_logger(name=__name__, category="core::routing_tables") diff --git a/src/llama_stack/core/routing_tables/datasets.py b/src/llama_stack/core/routing_tables/datasets.py index b129c9ec5..62fd07b13 100644 --- a/src/llama_stack/core/routing_tables/datasets.py +++ b/src/llama_stack/core/routing_tables/datasets.py @@ -7,22 +7,22 @@ import uuid from typing import Any -from llama_stack.apis.common.errors import DatasetNotFoundError -from llama_stack.apis.datasets import ( +from llama_stack.core.datatypes import ( + DatasetWithOwner, +) +from llama_stack.log import get_logger +from llama_stack_api import ( Dataset, + DatasetNotFoundError, DatasetPurpose, Datasets, DatasetType, DataSource, ListDatasetsResponse, + ResourceType, RowsDataSource, URIDataSource, ) -from llama_stack.apis.resource import ResourceType -from llama_stack.core.datatypes import ( - DatasetWithOwner, -) -from llama_stack.log import get_logger from .common import CommonRoutingTableImpl diff --git a/src/llama_stack/core/routing_tables/models.py b/src/llama_stack/core/routing_tables/models.py index 1fb1186cd..1facbb27b 100644 --- a/src/llama_stack/core/routing_tables/models.py +++ b/src/llama_stack/core/routing_tables/models.py @@ -7,8 +7,6 @@ import time from typing import Any -from llama_stack.apis.common.errors import ModelNotFoundError -from llama_stack.apis.models import ListModelsResponse, Model, Models, ModelType, OpenAIListModelsResponse, OpenAIModel from llama_stack.core.datatypes import ( ModelWithOwner, RegistryEntrySource, @@ -16,6 +14,15 @@ from llama_stack.core.datatypes import ( from llama_stack.core.request_headers import PROVIDER_DATA_VAR, NeedsRequestProviderData from llama_stack.core.utils.dynamic import instantiate_class_type from llama_stack.log import get_logger +from llama_stack_api import ( + ListModelsResponse, + Model, + ModelNotFoundError, + Models, + ModelType, + OpenAIListModelsResponse, + OpenAIModel, +) from .common import CommonRoutingTableImpl, lookup_model diff --git a/src/llama_stack/core/routing_tables/scoring_functions.py b/src/llama_stack/core/routing_tables/scoring_functions.py index 520f07014..65ed26b85 100644 --- a/src/llama_stack/core/routing_tables/scoring_functions.py +++ b/src/llama_stack/core/routing_tables/scoring_functions.py @@ -4,18 +4,18 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import ParamType -from llama_stack.apis.resource import ResourceType -from llama_stack.apis.scoring_functions import ( - ListScoringFunctionsResponse, - ScoringFn, - ScoringFnParams, - ScoringFunctions, -) from llama_stack.core.datatypes import ( ScoringFnWithOwner, ) from llama_stack.log import get_logger +from llama_stack_api import ( + ListScoringFunctionsResponse, + ParamType, + ResourceType, + ScoringFn, + ScoringFnParams, + ScoringFunctions, +) from .common import CommonRoutingTableImpl diff --git a/src/llama_stack/core/routing_tables/shields.py b/src/llama_stack/core/routing_tables/shields.py index b1918d20a..97b2efb96 100644 --- a/src/llama_stack/core/routing_tables/shields.py +++ b/src/llama_stack/core/routing_tables/shields.py @@ -6,12 +6,11 @@ from typing import Any -from llama_stack.apis.resource import ResourceType -from llama_stack.apis.shields import ListShieldsResponse, Shield, Shields from llama_stack.core.datatypes import ( ShieldWithOwner, ) from llama_stack.log import get_logger +from llama_stack_api import ListShieldsResponse, ResourceType, Shield, Shields from .common import CommonRoutingTableImpl diff --git a/src/llama_stack/core/routing_tables/toolgroups.py b/src/llama_stack/core/routing_tables/toolgroups.py index 2d47bbb17..8676ce35e 100644 --- a/src/llama_stack/core/routing_tables/toolgroups.py +++ b/src/llama_stack/core/routing_tables/toolgroups.py @@ -6,11 +6,17 @@ from typing import Any -from llama_stack.apis.common.content_types import URL -from llama_stack.apis.common.errors import ToolGroupNotFoundError -from llama_stack.apis.tools import ListToolDefsResponse, ListToolGroupsResponse, ToolDef, ToolGroup, ToolGroups from llama_stack.core.datatypes import AuthenticationRequiredError, ToolGroupWithOwner from llama_stack.log import get_logger +from llama_stack_api import ( + URL, + ListToolDefsResponse, + ListToolGroupsResponse, + ToolDef, + ToolGroup, + ToolGroupNotFoundError, + ToolGroups, +) from .common import CommonRoutingTableImpl @@ -43,7 +49,9 @@ class ToolGroupsRoutingTable(CommonRoutingTableImpl, ToolGroups): routing_key = self.tool_to_toolgroup[routing_key] return await super().get_provider_impl(routing_key, provider_id) - async def list_tools(self, toolgroup_id: str | None = None) -> ListToolDefsResponse: + async def list_tools( + self, toolgroup_id: str | None = None, authorization: str | None = None + ) -> ListToolDefsResponse: if toolgroup_id: if group_id := parse_toolgroup_from_toolgroup_name_pair(toolgroup_id): toolgroup_id = group_id @@ -55,7 +63,7 @@ class ToolGroupsRoutingTable(CommonRoutingTableImpl, ToolGroups): for toolgroup in toolgroups: if toolgroup.identifier not in self.toolgroups_to_tools: try: - await self._index_tools(toolgroup) + await self._index_tools(toolgroup, authorization=authorization) except AuthenticationRequiredError: # Send authentication errors back to the client so it knows # that it needs to supply credentials for remote MCP servers. @@ -70,9 +78,11 @@ class ToolGroupsRoutingTable(CommonRoutingTableImpl, ToolGroups): return ListToolDefsResponse(data=all_tools) - async def _index_tools(self, toolgroup: ToolGroup): + async def _index_tools(self, toolgroup: ToolGroup, authorization: str | None = None): provider_impl = await super().get_provider_impl(toolgroup.identifier, toolgroup.provider_id) - tooldefs_response = await provider_impl.list_runtime_tools(toolgroup.identifier, toolgroup.mcp_endpoint) + tooldefs_response = await provider_impl.list_runtime_tools( + toolgroup.identifier, toolgroup.mcp_endpoint, authorization=authorization + ) tooldefs = tooldefs_response.data for t in tooldefs: diff --git a/src/llama_stack/core/routing_tables/vector_stores.py b/src/llama_stack/core/routing_tables/vector_stores.py index e77739abe..93c119542 100644 --- a/src/llama_stack/core/routing_tables/vector_stores.py +++ b/src/llama_stack/core/routing_tables/vector_stores.py @@ -6,12 +6,17 @@ from typing import Any -from llama_stack.apis.common.errors import ModelNotFoundError, ModelTypeError -from llama_stack.apis.models import ModelType -from llama_stack.apis.resource import ResourceType +from llama_stack.core.datatypes import ( + VectorStoreWithOwner, +) +from llama_stack.log import get_logger # Removed VectorStores import to avoid exposing public API -from llama_stack.apis.vector_io.vector_io import ( +from llama_stack_api import ( + ModelNotFoundError, + ModelType, + ModelTypeError, + ResourceType, SearchRankingOptions, VectorStoreChunkingStrategy, VectorStoreDeleteResponse, @@ -22,10 +27,6 @@ from llama_stack.apis.vector_io.vector_io import ( VectorStoreObject, VectorStoreSearchResponsePage, ) -from llama_stack.core.datatypes import ( - VectorStoreWithOwner, -) -from llama_stack.log import get_logger from .common import CommonRoutingTableImpl, lookup_model diff --git a/src/llama_stack/core/server/auth_providers.py b/src/llama_stack/core/server/auth_providers.py index da398bf99..66942dd39 100644 --- a/src/llama_stack/core/server/auth_providers.py +++ b/src/llama_stack/core/server/auth_providers.py @@ -13,7 +13,6 @@ import httpx import jwt from pydantic import BaseModel, Field -from llama_stack.apis.common.errors import TokenValidationError from llama_stack.core.datatypes import ( AuthenticationConfig, CustomAuthConfig, @@ -23,6 +22,7 @@ from llama_stack.core.datatypes import ( User, ) from llama_stack.log import get_logger +from llama_stack_api import TokenValidationError logger = get_logger(name=__name__, category="core::auth") diff --git a/src/llama_stack/core/server/routes.py b/src/llama_stack/core/server/routes.py index 4f7ff2295..af5002565 100644 --- a/src/llama_stack/core/server/routes.py +++ b/src/llama_stack/core/server/routes.py @@ -12,9 +12,8 @@ from typing import Any from aiohttp import hdrs from starlette.routing import Route -from llama_stack.apis.datatypes import Api, ExternalApiSpec from llama_stack.core.resolver import api_protocol_map -from llama_stack.schema_utils import WebMethod +from llama_stack_api import Api, ExternalApiSpec, WebMethod EndpointFunc = Callable[..., Any] PathParams = dict[str, str] diff --git a/src/llama_stack/core/server/server.py b/src/llama_stack/core/server/server.py index 80505c3f9..0d3513980 100644 --- a/src/llama_stack/core/server/server.py +++ b/src/llama_stack/core/server/server.py @@ -31,8 +31,6 @@ from fastapi.responses import JSONResponse, StreamingResponse from openai import BadRequestError from pydantic import BaseModel, ValidationError -from llama_stack.apis.common.errors import ConflictError, ResourceNotFoundError -from llama_stack.apis.common.responses import PaginatedResponse from llama_stack.core.access_control.access_control import AccessDeniedError from llama_stack.core.datatypes import ( AuthenticationRequiredError, @@ -58,7 +56,7 @@ from llama_stack.core.utils.config import redact_sensitive_fields from llama_stack.core.utils.config_resolution import Mode, resolve_config_or_distro from llama_stack.core.utils.context import preserve_contexts_async_generator from llama_stack.log import LoggingConfig, get_logger, setup_logging -from llama_stack.providers.datatypes import Api +from llama_stack_api import Api, ConflictError, PaginatedResponse, ResourceNotFoundError from .auth import AuthenticationMiddleware from .quota import QuotaMiddleware @@ -526,8 +524,8 @@ def extract_path_params(route: str) -> list[str]: def remove_disabled_providers(obj): if isinstance(obj, dict): - keys = ["provider_id", "shield_id", "provider_model_id", "model_id"] - if any(k in obj and obj[k] in ("__disabled__", "", None) for k in keys): + # Filter out items where provider_id is explicitly disabled or empty + if "provider_id" in obj and obj["provider_id"] in ("__disabled__", "", None): return None return {k: v for k, v in ((k, remove_disabled_providers(v)) for k, v in obj.items()) if v is not None} elif isinstance(obj, list): diff --git a/src/llama_stack/core/stack.py b/src/llama_stack/core/stack.py index 2ed0eccd2..00d990cb1 100644 --- a/src/llama_stack/core/stack.py +++ b/src/llama_stack/core/stack.py @@ -13,26 +13,6 @@ from typing import Any import yaml -from llama_stack.apis.agents import Agents -from llama_stack.apis.batches import Batches -from llama_stack.apis.benchmarks import Benchmarks -from llama_stack.apis.conversations import Conversations -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Datasets -from llama_stack.apis.eval import Eval -from llama_stack.apis.files import Files -from llama_stack.apis.inference import Inference -from llama_stack.apis.inspect import Inspect -from llama_stack.apis.models import Models -from llama_stack.apis.post_training import PostTraining -from llama_stack.apis.prompts import Prompts -from llama_stack.apis.providers import Providers -from llama_stack.apis.safety import Safety -from llama_stack.apis.scoring import Scoring -from llama_stack.apis.scoring_functions import ScoringFunctions -from llama_stack.apis.shields import Shields -from llama_stack.apis.tools import ToolGroups, ToolRuntime -from llama_stack.apis.vector_io import VectorIO from llama_stack.core.conversations.conversations import ConversationServiceConfig, ConversationServiceImpl from llama_stack.core.datatypes import Provider, SafetyConfig, StackRunConfig, VectorStoresConfig from llama_stack.core.distribution import get_provider_registry @@ -54,7 +34,30 @@ from llama_stack.core.storage.datatypes import ( from llama_stack.core.store.registry import create_dist_registry from llama_stack.core.utils.dynamic import instantiate_class_type from llama_stack.log import get_logger -from llama_stack.providers.datatypes import Api +from llama_stack_api import ( + Agents, + Api, + Batches, + Benchmarks, + Conversations, + DatasetIO, + Datasets, + Eval, + Files, + Inference, + Inspect, + Models, + PostTraining, + Prompts, + Providers, + Safety, + Scoring, + ScoringFunctions, + Shields, + ToolGroups, + ToolRuntime, + VectorIO, +) logger = get_logger(name=__name__, category="core") diff --git a/src/llama_stack/core/telemetry/telemetry.py b/src/llama_stack/core/telemetry/telemetry.py index 459c1aa1a..5268fa641 100644 --- a/src/llama_stack/core/telemetry/telemetry.py +++ b/src/llama_stack/core/telemetry/telemetry.py @@ -28,7 +28,7 @@ from pydantic import BaseModel, Field from llama_stack.log import get_logger from llama_stack.models.llama.datatypes import Primitive -from llama_stack.schema_utils import json_schema_type, register_schema +from llama_stack_api import json_schema_type, register_schema ROOT_SPAN_MARKERS = ["__root__", "__root_span__"] diff --git a/src/llama_stack/distributions/dell/dell.py b/src/llama_stack/distributions/dell/dell.py index 88e72688f..52a07b7f1 100644 --- a/src/llama_stack/distributions/dell/dell.py +++ b/src/llama_stack/distributions/dell/dell.py @@ -4,7 +4,6 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.models import ModelType from llama_stack.core.datatypes import ( BuildProvider, ModelInput, @@ -17,6 +16,7 @@ from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) from llama_stack.providers.remote.vector_io.chroma import ChromaVectorIOConfig +from llama_stack_api import ModelType def get_distribution_template() -> DistributionTemplate: diff --git a/src/llama_stack/distributions/meta-reference-gpu/meta_reference.py b/src/llama_stack/distributions/meta-reference-gpu/meta_reference.py index 4e4ddef33..a515794d5 100644 --- a/src/llama_stack/distributions/meta-reference-gpu/meta_reference.py +++ b/src/llama_stack/distributions/meta-reference-gpu/meta_reference.py @@ -6,7 +6,6 @@ from pathlib import Path -from llama_stack.apis.models import ModelType from llama_stack.core.datatypes import ( BuildProvider, ModelInput, @@ -22,6 +21,7 @@ from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, ) from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig +from llama_stack_api import ModelType def get_distribution_template() -> DistributionTemplate: diff --git a/src/llama_stack/distributions/open-benchmark/open_benchmark.py b/src/llama_stack/distributions/open-benchmark/open_benchmark.py index 2b7760894..1f4dbf2c2 100644 --- a/src/llama_stack/distributions/open-benchmark/open_benchmark.py +++ b/src/llama_stack/distributions/open-benchmark/open_benchmark.py @@ -5,8 +5,6 @@ # the root directory of this source tree. -from llama_stack.apis.datasets import DatasetPurpose, URIDataSource -from llama_stack.apis.models import ModelType from llama_stack.core.datatypes import ( BenchmarkInput, BuildProvider, @@ -34,6 +32,7 @@ from llama_stack.providers.remote.vector_io.pgvector.config import ( PGVectorVectorIOConfig, ) from llama_stack.providers.utils.inference.model_registry import ProviderModelEntry +from llama_stack_api import DatasetPurpose, ModelType, URIDataSource def get_inference_providers() -> tuple[list[Provider], dict[str, list[ProviderModelEntry]]]: diff --git a/src/llama_stack/distributions/starter/starter.py b/src/llama_stack/distributions/starter/starter.py index c31ee0296..362e76e5a 100644 --- a/src/llama_stack/distributions/starter/starter.py +++ b/src/llama_stack/distributions/starter/starter.py @@ -19,7 +19,6 @@ from llama_stack.core.datatypes import ( ) from llama_stack.core.utils.dynamic import instantiate_class_type from llama_stack.distributions.template import DistributionTemplate, RunConfigSettings -from llama_stack.providers.datatypes import RemoteProviderSpec from llama_stack.providers.inline.files.localfs.config import LocalfsFilesImplConfig from llama_stack.providers.inline.inference.sentence_transformers import ( SentenceTransformersInferenceConfig, @@ -38,6 +37,7 @@ from llama_stack.providers.remote.vector_io.qdrant.config import QdrantVectorIOC from llama_stack.providers.remote.vector_io.weaviate.config import WeaviateVectorIOConfig from llama_stack.providers.utils.kvstore.config import PostgresKVStoreConfig from llama_stack.providers.utils.sqlstore.sqlstore import PostgresSqlStoreConfig +from llama_stack_api import RemoteProviderSpec def _get_config_for_provider(provider_spec: ProviderSpec) -> dict[str, Any]: diff --git a/src/llama_stack/distributions/template.py b/src/llama_stack/distributions/template.py index e6813806a..5755a26de 100644 --- a/src/llama_stack/distributions/template.py +++ b/src/llama_stack/distributions/template.py @@ -12,8 +12,6 @@ import rich import yaml from pydantic import BaseModel, Field -from llama_stack.apis.datasets import DatasetPurpose -from llama_stack.apis.models import ModelType from llama_stack.core.datatypes import ( LLAMA_STACK_RUN_CONFIG_VERSION, Api, @@ -44,6 +42,7 @@ from llama_stack.providers.utils.kvstore.config import SqliteKVStoreConfig from llama_stack.providers.utils.kvstore.config import get_pip_packages as get_kv_pip_packages from llama_stack.providers.utils.sqlstore.sqlstore import SqliteSqlStoreConfig from llama_stack.providers.utils.sqlstore.sqlstore import get_pip_packages as get_sql_pip_packages +from llama_stack_api import DatasetPurpose, ModelType def filter_empty_values(obj: Any) -> Any: diff --git a/src/llama_stack/providers/inline/agents/meta_reference/agents.py b/src/llama_stack/providers/inline/agents/meta_reference/agents.py index 880e0b680..347f6fdb1 100644 --- a/src/llama_stack/providers/inline/agents/meta_reference/agents.py +++ b/src/llama_stack/providers/inline/agents/meta_reference/agents.py @@ -5,29 +5,29 @@ # the root directory of this source tree. -from llama_stack.apis.agents import ( +from llama_stack.core.datatypes import AccessRule +from llama_stack.log import get_logger +from llama_stack.providers.utils.kvstore import InmemoryKVStoreImpl, kvstore_impl +from llama_stack.providers.utils.responses.responses_store import ResponsesStore +from llama_stack_api import ( Agents, + Conversations, + Inference, ListOpenAIResponseInputItem, ListOpenAIResponseObject, OpenAIDeleteResponseObject, OpenAIResponseInput, OpenAIResponseInputTool, OpenAIResponseObject, + OpenAIResponsePrompt, + OpenAIResponseText, Order, + ResponseGuardrail, + Safety, + ToolGroups, + ToolRuntime, + VectorIO, ) -from llama_stack.apis.agents.agents import ResponseGuardrail -from llama_stack.apis.agents.openai_responses import OpenAIResponsePrompt, OpenAIResponseText -from llama_stack.apis.conversations import Conversations -from llama_stack.apis.inference import ( - Inference, -) -from llama_stack.apis.safety import Safety -from llama_stack.apis.tools import ToolGroups, ToolRuntime -from llama_stack.apis.vector_io import VectorIO -from llama_stack.core.datatypes import AccessRule -from llama_stack.log import get_logger -from llama_stack.providers.utils.kvstore import InmemoryKVStoreImpl, kvstore_impl -from llama_stack.providers.utils.responses.responses_store import ResponsesStore from .config import MetaReferenceAgentsImplConfig from .responses.openai_responses import OpenAIResponsesImpl diff --git a/src/llama_stack/providers/inline/agents/meta_reference/responses/openai_responses.py b/src/llama_stack/providers/inline/agents/meta_reference/responses/openai_responses.py index ed7f959c0..cb0fe284e 100644 --- a/src/llama_stack/providers/inline/agents/meta_reference/responses/openai_responses.py +++ b/src/llama_stack/providers/inline/agents/meta_reference/responses/openai_responses.py @@ -10,12 +10,20 @@ from collections.abc import AsyncIterator from pydantic import BaseModel, TypeAdapter -from llama_stack.apis.agents import Order -from llama_stack.apis.agents.agents import ResponseGuardrailSpec -from llama_stack.apis.agents.openai_responses import ( +from llama_stack.log import get_logger +from llama_stack.providers.utils.responses.responses_store import ( + ResponsesStore, + _OpenAIResponseObjectWithInputAndMessages, +) +from llama_stack_api import ( + ConversationItem, + Conversations, + Inference, + InvalidConversationIdError, ListOpenAIResponseInputItem, ListOpenAIResponseObject, OpenAIDeleteResponseObject, + OpenAIMessageParam, OpenAIResponseInput, OpenAIResponseInputMessageContentText, OpenAIResponseInputTool, @@ -25,24 +33,13 @@ from llama_stack.apis.agents.openai_responses import ( OpenAIResponsePrompt, OpenAIResponseText, OpenAIResponseTextFormat, -) -from llama_stack.apis.common.errors import ( - InvalidConversationIdError, -) -from llama_stack.apis.conversations import Conversations -from llama_stack.apis.conversations.conversations import ConversationItem -from llama_stack.apis.inference import ( - Inference, - OpenAIMessageParam, OpenAISystemMessageParam, -) -from llama_stack.apis.safety import Safety -from llama_stack.apis.tools import ToolGroups, ToolRuntime -from llama_stack.apis.vector_io import VectorIO -from llama_stack.log import get_logger -from llama_stack.providers.utils.responses.responses_store import ( - ResponsesStore, - _OpenAIResponseObjectWithInputAndMessages, + Order, + ResponseGuardrailSpec, + Safety, + ToolGroups, + ToolRuntime, + VectorIO, ) from .streaming import StreamingResponseOrchestrator @@ -260,6 +257,19 @@ class OpenAIResponsesImpl: stream = bool(stream) text = OpenAIResponseText(format=OpenAIResponseTextFormat(type="text")) if text is None else text + # Validate MCP tools: ensure Authorization header is not passed via headers dict + if tools: + from llama_stack_api.openai_responses import OpenAIResponseInputToolMCP + + for tool in tools: + if isinstance(tool, OpenAIResponseInputToolMCP) and tool.headers: + for key in tool.headers.keys(): + if key.lower() == "authorization": + raise ValueError( + "Authorization header cannot be passed via 'headers'. " + "Please use the 'authorization' parameter instead." + ) + guardrail_ids = extract_guardrail_ids(guardrails) if guardrails else [] if conversation is not None: diff --git a/src/llama_stack/providers/inline/agents/meta_reference/responses/streaming.py b/src/llama_stack/providers/inline/agents/meta_reference/responses/streaming.py index c16bc8df3..c0b62958f 100644 --- a/src/llama_stack/providers/inline/agents/meta_reference/responses/streaming.py +++ b/src/llama_stack/providers/inline/agents/meta_reference/responses/streaming.py @@ -8,10 +8,21 @@ import uuid from collections.abc import AsyncIterator from typing import Any -from llama_stack.apis.agents.openai_responses import ( +from llama_stack.core.telemetry import tracing +from llama_stack.log import get_logger +from llama_stack.providers.utils.inference.prompt_adapter import interleaved_content_as_str +from llama_stack_api import ( AllowedToolsFilter, ApprovalFilter, + Inference, MCPListToolsTool, + OpenAIAssistantMessageParam, + OpenAIChatCompletion, + OpenAIChatCompletionChunk, + OpenAIChatCompletionRequestWithExtraBody, + OpenAIChatCompletionToolCall, + OpenAIChoice, + OpenAIMessageParam, OpenAIResponseContentPartOutputText, OpenAIResponseContentPartReasoningText, OpenAIResponseContentPartRefusal, @@ -56,19 +67,6 @@ from llama_stack.apis.agents.openai_responses import ( OpenAIResponseUsageOutputTokensDetails, WebSearchToolTypes, ) -from llama_stack.apis.inference import ( - Inference, - OpenAIAssistantMessageParam, - OpenAIChatCompletion, - OpenAIChatCompletionChunk, - OpenAIChatCompletionRequestWithExtraBody, - OpenAIChatCompletionToolCall, - OpenAIChoice, - OpenAIMessageParam, -) -from llama_stack.core.telemetry import tracing -from llama_stack.log import get_logger -from llama_stack.providers.utils.inference.prompt_adapter import interleaved_content_as_str from .types import ChatCompletionContext, ChatCompletionResult from .utils import ( @@ -1025,9 +1023,9 @@ class StreamingResponseOrchestrator: """Process all tools and emit appropriate streaming events.""" from openai.types.chat import ChatCompletionToolParam - from llama_stack.apis.tools import ToolDef from llama_stack.models.llama.datatypes import ToolDefinition from llama_stack.providers.utils.inference.openai_compat import convert_tooldef_to_openai_tool + from llama_stack_api import ToolDef def make_openai_tool(tool_name: str, tool: ToolDef) -> ChatCompletionToolParam: tool_def = ToolDefinition( @@ -1093,10 +1091,12 @@ class StreamingResponseOrchestrator: "server_url": mcp_tool.server_url, "mcp_list_tools_id": list_id, } + # List MCP tools with authorization from tool config async with tracing.span("list_mcp_tools", attributes): tool_defs = await list_mcp_tools( endpoint=mcp_tool.server_url, - headers=mcp_tool.headers or {}, + headers=mcp_tool.headers, + authorization=mcp_tool.authorization, ) # Create the MCP list tools message diff --git a/src/llama_stack/providers/inline/agents/meta_reference/responses/tool_executor.py b/src/llama_stack/providers/inline/agents/meta_reference/responses/tool_executor.py index 09a161d50..4f294a979 100644 --- a/src/llama_stack/providers/inline/agents/meta_reference/responses/tool_executor.py +++ b/src/llama_stack/providers/inline/agents/meta_reference/responses/tool_executor.py @@ -9,7 +9,14 @@ import json from collections.abc import AsyncIterator from typing import Any -from llama_stack.apis.agents.openai_responses import ( +from llama_stack.core.telemetry import tracing +from llama_stack.log import get_logger +from llama_stack_api import ( + ImageContentItem, + OpenAIChatCompletionContentPartImageParam, + OpenAIChatCompletionContentPartTextParam, + OpenAIChatCompletionToolCall, + OpenAIImageURL, OpenAIResponseInputToolFileSearch, OpenAIResponseInputToolMCP, OpenAIResponseObjectStreamResponseFileSearchCallCompleted, @@ -23,24 +30,14 @@ from llama_stack.apis.agents.openai_responses import ( OpenAIResponseObjectStreamResponseWebSearchCallSearching, OpenAIResponseOutputMessageFileSearchToolCall, OpenAIResponseOutputMessageFileSearchToolCallResults, - OpenAIResponseOutputMessageMCPCall, OpenAIResponseOutputMessageWebSearchToolCall, -) -from llama_stack.apis.common.content_types import ( - ImageContentItem, - TextContentItem, -) -from llama_stack.apis.inference import ( - OpenAIChatCompletionContentPartImageParam, - OpenAIChatCompletionContentPartTextParam, - OpenAIChatCompletionToolCall, - OpenAIImageURL, OpenAIToolMessageParam, + TextContentItem, + ToolGroups, + ToolInvocationResult, + ToolRuntime, + VectorIO, ) -from llama_stack.apis.tools import ToolGroups, ToolInvocationResult, ToolRuntime -from llama_stack.apis.vector_io import VectorIO -from llama_stack.core.telemetry import tracing -from llama_stack.log import get_logger from .types import ChatCompletionContext, ToolExecutionResult @@ -299,12 +296,14 @@ class ToolExecutor: "server_url": mcp_tool.server_url, "tool_name": function_name, } + # Invoke MCP tool with authorization from tool config async with tracing.span("invoke_mcp_tool", attributes): result = await invoke_mcp_tool( endpoint=mcp_tool.server_url, - headers=mcp_tool.headers or {}, tool_name=function_name, kwargs=tool_kwargs, + headers=mcp_tool.headers, + authorization=mcp_tool.authorization, ) elif function_name == "knowledge_search": response_file_search_tool = ( @@ -398,6 +397,10 @@ class ToolExecutor: # Build output message message: Any if mcp_tool_to_server and function.name in mcp_tool_to_server: + from llama_stack_api import ( + OpenAIResponseOutputMessageMCPCall, + ) + message = OpenAIResponseOutputMessageMCPCall( id=item_id, arguments=function.arguments, diff --git a/src/llama_stack/providers/inline/agents/meta_reference/responses/types.py b/src/llama_stack/providers/inline/agents/meta_reference/responses/types.py index 3b9a14b01..f6efcee22 100644 --- a/src/llama_stack/providers/inline/agents/meta_reference/responses/types.py +++ b/src/llama_stack/providers/inline/agents/meta_reference/responses/types.py @@ -10,7 +10,10 @@ from typing import cast from openai.types.chat import ChatCompletionToolParam from pydantic import BaseModel -from llama_stack.apis.agents.openai_responses import ( +from llama_stack_api import ( + OpenAIChatCompletionToolCall, + OpenAIMessageParam, + OpenAIResponseFormatParam, OpenAIResponseInput, OpenAIResponseInputTool, OpenAIResponseInputToolFileSearch, @@ -26,7 +29,6 @@ from llama_stack.apis.agents.openai_responses import ( OpenAIResponseTool, OpenAIResponseToolMCP, ) -from llama_stack.apis.inference import OpenAIChatCompletionToolCall, OpenAIMessageParam, OpenAIResponseFormatParam class ToolExecutionResult(BaseModel): diff --git a/src/llama_stack/providers/inline/agents/meta_reference/responses/utils.py b/src/llama_stack/providers/inline/agents/meta_reference/responses/utils.py index 26af1d595..943bbae41 100644 --- a/src/llama_stack/providers/inline/agents/meta_reference/responses/utils.py +++ b/src/llama_stack/providers/inline/agents/meta_reference/responses/utils.py @@ -9,9 +9,23 @@ import re import uuid from collections.abc import Sequence -from llama_stack.apis.agents.agents import ResponseGuardrailSpec -from llama_stack.apis.agents.openai_responses import ( +from llama_stack_api import ( + OpenAIAssistantMessageParam, + OpenAIChatCompletionContentPartImageParam, + OpenAIChatCompletionContentPartParam, + OpenAIChatCompletionContentPartTextParam, + OpenAIChatCompletionToolCall, + OpenAIChatCompletionToolCallFunction, + OpenAIChoice, + OpenAIDeveloperMessageParam, + OpenAIImageURL, + OpenAIJSONSchema, + OpenAIMessageParam, OpenAIResponseAnnotationFileCitation, + OpenAIResponseFormatJSONObject, + OpenAIResponseFormatJSONSchema, + OpenAIResponseFormatParam, + OpenAIResponseFormatText, OpenAIResponseInput, OpenAIResponseInputFunctionToolCallOutput, OpenAIResponseInputMessageContent, @@ -27,28 +41,12 @@ from llama_stack.apis.agents.openai_responses import ( OpenAIResponseOutputMessageMCPCall, OpenAIResponseOutputMessageMCPListTools, OpenAIResponseText, -) -from llama_stack.apis.inference import ( - OpenAIAssistantMessageParam, - OpenAIChatCompletionContentPartImageParam, - OpenAIChatCompletionContentPartParam, - OpenAIChatCompletionContentPartTextParam, - OpenAIChatCompletionToolCall, - OpenAIChatCompletionToolCallFunction, - OpenAIChoice, - OpenAIDeveloperMessageParam, - OpenAIImageURL, - OpenAIJSONSchema, - OpenAIMessageParam, - OpenAIResponseFormatJSONObject, - OpenAIResponseFormatJSONSchema, - OpenAIResponseFormatParam, - OpenAIResponseFormatText, OpenAISystemMessageParam, OpenAIToolMessageParam, OpenAIUserMessageParam, + ResponseGuardrailSpec, + Safety, ) -from llama_stack.apis.safety import Safety async def convert_chat_choice_to_response_message( diff --git a/src/llama_stack/providers/inline/agents/meta_reference/safety.py b/src/llama_stack/providers/inline/agents/meta_reference/safety.py index f0ae51423..bfb557a99 100644 --- a/src/llama_stack/providers/inline/agents/meta_reference/safety.py +++ b/src/llama_stack/providers/inline/agents/meta_reference/safety.py @@ -6,10 +6,9 @@ import asyncio -from llama_stack.apis.inference import OpenAIMessageParam -from llama_stack.apis.safety import Safety, SafetyViolation, ViolationLevel from llama_stack.core.telemetry import tracing from llama_stack.log import get_logger +from llama_stack_api import OpenAIMessageParam, Safety, SafetyViolation, ViolationLevel log = get_logger(name=__name__, category="agents::meta_reference") diff --git a/src/llama_stack/providers/inline/batches/reference/__init__.py b/src/llama_stack/providers/inline/batches/reference/__init__.py index a8ae92eb2..11c4b06a9 100644 --- a/src/llama_stack/providers/inline/batches/reference/__init__.py +++ b/src/llama_stack/providers/inline/batches/reference/__init__.py @@ -6,11 +6,9 @@ from typing import Any -from llama_stack.apis.files import Files -from llama_stack.apis.inference import Inference -from llama_stack.apis.models import Models from llama_stack.core.datatypes import AccessRule, Api from llama_stack.providers.utils.kvstore import kvstore_impl +from llama_stack_api import Files, Inference, Models from .batches import ReferenceBatchesImpl from .config import ReferenceBatchesImplConfig diff --git a/src/llama_stack/providers/inline/batches/reference/batches.py b/src/llama_stack/providers/inline/batches/reference/batches.py index 7c4358b84..73727799d 100644 --- a/src/llama_stack/providers/inline/batches/reference/batches.py +++ b/src/llama_stack/providers/inline/batches/reference/batches.py @@ -16,24 +16,28 @@ from typing import Any, Literal from openai.types.batch import BatchError, Errors from pydantic import BaseModel -from llama_stack.apis.batches import Batches, BatchObject, ListBatchesResponse -from llama_stack.apis.common.errors import ConflictError, ResourceNotFoundError -from llama_stack.apis.files import Files, OpenAIFilePurpose -from llama_stack.apis.inference import ( +from llama_stack.log import get_logger +from llama_stack.providers.utils.kvstore import KVStore +from llama_stack_api import ( + Batches, + BatchObject, + ConflictError, + Files, Inference, + ListBatchesResponse, + Models, OpenAIAssistantMessageParam, OpenAIChatCompletionRequestWithExtraBody, OpenAICompletionRequestWithExtraBody, OpenAIDeveloperMessageParam, OpenAIEmbeddingsRequestWithExtraBody, + OpenAIFilePurpose, OpenAIMessageParam, OpenAISystemMessageParam, OpenAIToolMessageParam, OpenAIUserMessageParam, + ResourceNotFoundError, ) -from llama_stack.apis.models import Models -from llama_stack.log import get_logger -from llama_stack.providers.utils.kvstore import KVStore from .config import ReferenceBatchesImplConfig diff --git a/src/llama_stack/providers/inline/datasetio/localfs/datasetio.py b/src/llama_stack/providers/inline/datasetio/localfs/datasetio.py index e8ebeb30d..6ab1a540f 100644 --- a/src/llama_stack/providers/inline/datasetio/localfs/datasetio.py +++ b/src/llama_stack/providers/inline/datasetio/localfs/datasetio.py @@ -5,13 +5,10 @@ # the root directory of this source tree. from typing import Any -from llama_stack.apis.common.responses import PaginatedResponse -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Dataset -from llama_stack.providers.datatypes import DatasetsProtocolPrivate from llama_stack.providers.utils.datasetio.url_utils import get_dataframe_from_uri from llama_stack.providers.utils.kvstore import kvstore_impl from llama_stack.providers.utils.pagination import paginate_records +from llama_stack_api import Dataset, DatasetIO, DatasetsProtocolPrivate, PaginatedResponse from .config import LocalFSDatasetIOConfig diff --git a/src/llama_stack/providers/inline/eval/meta_reference/eval.py b/src/llama_stack/providers/inline/eval/meta_reference/eval.py index 5ddbd56c5..d43e569e2 100644 --- a/src/llama_stack/providers/inline/eval/meta_reference/eval.py +++ b/src/llama_stack/providers/inline/eval/meta_reference/eval.py @@ -8,24 +8,27 @@ from typing import Any from tqdm import tqdm -from llama_stack.apis.agents import Agents -from llama_stack.apis.benchmarks import Benchmark -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Datasets -from llama_stack.apis.inference import ( +from llama_stack.providers.utils.common.data_schema_validator import ColumnName +from llama_stack.providers.utils.kvstore import kvstore_impl +from llama_stack_api import ( + Agents, + Benchmark, + BenchmarkConfig, + BenchmarksProtocolPrivate, + DatasetIO, + Datasets, + Eval, + EvaluateResponse, Inference, + Job, + JobStatus, OpenAIChatCompletionRequestWithExtraBody, OpenAICompletionRequestWithExtraBody, OpenAISystemMessageParam, OpenAIUserMessageParam, + Scoring, ) -from llama_stack.apis.scoring import Scoring -from llama_stack.providers.datatypes import BenchmarksProtocolPrivate -from llama_stack.providers.utils.common.data_schema_validator import ColumnName -from llama_stack.providers.utils.kvstore import kvstore_impl -from .....apis.common.job_types import Job, JobStatus -from .....apis.eval.eval import BenchmarkConfig, Eval, EvaluateResponse from .config import MetaReferenceEvalConfig EVAL_TASKS_PREFIX = "benchmarks:" diff --git a/src/llama_stack/providers/inline/files/localfs/files.py b/src/llama_stack/providers/inline/files/localfs/files.py index a76b982ce..5fb35a378 100644 --- a/src/llama_stack/providers/inline/files/localfs/files.py +++ b/src/llama_stack/providers/inline/files/localfs/files.py @@ -11,16 +11,6 @@ from typing import Annotated from fastapi import Depends, File, Form, Response, UploadFile -from llama_stack.apis.common.errors import ResourceNotFoundError -from llama_stack.apis.common.responses import Order -from llama_stack.apis.files import ( - ExpiresAfter, - Files, - ListOpenAIFileResponse, - OpenAIFileDeleteResponse, - OpenAIFileObject, - OpenAIFilePurpose, -) from llama_stack.core.datatypes import AccessRule from llama_stack.core.id_generation import generate_object_id from llama_stack.log import get_logger @@ -28,6 +18,16 @@ from llama_stack.providers.utils.files.form_data import parse_expires_after from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl +from llama_stack_api import ( + ExpiresAfter, + Files, + ListOpenAIFileResponse, + OpenAIFileDeleteResponse, + OpenAIFileObject, + OpenAIFilePurpose, + Order, + ResourceNotFoundError, +) from .config import LocalfsFilesImplConfig diff --git a/src/llama_stack/providers/inline/inference/meta_reference/config.py b/src/llama_stack/providers/inline/inference/meta_reference/config.py index 961548f9c..ec6e8bfe8 100644 --- a/src/llama_stack/providers/inline/inference/meta_reference/config.py +++ b/src/llama_stack/providers/inline/inference/meta_reference/config.py @@ -8,8 +8,8 @@ from typing import Any from pydantic import BaseModel, field_validator -from llama_stack.apis.inference import QuantizationConfig from llama_stack.providers.utils.inference import supported_inference_models +from llama_stack_api import QuantizationConfig class MetaReferenceInferenceConfig(BaseModel): diff --git a/src/llama_stack/providers/inline/inference/meta_reference/generators.py b/src/llama_stack/providers/inline/inference/meta_reference/generators.py index 51a2ddfad..6781d0af9 100644 --- a/src/llama_stack/providers/inline/inference/meta_reference/generators.py +++ b/src/llama_stack/providers/inline/inference/meta_reference/generators.py @@ -10,7 +10,13 @@ from typing import Optional import torch from lmformatenforcer import JsonSchemaParser, TokenEnforcer, TokenEnforcerTokenizerData -from llama_stack.apis.inference import ( +from llama_stack.models.llama.datatypes import QuantizationMode, ToolPromptFormat +from llama_stack.models.llama.llama3.generation import Llama3 +from llama_stack.models.llama.llama3.tokenizer import Tokenizer as Llama3Tokenizer +from llama_stack.models.llama.llama4.generation import Llama4 +from llama_stack.models.llama.llama4.tokenizer import Tokenizer as Llama4Tokenizer +from llama_stack.models.llama.sku_types import Model, ModelFamily +from llama_stack_api import ( GreedySamplingStrategy, JsonSchemaResponseFormat, OpenAIChatCompletionRequestWithExtraBody, @@ -20,12 +26,6 @@ from llama_stack.apis.inference import ( SamplingParams, TopPSamplingStrategy, ) -from llama_stack.models.llama.datatypes import QuantizationMode, ToolPromptFormat -from llama_stack.models.llama.llama3.generation import Llama3 -from llama_stack.models.llama.llama3.tokenizer import Tokenizer as Llama3Tokenizer -from llama_stack.models.llama.llama4.generation import Llama4 -from llama_stack.models.llama.llama4.tokenizer import Tokenizer as Llama4Tokenizer -from llama_stack.models.llama.sku_types import Model, ModelFamily from .common import model_checkpoint_dir from .config import MetaReferenceInferenceConfig diff --git a/src/llama_stack/providers/inline/inference/meta_reference/inference.py b/src/llama_stack/providers/inline/inference/meta_reference/inference.py index ef21132a0..42d1299ab 100644 --- a/src/llama_stack/providers/inline/inference/meta_reference/inference.py +++ b/src/llama_stack/providers/inline/inference/meta_reference/inference.py @@ -9,22 +9,6 @@ import time import uuid from collections.abc import AsyncIterator -from llama_stack.apis.inference import ( - InferenceProvider, - OpenAIAssistantMessageParam, - OpenAIChatCompletionRequestWithExtraBody, - OpenAIChatCompletionUsage, - OpenAIChoice, - OpenAICompletionRequestWithExtraBody, - OpenAIUserMessageParam, - ToolChoice, -) -from llama_stack.apis.inference.inference import ( - OpenAIChatCompletion, - OpenAIChatCompletionChunk, - OpenAICompletion, -) -from llama_stack.apis.models import Model, ModelType from llama_stack.log import get_logger from llama_stack.models.llama.datatypes import RawMessage, RawTextItem, ToolDefinition from llama_stack.models.llama.llama3.chat_format import ChatFormat as Llama3ChatFormat @@ -40,7 +24,6 @@ from llama_stack.models.llama.llama4.prompt_templates.system_prompts import ( from llama_stack.models.llama.llama4.tokenizer import Tokenizer as Llama4Tokenizer from llama_stack.models.llama.sku_list import resolve_model from llama_stack.models.llama.sku_types import ModelFamily, is_multimodal -from llama_stack.providers.datatypes import ModelsProtocolPrivate from llama_stack.providers.utils.inference.embedding_mixin import ( SentenceTransformerEmbeddingMixin, ) @@ -48,6 +31,22 @@ from llama_stack.providers.utils.inference.model_registry import ( ModelRegistryHelper, build_hf_repo_model_entry, ) +from llama_stack_api import ( + InferenceProvider, + Model, + ModelsProtocolPrivate, + ModelType, + OpenAIAssistantMessageParam, + OpenAIChatCompletion, + OpenAIChatCompletionChunk, + OpenAIChatCompletionRequestWithExtraBody, + OpenAIChatCompletionUsage, + OpenAIChoice, + OpenAICompletion, + OpenAICompletionRequestWithExtraBody, + OpenAIUserMessageParam, + ToolChoice, +) from .config import MetaReferenceInferenceConfig from .generators import LlamaGenerator @@ -376,7 +375,7 @@ class MetaReferenceInferenceImpl( # Convert tool calls to OpenAI format openai_tool_calls = None if decoded_message.tool_calls: - from llama_stack.apis.inference import ( + from llama_stack_api import ( OpenAIChatCompletionToolCall, OpenAIChatCompletionToolCallFunction, ) @@ -441,15 +440,15 @@ class MetaReferenceInferenceImpl( params: OpenAIChatCompletionRequestWithExtraBody, ) -> AsyncIterator[OpenAIChatCompletionChunk]: """Stream chat completion chunks as they're generated.""" - from llama_stack.apis.inference import ( + from llama_stack.models.llama.datatypes import StopReason + from llama_stack.providers.utils.inference.prompt_adapter import decode_assistant_message + from llama_stack_api import ( OpenAIChatCompletionChunk, OpenAIChatCompletionToolCall, OpenAIChatCompletionToolCallFunction, OpenAIChoiceDelta, OpenAIChunkChoice, ) - from llama_stack.models.llama.datatypes import StopReason - from llama_stack.providers.utils.inference.prompt_adapter import decode_assistant_message response_id = f"chatcmpl-{uuid.uuid4().hex[:24]}" created = int(time.time()) diff --git a/src/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py b/src/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py index e6dcf3ae7..b5cadeec2 100644 --- a/src/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py +++ b/src/llama_stack/providers/inline/inference/sentence_transformers/sentence_transformers.py @@ -6,22 +6,21 @@ from collections.abc import AsyncIterator -from llama_stack.apis.inference import ( - InferenceProvider, - OpenAIChatCompletionRequestWithExtraBody, - OpenAICompletionRequestWithExtraBody, -) -from llama_stack.apis.inference.inference import ( - OpenAIChatCompletion, - OpenAIChatCompletionChunk, - OpenAICompletion, -) -from llama_stack.apis.models import ModelType from llama_stack.log import get_logger -from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate from llama_stack.providers.utils.inference.embedding_mixin import ( SentenceTransformerEmbeddingMixin, ) +from llama_stack_api import ( + InferenceProvider, + Model, + ModelsProtocolPrivate, + ModelType, + OpenAIChatCompletion, + OpenAIChatCompletionChunk, + OpenAIChatCompletionRequestWithExtraBody, + OpenAICompletion, + OpenAICompletionRequestWithExtraBody, +) from .config import SentenceTransformersInferenceConfig diff --git a/src/llama_stack/providers/inline/post_training/common/validator.py b/src/llama_stack/providers/inline/post_training/common/validator.py index 950b75f86..cc018c865 100644 --- a/src/llama_stack/providers/inline/post_training/common/validator.py +++ b/src/llama_stack/providers/inline/post_training/common/validator.py @@ -12,14 +12,10 @@ from typing import Any -from llama_stack.apis.common.type_system import ( - ChatCompletionInputType, - DialogType, - StringType, -) from llama_stack.providers.utils.common.data_schema_validator import ( ColumnName, ) +from llama_stack_api import ChatCompletionInputType, DialogType, StringType EXPECTED_DATASET_SCHEMA: dict[str, list[dict[str, Any]]] = { "instruct": [ diff --git a/src/llama_stack/providers/inline/post_training/huggingface/post_training.py b/src/llama_stack/providers/inline/post_training/huggingface/post_training.py index 22ace1ae0..fa939d439 100644 --- a/src/llama_stack/providers/inline/post_training/huggingface/post_training.py +++ b/src/llama_stack/providers/inline/post_training/huggingface/post_training.py @@ -6,11 +6,16 @@ from enum import Enum from typing import Any -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Datasets -from llama_stack.apis.post_training import ( +from llama_stack.providers.inline.post_training.huggingface.config import ( + HuggingFacePostTrainingConfig, +) +from llama_stack.providers.utils.scheduler import JobArtifact, Scheduler +from llama_stack.providers.utils.scheduler import JobStatus as SchedulerJobStatus +from llama_stack_api import ( AlgorithmConfig, Checkpoint, + DatasetIO, + Datasets, DPOAlignmentConfig, JobStatus, ListPostTrainingJobsResponse, @@ -19,11 +24,6 @@ from llama_stack.apis.post_training import ( PostTrainingJobStatusResponse, TrainingConfig, ) -from llama_stack.providers.inline.post_training.huggingface.config import ( - HuggingFacePostTrainingConfig, -) -from llama_stack.providers.utils.scheduler import JobArtifact, Scheduler -from llama_stack.providers.utils.scheduler import JobStatus as SchedulerJobStatus class TrainingArtifactType(Enum): diff --git a/src/llama_stack/providers/inline/post_training/huggingface/recipes/finetune_single_device.py b/src/llama_stack/providers/inline/post_training/huggingface/recipes/finetune_single_device.py index 39b83a3fd..c7c737fbd 100644 --- a/src/llama_stack/providers/inline/post_training/huggingface/recipes/finetune_single_device.py +++ b/src/llama_stack/providers/inline/post_training/huggingface/recipes/finetune_single_device.py @@ -18,16 +18,16 @@ from transformers import ( ) from trl import SFTConfig, SFTTrainer -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Datasets -from llama_stack.apis.post_training import ( +from llama_stack.log import get_logger +from llama_stack.providers.inline.post_training.common.utils import evacuate_model_from_device +from llama_stack_api import ( Checkpoint, DataConfig, + DatasetIO, + Datasets, LoraFinetuningConfig, TrainingConfig, ) -from llama_stack.log import get_logger -from llama_stack.providers.inline.post_training.common.utils import evacuate_model_from_device from ..config import HuggingFacePostTrainingConfig from ..utils import ( diff --git a/src/llama_stack/providers/inline/post_training/huggingface/recipes/finetune_single_device_dpo.py b/src/llama_stack/providers/inline/post_training/huggingface/recipes/finetune_single_device_dpo.py index 11d707df9..da2626555 100644 --- a/src/llama_stack/providers/inline/post_training/huggingface/recipes/finetune_single_device_dpo.py +++ b/src/llama_stack/providers/inline/post_training/huggingface/recipes/finetune_single_device_dpo.py @@ -16,15 +16,15 @@ from transformers import ( ) from trl import DPOConfig, DPOTrainer -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Datasets -from llama_stack.apis.post_training import ( +from llama_stack.log import get_logger +from llama_stack.providers.inline.post_training.common.utils import evacuate_model_from_device +from llama_stack_api import ( Checkpoint, + DatasetIO, + Datasets, DPOAlignmentConfig, TrainingConfig, ) -from llama_stack.log import get_logger -from llama_stack.providers.inline.post_training.common.utils import evacuate_model_from_device from ..config import HuggingFacePostTrainingConfig from ..utils import ( diff --git a/src/llama_stack/providers/inline/post_training/huggingface/utils.py b/src/llama_stack/providers/inline/post_training/huggingface/utils.py index a930602d0..2037f70e7 100644 --- a/src/llama_stack/providers/inline/post_training/huggingface/utils.py +++ b/src/llama_stack/providers/inline/post_training/huggingface/utils.py @@ -16,6 +16,8 @@ import torch from datasets import Dataset from transformers import AutoConfig, AutoModelForCausalLM +from llama_stack_api import Checkpoint, DatasetIO, TrainingConfig + if TYPE_CHECKING: from transformers import PretrainedConfig @@ -34,8 +36,6 @@ class HFAutoModel(Protocol): def save_pretrained(self, save_directory: str | Path) -> None: ... -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.post_training import Checkpoint, TrainingConfig from llama_stack.log import get_logger from .config import HuggingFacePostTrainingConfig diff --git a/src/llama_stack/providers/inline/post_training/torchtune/common/utils.py b/src/llama_stack/providers/inline/post_training/torchtune/common/utils.py index f0fa052a2..f929ea4dd 100644 --- a/src/llama_stack/providers/inline/post_training/torchtune/common/utils.py +++ b/src/llama_stack/providers/inline/post_training/torchtune/common/utils.py @@ -21,9 +21,9 @@ from torchtune.models.llama3_1 import lora_llama3_1_8b from torchtune.models.llama3_2 import lora_llama3_2_3b from torchtune.modules.transforms import Transform -from llama_stack.apis.post_training import DatasetFormat from llama_stack.models.llama.sku_list import resolve_model from llama_stack.models.llama.sku_types import Model +from llama_stack_api import DatasetFormat BuildLoraModelCallable = Callable[..., torch.nn.Module] BuildTokenizerCallable = Callable[..., Llama3Tokenizer] diff --git a/src/llama_stack/providers/inline/post_training/torchtune/post_training.py b/src/llama_stack/providers/inline/post_training/torchtune/post_training.py index 765f6789d..515ff7b66 100644 --- a/src/llama_stack/providers/inline/post_training/torchtune/post_training.py +++ b/src/llama_stack/providers/inline/post_training/torchtune/post_training.py @@ -6,11 +6,16 @@ from enum import Enum from typing import Any -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Datasets -from llama_stack.apis.post_training import ( +from llama_stack.providers.inline.post_training.torchtune.config import ( + TorchtunePostTrainingConfig, +) +from llama_stack.providers.utils.scheduler import JobArtifact, Scheduler +from llama_stack.providers.utils.scheduler import JobStatus as SchedulerJobStatus +from llama_stack_api import ( AlgorithmConfig, Checkpoint, + DatasetIO, + Datasets, DPOAlignmentConfig, JobStatus, ListPostTrainingJobsResponse, @@ -20,11 +25,6 @@ from llama_stack.apis.post_training import ( PostTrainingJobStatusResponse, TrainingConfig, ) -from llama_stack.providers.inline.post_training.torchtune.config import ( - TorchtunePostTrainingConfig, -) -from llama_stack.providers.utils.scheduler import JobArtifact, Scheduler -from llama_stack.providers.utils.scheduler import JobStatus as SchedulerJobStatus class TrainingArtifactType(Enum): diff --git a/src/llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py b/src/llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py index c648cdc46..f5e5db415 100644 --- a/src/llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py +++ b/src/llama_stack/providers/inline/post_training/torchtune/recipes/lora_finetuning_single_device.py @@ -32,17 +32,6 @@ from torchtune.training.lr_schedulers import get_cosine_schedule_with_warmup from torchtune.training.metric_logging import DiskLogger from tqdm import tqdm -from llama_stack.apis.common.training_types import PostTrainingMetric -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Datasets -from llama_stack.apis.post_training import ( - Checkpoint, - DataConfig, - LoraFinetuningConfig, - OptimizerConfig, - QATFinetuningConfig, - TrainingConfig, -) from llama_stack.core.utils.config_dirs import DEFAULT_CHECKPOINT_DIR from llama_stack.core.utils.model_utils import model_local_dir from llama_stack.log import get_logger @@ -56,6 +45,17 @@ from llama_stack.providers.inline.post_training.torchtune.config import ( TorchtunePostTrainingConfig, ) from llama_stack.providers.inline.post_training.torchtune.datasets.sft import SFTDataset +from llama_stack_api import ( + Checkpoint, + DataConfig, + DatasetIO, + Datasets, + LoraFinetuningConfig, + OptimizerConfig, + PostTrainingMetric, + QATFinetuningConfig, + TrainingConfig, +) log = get_logger(name=__name__, category="post_training") diff --git a/src/llama_stack/providers/inline/safety/code_scanner/code_scanner.py b/src/llama_stack/providers/inline/safety/code_scanner/code_scanner.py index 7da9ea0d7..071fbe2dc 100644 --- a/src/llama_stack/providers/inline/safety/code_scanner/code_scanner.py +++ b/src/llama_stack/providers/inline/safety/code_scanner/code_scanner.py @@ -10,19 +10,20 @@ from typing import TYPE_CHECKING, Any if TYPE_CHECKING: from codeshield.cs import CodeShieldScanResult -from llama_stack.apis.inference import OpenAIMessageParam -from llama_stack.apis.safety import ( - RunShieldResponse, - Safety, - SafetyViolation, - ViolationLevel, -) -from llama_stack.apis.safety.safety import ModerationObject, ModerationObjectResults -from llama_stack.apis.shields import Shield from llama_stack.log import get_logger from llama_stack.providers.utils.inference.prompt_adapter import ( interleaved_content_as_str, ) +from llama_stack_api import ( + ModerationObject, + ModerationObjectResults, + OpenAIMessageParam, + RunShieldResponse, + Safety, + SafetyViolation, + Shield, + ViolationLevel, +) from .config import CodeScannerConfig diff --git a/src/llama_stack/providers/inline/safety/llama_guard/llama_guard.py b/src/llama_stack/providers/inline/safety/llama_guard/llama_guard.py index 6f6346e82..ff1536bea 100644 --- a/src/llama_stack/providers/inline/safety/llama_guard/llama_guard.py +++ b/src/llama_stack/providers/inline/safety/llama_guard/llama_guard.py @@ -9,29 +9,29 @@ import uuid from string import Template from typing import Any -from llama_stack.apis.common.content_types import ImageContentItem, TextContentItem -from llama_stack.apis.inference import ( - Inference, - OpenAIChatCompletionRequestWithExtraBody, - OpenAIMessageParam, - OpenAIUserMessageParam, -) -from llama_stack.apis.safety import ( - RunShieldResponse, - Safety, - SafetyViolation, - ViolationLevel, -) -from llama_stack.apis.safety.safety import ModerationObject, ModerationObjectResults -from llama_stack.apis.shields import Shield from llama_stack.core.datatypes import Api from llama_stack.log import get_logger from llama_stack.models.llama.datatypes import Role from llama_stack.models.llama.sku_types import CoreModelId -from llama_stack.providers.datatypes import ShieldsProtocolPrivate from llama_stack.providers.utils.inference.prompt_adapter import ( interleaved_content_as_str, ) +from llama_stack_api import ( + ImageContentItem, + Inference, + ModerationObject, + ModerationObjectResults, + OpenAIChatCompletionRequestWithExtraBody, + OpenAIMessageParam, + OpenAIUserMessageParam, + RunShieldResponse, + Safety, + SafetyViolation, + Shield, + ShieldsProtocolPrivate, + TextContentItem, + ViolationLevel, +) from .config import LlamaGuardConfig diff --git a/src/llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py b/src/llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py index 2015e1150..51383da1b 100644 --- a/src/llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py +++ b/src/llama_stack/providers/inline/safety/prompt_guard/prompt_guard.py @@ -9,20 +9,20 @@ from typing import Any import torch from transformers import AutoModelForSequenceClassification, AutoTokenizer -from llama_stack.apis.inference import OpenAIMessageParam -from llama_stack.apis.safety import ( +from llama_stack.core.utils.model_utils import model_local_dir +from llama_stack.log import get_logger +from llama_stack.providers.utils.inference.prompt_adapter import interleaved_content_as_str +from llama_stack_api import ( + ModerationObject, + OpenAIMessageParam, RunShieldResponse, Safety, SafetyViolation, + Shield, + ShieldsProtocolPrivate, ShieldStore, ViolationLevel, ) -from llama_stack.apis.safety.safety import ModerationObject -from llama_stack.apis.shields import Shield -from llama_stack.core.utils.model_utils import model_local_dir -from llama_stack.log import get_logger -from llama_stack.providers.datatypes import ShieldsProtocolPrivate -from llama_stack.providers.utils.inference.prompt_adapter import interleaved_content_as_str from .config import PromptGuardConfig, PromptGuardType diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring.py b/src/llama_stack/providers/inline/scoring/basic/scoring.py index b19b68039..cf5cb79ba 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring.py @@ -5,21 +5,22 @@ # the root directory of this source tree. from typing import Any -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Datasets -from llama_stack.apis.scoring import ( - ScoreBatchResponse, - ScoreResponse, - Scoring, - ScoringResult, -) -from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams from llama_stack.core.datatypes import Api -from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate from llama_stack.providers.utils.common.data_schema_validator import ( get_valid_schemas, validate_dataset_schema, ) +from llama_stack_api import ( + DatasetIO, + Datasets, + ScoreBatchResponse, + ScoreResponse, + Scoring, + ScoringFn, + ScoringFnParams, + ScoringFunctionsProtocolPrivate, + ScoringResult, +) from .config import BasicScoringConfig from .scoring_fn.docvqa_scoring_fn import DocVQAScoringFn diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/docvqa_scoring_fn.py b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/docvqa_scoring_fn.py index b87974d08..e48bab8fa 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/docvqa_scoring_fn.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/docvqa_scoring_fn.py @@ -8,9 +8,8 @@ import json import re from typing import Any -from llama_stack.apis.scoring import ScoringResultRow -from llama_stack.apis.scoring_functions import ScoringFnParams from llama_stack.providers.utils.scoring.base_scoring_fn import RegisteredBaseScoringFn +from llama_stack_api import ScoringFnParams, ScoringResultRow from .fn_defs.docvqa import docvqa diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/equality_scoring_fn.py b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/equality_scoring_fn.py index 60804330f..2e79240be 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/equality_scoring_fn.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/equality_scoring_fn.py @@ -6,9 +6,8 @@ from typing import Any -from llama_stack.apis.scoring import ScoringResultRow -from llama_stack.apis.scoring_functions import ScoringFnParams from llama_stack.providers.utils.scoring.base_scoring_fn import RegisteredBaseScoringFn +from llama_stack_api import ScoringFnParams, ScoringResultRow from .fn_defs.equality import equality diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/docvqa.py b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/docvqa.py index aad3dfe26..a7305d13a 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/docvqa.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/docvqa.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/equality.py b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/equality.py index 9b24ff791..f7d2f32ae 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/equality.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/equality.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/ifeval.py b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/ifeval.py index adca0791d..a2ed1d695 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/ifeval.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/ifeval.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/regex_parser_math_response.py b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/regex_parser_math_response.py index 8b1bf5352..4e2b49a1f 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/regex_parser_math_response.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/regex_parser_math_response.py @@ -4,9 +4,9 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, + NumberType, RegexParserScoringFnParams, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/regex_parser_multiple_choice_answer.py b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/regex_parser_multiple_choice_answer.py index ea04331c9..df0cf52d9 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/regex_parser_multiple_choice_answer.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/regex_parser_multiple_choice_answer.py @@ -4,9 +4,9 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, + NumberType, RegexParserScoringFnParams, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/subset_of.py b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/subset_of.py index 9cae66fa6..1f143c4a6 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/subset_of.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/fn_defs/subset_of.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/ifeval_scoring_fn.py b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/ifeval_scoring_fn.py index 77f6176e6..33b1c5a31 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/ifeval_scoring_fn.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/ifeval_scoring_fn.py @@ -6,9 +6,8 @@ from typing import Any -from llama_stack.apis.scoring import ScoringResultRow -from llama_stack.apis.scoring_functions import ScoringFnParams from llama_stack.providers.utils.scoring.base_scoring_fn import RegisteredBaseScoringFn +from llama_stack_api import ScoringFnParams, ScoringResultRow from .fn_defs.ifeval import ( ifeval, diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_math_response_scoring_fn.py b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_math_response_scoring_fn.py index d765959a8..1f4f2f979 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_math_response_scoring_fn.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_math_response_scoring_fn.py @@ -5,9 +5,8 @@ # the root directory of this source tree. from typing import Any -from llama_stack.apis.scoring import ScoringResultRow -from llama_stack.apis.scoring_functions import ScoringFnParams, ScoringFnParamsType from llama_stack.providers.utils.scoring.base_scoring_fn import RegisteredBaseScoringFn +from llama_stack_api import ScoringFnParams, ScoringFnParamsType, ScoringResultRow from ..utils.math_utils import first_answer, normalize_final_answer, try_evaluate_frac, try_evaluate_latex from .fn_defs.regex_parser_math_response import ( diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_scoring_fn.py b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_scoring_fn.py index cb336e303..1cc74f874 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_scoring_fn.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/regex_parser_scoring_fn.py @@ -6,9 +6,8 @@ import re from typing import Any -from llama_stack.apis.scoring import ScoringResultRow -from llama_stack.apis.scoring_functions import ScoringFnParams, ScoringFnParamsType from llama_stack.providers.utils.scoring.base_scoring_fn import RegisteredBaseScoringFn +from llama_stack_api import ScoringFnParams, ScoringFnParamsType, ScoringResultRow from .fn_defs.regex_parser_multiple_choice_answer import ( regex_parser_multiple_choice_answer, diff --git a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/subset_of_scoring_fn.py b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/subset_of_scoring_fn.py index d6e10e6c9..fe15a4972 100644 --- a/src/llama_stack/providers/inline/scoring/basic/scoring_fn/subset_of_scoring_fn.py +++ b/src/llama_stack/providers/inline/scoring/basic/scoring_fn/subset_of_scoring_fn.py @@ -6,9 +6,8 @@ from typing import Any -from llama_stack.apis.scoring import ScoringResultRow -from llama_stack.apis.scoring_functions import ScoringFnParams from llama_stack.providers.utils.scoring.base_scoring_fn import RegisteredBaseScoringFn +from llama_stack_api import ScoringFnParams, ScoringResultRow from .fn_defs.subset_of import subset_of diff --git a/src/llama_stack/providers/inline/scoring/braintrust/braintrust.py b/src/llama_stack/providers/inline/scoring/braintrust/braintrust.py index 14810f706..cfa35547b 100644 --- a/src/llama_stack/providers/inline/scoring/braintrust/braintrust.py +++ b/src/llama_stack/providers/inline/scoring/braintrust/braintrust.py @@ -19,25 +19,26 @@ from autoevals.ragas import ( ) from pydantic import BaseModel -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Datasets -from llama_stack.apis.scoring import ( - ScoreBatchResponse, - ScoreResponse, - Scoring, - ScoringResult, - ScoringResultRow, -) -from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams from llama_stack.core.datatypes import Api from llama_stack.core.request_headers import NeedsRequestProviderData -from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate from llama_stack.providers.utils.common.data_schema_validator import ( get_valid_schemas, validate_dataset_schema, validate_row_schema, ) from llama_stack.providers.utils.scoring.aggregation_utils import aggregate_metrics +from llama_stack_api import ( + DatasetIO, + Datasets, + ScoreBatchResponse, + ScoreResponse, + Scoring, + ScoringFn, + ScoringFnParams, + ScoringFunctionsProtocolPrivate, + ScoringResult, + ScoringResultRow, +) from .config import BraintrustScoringConfig from .scoring_fn.fn_defs.answer_correctness import answer_correctness_fn_def diff --git a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_correctness.py b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_correctness.py index 4fe07f822..b058305b4 100644 --- a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_correctness.py +++ b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_correctness.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_relevancy.py b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_relevancy.py index a1995cc4e..d619d38a8 100644 --- a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_relevancy.py +++ b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_relevancy.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_similarity.py b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_similarity.py index e8fe15259..34354a1fc 100644 --- a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_similarity.py +++ b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/answer_similarity.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_entity_recall.py b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_entity_recall.py index d9b129a8b..4092ccc4a 100644 --- a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_entity_recall.py +++ b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_entity_recall.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_precision.py b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_precision.py index c1d7e855b..2b32b9eec 100644 --- a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_precision.py +++ b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_precision.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_recall.py b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_recall.py index 01ddd0dd0..4d6547002 100644 --- a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_recall.py +++ b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_recall.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_relevancy.py b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_relevancy.py index 55d89344a..739dfd7bd 100644 --- a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_relevancy.py +++ b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/context_relevancy.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/factuality.py b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/factuality.py index c621ecf7f..59ed5949b 100644 --- a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/factuality.py +++ b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/factuality.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/faithfulness.py b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/faithfulness.py index 2e85c0c7c..96c36d226 100644 --- a/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/faithfulness.py +++ b/src/llama_stack/providers/inline/scoring/braintrust/scoring_fn/fn_defs/faithfulness.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, BasicScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring.py b/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring.py index 9b7628524..23e6ad705 100644 --- a/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring.py +++ b/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring.py @@ -5,22 +5,23 @@ # the root directory of this source tree. from typing import Any -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Datasets -from llama_stack.apis.inference import Inference -from llama_stack.apis.scoring import ( - ScoreBatchResponse, - ScoreResponse, - Scoring, - ScoringResult, -) -from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams from llama_stack.core.datatypes import Api -from llama_stack.providers.datatypes import ScoringFunctionsProtocolPrivate from llama_stack.providers.utils.common.data_schema_validator import ( get_valid_schemas, validate_dataset_schema, ) +from llama_stack_api import ( + DatasetIO, + Datasets, + Inference, + ScoreBatchResponse, + ScoreResponse, + Scoring, + ScoringFn, + ScoringFnParams, + ScoringFunctionsProtocolPrivate, + ScoringResult, +) from .config import LlmAsJudgeScoringConfig from .scoring_fn.llm_as_judge_scoring_fn import LlmAsJudgeScoringFn diff --git a/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_405b_simpleqa.py b/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_405b_simpleqa.py index 074f1ff46..ed26169a5 100644 --- a/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_405b_simpleqa.py +++ b/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_405b_simpleqa.py @@ -4,10 +4,10 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import ( +from llama_stack_api import ( AggregationFunctionType, LLMAsJudgeScoringFnParams, + NumberType, ScoringFn, ) diff --git a/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_base.py b/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_base.py index 205e0bbf3..bffffd878 100644 --- a/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_base.py +++ b/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/fn_defs/llm_as_judge_base.py @@ -4,8 +4,7 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.scoring_functions import LLMAsJudgeScoringFnParams, ScoringFn +from llama_stack_api import LLMAsJudgeScoringFnParams, NumberType, ScoringFn llm_as_judge_base = ScoringFn( identifier="llm-as-judge::base", diff --git a/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_scoring_fn.py b/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_scoring_fn.py index fbecb6e20..73ce82cda 100644 --- a/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_scoring_fn.py +++ b/src/llama_stack/providers/inline/scoring/llm_as_judge/scoring_fn/llm_as_judge_scoring_fn.py @@ -6,10 +6,8 @@ import re from typing import Any -from llama_stack.apis.inference import Inference, OpenAIChatCompletionRequestWithExtraBody -from llama_stack.apis.scoring import ScoringResultRow -from llama_stack.apis.scoring_functions import ScoringFnParams from llama_stack.providers.utils.scoring.base_scoring_fn import RegisteredBaseScoringFn +from llama_stack_api import Inference, OpenAIChatCompletionRequestWithExtraBody, ScoringFnParams, ScoringResultRow from .fn_defs.llm_as_judge_405b_simpleqa import llm_as_judge_405b_simpleqa from .fn_defs.llm_as_judge_base import llm_as_judge_base diff --git a/src/llama_stack/providers/inline/tool_runtime/rag/__init__.py b/src/llama_stack/providers/inline/tool_runtime/rag/__init__.py index f9a7e7b89..60117dc3d 100644 --- a/src/llama_stack/providers/inline/tool_runtime/rag/__init__.py +++ b/src/llama_stack/providers/inline/tool_runtime/rag/__init__.py @@ -6,7 +6,7 @@ from typing import Any -from llama_stack.providers.datatypes import Api +from llama_stack_api import Api from .config import RagToolRuntimeConfig diff --git a/src/llama_stack/providers/inline/tool_runtime/rag/context_retriever.py b/src/llama_stack/providers/inline/tool_runtime/rag/context_retriever.py index 14cbec49d..240df199b 100644 --- a/src/llama_stack/providers/inline/tool_runtime/rag/context_retriever.py +++ b/src/llama_stack/providers/inline/tool_runtime/rag/context_retriever.py @@ -7,17 +7,18 @@ from jinja2 import Template -from llama_stack.apis.common.content_types import InterleavedContent -from llama_stack.apis.inference import OpenAIChatCompletionRequestWithExtraBody, OpenAIUserMessageParam -from llama_stack.apis.tools.rag_tool import ( - DefaultRAGQueryGeneratorConfig, - LLMRAGQueryGeneratorConfig, - RAGQueryGenerator, - RAGQueryGeneratorConfig, -) from llama_stack.providers.utils.inference.prompt_adapter import ( interleaved_content_as_str, ) +from llama_stack_api import ( + DefaultRAGQueryGeneratorConfig, + InterleavedContent, + LLMRAGQueryGeneratorConfig, + OpenAIChatCompletionRequestWithExtraBody, + OpenAIUserMessageParam, + RAGQueryGenerator, + RAGQueryGeneratorConfig, +) async def generate_rag_query( diff --git a/src/llama_stack/providers/inline/tool_runtime/rag/memory.py b/src/llama_stack/providers/inline/tool_runtime/rag/memory.py index 6a59be0ca..afb54a8a9 100644 --- a/src/llama_stack/providers/inline/tool_runtime/rag/memory.py +++ b/src/llama_stack/providers/inline/tool_runtime/rag/memory.py @@ -14,34 +14,31 @@ import httpx from fastapi import UploadFile from pydantic import TypeAdapter -from llama_stack.apis.common.content_types import ( +from llama_stack.log import get_logger +from llama_stack.providers.utils.inference.prompt_adapter import interleaved_content_as_str +from llama_stack.providers.utils.memory.vector_store import parse_data_url +from llama_stack_api import ( URL, + Files, + Inference, InterleavedContent, InterleavedContentItem, - TextContentItem, -) -from llama_stack.apis.files import Files, OpenAIFilePurpose -from llama_stack.apis.inference import Inference -from llama_stack.apis.tools import ( ListToolDefsResponse, + OpenAIFilePurpose, + QueryChunksResponse, RAGDocument, RAGQueryConfig, RAGQueryResult, + TextContentItem, ToolDef, ToolGroup, + ToolGroupsProtocolPrivate, ToolInvocationResult, ToolRuntime, -) -from llama_stack.apis.vector_io import ( - QueryChunksResponse, VectorIO, VectorStoreChunkingStrategyStatic, VectorStoreChunkingStrategyStaticConfig, ) -from llama_stack.log import get_logger -from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate -from llama_stack.providers.utils.inference.prompt_adapter import interleaved_content_as_str -from llama_stack.providers.utils.memory.vector_store import parse_data_url from .config import RagToolRuntimeConfig from .context_retriever import generate_rag_query @@ -279,7 +276,10 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime): ) async def list_runtime_tools( - self, tool_group_id: str | None = None, mcp_endpoint: URL | None = None + self, + tool_group_id: str | None = None, + mcp_endpoint: URL | None = None, + authorization: str | None = None, ) -> ListToolDefsResponse: # Parameters are not listed since these methods are not yet invoked automatically # by the LLM. The method is only implemented so things like /tools can list without @@ -307,7 +307,9 @@ class MemoryToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime): ] ) - async def invoke_tool(self, tool_name: str, kwargs: dict[str, Any]) -> ToolInvocationResult: + async def invoke_tool( + self, tool_name: str, kwargs: dict[str, Any], authorization: str | None = None + ) -> ToolInvocationResult: vector_store_ids = kwargs.get("vector_store_ids", []) query_config = kwargs.get("query_config") if query_config: diff --git a/src/llama_stack/providers/inline/vector_io/chroma/__init__.py b/src/llama_stack/providers/inline/vector_io/chroma/__init__.py index 575e5ad88..155b8a0cb 100644 --- a/src/llama_stack/providers/inline/vector_io/chroma/__init__.py +++ b/src/llama_stack/providers/inline/vector_io/chroma/__init__.py @@ -6,7 +6,7 @@ from typing import Any -from llama_stack.providers.datatypes import Api +from llama_stack_api import Api from .config import ChromaVectorIOConfig diff --git a/src/llama_stack/providers/inline/vector_io/chroma/config.py b/src/llama_stack/providers/inline/vector_io/chroma/config.py index 1798f10de..3897991f5 100644 --- a/src/llama_stack/providers/inline/vector_io/chroma/config.py +++ b/src/llama_stack/providers/inline/vector_io/chroma/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.core.storage.datatypes import KVStoreReference -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/inline/vector_io/faiss/__init__.py b/src/llama_stack/providers/inline/vector_io/faiss/__init__.py index 24d1f292a..b834589e3 100644 --- a/src/llama_stack/providers/inline/vector_io/faiss/__init__.py +++ b/src/llama_stack/providers/inline/vector_io/faiss/__init__.py @@ -6,7 +6,7 @@ from typing import Any -from llama_stack.providers.datatypes import Api +from llama_stack_api import Api from .config import FaissVectorIOConfig diff --git a/src/llama_stack/providers/inline/vector_io/faiss/config.py b/src/llama_stack/providers/inline/vector_io/faiss/config.py index dd7a7aeca..d516d9fe9 100644 --- a/src/llama_stack/providers/inline/vector_io/faiss/config.py +++ b/src/llama_stack/providers/inline/vector_io/faiss/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel from llama_stack.core.storage.datatypes import KVStoreReference -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/inline/vector_io/faiss/faiss.py b/src/llama_stack/providers/inline/vector_io/faiss/faiss.py index 96760b834..d52a54e6a 100644 --- a/src/llama_stack/providers/inline/vector_io/faiss/faiss.py +++ b/src/llama_stack/providers/inline/vector_io/faiss/faiss.py @@ -14,17 +14,24 @@ import faiss # type: ignore[import-untyped] import numpy as np from numpy.typing import NDArray -from llama_stack.apis.common.errors import VectorStoreNotFoundError -from llama_stack.apis.files import Files -from llama_stack.apis.inference import Inference, InterleavedContent -from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO -from llama_stack.apis.vector_stores import VectorStore from llama_stack.log import get_logger -from llama_stack.providers.datatypes import HealthResponse, HealthStatus, VectorStoresProtocolPrivate from llama_stack.providers.utils.kvstore import kvstore_impl from llama_stack.providers.utils.kvstore.api import KVStore from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin from llama_stack.providers.utils.memory.vector_store import ChunkForDeletion, EmbeddingIndex, VectorStoreWithIndex +from llama_stack_api import ( + Chunk, + Files, + HealthResponse, + HealthStatus, + Inference, + InterleavedContent, + QueryChunksResponse, + VectorIO, + VectorStore, + VectorStoreNotFoundError, + VectorStoresProtocolPrivate, +) from .config import FaissVectorIOConfig diff --git a/src/llama_stack/providers/inline/vector_io/milvus/__init__.py b/src/llama_stack/providers/inline/vector_io/milvus/__init__.py index 7dc9c6a33..2f84769f3 100644 --- a/src/llama_stack/providers/inline/vector_io/milvus/__init__.py +++ b/src/llama_stack/providers/inline/vector_io/milvus/__init__.py @@ -6,7 +6,7 @@ from typing import Any -from llama_stack.providers.datatypes import Api +from llama_stack_api import Api from .config import MilvusVectorIOConfig diff --git a/src/llama_stack/providers/inline/vector_io/milvus/config.py b/src/llama_stack/providers/inline/vector_io/milvus/config.py index b333b04ea..14ddd2362 100644 --- a/src/llama_stack/providers/inline/vector_io/milvus/config.py +++ b/src/llama_stack/providers/inline/vector_io/milvus/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.core.storage.datatypes import KVStoreReference -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/inline/vector_io/qdrant/__init__.py b/src/llama_stack/providers/inline/vector_io/qdrant/__init__.py index bef6d50e6..145d19455 100644 --- a/src/llama_stack/providers/inline/vector_io/qdrant/__init__.py +++ b/src/llama_stack/providers/inline/vector_io/qdrant/__init__.py @@ -6,7 +6,7 @@ from typing import Any -from llama_stack.providers.datatypes import Api +from llama_stack_api import Api from .config import QdrantVectorIOConfig diff --git a/src/llama_stack/providers/inline/vector_io/qdrant/config.py b/src/llama_stack/providers/inline/vector_io/qdrant/config.py index e7ecde7b7..4251f2f39 100644 --- a/src/llama_stack/providers/inline/vector_io/qdrant/config.py +++ b/src/llama_stack/providers/inline/vector_io/qdrant/config.py @@ -10,7 +10,7 @@ from typing import Any from pydantic import BaseModel from llama_stack.core.storage.datatypes import KVStoreReference -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/inline/vector_io/sqlite_vec/__init__.py b/src/llama_stack/providers/inline/vector_io/sqlite_vec/__init__.py index df96e927c..e84c299dc 100644 --- a/src/llama_stack/providers/inline/vector_io/sqlite_vec/__init__.py +++ b/src/llama_stack/providers/inline/vector_io/sqlite_vec/__init__.py @@ -6,7 +6,7 @@ from typing import Any -from llama_stack.providers.datatypes import Api +from llama_stack_api import Api from .config import SQLiteVectorIOConfig diff --git a/src/llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py b/src/llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py index 399800d3e..74bc349a5 100644 --- a/src/llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py +++ b/src/llama_stack/providers/inline/vector_io/sqlite_vec/sqlite_vec.py @@ -14,13 +14,7 @@ import numpy as np import sqlite_vec # type: ignore[import-untyped] from numpy.typing import NDArray -from llama_stack.apis.common.errors import VectorStoreNotFoundError -from llama_stack.apis.files import Files -from llama_stack.apis.inference import Inference -from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO -from llama_stack.apis.vector_stores import VectorStore from llama_stack.log import get_logger -from llama_stack.providers.datatypes import VectorStoresProtocolPrivate from llama_stack.providers.utils.kvstore import kvstore_impl from llama_stack.providers.utils.kvstore.api import KVStore from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin @@ -31,6 +25,16 @@ from llama_stack.providers.utils.memory.vector_store import ( VectorStoreWithIndex, ) from llama_stack.providers.utils.vector_io.vector_utils import WeightedInMemoryAggregator +from llama_stack_api import ( + Chunk, + Files, + Inference, + QueryChunksResponse, + VectorIO, + VectorStore, + VectorStoreNotFoundError, + VectorStoresProtocolPrivate, +) logger = get_logger(name=__name__, category="vector_io") diff --git a/src/llama_stack/providers/registry/agents.py b/src/llama_stack/providers/registry/agents.py index ca7c353cd..5833cb605 100644 --- a/src/llama_stack/providers/registry/agents.py +++ b/src/llama_stack/providers/registry/agents.py @@ -5,12 +5,12 @@ # the root directory of this source tree. -from llama_stack.providers.datatypes import ( +from llama_stack.providers.utils.kvstore import kvstore_dependencies +from llama_stack_api import ( Api, InlineProviderSpec, ProviderSpec, ) -from llama_stack.providers.utils.kvstore import kvstore_dependencies def available_providers() -> list[ProviderSpec]: diff --git a/src/llama_stack/providers/registry/batches.py b/src/llama_stack/providers/registry/batches.py index a07942486..e11bb8332 100644 --- a/src/llama_stack/providers/registry/batches.py +++ b/src/llama_stack/providers/registry/batches.py @@ -5,7 +5,7 @@ # the root directory of this source tree. -from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec +from llama_stack_api import Api, InlineProviderSpec, ProviderSpec def available_providers() -> list[ProviderSpec]: diff --git a/src/llama_stack/providers/registry/datasetio.py b/src/llama_stack/providers/registry/datasetio.py index a9feb0bac..bfd7ede3c 100644 --- a/src/llama_stack/providers/registry/datasetio.py +++ b/src/llama_stack/providers/registry/datasetio.py @@ -5,7 +5,7 @@ # the root directory of this source tree. -from llama_stack.providers.datatypes import ( +from llama_stack_api import ( Api, InlineProviderSpec, ProviderSpec, diff --git a/src/llama_stack/providers/registry/eval.py b/src/llama_stack/providers/registry/eval.py index 4ef0bb41f..9c8b1eebd 100644 --- a/src/llama_stack/providers/registry/eval.py +++ b/src/llama_stack/providers/registry/eval.py @@ -5,7 +5,7 @@ # the root directory of this source tree. -from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec +from llama_stack_api import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec def available_providers() -> list[ProviderSpec]: diff --git a/src/llama_stack/providers/registry/files.py b/src/llama_stack/providers/registry/files.py index 3f5949ba2..024254b57 100644 --- a/src/llama_stack/providers/registry/files.py +++ b/src/llama_stack/providers/registry/files.py @@ -4,8 +4,8 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec from llama_stack.providers.utils.sqlstore.sqlstore import sql_store_pip_packages +from llama_stack_api import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec def available_providers() -> list[ProviderSpec]: diff --git a/src/llama_stack/providers/registry/inference.py b/src/llama_stack/providers/registry/inference.py index 3cbfd408b..819e5aff5 100644 --- a/src/llama_stack/providers/registry/inference.py +++ b/src/llama_stack/providers/registry/inference.py @@ -5,7 +5,7 @@ # the root directory of this source tree. -from llama_stack.providers.datatypes import ( +from llama_stack_api import ( Api, InlineProviderSpec, ProviderSpec, diff --git a/src/llama_stack/providers/registry/post_training.py b/src/llama_stack/providers/registry/post_training.py index 2092e3b2d..a5529b714 100644 --- a/src/llama_stack/providers/registry/post_training.py +++ b/src/llama_stack/providers/registry/post_training.py @@ -7,7 +7,7 @@ from typing import cast -from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec +from llama_stack_api import Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec # We provide two versions of these providers so that distributions can package the appropriate version of torch. # The CPU version is used for distributions that don't have GPU support -- they result in smaller container images. diff --git a/src/llama_stack/providers/registry/safety.py b/src/llama_stack/providers/registry/safety.py index b30074398..c9dbbce24 100644 --- a/src/llama_stack/providers/registry/safety.py +++ b/src/llama_stack/providers/registry/safety.py @@ -5,7 +5,7 @@ # the root directory of this source tree. -from llama_stack.providers.datatypes import ( +from llama_stack_api import ( Api, InlineProviderSpec, ProviderSpec, diff --git a/src/llama_stack/providers/registry/scoring.py b/src/llama_stack/providers/registry/scoring.py index a4ec54ed2..45c5dbed7 100644 --- a/src/llama_stack/providers/registry/scoring.py +++ b/src/llama_stack/providers/registry/scoring.py @@ -5,7 +5,7 @@ # the root directory of this source tree. -from llama_stack.providers.datatypes import Api, InlineProviderSpec, ProviderSpec +from llama_stack_api import Api, InlineProviderSpec, ProviderSpec def available_providers() -> list[ProviderSpec]: diff --git a/src/llama_stack/providers/registry/tool_runtime.py b/src/llama_stack/providers/registry/tool_runtime.py index 39dc7fccd..d34312353 100644 --- a/src/llama_stack/providers/registry/tool_runtime.py +++ b/src/llama_stack/providers/registry/tool_runtime.py @@ -5,13 +5,13 @@ # the root directory of this source tree. -from llama_stack.providers.datatypes import ( +from llama_stack.providers.registry.vector_io import DEFAULT_VECTOR_IO_DEPS +from llama_stack_api import ( Api, InlineProviderSpec, ProviderSpec, RemoteProviderSpec, ) -from llama_stack.providers.registry.vector_io import DEFAULT_VECTOR_IO_DEPS def available_providers() -> list[ProviderSpec]: diff --git a/src/llama_stack/providers/registry/vector_io.py b/src/llama_stack/providers/registry/vector_io.py index 55b302751..a00941586 100644 --- a/src/llama_stack/providers/registry/vector_io.py +++ b/src/llama_stack/providers/registry/vector_io.py @@ -5,7 +5,7 @@ # the root directory of this source tree. -from llama_stack.providers.datatypes import ( +from llama_stack_api import ( Api, InlineProviderSpec, ProviderSpec, @@ -244,7 +244,7 @@ Two ranker types are supported: Example using RAGQueryConfig with different search modes: ```python -from llama_stack.apis.tools import RAGQueryConfig, RRFRanker, WeightedRanker +from llama_stack_api import RAGQueryConfig, RRFRanker, WeightedRanker # Vector search config = RAGQueryConfig(mode="vector", max_chunks=5) diff --git a/src/llama_stack/providers/remote/datasetio/huggingface/huggingface.py b/src/llama_stack/providers/remote/datasetio/huggingface/huggingface.py index a34e354bf..72069f716 100644 --- a/src/llama_stack/providers/remote/datasetio/huggingface/huggingface.py +++ b/src/llama_stack/providers/remote/datasetio/huggingface/huggingface.py @@ -6,12 +6,9 @@ from typing import Any from urllib.parse import parse_qs, urlparse -from llama_stack.apis.common.responses import PaginatedResponse -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Dataset -from llama_stack.providers.datatypes import DatasetsProtocolPrivate from llama_stack.providers.utils.kvstore import kvstore_impl from llama_stack.providers.utils.pagination import paginate_records +from llama_stack_api import Dataset, DatasetIO, DatasetsProtocolPrivate, PaginatedResponse from .config import HuggingfaceDatasetIOConfig diff --git a/src/llama_stack/providers/remote/datasetio/nvidia/datasetio.py b/src/llama_stack/providers/remote/datasetio/nvidia/datasetio.py index f723c92cc..2f5548fa9 100644 --- a/src/llama_stack/providers/remote/datasetio/nvidia/datasetio.py +++ b/src/llama_stack/providers/remote/datasetio/nvidia/datasetio.py @@ -8,10 +8,7 @@ from typing import Any import aiohttp -from llama_stack.apis.common.content_types import URL -from llama_stack.apis.common.responses import PaginatedResponse -from llama_stack.apis.common.type_system import ParamType -from llama_stack.apis.datasets import Dataset +from llama_stack_api import URL, Dataset, PaginatedResponse, ParamType from .config import NvidiaDatasetIOConfig diff --git a/src/llama_stack/providers/remote/eval/nvidia/eval.py b/src/llama_stack/providers/remote/eval/nvidia/eval.py index 8fc7ffdd3..5802cb098 100644 --- a/src/llama_stack/providers/remote/eval/nvidia/eval.py +++ b/src/llama_stack/providers/remote/eval/nvidia/eval.py @@ -7,17 +7,23 @@ from typing import Any import requests -from llama_stack.apis.agents import Agents -from llama_stack.apis.benchmarks import Benchmark -from llama_stack.apis.datasetio import DatasetIO -from llama_stack.apis.datasets import Datasets -from llama_stack.apis.inference import Inference -from llama_stack.apis.scoring import Scoring, ScoringResult -from llama_stack.providers.datatypes import BenchmarksProtocolPrivate from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper +from llama_stack_api import ( + Agents, + Benchmark, + BenchmarkConfig, + BenchmarksProtocolPrivate, + DatasetIO, + Datasets, + Eval, + EvaluateResponse, + Inference, + Job, + JobStatus, + Scoring, + ScoringResult, +) -from .....apis.common.job_types import Job, JobStatus -from .....apis.eval.eval import BenchmarkConfig, Eval, EvaluateResponse from .config import NVIDIAEvalConfig DEFAULT_NAMESPACE = "nvidia" diff --git a/src/llama_stack/providers/remote/files/openai/files.py b/src/llama_stack/providers/remote/files/openai/files.py index c5d4194df..d2f5a08eb 100644 --- a/src/llama_stack/providers/remote/files/openai/files.py +++ b/src/llama_stack/providers/remote/files/openai/files.py @@ -9,21 +9,21 @@ from typing import Annotated, Any from fastapi import Depends, File, Form, Response, UploadFile -from llama_stack.apis.common.errors import ResourceNotFoundError -from llama_stack.apis.common.responses import Order -from llama_stack.apis.files import ( +from llama_stack.core.datatypes import AccessRule +from llama_stack.providers.utils.files.form_data import parse_expires_after +from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType +from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore +from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl +from llama_stack_api import ( ExpiresAfter, Files, ListOpenAIFileResponse, OpenAIFileDeleteResponse, OpenAIFileObject, OpenAIFilePurpose, + Order, + ResourceNotFoundError, ) -from llama_stack.core.datatypes import AccessRule -from llama_stack.providers.utils.files.form_data import parse_expires_after -from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType -from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore -from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl from openai import OpenAI from .config import OpenAIFilesImplConfig diff --git a/src/llama_stack/providers/remote/files/s3/files.py b/src/llama_stack/providers/remote/files/s3/files.py index 76261bdf4..68822eb77 100644 --- a/src/llama_stack/providers/remote/files/s3/files.py +++ b/src/llama_stack/providers/remote/files/s3/files.py @@ -17,22 +17,22 @@ from fastapi import Depends, File, Form, Response, UploadFile if TYPE_CHECKING: from mypy_boto3_s3.client import S3Client -from llama_stack.apis.common.errors import ResourceNotFoundError -from llama_stack.apis.common.responses import Order -from llama_stack.apis.files import ( - ExpiresAfter, - Files, - ListOpenAIFileResponse, - OpenAIFileDeleteResponse, - OpenAIFileObject, - OpenAIFilePurpose, -) from llama_stack.core.datatypes import AccessRule from llama_stack.core.id_generation import generate_object_id from llama_stack.providers.utils.files.form_data import parse_expires_after from llama_stack.providers.utils.sqlstore.api import ColumnDefinition, ColumnType from llama_stack.providers.utils.sqlstore.authorized_sqlstore import AuthorizedSqlStore from llama_stack.providers.utils.sqlstore.sqlstore import sqlstore_impl +from llama_stack_api import ( + ExpiresAfter, + Files, + ListOpenAIFileResponse, + OpenAIFileDeleteResponse, + OpenAIFileObject, + OpenAIFilePurpose, + Order, + ResourceNotFoundError, +) from .config import S3FilesImplConfig diff --git a/src/llama_stack/providers/remote/inference/anthropic/config.py b/src/llama_stack/providers/remote/inference/anthropic/config.py index 31e6aa12b..b706b90e1 100644 --- a/src/llama_stack/providers/remote/inference/anthropic/config.py +++ b/src/llama_stack/providers/remote/inference/anthropic/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class AnthropicProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/azure/config.py b/src/llama_stack/providers/remote/inference/azure/config.py index 7c31df7a6..b801b91b2 100644 --- a/src/llama_stack/providers/remote/inference/azure/config.py +++ b/src/llama_stack/providers/remote/inference/azure/config.py @@ -10,7 +10,7 @@ from typing import Any from pydantic import BaseModel, Field, HttpUrl, SecretStr from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class AzureProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/bedrock/bedrock.py b/src/llama_stack/providers/remote/inference/bedrock/bedrock.py index 1bf44b51a..70ee95916 100644 --- a/src/llama_stack/providers/remote/inference/bedrock/bedrock.py +++ b/src/llama_stack/providers/remote/inference/bedrock/bedrock.py @@ -8,7 +8,10 @@ from collections.abc import AsyncIterator, Iterable from openai import AuthenticationError -from llama_stack.apis.inference import ( +from llama_stack.core.telemetry.tracing import get_current_span +from llama_stack.log import get_logger +from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import ( OpenAIChatCompletion, OpenAIChatCompletionChunk, OpenAIChatCompletionRequestWithExtraBody, @@ -17,9 +20,6 @@ from llama_stack.apis.inference import ( OpenAIEmbeddingsRequestWithExtraBody, OpenAIEmbeddingsResponse, ) -from llama_stack.core.telemetry.tracing import get_current_span -from llama_stack.log import get_logger -from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin from .config import BedrockConfig diff --git a/src/llama_stack/providers/remote/inference/cerebras/cerebras.py b/src/llama_stack/providers/remote/inference/cerebras/cerebras.py index d5def9da1..680431e22 100644 --- a/src/llama_stack/providers/remote/inference/cerebras/cerebras.py +++ b/src/llama_stack/providers/remote/inference/cerebras/cerebras.py @@ -6,11 +6,11 @@ from urllib.parse import urljoin -from llama_stack.apis.inference import ( +from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import ( OpenAIEmbeddingsRequestWithExtraBody, OpenAIEmbeddingsResponse, ) -from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin from .config import CerebrasImplConfig diff --git a/src/llama_stack/providers/remote/inference/cerebras/config.py b/src/llama_stack/providers/remote/inference/cerebras/config.py index 9ba773724..db357fd1c 100644 --- a/src/llama_stack/providers/remote/inference/cerebras/config.py +++ b/src/llama_stack/providers/remote/inference/cerebras/config.py @@ -10,7 +10,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type DEFAULT_BASE_URL = "https://api.cerebras.ai" diff --git a/src/llama_stack/providers/remote/inference/databricks/config.py b/src/llama_stack/providers/remote/inference/databricks/config.py index 84357f764..bd409fa13 100644 --- a/src/llama_stack/providers/remote/inference/databricks/config.py +++ b/src/llama_stack/providers/remote/inference/databricks/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field, SecretStr from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class DatabricksProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/databricks/databricks.py b/src/llama_stack/providers/remote/inference/databricks/databricks.py index 636241383..c07d97b67 100644 --- a/src/llama_stack/providers/remote/inference/databricks/databricks.py +++ b/src/llama_stack/providers/remote/inference/databricks/databricks.py @@ -8,9 +8,9 @@ from collections.abc import Iterable from databricks.sdk import WorkspaceClient -from llama_stack.apis.inference import OpenAICompletion, OpenAICompletionRequestWithExtraBody from llama_stack.log import get_logger from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import OpenAICompletion, OpenAICompletionRequestWithExtraBody from .config import DatabricksImplConfig diff --git a/src/llama_stack/providers/remote/inference/fireworks/config.py b/src/llama_stack/providers/remote/inference/fireworks/config.py index 20ba99606..e36c76054 100644 --- a/src/llama_stack/providers/remote/inference/fireworks/config.py +++ b/src/llama_stack/providers/remote/inference/fireworks/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/remote/inference/gemini/config.py b/src/llama_stack/providers/remote/inference/gemini/config.py index df5da29a2..46cec7d0d 100644 --- a/src/llama_stack/providers/remote/inference/gemini/config.py +++ b/src/llama_stack/providers/remote/inference/gemini/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class GeminiProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/gemini/gemini.py b/src/llama_stack/providers/remote/inference/gemini/gemini.py index ee960d13b..f6f48cc2b 100644 --- a/src/llama_stack/providers/remote/inference/gemini/gemini.py +++ b/src/llama_stack/providers/remote/inference/gemini/gemini.py @@ -6,13 +6,13 @@ from typing import Any -from llama_stack.apis.inference import ( +from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import ( OpenAIEmbeddingData, OpenAIEmbeddingsRequestWithExtraBody, OpenAIEmbeddingsResponse, OpenAIEmbeddingUsage, ) -from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin from .config import GeminiConfig diff --git a/src/llama_stack/providers/remote/inference/groq/config.py b/src/llama_stack/providers/remote/inference/groq/config.py index c1aedca3e..cca53a4e8 100644 --- a/src/llama_stack/providers/remote/inference/groq/config.py +++ b/src/llama_stack/providers/remote/inference/groq/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class GroqProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/llama_openai_compat/config.py b/src/llama_stack/providers/remote/inference/llama_openai_compat/config.py index 4b5750ed4..ded210d89 100644 --- a/src/llama_stack/providers/remote/inference/llama_openai_compat/config.py +++ b/src/llama_stack/providers/remote/inference/llama_openai_compat/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class LlamaProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/llama_openai_compat/llama.py b/src/llama_stack/providers/remote/inference/llama_openai_compat/llama.py index 05d6e8cc8..a5f67ecd1 100644 --- a/src/llama_stack/providers/remote/inference/llama_openai_compat/llama.py +++ b/src/llama_stack/providers/remote/inference/llama_openai_compat/llama.py @@ -4,15 +4,15 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.inference.inference import ( +from llama_stack.log import get_logger +from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig +from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import ( OpenAICompletion, OpenAICompletionRequestWithExtraBody, OpenAIEmbeddingsRequestWithExtraBody, OpenAIEmbeddingsResponse, ) -from llama_stack.log import get_logger -from llama_stack.providers.remote.inference.llama_openai_compat.config import LlamaCompatConfig -from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin logger = get_logger(name=__name__, category="inference::llama_openai_compat") diff --git a/src/llama_stack/providers/remote/inference/nvidia/__init__.py b/src/llama_stack/providers/remote/inference/nvidia/__init__.py index b4926f33e..b89b2a750 100644 --- a/src/llama_stack/providers/remote/inference/nvidia/__init__.py +++ b/src/llama_stack/providers/remote/inference/nvidia/__init__.py @@ -4,7 +4,7 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.inference import Inference +from llama_stack_api import Inference from .config import NVIDIAConfig diff --git a/src/llama_stack/providers/remote/inference/nvidia/config.py b/src/llama_stack/providers/remote/inference/nvidia/config.py index 618bbe078..e5b0c6b73 100644 --- a/src/llama_stack/providers/remote/inference/nvidia/config.py +++ b/src/llama_stack/providers/remote/inference/nvidia/config.py @@ -10,7 +10,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class NVIDIAProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/nvidia/nvidia.py b/src/llama_stack/providers/remote/inference/nvidia/nvidia.py index bc5aa7953..17f8775bf 100644 --- a/src/llama_stack/providers/remote/inference/nvidia/nvidia.py +++ b/src/llama_stack/providers/remote/inference/nvidia/nvidia.py @@ -9,17 +9,16 @@ from collections.abc import Iterable import aiohttp -from llama_stack.apis.inference import ( +from llama_stack.log import get_logger +from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import ( + Model, + ModelType, + OpenAIChatCompletionContentPartImageParam, + OpenAIChatCompletionContentPartTextParam, RerankData, RerankResponse, ) -from llama_stack.apis.inference.inference import ( - OpenAIChatCompletionContentPartImageParam, - OpenAIChatCompletionContentPartTextParam, -) -from llama_stack.apis.models import Model, ModelType -from llama_stack.log import get_logger -from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin from . import NVIDIAConfig from .utils import _is_nvidia_hosted diff --git a/src/llama_stack/providers/remote/inference/oci/__init__.py b/src/llama_stack/providers/remote/inference/oci/__init__.py index 280a8c1d2..b7d6125f3 100644 --- a/src/llama_stack/providers/remote/inference/oci/__init__.py +++ b/src/llama_stack/providers/remote/inference/oci/__init__.py @@ -4,7 +4,7 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.inference import InferenceProvider +from llama_stack_api import InferenceProvider from .config import OCIConfig diff --git a/src/llama_stack/providers/remote/inference/oci/config.py b/src/llama_stack/providers/remote/inference/oci/config.py index 9747b08ea..93cc36d76 100644 --- a/src/llama_stack/providers/remote/inference/oci/config.py +++ b/src/llama_stack/providers/remote/inference/oci/config.py @@ -10,7 +10,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class OCIProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/oci/oci.py b/src/llama_stack/providers/remote/inference/oci/oci.py index 253dcf2b6..239443963 100644 --- a/src/llama_stack/providers/remote/inference/oci/oci.py +++ b/src/llama_stack/providers/remote/inference/oci/oci.py @@ -14,15 +14,15 @@ from oci.generative_ai.generative_ai_client import GenerativeAiClient from oci.generative_ai.models import ModelCollection from openai._base_client import DefaultAsyncHttpxClient -from llama_stack.apis.inference.inference import ( - OpenAIEmbeddingsRequestWithExtraBody, - OpenAIEmbeddingsResponse, -) -from llama_stack.apis.models import ModelType from llama_stack.log import get_logger from llama_stack.providers.remote.inference.oci.auth import OciInstancePrincipalAuth, OciUserPrincipalAuth from llama_stack.providers.remote.inference.oci.config import OCIConfig from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import ( + ModelType, + OpenAIEmbeddingsRequestWithExtraBody, + OpenAIEmbeddingsResponse, +) logger = get_logger(name=__name__, category="inference::oci") diff --git a/src/llama_stack/providers/remote/inference/ollama/ollama.py b/src/llama_stack/providers/remote/inference/ollama/ollama.py index 50f36d045..d1bf85361 100644 --- a/src/llama_stack/providers/remote/inference/ollama/ollama.py +++ b/src/llama_stack/providers/remote/inference/ollama/ollama.py @@ -9,15 +9,15 @@ import asyncio from ollama import AsyncClient as AsyncOllamaClient -from llama_stack.apis.common.errors import UnsupportedModelError -from llama_stack.apis.models import Model from llama_stack.log import get_logger -from llama_stack.providers.datatypes import ( - HealthResponse, - HealthStatus, -) from llama_stack.providers.remote.inference.ollama.config import OllamaImplConfig from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import ( + HealthResponse, + HealthStatus, + Model, + UnsupportedModelError, +) logger = get_logger(name=__name__, category="inference::ollama") diff --git a/src/llama_stack/providers/remote/inference/openai/config.py b/src/llama_stack/providers/remote/inference/openai/config.py index 36c66bd28..ab28e571f 100644 --- a/src/llama_stack/providers/remote/inference/openai/config.py +++ b/src/llama_stack/providers/remote/inference/openai/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class OpenAIProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/passthrough/config.py b/src/llama_stack/providers/remote/inference/passthrough/config.py index eca28a86a..54508b6fb 100644 --- a/src/llama_stack/providers/remote/inference/passthrough/config.py +++ b/src/llama_stack/providers/remote/inference/passthrough/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/remote/inference/passthrough/passthrough.py b/src/llama_stack/providers/remote/inference/passthrough/passthrough.py index 3c56acfbd..75eedf026 100644 --- a/src/llama_stack/providers/remote/inference/passthrough/passthrough.py +++ b/src/llama_stack/providers/remote/inference/passthrough/passthrough.py @@ -8,8 +8,10 @@ from collections.abc import AsyncIterator from openai import AsyncOpenAI -from llama_stack.apis.inference import ( +from llama_stack.core.request_headers import NeedsRequestProviderData +from llama_stack_api import ( Inference, + Model, OpenAIChatCompletion, OpenAIChatCompletionChunk, OpenAIChatCompletionRequestWithExtraBody, @@ -18,8 +20,6 @@ from llama_stack.apis.inference import ( OpenAIEmbeddingsRequestWithExtraBody, OpenAIEmbeddingsResponse, ) -from llama_stack.apis.models import Model -from llama_stack.core.request_headers import NeedsRequestProviderData from .config import PassthroughImplConfig diff --git a/src/llama_stack/providers/remote/inference/runpod/config.py b/src/llama_stack/providers/remote/inference/runpod/config.py index a2a1add97..2ee56ca94 100644 --- a/src/llama_stack/providers/remote/inference/runpod/config.py +++ b/src/llama_stack/providers/remote/inference/runpod/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field, SecretStr from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class RunpodProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/runpod/runpod.py b/src/llama_stack/providers/remote/inference/runpod/runpod.py index a76e941cb..9c770cc24 100644 --- a/src/llama_stack/providers/remote/inference/runpod/runpod.py +++ b/src/llama_stack/providers/remote/inference/runpod/runpod.py @@ -6,12 +6,12 @@ from collections.abc import AsyncIterator -from llama_stack.apis.inference import ( +from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import ( OpenAIChatCompletion, OpenAIChatCompletionChunk, OpenAIChatCompletionRequestWithExtraBody, ) -from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin from .config import RunpodImplConfig diff --git a/src/llama_stack/providers/remote/inference/sambanova/config.py b/src/llama_stack/providers/remote/inference/sambanova/config.py index f63210434..93679ba99 100644 --- a/src/llama_stack/providers/remote/inference/sambanova/config.py +++ b/src/llama_stack/providers/remote/inference/sambanova/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class SambaNovaProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/tgi/config.py b/src/llama_stack/providers/remote/inference/tgi/config.py index 47952abba..74edc8523 100644 --- a/src/llama_stack/providers/remote/inference/tgi/config.py +++ b/src/llama_stack/providers/remote/inference/tgi/config.py @@ -8,7 +8,7 @@ from pydantic import BaseModel, Field, SecretStr from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/remote/inference/tgi/tgi.py b/src/llama_stack/providers/remote/inference/tgi/tgi.py index 6ae7b2544..dd47ccc62 100644 --- a/src/llama_stack/providers/remote/inference/tgi/tgi.py +++ b/src/llama_stack/providers/remote/inference/tgi/tgi.py @@ -10,12 +10,12 @@ from collections.abc import Iterable from huggingface_hub import AsyncInferenceClient, HfApi from pydantic import SecretStr -from llama_stack.apis.inference import ( +from llama_stack.log import get_logger +from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import ( OpenAIEmbeddingsRequestWithExtraBody, OpenAIEmbeddingsResponse, ) -from llama_stack.log import get_logger -from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin from .config import InferenceAPIImplConfig, InferenceEndpointImplConfig, TGIImplConfig diff --git a/src/llama_stack/providers/remote/inference/together/config.py b/src/llama_stack/providers/remote/inference/together/config.py index 47392c8e7..c1b3c4a55 100644 --- a/src/llama_stack/providers/remote/inference/together/config.py +++ b/src/llama_stack/providers/remote/inference/together/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/remote/inference/together/together.py b/src/llama_stack/providers/remote/inference/together/together.py index 963b384a0..cd34aec5e 100644 --- a/src/llama_stack/providers/remote/inference/together/together.py +++ b/src/llama_stack/providers/remote/inference/together/together.py @@ -11,15 +11,15 @@ from typing import Any, cast from together import AsyncTogether # type: ignore[import-untyped] from together.constants import BASE_URL # type: ignore[import-untyped] -from llama_stack.apis.inference import ( - OpenAIEmbeddingsRequestWithExtraBody, - OpenAIEmbeddingsResponse, -) -from llama_stack.apis.inference.inference import OpenAIEmbeddingUsage -from llama_stack.apis.models import Model from llama_stack.core.request_headers import NeedsRequestProviderData from llama_stack.log import get_logger from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import ( + Model, + OpenAIEmbeddingsRequestWithExtraBody, + OpenAIEmbeddingsResponse, + OpenAIEmbeddingUsage, +) from .config import TogetherImplConfig diff --git a/src/llama_stack/providers/remote/inference/vertexai/config.py b/src/llama_stack/providers/remote/inference/vertexai/config.py index 5f2efa894..5891f7cd0 100644 --- a/src/llama_stack/providers/remote/inference/vertexai/config.py +++ b/src/llama_stack/providers/remote/inference/vertexai/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field, SecretStr from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class VertexAIProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/vllm/config.py b/src/llama_stack/providers/remote/inference/vllm/config.py index e362aece6..c43533ee4 100644 --- a/src/llama_stack/providers/remote/inference/vllm/config.py +++ b/src/llama_stack/providers/remote/inference/vllm/config.py @@ -9,7 +9,7 @@ from pathlib import Path from pydantic import Field, SecretStr, field_validator from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/remote/inference/vllm/vllm.py b/src/llama_stack/providers/remote/inference/vllm/vllm.py index fa350ec48..1510e9384 100644 --- a/src/llama_stack/providers/remote/inference/vllm/vllm.py +++ b/src/llama_stack/providers/remote/inference/vllm/vllm.py @@ -9,18 +9,16 @@ from urllib.parse import urljoin import httpx from pydantic import ConfigDict -from llama_stack.apis.inference import ( +from llama_stack.log import get_logger +from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import ( + HealthResponse, + HealthStatus, OpenAIChatCompletion, OpenAIChatCompletionChunk, OpenAIChatCompletionRequestWithExtraBody, ToolChoice, ) -from llama_stack.log import get_logger -from llama_stack.providers.datatypes import ( - HealthResponse, - HealthStatus, -) -from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin from .config import VLLMInferenceAdapterConfig diff --git a/src/llama_stack/providers/remote/inference/watsonx/config.py b/src/llama_stack/providers/remote/inference/watsonx/config.py index 8d8df13b4..914f80820 100644 --- a/src/llama_stack/providers/remote/inference/watsonx/config.py +++ b/src/llama_stack/providers/remote/inference/watsonx/config.py @@ -10,7 +10,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class WatsonXProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/inference/watsonx/watsonx.py b/src/llama_stack/providers/remote/inference/watsonx/watsonx.py index e71ffe5e1..aab9e2dca 100644 --- a/src/llama_stack/providers/remote/inference/watsonx/watsonx.py +++ b/src/llama_stack/providers/remote/inference/watsonx/watsonx.py @@ -10,7 +10,14 @@ from typing import Any import litellm import requests -from llama_stack.apis.inference.inference import ( +from llama_stack.core.telemetry.tracing import get_current_span +from llama_stack.log import get_logger +from llama_stack.providers.remote.inference.watsonx.config import WatsonXConfig +from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin +from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params +from llama_stack_api import ( + Model, + ModelType, OpenAIChatCompletion, OpenAIChatCompletionChunk, OpenAIChatCompletionRequestWithExtraBody, @@ -20,13 +27,6 @@ from llama_stack.apis.inference.inference import ( OpenAIEmbeddingsRequestWithExtraBody, OpenAIEmbeddingsResponse, ) -from llama_stack.apis.models import Model -from llama_stack.apis.models.models import ModelType -from llama_stack.core.telemetry.tracing import get_current_span -from llama_stack.log import get_logger -from llama_stack.providers.remote.inference.watsonx.config import WatsonXConfig -from llama_stack.providers.utils.inference.litellm_openai_mixin import LiteLLMOpenAIMixin -from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params logger = get_logger(name=__name__, category="providers::remote::watsonx") @@ -238,8 +238,8 @@ class WatsonXInferenceAdapter(LiteLLMOpenAIMixin): ) # Convert response to OpenAI format - from llama_stack.apis.inference import OpenAIEmbeddingUsage from llama_stack.providers.utils.inference.litellm_openai_mixin import b64_encode_openai_embeddings_response + from llama_stack_api import OpenAIEmbeddingUsage data = b64_encode_openai_embeddings_response(response.data, params.encoding_format) diff --git a/src/llama_stack/providers/remote/post_training/nvidia/README.md b/src/llama_stack/providers/remote/post_training/nvidia/README.md index 83f20a44e..f998f44ba 100644 --- a/src/llama_stack/providers/remote/post_training/nvidia/README.md +++ b/src/llama_stack/providers/remote/post_training/nvidia/README.md @@ -128,7 +128,7 @@ client.post_training.job.cancel(job_uuid="your-job-id") #### 1. Register the model ```python -from llama_stack.apis.models import Model, ModelType +from llama_stack_api.models import Model, ModelType client.models.register( model_id="test-example-model@v1", diff --git a/src/llama_stack/providers/remote/post_training/nvidia/post_training.py b/src/llama_stack/providers/remote/post_training/nvidia/post_training.py index d839ffd6f..830a9f747 100644 --- a/src/llama_stack/providers/remote/post_training/nvidia/post_training.py +++ b/src/llama_stack/providers/remote/post_training/nvidia/post_training.py @@ -10,7 +10,10 @@ from typing import Any, Literal import aiohttp from pydantic import BaseModel, ConfigDict -from llama_stack.apis.post_training import ( +from llama_stack.providers.remote.post_training.nvidia.config import NvidiaPostTrainingConfig +from llama_stack.providers.remote.post_training.nvidia.utils import warn_unsupported_params +from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper +from llama_stack_api import ( AlgorithmConfig, DPOAlignmentConfig, JobStatus, @@ -19,9 +22,6 @@ from llama_stack.apis.post_training import ( PostTrainingJobStatusResponse, TrainingConfig, ) -from llama_stack.providers.remote.post_training.nvidia.config import NvidiaPostTrainingConfig -from llama_stack.providers.remote.post_training.nvidia.utils import warn_unsupported_params -from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper from .models import _MODEL_ENTRIES diff --git a/src/llama_stack/providers/remote/post_training/nvidia/utils.py b/src/llama_stack/providers/remote/post_training/nvidia/utils.py index 162951ff3..bd40dacb4 100644 --- a/src/llama_stack/providers/remote/post_training/nvidia/utils.py +++ b/src/llama_stack/providers/remote/post_training/nvidia/utils.py @@ -9,9 +9,9 @@ from typing import Any from pydantic import BaseModel -from llama_stack.apis.post_training import TrainingConfig from llama_stack.log import get_logger from llama_stack.providers.remote.post_training.nvidia.config import SFTLoRADefaultConfig +from llama_stack_api import TrainingConfig from .config import NvidiaPostTrainingConfig diff --git a/src/llama_stack/providers/remote/safety/bedrock/bedrock.py b/src/llama_stack/providers/remote/safety/bedrock/bedrock.py index 75f96816a..c321f759b 100644 --- a/src/llama_stack/providers/remote/safety/bedrock/bedrock.py +++ b/src/llama_stack/providers/remote/safety/bedrock/bedrock.py @@ -7,17 +7,17 @@ import json from typing import Any -from llama_stack.apis.inference import OpenAIMessageParam -from llama_stack.apis.safety import ( +from llama_stack.log import get_logger +from llama_stack.providers.utils.bedrock.client import create_bedrock_client +from llama_stack_api import ( + OpenAIMessageParam, RunShieldResponse, Safety, SafetyViolation, + Shield, + ShieldsProtocolPrivate, ViolationLevel, ) -from llama_stack.apis.shields import Shield -from llama_stack.log import get_logger -from llama_stack.providers.datatypes import ShieldsProtocolPrivate -from llama_stack.providers.utils.bedrock.client import create_bedrock_client from .config import BedrockSafetyConfig diff --git a/src/llama_stack/providers/remote/safety/bedrock/config.py b/src/llama_stack/providers/remote/safety/bedrock/config.py index 1ca8d95cb..0b1f2581a 100644 --- a/src/llama_stack/providers/remote/safety/bedrock/config.py +++ b/src/llama_stack/providers/remote/safety/bedrock/config.py @@ -6,7 +6,7 @@ from llama_stack.providers.utils.bedrock.config import BedrockBaseConfig -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/remote/safety/nvidia/README.md b/src/llama_stack/providers/remote/safety/nvidia/README.md index af11b2539..f3ec0f1e0 100644 --- a/src/llama_stack/providers/remote/safety/nvidia/README.md +++ b/src/llama_stack/providers/remote/safety/nvidia/README.md @@ -42,8 +42,8 @@ client.initialize() #### Create a safety shield ```python -from llama_stack.apis.safety import Shield -from llama_stack.apis.inference import Message +from llama_stack_api.safety import Shield +from llama_stack_api.inference import Message # Create a safety shield shield = Shield( diff --git a/src/llama_stack/providers/remote/safety/nvidia/config.py b/src/llama_stack/providers/remote/safety/nvidia/config.py index 1c618f4f4..f11de5feb 100644 --- a/src/llama_stack/providers/remote/safety/nvidia/config.py +++ b/src/llama_stack/providers/remote/safety/nvidia/config.py @@ -8,7 +8,7 @@ from typing import Any from pydantic import BaseModel, Field -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/remote/safety/nvidia/nvidia.py b/src/llama_stack/providers/remote/safety/nvidia/nvidia.py index 236f16207..43ff45cc9 100644 --- a/src/llama_stack/providers/remote/safety/nvidia/nvidia.py +++ b/src/llama_stack/providers/remote/safety/nvidia/nvidia.py @@ -8,11 +8,17 @@ from typing import Any import requests -from llama_stack.apis.inference import OpenAIMessageParam -from llama_stack.apis.safety import ModerationObject, RunShieldResponse, Safety, SafetyViolation, ViolationLevel -from llama_stack.apis.shields import Shield from llama_stack.log import get_logger -from llama_stack.providers.datatypes import ShieldsProtocolPrivate +from llama_stack_api import ( + ModerationObject, + OpenAIMessageParam, + RunShieldResponse, + Safety, + SafetyViolation, + Shield, + ShieldsProtocolPrivate, + ViolationLevel, +) from .config import NVIDIASafetyConfig diff --git a/src/llama_stack/providers/remote/safety/sambanova/config.py b/src/llama_stack/providers/remote/safety/sambanova/config.py index 2cde97098..bfb42d88a 100644 --- a/src/llama_stack/providers/remote/safety/sambanova/config.py +++ b/src/llama_stack/providers/remote/safety/sambanova/config.py @@ -8,7 +8,7 @@ from typing import Any from pydantic import BaseModel, Field, SecretStr -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type class SambaNovaProviderDataValidator(BaseModel): diff --git a/src/llama_stack/providers/remote/safety/sambanova/sambanova.py b/src/llama_stack/providers/remote/safety/sambanova/sambanova.py index 72359badd..c11cb544d 100644 --- a/src/llama_stack/providers/remote/safety/sambanova/sambanova.py +++ b/src/llama_stack/providers/remote/safety/sambanova/sambanova.py @@ -9,17 +9,17 @@ from typing import Any import litellm import requests -from llama_stack.apis.inference import OpenAIMessageParam -from llama_stack.apis.safety import ( +from llama_stack.core.request_headers import NeedsRequestProviderData +from llama_stack.log import get_logger +from llama_stack_api import ( + OpenAIMessageParam, RunShieldResponse, Safety, SafetyViolation, + Shield, + ShieldsProtocolPrivate, ViolationLevel, ) -from llama_stack.apis.shields import Shield -from llama_stack.core.request_headers import NeedsRequestProviderData -from llama_stack.log import get_logger -from llama_stack.providers.datatypes import ShieldsProtocolPrivate from .config import SambaNovaSafetyConfig diff --git a/src/llama_stack/providers/remote/tool_runtime/bing_search/bing_search.py b/src/llama_stack/providers/remote/tool_runtime/bing_search/bing_search.py index 9a98964b7..77c5a3bf7 100644 --- a/src/llama_stack/providers/remote/tool_runtime/bing_search/bing_search.py +++ b/src/llama_stack/providers/remote/tool_runtime/bing_search/bing_search.py @@ -9,16 +9,16 @@ from typing import Any import httpx -from llama_stack.apis.common.content_types import URL -from llama_stack.apis.tools import ( +from llama_stack.core.request_headers import NeedsRequestProviderData +from llama_stack_api import ( + URL, ListToolDefsResponse, ToolDef, ToolGroup, + ToolGroupsProtocolPrivate, ToolInvocationResult, ToolRuntime, ) -from llama_stack.core.request_headers import NeedsRequestProviderData -from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate from .config import BingSearchToolConfig @@ -49,7 +49,10 @@ class BingSearchToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, NeedsReq return provider_data.bing_search_api_key async def list_runtime_tools( - self, tool_group_id: str | None = None, mcp_endpoint: URL | None = None + self, + tool_group_id: str | None = None, + mcp_endpoint: URL | None = None, + authorization: str | None = None, ) -> ListToolDefsResponse: return ListToolDefsResponse( data=[ @@ -70,7 +73,9 @@ class BingSearchToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, NeedsReq ] ) - async def invoke_tool(self, tool_name: str, kwargs: dict[str, Any]) -> ToolInvocationResult: + async def invoke_tool( + self, tool_name: str, kwargs: dict[str, Any], authorization: str | None = None + ) -> ToolInvocationResult: api_key = self._get_api_key() headers = { "Ocp-Apim-Subscription-Key": api_key, diff --git a/src/llama_stack/providers/remote/tool_runtime/brave_search/brave_search.py b/src/llama_stack/providers/remote/tool_runtime/brave_search/brave_search.py index 02e5b5c69..1f49671cf 100644 --- a/src/llama_stack/providers/remote/tool_runtime/brave_search/brave_search.py +++ b/src/llama_stack/providers/remote/tool_runtime/brave_search/brave_search.py @@ -8,17 +8,17 @@ from typing import Any import httpx -from llama_stack.apis.common.content_types import URL -from llama_stack.apis.tools import ( +from llama_stack.core.request_headers import NeedsRequestProviderData +from llama_stack.models.llama.datatypes import BuiltinTool +from llama_stack_api import ( + URL, ListToolDefsResponse, ToolDef, ToolGroup, + ToolGroupsProtocolPrivate, ToolInvocationResult, ToolRuntime, ) -from llama_stack.core.request_headers import NeedsRequestProviderData -from llama_stack.models.llama.datatypes import BuiltinTool -from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate from .config import BraveSearchToolConfig @@ -48,7 +48,10 @@ class BraveSearchToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, NeedsRe return provider_data.brave_search_api_key async def list_runtime_tools( - self, tool_group_id: str | None = None, mcp_endpoint: URL | None = None + self, + tool_group_id: str | None = None, + mcp_endpoint: URL | None = None, + authorization: str | None = None, ) -> ListToolDefsResponse: return ListToolDefsResponse( data=[ @@ -70,7 +73,9 @@ class BraveSearchToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, NeedsRe ] ) - async def invoke_tool(self, tool_name: str, kwargs: dict[str, Any]) -> ToolInvocationResult: + async def invoke_tool( + self, tool_name: str, kwargs: dict[str, Any], authorization: str | None = None + ) -> ToolInvocationResult: api_key = self._get_api_key() url = "https://api.search.brave.com/res/v1/web/search" headers = { diff --git a/src/llama_stack/providers/remote/tool_runtime/model_context_protocol/config.py b/src/llama_stack/providers/remote/tool_runtime/model_context_protocol/config.py index b8c5e77fd..9acabfc34 100644 --- a/src/llama_stack/providers/remote/tool_runtime/model_context_protocol/config.py +++ b/src/llama_stack/providers/remote/tool_runtime/model_context_protocol/config.py @@ -10,8 +10,14 @@ from pydantic import BaseModel class MCPProviderDataValidator(BaseModel): - # mcp_endpoint => dict of headers to send - mcp_headers: dict[str, dict[str, str]] | None = None + """ + Validator for MCP provider-specific data passed via request headers. + + Phase 1: Support old header-based authentication for backward compatibility. + In Phase 2, this will be deprecated in favor of the authorization parameter. + """ + + mcp_headers: dict[str, dict[str, str]] | None = None # Map of URI -> headers dict class MCPProviderConfig(BaseModel): diff --git a/src/llama_stack/providers/remote/tool_runtime/model_context_protocol/model_context_protocol.py b/src/llama_stack/providers/remote/tool_runtime/model_context_protocol/model_context_protocol.py index 578bb6d34..649bddecb 100644 --- a/src/llama_stack/providers/remote/tool_runtime/model_context_protocol/model_context_protocol.py +++ b/src/llama_stack/providers/remote/tool_runtime/model_context_protocol/model_context_protocol.py @@ -7,18 +7,18 @@ from typing import Any from urllib.parse import urlparse -from llama_stack.apis.common.content_types import URL -from llama_stack.apis.datatypes import Api -from llama_stack.apis.tools import ( +from llama_stack.core.request_headers import NeedsRequestProviderData +from llama_stack.log import get_logger +from llama_stack.providers.utils.tools.mcp import invoke_mcp_tool, list_mcp_tools +from llama_stack_api import ( + URL, + Api, ListToolDefsResponse, ToolGroup, + ToolGroupsProtocolPrivate, ToolInvocationResult, ToolRuntime, ) -from llama_stack.core.request_headers import NeedsRequestProviderData -from llama_stack.log import get_logger -from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate -from llama_stack.providers.utils.tools.mcp import invoke_mcp_tool, list_mcp_tools from .config import MCPProviderConfig @@ -39,15 +39,29 @@ class ModelContextProtocolToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime return async def list_runtime_tools( - self, tool_group_id: str | None = None, mcp_endpoint: URL | None = None + self, + tool_group_id: str | None = None, + mcp_endpoint: URL | None = None, + authorization: str | None = None, ) -> ListToolDefsResponse: # this endpoint should be retrieved by getting the tool group right? if mcp_endpoint is None: raise ValueError("mcp_endpoint is required") - headers = await self.get_headers_from_request(mcp_endpoint.uri) - return await list_mcp_tools(mcp_endpoint.uri, headers) - async def invoke_tool(self, tool_name: str, kwargs: dict[str, Any]) -> ToolInvocationResult: + # Phase 1: Support both old header-based auth AND new authorization parameter + # Get headers and auth from provider data (old approach) + provider_headers, provider_auth = await self.get_headers_from_request(mcp_endpoint.uri) + + # New authorization parameter takes precedence over provider data + final_authorization = authorization or provider_auth + + return await list_mcp_tools( + endpoint=mcp_endpoint.uri, headers=provider_headers, authorization=final_authorization + ) + + async def invoke_tool( + self, tool_name: str, kwargs: dict[str, Any], authorization: str | None = None + ) -> ToolInvocationResult: tool = await self.tool_store.get_tool(tool_name) if tool.metadata is None or tool.metadata.get("endpoint") is None: raise ValueError(f"Tool {tool_name} does not have metadata") @@ -55,19 +69,57 @@ class ModelContextProtocolToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime if urlparse(endpoint).scheme not in ("http", "https"): raise ValueError(f"Endpoint {endpoint} is not a valid HTTP(S) URL") - headers = await self.get_headers_from_request(endpoint) - return await invoke_mcp_tool(endpoint, headers, tool_name, kwargs) + # Phase 1: Support both old header-based auth AND new authorization parameter + # Get headers and auth from provider data (old approach) + provider_headers, provider_auth = await self.get_headers_from_request(endpoint) + + # New authorization parameter takes precedence over provider data + final_authorization = authorization or provider_auth + + return await invoke_mcp_tool( + endpoint=endpoint, + tool_name=tool_name, + kwargs=kwargs, + headers=provider_headers, + authorization=final_authorization, + ) + + async def get_headers_from_request(self, mcp_endpoint_uri: str) -> tuple[dict[str, str], str | None]: + """ + Extract headers and authorization from request provider data (Phase 1 backward compatibility). + + Phase 1: Temporarily allows Authorization to be passed via mcp_headers for backward compatibility. + Phase 2: Will enforce that Authorization should use the dedicated authorization parameter instead. + + Returns: + Tuple of (headers_dict, authorization_token) + - headers_dict: All headers except Authorization + - authorization_token: Token from Authorization header (with "Bearer " prefix removed), or None + """ - async def get_headers_from_request(self, mcp_endpoint_uri: str) -> dict[str, str]: def canonicalize_uri(uri: str) -> str: return f"{urlparse(uri).netloc or ''}/{urlparse(uri).path or ''}" headers = {} + authorization = None provider_data = self.get_request_provider_data() - if provider_data and provider_data.mcp_headers: + if provider_data and hasattr(provider_data, "mcp_headers") and provider_data.mcp_headers: for uri, values in provider_data.mcp_headers.items(): if canonicalize_uri(uri) != canonicalize_uri(mcp_endpoint_uri): continue - headers.update(values) - return headers + + # Phase 1: Extract Authorization from mcp_headers for backward compatibility + # (Phase 2 will reject this and require the dedicated authorization parameter) + for key in values.keys(): + if key.lower() == "authorization": + # Extract authorization token and strip "Bearer " prefix if present + auth_value = values[key] + if auth_value.startswith("Bearer "): + authorization = auth_value[7:] # Remove "Bearer " prefix + else: + authorization = auth_value + else: + headers[key] = values[key] + + return headers, authorization diff --git a/src/llama_stack/providers/remote/tool_runtime/tavily_search/tavily_search.py b/src/llama_stack/providers/remote/tool_runtime/tavily_search/tavily_search.py index ca629fced..e12b41885 100644 --- a/src/llama_stack/providers/remote/tool_runtime/tavily_search/tavily_search.py +++ b/src/llama_stack/providers/remote/tool_runtime/tavily_search/tavily_search.py @@ -9,16 +9,16 @@ from typing import Any import httpx -from llama_stack.apis.common.content_types import URL -from llama_stack.apis.tools import ( +from llama_stack.core.request_headers import NeedsRequestProviderData +from llama_stack_api import ( + URL, ListToolDefsResponse, ToolDef, ToolGroup, + ToolGroupsProtocolPrivate, ToolInvocationResult, ToolRuntime, ) -from llama_stack.core.request_headers import NeedsRequestProviderData -from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate from .config import TavilySearchToolConfig @@ -48,7 +48,10 @@ class TavilySearchToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, NeedsR return provider_data.tavily_search_api_key async def list_runtime_tools( - self, tool_group_id: str | None = None, mcp_endpoint: URL | None = None + self, + tool_group_id: str | None = None, + mcp_endpoint: URL | None = None, + authorization: str | None = None, ) -> ListToolDefsResponse: return ListToolDefsResponse( data=[ @@ -69,7 +72,9 @@ class TavilySearchToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, NeedsR ] ) - async def invoke_tool(self, tool_name: str, kwargs: dict[str, Any]) -> ToolInvocationResult: + async def invoke_tool( + self, tool_name: str, kwargs: dict[str, Any], authorization: str | None = None + ) -> ToolInvocationResult: api_key = self._get_api_key() async with httpx.AsyncClient() as client: response = await client.post( diff --git a/src/llama_stack/providers/remote/tool_runtime/wolfram_alpha/wolfram_alpha.py b/src/llama_stack/providers/remote/tool_runtime/wolfram_alpha/wolfram_alpha.py index 410e34195..68f0ebaef 100644 --- a/src/llama_stack/providers/remote/tool_runtime/wolfram_alpha/wolfram_alpha.py +++ b/src/llama_stack/providers/remote/tool_runtime/wolfram_alpha/wolfram_alpha.py @@ -9,16 +9,16 @@ from typing import Any import httpx -from llama_stack.apis.common.content_types import URL -from llama_stack.apis.tools import ( +from llama_stack.core.request_headers import NeedsRequestProviderData +from llama_stack_api import ( + URL, ListToolDefsResponse, ToolDef, ToolGroup, + ToolGroupsProtocolPrivate, ToolInvocationResult, ToolRuntime, ) -from llama_stack.core.request_headers import NeedsRequestProviderData -from llama_stack.providers.datatypes import ToolGroupsProtocolPrivate from .config import WolframAlphaToolConfig @@ -49,7 +49,10 @@ class WolframAlphaToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, NeedsR return provider_data.wolfram_alpha_api_key async def list_runtime_tools( - self, tool_group_id: str | None = None, mcp_endpoint: URL | None = None + self, + tool_group_id: str | None = None, + mcp_endpoint: URL | None = None, + authorization: str | None = None, ) -> ListToolDefsResponse: return ListToolDefsResponse( data=[ @@ -70,7 +73,9 @@ class WolframAlphaToolRuntimeImpl(ToolGroupsProtocolPrivate, ToolRuntime, NeedsR ] ) - async def invoke_tool(self, tool_name: str, kwargs: dict[str, Any]) -> ToolInvocationResult: + async def invoke_tool( + self, tool_name: str, kwargs: dict[str, Any], authorization: str | None = None + ) -> ToolInvocationResult: api_key = self._get_api_key() params = { "input": kwargs["query"], diff --git a/src/llama_stack/providers/remote/vector_io/chroma/__init__.py b/src/llama_stack/providers/remote/vector_io/chroma/__init__.py index e4b77c68d..d774ea643 100644 --- a/src/llama_stack/providers/remote/vector_io/chroma/__init__.py +++ b/src/llama_stack/providers/remote/vector_io/chroma/__init__.py @@ -4,7 +4,7 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.providers.datatypes import Api, ProviderSpec +from llama_stack_api import Api, ProviderSpec from .config import ChromaVectorIOConfig diff --git a/src/llama_stack/providers/remote/vector_io/chroma/chroma.py b/src/llama_stack/providers/remote/vector_io/chroma/chroma.py index 97e2244b8..645b40661 100644 --- a/src/llama_stack/providers/remote/vector_io/chroma/chroma.py +++ b/src/llama_stack/providers/remote/vector_io/chroma/chroma.py @@ -11,17 +11,22 @@ from urllib.parse import urlparse import chromadb from numpy.typing import NDArray -from llama_stack.apis.files import Files -from llama_stack.apis.inference import Inference, InterleavedContent -from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO -from llama_stack.apis.vector_stores import VectorStore from llama_stack.log import get_logger -from llama_stack.providers.datatypes import VectorStoresProtocolPrivate from llama_stack.providers.inline.vector_io.chroma import ChromaVectorIOConfig as InlineChromaVectorIOConfig from llama_stack.providers.utils.kvstore import kvstore_impl from llama_stack.providers.utils.kvstore.api import KVStore from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin from llama_stack.providers.utils.memory.vector_store import ChunkForDeletion, EmbeddingIndex, VectorStoreWithIndex +from llama_stack_api import ( + Chunk, + Files, + Inference, + InterleavedContent, + QueryChunksResponse, + VectorIO, + VectorStore, + VectorStoresProtocolPrivate, +) from .config import ChromaVectorIOConfig as RemoteChromaVectorIOConfig diff --git a/src/llama_stack/providers/remote/vector_io/chroma/config.py b/src/llama_stack/providers/remote/vector_io/chroma/config.py index 209ba90bb..648d641ad 100644 --- a/src/llama_stack/providers/remote/vector_io/chroma/config.py +++ b/src/llama_stack/providers/remote/vector_io/chroma/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.core.storage.datatypes import KVStoreReference -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/remote/vector_io/milvus/__init__.py b/src/llama_stack/providers/remote/vector_io/milvus/__init__.py index 526075bb2..1b703d486 100644 --- a/src/llama_stack/providers/remote/vector_io/milvus/__init__.py +++ b/src/llama_stack/providers/remote/vector_io/milvus/__init__.py @@ -4,7 +4,7 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.providers.datatypes import Api, ProviderSpec +from llama_stack_api import Api, ProviderSpec from .config import MilvusVectorIOConfig diff --git a/src/llama_stack/providers/remote/vector_io/milvus/config.py b/src/llama_stack/providers/remote/vector_io/milvus/config.py index 8ff9e1328..4b9d6a566 100644 --- a/src/llama_stack/providers/remote/vector_io/milvus/config.py +++ b/src/llama_stack/providers/remote/vector_io/milvus/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, ConfigDict, Field from llama_stack.core.storage.datatypes import KVStoreReference -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/remote/vector_io/milvus/milvus.py b/src/llama_stack/providers/remote/vector_io/milvus/milvus.py index 73339b5be..aefa20317 100644 --- a/src/llama_stack/providers/remote/vector_io/milvus/milvus.py +++ b/src/llama_stack/providers/remote/vector_io/milvus/milvus.py @@ -11,13 +11,7 @@ from typing import Any from numpy.typing import NDArray from pymilvus import AnnSearchRequest, DataType, Function, FunctionType, MilvusClient, RRFRanker, WeightedRanker -from llama_stack.apis.common.errors import VectorStoreNotFoundError -from llama_stack.apis.files import Files -from llama_stack.apis.inference import Inference, InterleavedContent -from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO -from llama_stack.apis.vector_stores import VectorStore from llama_stack.log import get_logger -from llama_stack.providers.datatypes import VectorStoresProtocolPrivate from llama_stack.providers.inline.vector_io.milvus import MilvusVectorIOConfig as InlineMilvusVectorIOConfig from llama_stack.providers.utils.kvstore import kvstore_impl from llama_stack.providers.utils.kvstore.api import KVStore @@ -29,6 +23,17 @@ from llama_stack.providers.utils.memory.vector_store import ( VectorStoreWithIndex, ) from llama_stack.providers.utils.vector_io.vector_utils import sanitize_collection_name +from llama_stack_api import ( + Chunk, + Files, + Inference, + InterleavedContent, + QueryChunksResponse, + VectorIO, + VectorStore, + VectorStoreNotFoundError, + VectorStoresProtocolPrivate, +) from .config import MilvusVectorIOConfig as RemoteMilvusVectorIOConfig diff --git a/src/llama_stack/providers/remote/vector_io/pgvector/__init__.py b/src/llama_stack/providers/remote/vector_io/pgvector/__init__.py index 8086b7650..36018fd95 100644 --- a/src/llama_stack/providers/remote/vector_io/pgvector/__init__.py +++ b/src/llama_stack/providers/remote/vector_io/pgvector/__init__.py @@ -4,7 +4,7 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.providers.datatypes import Api, ProviderSpec +from llama_stack_api import Api, ProviderSpec from .config import PGVectorVectorIOConfig diff --git a/src/llama_stack/providers/remote/vector_io/pgvector/config.py b/src/llama_stack/providers/remote/vector_io/pgvector/config.py index d81e524e4..87d40a883 100644 --- a/src/llama_stack/providers/remote/vector_io/pgvector/config.py +++ b/src/llama_stack/providers/remote/vector_io/pgvector/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.core.storage.datatypes import KVStoreReference -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/remote/vector_io/pgvector/pgvector.py b/src/llama_stack/providers/remote/vector_io/pgvector/pgvector.py index cf10a0e01..2901bad97 100644 --- a/src/llama_stack/providers/remote/vector_io/pgvector/pgvector.py +++ b/src/llama_stack/providers/remote/vector_io/pgvector/pgvector.py @@ -13,19 +13,24 @@ from psycopg2 import sql from psycopg2.extras import Json, execute_values from pydantic import BaseModel, TypeAdapter -from llama_stack.apis.common.errors import VectorStoreNotFoundError -from llama_stack.apis.files import Files -from llama_stack.apis.inference import Inference, InterleavedContent -from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO -from llama_stack.apis.vector_stores import VectorStore from llama_stack.log import get_logger -from llama_stack.providers.datatypes import VectorStoresProtocolPrivate from llama_stack.providers.utils.inference.prompt_adapter import interleaved_content_as_str from llama_stack.providers.utils.kvstore import kvstore_impl from llama_stack.providers.utils.kvstore.api import KVStore from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin from llama_stack.providers.utils.memory.vector_store import ChunkForDeletion, EmbeddingIndex, VectorStoreWithIndex from llama_stack.providers.utils.vector_io.vector_utils import WeightedInMemoryAggregator, sanitize_collection_name +from llama_stack_api import ( + Chunk, + Files, + Inference, + InterleavedContent, + QueryChunksResponse, + VectorIO, + VectorStore, + VectorStoreNotFoundError, + VectorStoresProtocolPrivate, +) from .config import PGVectorVectorIOConfig diff --git a/src/llama_stack/providers/remote/vector_io/qdrant/__init__.py b/src/llama_stack/providers/remote/vector_io/qdrant/__init__.py index e9527f101..b5b02fe59 100644 --- a/src/llama_stack/providers/remote/vector_io/qdrant/__init__.py +++ b/src/llama_stack/providers/remote/vector_io/qdrant/__init__.py @@ -4,7 +4,7 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.providers.datatypes import Api, ProviderSpec +from llama_stack_api import Api, ProviderSpec from .config import QdrantVectorIOConfig diff --git a/src/llama_stack/providers/remote/vector_io/qdrant/config.py b/src/llama_stack/providers/remote/vector_io/qdrant/config.py index 01fbcc5cb..e0a3fe207 100644 --- a/src/llama_stack/providers/remote/vector_io/qdrant/config.py +++ b/src/llama_stack/providers/remote/vector_io/qdrant/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel from llama_stack.core.storage.datatypes import KVStoreReference -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/remote/vector_io/qdrant/qdrant.py b/src/llama_stack/providers/remote/vector_io/qdrant/qdrant.py index 7d17c5591..20ab653d0 100644 --- a/src/llama_stack/providers/remote/vector_io/qdrant/qdrant.py +++ b/src/llama_stack/providers/remote/vector_io/qdrant/qdrant.py @@ -13,23 +13,24 @@ from numpy.typing import NDArray from qdrant_client import AsyncQdrantClient, models from qdrant_client.models import PointStruct -from llama_stack.apis.common.errors import VectorStoreNotFoundError -from llama_stack.apis.files import Files -from llama_stack.apis.inference import Inference, InterleavedContent -from llama_stack.apis.vector_io import ( - Chunk, - QueryChunksResponse, - VectorIO, - VectorStoreChunkingStrategy, - VectorStoreFileObject, -) -from llama_stack.apis.vector_stores import VectorStore from llama_stack.log import get_logger -from llama_stack.providers.datatypes import VectorStoresProtocolPrivate from llama_stack.providers.inline.vector_io.qdrant import QdrantVectorIOConfig as InlineQdrantVectorIOConfig from llama_stack.providers.utils.kvstore import kvstore_impl from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin from llama_stack.providers.utils.memory.vector_store import ChunkForDeletion, EmbeddingIndex, VectorStoreWithIndex +from llama_stack_api import ( + Chunk, + Files, + Inference, + InterleavedContent, + QueryChunksResponse, + VectorIO, + VectorStore, + VectorStoreChunkingStrategy, + VectorStoreFileObject, + VectorStoreNotFoundError, + VectorStoresProtocolPrivate, +) from .config import QdrantVectorIOConfig as RemoteQdrantVectorIOConfig diff --git a/src/llama_stack/providers/remote/vector_io/weaviate/__init__.py b/src/llama_stack/providers/remote/vector_io/weaviate/__init__.py index 12e11d013..47546d459 100644 --- a/src/llama_stack/providers/remote/vector_io/weaviate/__init__.py +++ b/src/llama_stack/providers/remote/vector_io/weaviate/__init__.py @@ -4,7 +4,7 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.providers.datatypes import Api, ProviderSpec +from llama_stack_api import Api, ProviderSpec from .config import WeaviateVectorIOConfig diff --git a/src/llama_stack/providers/remote/vector_io/weaviate/config.py b/src/llama_stack/providers/remote/vector_io/weaviate/config.py index 66dbf1fed..75d1b7c51 100644 --- a/src/llama_stack/providers/remote/vector_io/weaviate/config.py +++ b/src/llama_stack/providers/remote/vector_io/weaviate/config.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel, Field from llama_stack.core.storage.datatypes import KVStoreReference -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/remote/vector_io/weaviate/weaviate.py b/src/llama_stack/providers/remote/vector_io/weaviate/weaviate.py index d200662da..ba3e6b7ea 100644 --- a/src/llama_stack/providers/remote/vector_io/weaviate/weaviate.py +++ b/src/llama_stack/providers/remote/vector_io/weaviate/weaviate.py @@ -12,15 +12,8 @@ from numpy.typing import NDArray from weaviate.classes.init import Auth from weaviate.classes.query import Filter, HybridFusion -from llama_stack.apis.common.content_types import InterleavedContent -from llama_stack.apis.common.errors import VectorStoreNotFoundError -from llama_stack.apis.files import Files -from llama_stack.apis.inference import Inference -from llama_stack.apis.vector_io import Chunk, QueryChunksResponse, VectorIO -from llama_stack.apis.vector_stores import VectorStore from llama_stack.core.request_headers import NeedsRequestProviderData from llama_stack.log import get_logger -from llama_stack.providers.datatypes import VectorStoresProtocolPrivate from llama_stack.providers.utils.kvstore import kvstore_impl from llama_stack.providers.utils.kvstore.api import KVStore from llama_stack.providers.utils.memory.openai_vector_store_mixin import OpenAIVectorStoreMixin @@ -31,6 +24,17 @@ from llama_stack.providers.utils.memory.vector_store import ( VectorStoreWithIndex, ) from llama_stack.providers.utils.vector_io.vector_utils import sanitize_collection_name +from llama_stack_api import ( + Chunk, + Files, + Inference, + InterleavedContent, + QueryChunksResponse, + VectorIO, + VectorStore, + VectorStoreNotFoundError, + VectorStoresProtocolPrivate, +) from .config import WeaviateVectorIOConfig diff --git a/src/llama_stack/providers/utils/common/data_schema_validator.py b/src/llama_stack/providers/utils/common/data_schema_validator.py index b0305104f..c9a3b0920 100644 --- a/src/llama_stack/providers/utils/common/data_schema_validator.py +++ b/src/llama_stack/providers/utils/common/data_schema_validator.py @@ -7,12 +7,8 @@ from enum import Enum from typing import Any -from llama_stack.apis.common.type_system import ( - ChatCompletionInputType, - CompletionInputType, - StringType, -) from llama_stack.core.datatypes import Api +from llama_stack_api import ChatCompletionInputType, CompletionInputType, StringType class ColumnName(Enum): diff --git a/src/llama_stack/providers/utils/files/form_data.py b/src/llama_stack/providers/utils/files/form_data.py index 3d8fb6d85..3fac14f38 100644 --- a/src/llama_stack/providers/utils/files/form_data.py +++ b/src/llama_stack/providers/utils/files/form_data.py @@ -9,7 +9,7 @@ import json from fastapi import Request from pydantic import BaseModel, ValidationError -from llama_stack.apis.files import ExpiresAfter +from llama_stack_api import ExpiresAfter async def parse_pydantic_from_form[T: BaseModel](request: Request, field_name: str, model_class: type[T]) -> T | None: diff --git a/src/llama_stack/providers/utils/inference/embedding_mixin.py b/src/llama_stack/providers/utils/inference/embedding_mixin.py index bab495eef..f7e5c711b 100644 --- a/src/llama_stack/providers/utils/inference/embedding_mixin.py +++ b/src/llama_stack/providers/utils/inference/embedding_mixin.py @@ -17,7 +17,7 @@ from llama_stack.log import get_logger if TYPE_CHECKING: from sentence_transformers import SentenceTransformer -from llama_stack.apis.inference import ( +from llama_stack_api import ( ModelStore, OpenAIEmbeddingData, OpenAIEmbeddingsRequestWithExtraBody, diff --git a/src/llama_stack/providers/utils/inference/inference_store.py b/src/llama_stack/providers/utils/inference/inference_store.py index a3a28aec0..49e3af7a1 100644 --- a/src/llama_stack/providers/utils/inference/inference_store.py +++ b/src/llama_stack/providers/utils/inference/inference_store.py @@ -8,16 +8,16 @@ from typing import Any from sqlalchemy.exc import IntegrityError -from llama_stack.apis.inference import ( +from llama_stack.core.datatypes import AccessRule +from llama_stack.core.storage.datatypes import InferenceStoreReference, StorageBackendType +from llama_stack.log import get_logger +from llama_stack_api import ( ListOpenAIChatCompletionResponse, OpenAIChatCompletion, OpenAICompletionWithInputMessages, OpenAIMessageParam, Order, ) -from llama_stack.core.datatypes import AccessRule -from llama_stack.core.storage.datatypes import InferenceStoreReference, StorageBackendType -from llama_stack.log import get_logger from ..sqlstore.api import ColumnDefinition, ColumnType from ..sqlstore.authorized_sqlstore import AuthorizedSqlStore diff --git a/src/llama_stack/providers/utils/inference/litellm_openai_mixin.py b/src/llama_stack/providers/utils/inference/litellm_openai_mixin.py index a793c499e..c462d1aad 100644 --- a/src/llama_stack/providers/utils/inference/litellm_openai_mixin.py +++ b/src/llama_stack/providers/utils/inference/litellm_openai_mixin.py @@ -10,7 +10,13 @@ from collections.abc import AsyncIterator import litellm -from llama_stack.apis.inference import ( +from llama_stack.core.request_headers import NeedsRequestProviderData +from llama_stack.log import get_logger +from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper, ProviderModelEntry +from llama_stack.providers.utils.inference.openai_compat import ( + prepare_openai_completion_params, +) +from llama_stack_api import ( InferenceProvider, OpenAIChatCompletion, OpenAIChatCompletionChunk, @@ -22,12 +28,6 @@ from llama_stack.apis.inference import ( OpenAIEmbeddingsResponse, OpenAIEmbeddingUsage, ) -from llama_stack.core.request_headers import NeedsRequestProviderData -from llama_stack.log import get_logger -from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper, ProviderModelEntry -from llama_stack.providers.utils.inference.openai_compat import ( - prepare_openai_completion_params, -) logger = get_logger(name=__name__, category="providers::utils") diff --git a/src/llama_stack/providers/utils/inference/model_registry.py b/src/llama_stack/providers/utils/inference/model_registry.py index 8a120b698..42b54497f 100644 --- a/src/llama_stack/providers/utils/inference/model_registry.py +++ b/src/llama_stack/providers/utils/inference/model_registry.py @@ -8,13 +8,11 @@ from typing import Any from pydantic import BaseModel, Field, SecretStr -from llama_stack.apis.common.errors import UnsupportedModelError -from llama_stack.apis.models import ModelType from llama_stack.log import get_logger -from llama_stack.providers.datatypes import Model, ModelsProtocolPrivate from llama_stack.providers.utils.inference import ( ALL_HUGGINGFACE_REPOS_TO_MODEL_DESCRIPTOR, ) +from llama_stack_api import Model, ModelsProtocolPrivate, ModelType, UnsupportedModelError logger = get_logger(name=__name__, category="providers::utils") diff --git a/src/llama_stack/providers/utils/inference/openai_compat.py b/src/llama_stack/providers/utils/inference/openai_compat.py index c2e6829e0..32d41ffde 100644 --- a/src/llama_stack/providers/utils/inference/openai_compat.py +++ b/src/llama_stack/providers/utils/inference/openai_compat.py @@ -25,20 +25,6 @@ from openai.types.chat import ( ) from pydantic import BaseModel -from llama_stack.apis.common.content_types import ( - URL, - ImageContentItem, - TextContentItem, - _URLOrData, -) -from llama_stack.apis.inference import ( - GreedySamplingStrategy, - JsonSchemaResponseFormat, - OpenAIResponseFormatParam, - SamplingParams, - TopKSamplingStrategy, - TopPSamplingStrategy, -) from llama_stack.log import get_logger from llama_stack.models.llama.datatypes import ( BuiltinTool, @@ -46,6 +32,18 @@ from llama_stack.models.llama.datatypes import ( ToolCall, ToolDefinition, ) +from llama_stack_api import ( + URL, + GreedySamplingStrategy, + ImageContentItem, + JsonSchemaResponseFormat, + OpenAIResponseFormatParam, + SamplingParams, + TextContentItem, + TopKSamplingStrategy, + TopPSamplingStrategy, + _URLOrData, +) logger = get_logger(name=__name__, category="providers::utils") diff --git a/src/llama_stack/providers/utils/inference/openai_mixin.py b/src/llama_stack/providers/utils/inference/openai_mixin.py index 09059da09..559ac90ce 100644 --- a/src/llama_stack/providers/utils/inference/openai_mixin.py +++ b/src/llama_stack/providers/utils/inference/openai_mixin.py @@ -13,8 +13,14 @@ from typing import Any from openai import AsyncOpenAI from pydantic import BaseModel, ConfigDict -from llama_stack.apis.inference import ( +from llama_stack.core.request_headers import NeedsRequestProviderData +from llama_stack.log import get_logger +from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig +from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params +from llama_stack.providers.utils.inference.prompt_adapter import localize_image_content +from llama_stack_api import ( Model, + ModelType, OpenAIChatCompletion, OpenAIChatCompletionChunk, OpenAIChatCompletionRequestWithExtraBody, @@ -26,12 +32,6 @@ from llama_stack.apis.inference import ( OpenAIEmbeddingUsage, OpenAIMessageParam, ) -from llama_stack.apis.models import ModelType -from llama_stack.core.request_headers import NeedsRequestProviderData -from llama_stack.log import get_logger -from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig -from llama_stack.providers.utils.inference.openai_compat import prepare_openai_completion_params -from llama_stack.providers.utils.inference.prompt_adapter import localize_image_content logger = get_logger(name=__name__, category="providers::utils") diff --git a/src/llama_stack/providers/utils/inference/prompt_adapter.py b/src/llama_stack/providers/utils/inference/prompt_adapter.py index 35a7b3484..6272c9eed 100644 --- a/src/llama_stack/providers/utils/inference/prompt_adapter.py +++ b/src/llama_stack/providers/utils/inference/prompt_adapter.py @@ -14,26 +14,6 @@ from typing import Any import httpx from PIL import Image as PIL_Image -from llama_stack.apis.common.content_types import ( - ImageContentItem, - InterleavedContent, - InterleavedContentItem, - TextContentItem, -) -from llama_stack.apis.inference import ( - CompletionRequest, - OpenAIAssistantMessageParam, - OpenAIChatCompletionContentPartImageParam, - OpenAIChatCompletionContentPartTextParam, - OpenAIFile, - OpenAIMessageParam, - OpenAISystemMessageParam, - OpenAIToolMessageParam, - OpenAIUserMessageParam, - ResponseFormat, - ResponseFormatType, - ToolChoice, -) from llama_stack.log import get_logger from llama_stack.models.llama.datatypes import ( RawContent, @@ -50,6 +30,24 @@ from llama_stack.models.llama.llama3.chat_format import ChatFormat from llama_stack.models.llama.llama3.tokenizer import Tokenizer from llama_stack.models.llama.sku_list import resolve_model from llama_stack.models.llama.sku_types import ModelFamily, is_multimodal +from llama_stack_api import ( + CompletionRequest, + ImageContentItem, + InterleavedContent, + InterleavedContentItem, + OpenAIAssistantMessageParam, + OpenAIChatCompletionContentPartImageParam, + OpenAIChatCompletionContentPartTextParam, + OpenAIFile, + OpenAIMessageParam, + OpenAISystemMessageParam, + OpenAIToolMessageParam, + OpenAIUserMessageParam, + ResponseFormat, + ResponseFormatType, + TextContentItem, + ToolChoice, +) log = get_logger(name=__name__, category="providers::utils") diff --git a/src/llama_stack/providers/utils/kvstore/sqlite/config.py b/src/llama_stack/providers/utils/kvstore/sqlite/config.py index 6a8b0a7cf..0f8fa0a95 100644 --- a/src/llama_stack/providers/utils/kvstore/sqlite/config.py +++ b/src/llama_stack/providers/utils/kvstore/sqlite/config.py @@ -6,7 +6,7 @@ from pydantic import BaseModel, Field -from llama_stack.schema_utils import json_schema_type +from llama_stack_api import json_schema_type @json_schema_type diff --git a/src/llama_stack/providers/utils/memory/file_utils.py b/src/llama_stack/providers/utils/memory/file_utils.py index 4c40056f3..6786293c6 100644 --- a/src/llama_stack/providers/utils/memory/file_utils.py +++ b/src/llama_stack/providers/utils/memory/file_utils.py @@ -8,7 +8,7 @@ import base64 import mimetypes import os -from llama_stack.apis.common.content_types import URL +from llama_stack_api import URL def data_url_from_file(file_path: str) -> URL: diff --git a/src/llama_stack/providers/utils/memory/openai_vector_store_mixin.py b/src/llama_stack/providers/utils/memory/openai_vector_store_mixin.py index 853245598..540ff5940 100644 --- a/src/llama_stack/providers/utils/memory/openai_vector_store_mixin.py +++ b/src/llama_stack/providers/utils/memory/openai_vector_store_mixin.py @@ -15,14 +15,23 @@ from typing import Annotated, Any from fastapi import Body from pydantic import TypeAdapter -from llama_stack.apis.common.errors import VectorStoreNotFoundError -from llama_stack.apis.files import Files, OpenAIFileObject -from llama_stack.apis.vector_io import ( +from llama_stack.core.id_generation import generate_object_id +from llama_stack.log import get_logger +from llama_stack.providers.utils.kvstore.api import KVStore +from llama_stack.providers.utils.memory.vector_store import ( + ChunkForDeletion, + content_from_data_and_mime_type, + make_overlapped_chunks, +) +from llama_stack_api import ( Chunk, + Files, OpenAICreateVectorStoreFileBatchRequestWithExtraBody, OpenAICreateVectorStoreRequestWithExtraBody, + OpenAIFileObject, QueryChunksResponse, SearchRankingOptions, + VectorStore, VectorStoreChunkingStrategy, VectorStoreChunkingStrategyAuto, VectorStoreChunkingStrategyStatic, @@ -39,19 +48,11 @@ from llama_stack.apis.vector_io import ( VectorStoreFileStatus, VectorStoreListFilesResponse, VectorStoreListResponse, + VectorStoreNotFoundError, VectorStoreObject, VectorStoreSearchResponse, VectorStoreSearchResponsePage, ) -from llama_stack.apis.vector_stores import VectorStore -from llama_stack.core.id_generation import generate_object_id -from llama_stack.log import get_logger -from llama_stack.providers.utils.kvstore.api import KVStore -from llama_stack.providers.utils.memory.vector_store import ( - ChunkForDeletion, - content_from_data_and_mime_type, - make_overlapped_chunks, -) EMBEDDING_DIMENSION = 768 diff --git a/src/llama_stack/providers/utils/memory/vector_store.py b/src/llama_stack/providers/utils/memory/vector_store.py index 99f875227..b6a671ddb 100644 --- a/src/llama_stack/providers/utils/memory/vector_store.py +++ b/src/llama_stack/providers/utils/memory/vector_store.py @@ -17,21 +17,23 @@ import numpy as np from numpy.typing import NDArray from pydantic import BaseModel -from llama_stack.apis.common.content_types import ( - URL, - InterleavedContent, -) -from llama_stack.apis.inference import OpenAIEmbeddingsRequestWithExtraBody -from llama_stack.apis.tools import RAGDocument -from llama_stack.apis.vector_io import Chunk, ChunkMetadata, QueryChunksResponse -from llama_stack.apis.vector_stores import VectorStore from llama_stack.log import get_logger from llama_stack.models.llama.llama3.tokenizer import Tokenizer -from llama_stack.providers.datatypes import Api from llama_stack.providers.utils.inference.prompt_adapter import ( interleaved_content_as_str, ) from llama_stack.providers.utils.vector_io.vector_utils import generate_chunk_id +from llama_stack_api import ( + URL, + Api, + Chunk, + ChunkMetadata, + InterleavedContent, + OpenAIEmbeddingsRequestWithExtraBody, + QueryChunksResponse, + RAGDocument, + VectorStore, +) log = get_logger(name=__name__, category="providers::utils") diff --git a/src/llama_stack/providers/utils/pagination.py b/src/llama_stack/providers/utils/pagination.py index 033022491..d1d9e36c5 100644 --- a/src/llama_stack/providers/utils/pagination.py +++ b/src/llama_stack/providers/utils/pagination.py @@ -6,7 +6,7 @@ from typing import Any -from llama_stack.apis.common.responses import PaginatedResponse +from llama_stack_api import PaginatedResponse def paginate_records( diff --git a/src/llama_stack/providers/utils/responses/responses_store.py b/src/llama_stack/providers/utils/responses/responses_store.py index fdca8ddee..f6e7c435d 100644 --- a/src/llama_stack/providers/utils/responses/responses_store.py +++ b/src/llama_stack/providers/utils/responses/responses_store.py @@ -4,21 +4,19 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.agents import ( - Order, -) -from llama_stack.apis.agents.openai_responses import ( - ListOpenAIResponseInputItem, - ListOpenAIResponseObject, - OpenAIDeleteResponseObject, - OpenAIResponseInput, - OpenAIResponseObject, - OpenAIResponseObjectWithInput, -) -from llama_stack.apis.inference import OpenAIMessageParam from llama_stack.core.datatypes import AccessRule from llama_stack.core.storage.datatypes import ResponsesStoreReference, SqlStoreReference from llama_stack.log import get_logger +from llama_stack_api import ( + ListOpenAIResponseInputItem, + ListOpenAIResponseObject, + OpenAIDeleteResponseObject, + OpenAIMessageParam, + OpenAIResponseInput, + OpenAIResponseObject, + OpenAIResponseObjectWithInput, + Order, +) from ..sqlstore.api import ColumnDefinition, ColumnType from ..sqlstore.authorized_sqlstore import AuthorizedSqlStore diff --git a/src/llama_stack/providers/utils/scoring/aggregation_utils.py b/src/llama_stack/providers/utils/scoring/aggregation_utils.py index cff9a112f..aa6fe7248 100644 --- a/src/llama_stack/providers/utils/scoring/aggregation_utils.py +++ b/src/llama_stack/providers/utils/scoring/aggregation_utils.py @@ -6,8 +6,7 @@ import statistics from typing import Any -from llama_stack.apis.scoring import ScoringResultRow -from llama_stack.apis.scoring_functions import AggregationFunctionType +from llama_stack_api import AggregationFunctionType, ScoringResultRow def aggregate_accuracy(scoring_results: list[ScoringResultRow]) -> dict[str, Any]: diff --git a/src/llama_stack/providers/utils/scoring/base_scoring_fn.py b/src/llama_stack/providers/utils/scoring/base_scoring_fn.py index 2fae177b7..f372db8b5 100644 --- a/src/llama_stack/providers/utils/scoring/base_scoring_fn.py +++ b/src/llama_stack/providers/utils/scoring/base_scoring_fn.py @@ -6,9 +6,8 @@ from abc import ABC, abstractmethod from typing import Any -from llama_stack.apis.scoring import ScoringFnParams, ScoringResultRow -from llama_stack.apis.scoring_functions import ScoringFn from llama_stack.providers.utils.scoring.aggregation_utils import aggregate_metrics +from llama_stack_api import ScoringFn, ScoringFnParams, ScoringResultRow class BaseScoringFn(ABC): diff --git a/src/llama_stack/providers/utils/sqlstore/api.py b/src/llama_stack/providers/utils/sqlstore/api.py index bcd224234..708fc7095 100644 --- a/src/llama_stack/providers/utils/sqlstore/api.py +++ b/src/llama_stack/providers/utils/sqlstore/api.py @@ -10,7 +10,7 @@ from typing import Any, Literal, Protocol from pydantic import BaseModel -from llama_stack.apis.common.responses import PaginatedResponse +from llama_stack_api import PaginatedResponse class ColumnType(Enum): diff --git a/src/llama_stack/providers/utils/sqlstore/sqlalchemy_sqlstore.py b/src/llama_stack/providers/utils/sqlstore/sqlalchemy_sqlstore.py index cfc3131f4..10009d396 100644 --- a/src/llama_stack/providers/utils/sqlstore/sqlalchemy_sqlstore.py +++ b/src/llama_stack/providers/utils/sqlstore/sqlalchemy_sqlstore.py @@ -26,9 +26,9 @@ from sqlalchemy.ext.asyncio import async_sessionmaker, create_async_engine from sqlalchemy.ext.asyncio.engine import AsyncEngine from sqlalchemy.sql.elements import ColumnElement -from llama_stack.apis.common.responses import PaginatedResponse from llama_stack.core.storage.datatypes import SqlAlchemySqlStoreConfig from llama_stack.log import get_logger +from llama_stack_api import PaginatedResponse from .api import ColumnDefinition, ColumnType, SqlStore diff --git a/src/llama_stack/providers/utils/tools/mcp.py b/src/llama_stack/providers/utils/tools/mcp.py index a271cb959..9c5e9cd96 100644 --- a/src/llama_stack/providers/utils/tools/mcp.py +++ b/src/llama_stack/providers/utils/tools/mcp.py @@ -15,18 +15,55 @@ from mcp import types as mcp_types from mcp.client.sse import sse_client from mcp.client.streamable_http import streamablehttp_client -from llama_stack.apis.common.content_types import ImageContentItem, InterleavedContentItem, TextContentItem, _URLOrData -from llama_stack.apis.tools import ( - ListToolDefsResponse, - ToolDef, - ToolInvocationResult, -) from llama_stack.core.datatypes import AuthenticationRequiredError from llama_stack.log import get_logger from llama_stack.providers.utils.tools.ttl_dict import TTLDict +from llama_stack_api import ( + ImageContentItem, + InterleavedContentItem, + ListToolDefsResponse, + TextContentItem, + ToolDef, + ToolInvocationResult, + _URLOrData, +) logger = get_logger(__name__, category="tools") + +def prepare_mcp_headers(base_headers: dict[str, str] | None, authorization: str | None) -> dict[str, str]: + """ + Prepare headers for MCP requests with authorization support. + + Args: + base_headers: Base headers dictionary (can be None) + authorization: OAuth access token (without "Bearer " prefix) + + Returns: + Headers dictionary with Authorization header if token provided + + Raises: + ValueError: If Authorization header is specified in the headers dict (security risk) + """ + headers = dict(base_headers or {}) + + # Security check: reject any Authorization header in the headers dict + # Users must use the authorization parameter instead to avoid security risks + existing_keys_lower = {k.lower() for k in headers.keys()} + if "authorization" in existing_keys_lower: + raise ValueError( + "For security reasons, Authorization header cannot be passed via 'headers'. " + "Please use the 'authorization' parameter instead." + ) + + # Add Authorization header if token provided + if authorization: + # OAuth access token - add "Bearer " prefix + headers["Authorization"] = f"Bearer {authorization}" + + return headers + + protocol_cache = TTLDict(ttl_seconds=3600) @@ -109,9 +146,29 @@ async def client_wrapper(endpoint: str, headers: dict[str, str]) -> AsyncGenerat raise -async def list_mcp_tools(endpoint: str, headers: dict[str, str]) -> ListToolDefsResponse: +async def list_mcp_tools( + endpoint: str, + headers: dict[str, str] | None = None, + authorization: str | None = None, +) -> ListToolDefsResponse: + """List tools available from an MCP server. + + Args: + endpoint: MCP server endpoint URL + headers: Optional base headers to include + authorization: Optional OAuth access token (just the token, not "Bearer ") + + Returns: + List of tool definitions from the MCP server + + Raises: + ValueError: If Authorization is found in the headers parameter + """ + # Prepare headers with authorization handling + final_headers = prepare_mcp_headers(headers, authorization) + tools = [] - async with client_wrapper(endpoint, headers) as session: + async with client_wrapper(endpoint, final_headers) as session: tools_result = await session.list_tools() for tool in tools_result.tools: tools.append( @@ -129,9 +186,31 @@ async def list_mcp_tools(endpoint: str, headers: dict[str, str]) -> ListToolDefs async def invoke_mcp_tool( - endpoint: str, headers: dict[str, str], tool_name: str, kwargs: dict[str, Any] + endpoint: str, + tool_name: str, + kwargs: dict[str, Any], + headers: dict[str, str] | None = None, + authorization: str | None = None, ) -> ToolInvocationResult: - async with client_wrapper(endpoint, headers) as session: + """Invoke an MCP tool with the given arguments. + + Args: + endpoint: MCP server endpoint URL + tool_name: Name of the tool to invoke + kwargs: Tool invocation arguments + headers: Optional base headers to include + authorization: Optional OAuth access token (just the token, not "Bearer ") + + Returns: + Tool invocation result with content and error information + + Raises: + ValueError: If Authorization header is found in the headers parameter + """ + # Prepare headers with authorization handling + final_headers = prepare_mcp_headers(headers, authorization) + + async with client_wrapper(endpoint, final_headers) as session: result = await session.call_tool(tool_name, kwargs) content: list[InterleavedContentItem] = [] diff --git a/src/llama_stack/testing/api_recorder.py b/src/llama_stack/testing/api_recorder.py index f46f07458..a7ad582f3 100644 --- a/src/llama_stack/testing/api_recorder.py +++ b/src/llama_stack/testing/api_recorder.py @@ -609,14 +609,14 @@ def _combine_model_list_responses(endpoint: str, records: list[dict[str, Any]]) async def _patched_tool_invoke_method( - original_method, provider_name: str, self, tool_name: str, kwargs: dict[str, Any] + original_method, provider_name: str, self, tool_name: str, kwargs: dict[str, Any], authorization: str | None = None ): """Patched version of tool runtime invoke_tool method for recording/replay.""" global _current_mode, _current_storage if _current_mode == APIRecordingMode.LIVE or _current_storage is None: # Normal operation - return await original_method(self, tool_name, kwargs) + return await original_method(self, tool_name, kwargs, authorization=authorization) request_hash = normalize_tool_request(provider_name, tool_name, kwargs) @@ -634,7 +634,7 @@ async def _patched_tool_invoke_method( if _current_mode in (APIRecordingMode.RECORD, APIRecordingMode.RECORD_IF_MISSING): # Make the tool call and record it - result = await original_method(self, tool_name, kwargs) + result = await original_method(self, tool_name, kwargs, authorization=authorization) request_data = { "test_id": get_test_context(), @@ -885,9 +885,11 @@ def patch_inference_clients(): OllamaAsyncClient.list = patched_ollama_list # Create patched methods for tool runtimes - async def patched_tavily_invoke_tool(self, tool_name: str, kwargs: dict[str, Any]): + async def patched_tavily_invoke_tool( + self, tool_name: str, kwargs: dict[str, Any], authorization: str | None = None + ): return await _patched_tool_invoke_method( - _original_methods["tavily_invoke_tool"], "tavily", self, tool_name, kwargs + _original_methods["tavily_invoke_tool"], "tavily", self, tool_name, kwargs, authorization=authorization ) # Apply tool runtime patches diff --git a/src/llama_stack_api/README.md b/src/llama_stack_api/README.md new file mode 100644 index 000000000..9bf1d2726 --- /dev/null +++ b/src/llama_stack_api/README.md @@ -0,0 +1,103 @@ +# llama-stack-api + +API and Provider specifications for Llama Stack - a lightweight package with protocol definitions and provider specs. + +## Overview + +`llama-stack-api` is a minimal dependency package that contains: + +- **API Protocol Definitions**: Type-safe protocol definitions for all Llama Stack APIs (inference, agents, safety, etc.) +- **Provider Specifications**: Provider spec definitions for building custom providers +- **Data Types**: Shared data types and models used across the Llama Stack ecosystem +- **Type Utilities**: Strong typing utilities and schema validation + +## What This Package Does NOT Include + +- Server implementation (see `llama-stack` package) +- Provider implementations (see `llama-stack` package) +- CLI tools (see `llama-stack` package) +- Runtime orchestration (see `llama-stack` package) + +## Use Cases + +This package is designed for: + +1. **Third-party Provider Developers**: Build custom providers without depending on the full Llama Stack server +2. **Client Library Authors**: Use type definitions without server dependencies +3. **Documentation Generation**: Generate API docs from protocol definitions +4. **Type Checking**: Validate implementations against the official specs + +## Installation + +```bash +pip install llama-stack-api +``` + +Or with uv: + +```bash +uv pip install llama-stack-api +``` + +## Dependencies + +Minimal dependencies: +- `pydantic>=2.11.9` - For data validation and serialization +- `jsonschema` - For JSON schema utilities + +## Versioning + +This package follows semantic versioning independently from the main `llama-stack` package: + +- **Patch versions** (0.1.x): Documentation, internal improvements +- **Minor versions** (0.x.0): New APIs, backward-compatible changes +- **Major versions** (x.0.0): Breaking changes to existing APIs + +Current version: **0.4.0.dev0** + +## Usage Example + +```python +from llama_stack_api.inference import Inference, ChatCompletionRequest +from llama_stack_api.providers.datatypes import ProviderSpec, InlineProviderSpec +from llama_stack_api.datatypes import Api + + +# Use protocol definitions for type checking +class MyInferenceProvider(Inference): + async def chat_completion(self, request: ChatCompletionRequest): + # Your implementation + pass + + +# Define provider specifications +my_provider_spec = InlineProviderSpec( + api=Api.inference, + provider_type="inline::my-provider", + pip_packages=["my-dependencies"], + module="my_package.providers.inference", + config_class="my_package.providers.inference.MyConfig", +) +``` + +## Relationship to llama-stack + +The main `llama-stack` package depends on `llama-stack-api` and provides: +- Full server implementation +- Built-in provider implementations +- CLI tools for running and managing stacks +- Runtime provider resolution and orchestration + +## Contributing + +See the main [Llama Stack repository](https://github.com/llamastack/llama-stack) for contribution guidelines. + +## License + +MIT License - see LICENSE file for details. + +## Links + +- [Main Llama Stack Repository](https://github.com/llamastack/llama-stack) +- [Documentation](https://llamastack.ai/) +- [Client Library](https://pypi.org/project/llama-stack-client/) diff --git a/src/llama_stack_api/__init__.py b/src/llama_stack_api/__init__.py new file mode 100644 index 000000000..19b29301b --- /dev/null +++ b/src/llama_stack_api/__init__.py @@ -0,0 +1,871 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the terms described in the LICENSE file in +# the root directory of this source tree. + +""" +Llama Stack API Specifications + +This package contains the API definitions, data types, and protocol specifications +for Llama Stack. It is designed to be a lightweight dependency for external providers +and clients that need to interact with Llama Stack APIs without requiring the full +server implementation. + +All imports from this package MUST use the form: + from llama_stack_api import + +Sub-module imports (e.g., from llama_stack_api.agents import Agents) are NOT supported +and considered a code smell. All exported symbols are explicitly listed in __all__. +""" + +__version__ = "0.4.0.dev0" + +# Import submodules for those who need them +from . import common, strong_typing # noqa: F401 + +# Import all public API symbols +from .agents import Agents, ResponseGuardrail, ResponseGuardrailSpec +from .batches import Batches, BatchObject, ListBatchesResponse +from .benchmarks import ( + Benchmark, + BenchmarkInput, + Benchmarks, + CommonBenchmarkFields, + ListBenchmarksResponse, +) + +# Import commonly used types from common submodule +from .common.content_types import ( + URL, + ImageContentItem, + InterleavedContent, + InterleavedContentItem, + TextContentItem, + _URLOrData, +) +from .common.errors import ( + ConflictError, + DatasetNotFoundError, + InvalidConversationIdError, + ModelNotFoundError, + ModelTypeError, + ResourceNotFoundError, + TokenValidationError, + ToolGroupNotFoundError, + UnsupportedModelError, + VectorStoreNotFoundError, +) +from .common.job_types import Job, JobStatus +from .common.responses import Order, PaginatedResponse +from .common.training_types import Checkpoint, PostTrainingMetric +from .common.type_system import ( + ChatCompletionInputType, + CompletionInputType, + NumberType, + ParamType, + StringType, +) +from .conversations import ( + Conversation, + ConversationDeletedResource, + ConversationItem, + ConversationItemCreateRequest, + ConversationItemDeletedResource, + ConversationItemInclude, + ConversationItemList, + ConversationMessage, + Conversations, + Metadata, +) +from .datasetio import DatasetIO, DatasetStore +from .datasets import ( + CommonDatasetFields, + Dataset, + DatasetInput, + DatasetPurpose, + Datasets, + DatasetType, + DataSource, + ListDatasetsResponse, + RowsDataSource, + URIDataSource, +) +from .datatypes import ( + Api, + BenchmarksProtocolPrivate, + DatasetsProtocolPrivate, + DynamicApiMeta, + Error, + ExternalApiSpec, + HealthResponse, + HealthStatus, + InlineProviderSpec, + ModelsProtocolPrivate, + ProviderSpec, + RemoteProviderConfig, + RemoteProviderSpec, + RoutingTable, + ScoringFunctionsProtocolPrivate, + ShieldsProtocolPrivate, + ToolGroupsProtocolPrivate, + VectorStoresProtocolPrivate, +) +from .eval import BenchmarkConfig, Eval, EvalCandidate, EvaluateResponse, ModelCandidate +from .files import ( + ExpiresAfter, + Files, + ListOpenAIFileResponse, + OpenAIFileDeleteResponse, + OpenAIFileObject, + OpenAIFilePurpose, +) +from .inference import ( + Bf16QuantizationConfig, + ChatCompletionResponseEventType, + CompletionRequest, + EmbeddingsResponse, + EmbeddingTaskType, + Fp8QuantizationConfig, + GrammarResponseFormat, + GreedySamplingStrategy, + Inference, + InferenceProvider, + Int4QuantizationConfig, + JsonSchemaResponseFormat, + ListOpenAIChatCompletionResponse, + LogProbConfig, + ModelStore, + OpenAIAssistantMessageParam, + OpenAIChatCompletion, + OpenAIChatCompletionChunk, + OpenAIChatCompletionContentPartImageParam, + OpenAIChatCompletionContentPartParam, + OpenAIChatCompletionContentPartTextParam, + OpenAIChatCompletionMessageContent, + OpenAIChatCompletionRequestWithExtraBody, + OpenAIChatCompletionTextOnlyMessageContent, + OpenAIChatCompletionToolCall, + OpenAIChatCompletionToolCallFunction, + OpenAIChatCompletionUsage, + OpenAIChatCompletionUsageCompletionTokensDetails, + OpenAIChatCompletionUsagePromptTokensDetails, + OpenAIChoice, + OpenAIChoiceDelta, + OpenAIChoiceLogprobs, + OpenAIChunkChoice, + OpenAICompletion, + OpenAICompletionChoice, + OpenAICompletionLogprobs, + OpenAICompletionRequestWithExtraBody, + OpenAICompletionWithInputMessages, + OpenAIDeveloperMessageParam, + OpenAIEmbeddingData, + OpenAIEmbeddingsRequestWithExtraBody, + OpenAIEmbeddingsResponse, + OpenAIEmbeddingUsage, + OpenAIFile, + OpenAIFileFile, + OpenAIImageURL, + OpenAIJSONSchema, + OpenAIMessageParam, + OpenAIResponseFormatJSONObject, + OpenAIResponseFormatJSONSchema, + OpenAIResponseFormatParam, + OpenAIResponseFormatText, + OpenAISystemMessageParam, + OpenAITokenLogProb, + OpenAIToolMessageParam, + OpenAITopLogProb, + OpenAIUserMessageParam, + QuantizationConfig, + QuantizationType, + RerankData, + RerankResponse, + ResponseFormat, + ResponseFormatType, + SamplingParams, + SamplingStrategy, + SystemMessage, + SystemMessageBehavior, + TextTruncation, + TokenLogProbs, + ToolChoice, + ToolResponseMessage, + TopKSamplingStrategy, + TopPSamplingStrategy, + UserMessage, +) +from .inspect import ( + ApiFilter, + HealthInfo, + Inspect, + ListRoutesResponse, + RouteInfo, + VersionInfo, +) +from .models import ( + CommonModelFields, + ListModelsResponse, + Model, + ModelInput, + Models, + ModelType, + OpenAIListModelsResponse, + OpenAIModel, +) +from .openai_responses import ( + AllowedToolsFilter, + ApprovalFilter, + ListOpenAIResponseInputItem, + ListOpenAIResponseObject, + MCPListToolsTool, + OpenAIDeleteResponseObject, + OpenAIResponseAnnotationCitation, + OpenAIResponseAnnotationContainerFileCitation, + OpenAIResponseAnnotationFileCitation, + OpenAIResponseAnnotationFilePath, + OpenAIResponseAnnotations, + OpenAIResponseContentPart, + OpenAIResponseContentPartOutputText, + OpenAIResponseContentPartReasoningSummary, + OpenAIResponseContentPartReasoningText, + OpenAIResponseContentPartRefusal, + OpenAIResponseError, + OpenAIResponseInput, + OpenAIResponseInputFunctionToolCallOutput, + OpenAIResponseInputMessageContent, + OpenAIResponseInputMessageContentFile, + OpenAIResponseInputMessageContentImage, + OpenAIResponseInputMessageContentText, + OpenAIResponseInputTool, + OpenAIResponseInputToolFileSearch, + OpenAIResponseInputToolFunction, + OpenAIResponseInputToolMCP, + OpenAIResponseInputToolWebSearch, + OpenAIResponseMCPApprovalRequest, + OpenAIResponseMCPApprovalResponse, + OpenAIResponseMessage, + OpenAIResponseObject, + OpenAIResponseObjectStream, + OpenAIResponseObjectStreamResponseCompleted, + OpenAIResponseObjectStreamResponseContentPartAdded, + OpenAIResponseObjectStreamResponseContentPartDone, + OpenAIResponseObjectStreamResponseCreated, + OpenAIResponseObjectStreamResponseFailed, + OpenAIResponseObjectStreamResponseFileSearchCallCompleted, + OpenAIResponseObjectStreamResponseFileSearchCallInProgress, + OpenAIResponseObjectStreamResponseFileSearchCallSearching, + OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta, + OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone, + OpenAIResponseObjectStreamResponseIncomplete, + OpenAIResponseObjectStreamResponseInProgress, + OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta, + OpenAIResponseObjectStreamResponseMcpCallArgumentsDone, + OpenAIResponseObjectStreamResponseMcpCallCompleted, + OpenAIResponseObjectStreamResponseMcpCallFailed, + OpenAIResponseObjectStreamResponseMcpCallInProgress, + OpenAIResponseObjectStreamResponseMcpListToolsCompleted, + OpenAIResponseObjectStreamResponseMcpListToolsFailed, + OpenAIResponseObjectStreamResponseMcpListToolsInProgress, + OpenAIResponseObjectStreamResponseOutputItemAdded, + OpenAIResponseObjectStreamResponseOutputItemDone, + OpenAIResponseObjectStreamResponseOutputTextAnnotationAdded, + OpenAIResponseObjectStreamResponseOutputTextDelta, + OpenAIResponseObjectStreamResponseOutputTextDone, + OpenAIResponseObjectStreamResponseReasoningSummaryPartAdded, + OpenAIResponseObjectStreamResponseReasoningSummaryPartDone, + OpenAIResponseObjectStreamResponseReasoningSummaryTextDelta, + OpenAIResponseObjectStreamResponseReasoningSummaryTextDone, + OpenAIResponseObjectStreamResponseReasoningTextDelta, + OpenAIResponseObjectStreamResponseReasoningTextDone, + OpenAIResponseObjectStreamResponseRefusalDelta, + OpenAIResponseObjectStreamResponseRefusalDone, + OpenAIResponseObjectStreamResponseWebSearchCallCompleted, + OpenAIResponseObjectStreamResponseWebSearchCallInProgress, + OpenAIResponseObjectStreamResponseWebSearchCallSearching, + OpenAIResponseObjectWithInput, + OpenAIResponseOutput, + OpenAIResponseOutputMessageContent, + OpenAIResponseOutputMessageContentOutputText, + OpenAIResponseOutputMessageFileSearchToolCall, + OpenAIResponseOutputMessageFileSearchToolCallResults, + OpenAIResponseOutputMessageFunctionToolCall, + OpenAIResponseOutputMessageMCPCall, + OpenAIResponseOutputMessageMCPListTools, + OpenAIResponseOutputMessageWebSearchToolCall, + OpenAIResponsePrompt, + OpenAIResponseText, + OpenAIResponseTextFormat, + OpenAIResponseTool, + OpenAIResponseToolMCP, + OpenAIResponseUsage, + OpenAIResponseUsageInputTokensDetails, + OpenAIResponseUsageOutputTokensDetails, + WebSearchToolTypes, +) +from .post_training import ( + AlgorithmConfig, + DataConfig, + DatasetFormat, + DPOAlignmentConfig, + DPOLossType, + EfficiencyConfig, + ListPostTrainingJobsResponse, + LoraFinetuningConfig, + OptimizerConfig, + OptimizerType, + PostTraining, + PostTrainingJob, + PostTrainingJobArtifactsResponse, + PostTrainingJobLogStream, + PostTrainingJobStatusResponse, + PostTrainingRLHFRequest, + QATFinetuningConfig, + RLHFAlgorithm, + TrainingConfig, +) +from .prompts import ListPromptsResponse, Prompt, Prompts +from .providers import ListProvidersResponse, ProviderInfo, Providers +from .rag_tool import ( + DefaultRAGQueryGeneratorConfig, + LLMRAGQueryGeneratorConfig, + RAGDocument, + RAGQueryConfig, + RAGQueryGenerator, + RAGQueryGeneratorConfig, + RAGQueryResult, + RAGSearchMode, + Ranker, + RRFRanker, + WeightedRanker, +) +from .resource import Resource, ResourceType +from .safety import ( + ModerationObject, + ModerationObjectResults, + RunShieldResponse, + Safety, + SafetyViolation, + ShieldStore, + ViolationLevel, +) +from .schema_utils import ( + CallableT, + ExtraBodyField, + WebMethod, + json_schema_type, + register_schema, + webmethod, +) +from .scoring import ( + ScoreBatchResponse, + ScoreResponse, + Scoring, + ScoringFunctionStore, + ScoringResult, + ScoringResultRow, +) +from .scoring_functions import ( + AggregationFunctionType, + BasicScoringFnParams, + CommonScoringFnFields, + ListScoringFunctionsResponse, + LLMAsJudgeScoringFnParams, + RegexParserScoringFnParams, + ScoringFn, + ScoringFnInput, + ScoringFnParams, + ScoringFnParamsType, + ScoringFunctions, +) +from .shields import ( + CommonShieldFields, + ListShieldsResponse, + Shield, + ShieldInput, + Shields, +) + +# Import from strong_typing +from .strong_typing.core import JsonType +from .strong_typing.docstring import Docstring, parse_type +from .strong_typing.inspection import ( + get_signature, + is_generic_list, + is_type_optional, + is_type_union, + is_unwrapped_body_param, + unwrap_generic_list, + unwrap_optional_type, + unwrap_union_types, +) +from .strong_typing.name import python_type_to_name +from .strong_typing.schema import ( + JsonSchemaGenerator, + Schema, + SchemaOptions, + StrictJsonType, + get_schema_identifier, +) +from .strong_typing.serialization import json_dump_string, object_to_json +from .tools import ( + ListToolDefsResponse, + ListToolGroupsResponse, + SpecialToolGroup, + ToolDef, + ToolGroup, + ToolGroupInput, + ToolGroups, + ToolInvocationResult, + ToolRuntime, + ToolStore, +) +from .vector_io import ( + Chunk, + ChunkMetadata, + OpenAICreateVectorStoreFileBatchRequestWithExtraBody, + OpenAICreateVectorStoreRequestWithExtraBody, + QueryChunksResponse, + SearchRankingOptions, + VectorIO, + VectorStoreChunkingStrategy, + VectorStoreChunkingStrategyAuto, + VectorStoreChunkingStrategyStatic, + VectorStoreChunkingStrategyStaticConfig, + VectorStoreContent, + VectorStoreCreateRequest, + VectorStoreDeleteResponse, + VectorStoreFileBatchObject, + VectorStoreFileContentResponse, + VectorStoreFileCounts, + VectorStoreFileDeleteResponse, + VectorStoreFileLastError, + VectorStoreFileObject, + VectorStoreFilesListInBatchResponse, + VectorStoreFileStatus, + VectorStoreListFilesResponse, + VectorStoreListResponse, + VectorStoreModifyRequest, + VectorStoreObject, + VectorStoreSearchRequest, + VectorStoreSearchResponse, + VectorStoreSearchResponsePage, + VectorStoreTable, +) +from .vector_stores import VectorStore, VectorStoreInput +from .version import ( + LLAMA_STACK_API_V1, + LLAMA_STACK_API_V1ALPHA, + LLAMA_STACK_API_V1BETA, +) + +__all__ = [ + # Submodules + "common", + "strong_typing", + # Version constants + "LLAMA_STACK_API_V1", + "LLAMA_STACK_API_V1ALPHA", + "LLAMA_STACK_API_V1BETA", + # API Symbols + "Agents", + "AggregationFunctionType", + "AlgorithmConfig", + "AllowedToolsFilter", + "Api", + "ApiFilter", + "ApprovalFilter", + "BasicScoringFnParams", + "Batches", + "BatchObject", + "Benchmark", + "BenchmarkConfig", + "BenchmarkInput", + "Benchmarks", + "BenchmarksProtocolPrivate", + "Bf16QuantizationConfig", + "CallableT", + "ChatCompletionInputType", + "ChatCompletionResponseEventType", + "Checkpoint", + "Chunk", + "ChunkMetadata", + "CommonBenchmarkFields", + "ConflictError", + "CommonDatasetFields", + "CommonModelFields", + "CommonScoringFnFields", + "CommonShieldFields", + "CompletionInputType", + "CompletionRequest", + "Conversation", + "ConversationDeletedResource", + "ConversationItem", + "ConversationItemCreateRequest", + "ConversationItemDeletedResource", + "ConversationItemInclude", + "ConversationItemList", + "ConversationMessage", + "Conversations", + "DPOAlignmentConfig", + "DPOLossType", + "DataConfig", + "DataSource", + "Dataset", + "DatasetFormat", + "DatasetIO", + "DatasetInput", + "DatasetPurpose", + "DatasetNotFoundError", + "DatasetStore", + "DatasetType", + "Datasets", + "DatasetsProtocolPrivate", + "DefaultRAGQueryGeneratorConfig", + "Docstring", + "DynamicApiMeta", + "EfficiencyConfig", + "EmbeddingTaskType", + "EmbeddingsResponse", + "Error", + "Eval", + "EvalCandidate", + "EvaluateResponse", + "ExpiresAfter", + "ExternalApiSpec", + "ExtraBodyField", + "Files", + "Fp8QuantizationConfig", + "get_schema_identifier", + "get_signature", + "GrammarResponseFormat", + "GreedySamplingStrategy", + "HealthInfo", + "HealthResponse", + "HealthStatus", + "ImageContentItem", + "Inference", + "InferenceProvider", + "InlineProviderSpec", + "Inspect", + "Int4QuantizationConfig", + "InterleavedContent", + "InterleavedContentItem", + "InvalidConversationIdError", + "is_generic_list", + "is_type_optional", + "is_type_union", + "is_unwrapped_body_param", + "Job", + "JobStatus", + "json_dump_string", + "json_schema_type", + "JsonSchemaGenerator", + "JsonSchemaResponseFormat", + "JsonType", + "LLMAsJudgeScoringFnParams", + "LLMRAGQueryGeneratorConfig", + "ListBatchesResponse", + "ListBenchmarksResponse", + "ListDatasetsResponse", + "ListModelsResponse", + "ListOpenAIChatCompletionResponse", + "ListOpenAIFileResponse", + "ListOpenAIResponseInputItem", + "ListOpenAIResponseObject", + "ListPostTrainingJobsResponse", + "ListPromptsResponse", + "ListProvidersResponse", + "ListRoutesResponse", + "ListScoringFunctionsResponse", + "ListShieldsResponse", + "ListToolDefsResponse", + "ListToolGroupsResponse", + "LogProbConfig", + "LoraFinetuningConfig", + "MCPListToolsTool", + "Metadata", + "Model", + "ModelCandidate", + "ModelInput", + "ModelNotFoundError", + "ModelStore", + "ModelType", + "ModelTypeError", + "Models", + "ModelsProtocolPrivate", + "ModerationObject", + "ModerationObjectResults", + "NumberType", + "object_to_json", + "OpenAIAssistantMessageParam", + "OpenAIChatCompletion", + "OpenAIChatCompletionChunk", + "OpenAIChatCompletionContentPartImageParam", + "OpenAIChatCompletionContentPartParam", + "OpenAIChatCompletionContentPartTextParam", + "OpenAIChatCompletionMessageContent", + "OpenAIChatCompletionRequestWithExtraBody", + "OpenAIChatCompletionTextOnlyMessageContent", + "OpenAIChatCompletionToolCall", + "OpenAIChatCompletionToolCallFunction", + "OpenAIChatCompletionUsage", + "OpenAIChatCompletionUsageCompletionTokensDetails", + "OpenAIChatCompletionUsagePromptTokensDetails", + "OpenAIChoice", + "OpenAIChoiceDelta", + "OpenAIChoiceLogprobs", + "OpenAIChunkChoice", + "OpenAICompletion", + "OpenAICompletionChoice", + "OpenAICompletionLogprobs", + "OpenAICompletionRequestWithExtraBody", + "OpenAICompletionWithInputMessages", + "OpenAICreateVectorStoreFileBatchRequestWithExtraBody", + "OpenAICreateVectorStoreRequestWithExtraBody", + "OpenAIDeleteResponseObject", + "OpenAIDeveloperMessageParam", + "OpenAIEmbeddingData", + "OpenAIEmbeddingUsage", + "OpenAIEmbeddingsRequestWithExtraBody", + "OpenAIEmbeddingsResponse", + "OpenAIFile", + "OpenAIFileDeleteResponse", + "OpenAIFileFile", + "OpenAIFileObject", + "OpenAIFilePurpose", + "OpenAIImageURL", + "OpenAIJSONSchema", + "OpenAIListModelsResponse", + "OpenAIMessageParam", + "OpenAIModel", + "Order", + "OpenAIResponseAnnotationCitation", + "OpenAIResponseAnnotationContainerFileCitation", + "OpenAIResponseAnnotationFileCitation", + "OpenAIResponseAnnotationFilePath", + "OpenAIResponseAnnotations", + "OpenAIResponseContentPart", + "OpenAIResponseContentPartOutputText", + "OpenAIResponseContentPartReasoningSummary", + "OpenAIResponseContentPartReasoningText", + "OpenAIResponseContentPartRefusal", + "OpenAIResponseError", + "OpenAIResponseFormatJSONObject", + "OpenAIResponseFormatJSONSchema", + "OpenAIResponseFormatParam", + "OpenAIResponseFormatText", + "OpenAIResponseInput", + "OpenAIResponseInputFunctionToolCallOutput", + "OpenAIResponseInputMessageContent", + "OpenAIResponseInputMessageContentFile", + "OpenAIResponseInputMessageContentImage", + "OpenAIResponseInputMessageContentText", + "OpenAIResponseInputTool", + "OpenAIResponseInputToolFileSearch", + "OpenAIResponseInputToolFunction", + "OpenAIResponseInputToolMCP", + "OpenAIResponseInputToolWebSearch", + "OpenAIResponseMCPApprovalRequest", + "OpenAIResponseMCPApprovalResponse", + "OpenAIResponseMessage", + "OpenAIResponseObject", + "OpenAIResponseObjectStream", + "OpenAIResponseObjectStreamResponseCompleted", + "OpenAIResponseObjectStreamResponseContentPartAdded", + "OpenAIResponseObjectStreamResponseContentPartDone", + "OpenAIResponseObjectStreamResponseCreated", + "OpenAIResponseObjectStreamResponseFailed", + "OpenAIResponseObjectStreamResponseFileSearchCallCompleted", + "OpenAIResponseObjectStreamResponseFileSearchCallInProgress", + "OpenAIResponseObjectStreamResponseFileSearchCallSearching", + "OpenAIResponseObjectStreamResponseFunctionCallArgumentsDelta", + "OpenAIResponseObjectStreamResponseFunctionCallArgumentsDone", + "OpenAIResponseObjectStreamResponseInProgress", + "OpenAIResponseObjectStreamResponseIncomplete", + "OpenAIResponseObjectStreamResponseMcpCallArgumentsDelta", + "OpenAIResponseObjectStreamResponseMcpCallArgumentsDone", + "OpenAIResponseObjectStreamResponseMcpCallCompleted", + "OpenAIResponseObjectStreamResponseMcpCallFailed", + "OpenAIResponseObjectStreamResponseMcpCallInProgress", + "OpenAIResponseObjectStreamResponseMcpListToolsCompleted", + "OpenAIResponseObjectStreamResponseMcpListToolsFailed", + "OpenAIResponseObjectStreamResponseMcpListToolsInProgress", + "OpenAIResponseObjectStreamResponseOutputItemAdded", + "OpenAIResponseObjectStreamResponseOutputItemDone", + "OpenAIResponseObjectStreamResponseOutputTextAnnotationAdded", + "OpenAIResponseObjectStreamResponseOutputTextDelta", + "OpenAIResponseObjectStreamResponseOutputTextDone", + "OpenAIResponseObjectStreamResponseReasoningSummaryPartAdded", + "OpenAIResponseObjectStreamResponseReasoningSummaryPartDone", + "OpenAIResponseObjectStreamResponseReasoningSummaryTextDelta", + "OpenAIResponseObjectStreamResponseReasoningSummaryTextDone", + "OpenAIResponseObjectStreamResponseReasoningTextDelta", + "OpenAIResponseObjectStreamResponseReasoningTextDone", + "OpenAIResponseObjectStreamResponseRefusalDelta", + "OpenAIResponseObjectStreamResponseRefusalDone", + "OpenAIResponseObjectStreamResponseWebSearchCallCompleted", + "OpenAIResponseObjectStreamResponseWebSearchCallInProgress", + "OpenAIResponseObjectStreamResponseWebSearchCallSearching", + "OpenAIResponseObjectWithInput", + "OpenAIResponseOutput", + "OpenAIResponseOutputMessageContent", + "OpenAIResponseOutputMessageContentOutputText", + "OpenAIResponseOutputMessageFileSearchToolCall", + "OpenAIResponseOutputMessageFileSearchToolCallResults", + "OpenAIResponseOutputMessageFunctionToolCall", + "OpenAIResponseOutputMessageMCPCall", + "OpenAIResponseOutputMessageMCPListTools", + "OpenAIResponseOutputMessageWebSearchToolCall", + "OpenAIResponsePrompt", + "OpenAIResponseText", + "OpenAIResponseTextFormat", + "OpenAIResponseTool", + "OpenAIResponseToolMCP", + "OpenAIResponseUsage", + "OpenAIResponseUsageInputTokensDetails", + "OpenAIResponseUsageOutputTokensDetails", + "OpenAISystemMessageParam", + "OpenAITokenLogProb", + "OpenAIToolMessageParam", + "OpenAITopLogProb", + "OpenAIUserMessageParam", + "OptimizerConfig", + "OptimizerType", + "PaginatedResponse", + "ParamType", + "parse_type", + "PostTraining", + "PostTrainingMetric", + "PostTrainingJob", + "PostTrainingJobArtifactsResponse", + "PostTrainingJobLogStream", + "PostTrainingJobStatusResponse", + "PostTrainingRLHFRequest", + "Prompt", + "Prompts", + "ProviderInfo", + "ProviderSpec", + "Providers", + "python_type_to_name", + "QATFinetuningConfig", + "QuantizationConfig", + "QuantizationType", + "QueryChunksResponse", + "RAGDocument", + "RAGQueryConfig", + "RAGQueryGenerator", + "RAGQueryGeneratorConfig", + "RAGQueryResult", + "RAGSearchMode", + "register_schema", + "RLHFAlgorithm", + "RRFRanker", + "Ranker", + "RegexParserScoringFnParams", + "RemoteProviderConfig", + "RemoteProviderSpec", + "RerankData", + "RerankResponse", + "Resource", + "ResourceNotFoundError", + "ResourceType", + "ResponseFormat", + "ResponseFormatType", + "ResponseGuardrail", + "ResponseGuardrailSpec", + "RouteInfo", + "RoutingTable", + "RowsDataSource", + "RunShieldResponse", + "Safety", + "SafetyViolation", + "SamplingParams", + "SamplingStrategy", + "ScoreBatchResponse", + "ScoreResponse", + "Scoring", + "ScoringFn", + "ScoringFnInput", + "ScoringFnParams", + "ScoringFnParamsType", + "ScoringFunctionStore", + "ScoringFunctions", + "ScoringFunctionsProtocolPrivate", + "ScoringResult", + "ScoringResultRow", + "Schema", + "SchemaOptions", + "SearchRankingOptions", + "Shield", + "ShieldInput", + "ShieldStore", + "Shields", + "ShieldsProtocolPrivate", + "SpecialToolGroup", + "StrictJsonType", + "StringType", + "SystemMessage", + "SystemMessageBehavior", + "TextContentItem", + "TextTruncation", + "TokenLogProbs", + "TokenValidationError", + "ToolChoice", + "ToolGroupNotFoundError", + "ToolDef", + "ToolGroup", + "ToolGroupInput", + "ToolGroups", + "ToolGroupsProtocolPrivate", + "ToolInvocationResult", + "ToolResponseMessage", + "ToolRuntime", + "ToolStore", + "TopKSamplingStrategy", + "TopPSamplingStrategy", + "TrainingConfig", + "UnsupportedModelError", + "unwrap_generic_list", + "unwrap_optional_type", + "unwrap_union_types", + "URIDataSource", + "URL", + "_URLOrData", + "UserMessage", + "VectorIO", + "VectorStore", + "VectorStoreChunkingStrategy", + "VectorStoreChunkingStrategyAuto", + "VectorStoreChunkingStrategyStatic", + "VectorStoreChunkingStrategyStaticConfig", + "VectorStoreContent", + "VectorStoreCreateRequest", + "VectorStoreDeleteResponse", + "VectorStoreFileBatchObject", + "VectorStoreFileContentResponse", + "VectorStoreFileCounts", + "VectorStoreFileDeleteResponse", + "VectorStoreFileLastError", + "VectorStoreFileObject", + "VectorStoreFileStatus", + "VectorStoreFilesListInBatchResponse", + "VectorStoreInput", + "VectorStoreListFilesResponse", + "VectorStoreListResponse", + "VectorStoreModifyRequest", + "VectorStoreObject", + "VectorStoreSearchRequest", + "VectorStoreSearchResponse", + "VectorStoreSearchResponsePage", + "VectorStoreTable", + "VectorStoreNotFoundError", + "VectorStoresProtocolPrivate", + "VersionInfo", + "ViolationLevel", + "webmethod", + "WebMethod", + "WebSearchToolTypes", + "WeightedRanker", +] diff --git a/src/llama_stack/apis/agents/agents.py b/src/llama_stack_api/agents.py similarity index 96% rename from src/llama_stack/apis/agents/agents.py rename to src/llama_stack_api/agents.py index 09687ef33..ca0611746 100644 --- a/src/llama_stack/apis/agents/agents.py +++ b/src/llama_stack_api/agents.py @@ -9,9 +9,9 @@ from typing import Annotated, Protocol, runtime_checkable from pydantic import BaseModel -from llama_stack.apis.common.responses import Order -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.schema_utils import ExtraBodyField, json_schema_type, webmethod +from llama_stack_api.common.responses import Order +from llama_stack_api.schema_utils import ExtraBodyField, json_schema_type, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1 from .openai_responses import ( ListOpenAIResponseInputItem, diff --git a/src/llama_stack/apis/batches/batches.py b/src/llama_stack_api/batches.py similarity index 96% rename from src/llama_stack/apis/batches/batches.py rename to src/llama_stack_api/batches.py index 1ee9fdb15..00c47d39f 100644 --- a/src/llama_stack/apis/batches/batches.py +++ b/src/llama_stack_api/batches.py @@ -8,8 +8,8 @@ from typing import Literal, Protocol, runtime_checkable from pydantic import BaseModel, Field -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.schema_utils import json_schema_type, webmethod +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1 try: from openai.types import Batch as BatchObject diff --git a/src/llama_stack/apis/benchmarks/benchmarks.py b/src/llama_stack_api/benchmarks.py similarity index 94% rename from src/llama_stack/apis/benchmarks/benchmarks.py rename to src/llama_stack_api/benchmarks.py index 9a67269c3..e9ac3a8b8 100644 --- a/src/llama_stack/apis/benchmarks/benchmarks.py +++ b/src/llama_stack_api/benchmarks.py @@ -7,9 +7,9 @@ from typing import Any, Literal, Protocol, runtime_checkable from pydantic import BaseModel, Field -from llama_stack.apis.resource import Resource, ResourceType -from llama_stack.apis.version import LLAMA_STACK_API_V1ALPHA -from llama_stack.schema_utils import json_schema_type, webmethod +from llama_stack_api.resource import Resource, ResourceType +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1ALPHA class CommonBenchmarkFields(BaseModel): diff --git a/src/llama_stack/apis/__init__.py b/src/llama_stack_api/common/__init__.py similarity index 100% rename from src/llama_stack/apis/__init__.py rename to src/llama_stack_api/common/__init__.py diff --git a/src/llama_stack/apis/common/content_types.py b/src/llama_stack_api/common/content_types.py similarity index 65% rename from src/llama_stack/apis/common/content_types.py rename to src/llama_stack_api/common/content_types.py index 950dd17ff..1bfe109c1 100644 --- a/src/llama_stack/apis/common/content_types.py +++ b/src/llama_stack_api/common/content_types.py @@ -4,13 +4,11 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from enum import Enum from typing import Annotated, Literal from pydantic import BaseModel, Field, model_validator -from llama_stack.models.llama.datatypes import ToolCall -from llama_stack.schema_utils import json_schema_type, register_schema +from llama_stack_api.schema_utils import json_schema_type, register_schema @json_schema_type @@ -101,43 +99,3 @@ class ImageDelta(BaseModel): type: Literal["image"] = "image" image: bytes - - -class ToolCallParseStatus(Enum): - """Status of tool call parsing during streaming. - :cvar started: Tool call parsing has begun - :cvar in_progress: Tool call parsing is ongoing - :cvar failed: Tool call parsing failed - :cvar succeeded: Tool call parsing completed successfully - """ - - started = "started" - in_progress = "in_progress" - failed = "failed" - succeeded = "succeeded" - - -@json_schema_type -class ToolCallDelta(BaseModel): - """A tool call content delta for streaming responses. - - :param type: Discriminator type of the delta. Always "tool_call" - :param tool_call: Either an in-progress tool call string or the final parsed tool call - :param parse_status: Current parsing status of the tool call - """ - - type: Literal["tool_call"] = "tool_call" - - # you either send an in-progress tool call so the client can stream a long - # code generation or you send the final parsed tool call at the end of the - # stream - tool_call: str | ToolCall - parse_status: ToolCallParseStatus - - -# streaming completions send a stream of ContentDeltas -ContentDelta = Annotated[ - TextDelta | ImageDelta | ToolCallDelta, - Field(discriminator="type"), -] -register_schema(ContentDelta, name="ContentDelta") diff --git a/src/llama_stack/apis/common/errors.py b/src/llama_stack_api/common/errors.py similarity index 100% rename from src/llama_stack/apis/common/errors.py rename to src/llama_stack_api/common/errors.py diff --git a/src/llama_stack/apis/common/job_types.py b/src/llama_stack_api/common/job_types.py similarity index 94% rename from src/llama_stack/apis/common/job_types.py rename to src/llama_stack_api/common/job_types.py index 5da42bfd3..b6ef35d7f 100644 --- a/src/llama_stack/apis/common/job_types.py +++ b/src/llama_stack_api/common/job_types.py @@ -7,7 +7,7 @@ from enum import Enum from pydantic import BaseModel -from llama_stack.schema_utils import json_schema_type +from llama_stack_api.schema_utils import json_schema_type class JobStatus(Enum): diff --git a/src/llama_stack/apis/common/responses.py b/src/llama_stack_api/common/responses.py similarity index 97% rename from src/llama_stack/apis/common/responses.py rename to src/llama_stack_api/common/responses.py index 53a290eea..c843ce1d9 100644 --- a/src/llama_stack/apis/common/responses.py +++ b/src/llama_stack_api/common/responses.py @@ -9,7 +9,7 @@ from typing import Any from pydantic import BaseModel -from llama_stack.schema_utils import json_schema_type +from llama_stack_api.schema_utils import json_schema_type class Order(Enum): diff --git a/src/llama_stack/apis/common/tracing.py b/src/llama_stack_api/common/tracing.py similarity index 100% rename from src/llama_stack/apis/common/tracing.py rename to src/llama_stack_api/common/tracing.py diff --git a/src/llama_stack/apis/common/training_types.py b/src/llama_stack_api/common/training_types.py similarity index 96% rename from src/llama_stack/apis/common/training_types.py rename to src/llama_stack_api/common/training_types.py index 5c236a25d..aa3481770 100644 --- a/src/llama_stack/apis/common/training_types.py +++ b/src/llama_stack_api/common/training_types.py @@ -8,7 +8,7 @@ from datetime import datetime from pydantic import BaseModel -from llama_stack.schema_utils import json_schema_type +from llama_stack_api.schema_utils import json_schema_type @json_schema_type diff --git a/src/llama_stack/apis/common/type_system.py b/src/llama_stack_api/common/type_system.py similarity index 97% rename from src/llama_stack/apis/common/type_system.py rename to src/llama_stack_api/common/type_system.py index c71501548..8297713cf 100644 --- a/src/llama_stack/apis/common/type_system.py +++ b/src/llama_stack_api/common/type_system.py @@ -8,7 +8,7 @@ from typing import Annotated, Literal from pydantic import BaseModel, Field -from llama_stack.schema_utils import json_schema_type, register_schema +from llama_stack_api.schema_utils import json_schema_type, register_schema @json_schema_type diff --git a/src/llama_stack/apis/conversations/conversations.py b/src/llama_stack_api/conversations.py similarity index 97% rename from src/llama_stack/apis/conversations/conversations.py rename to src/llama_stack_api/conversations.py index 3fdd3b47e..4854181d1 100644 --- a/src/llama_stack/apis/conversations/conversations.py +++ b/src/llama_stack_api/conversations.py @@ -9,7 +9,8 @@ from typing import Annotated, Literal, Protocol, runtime_checkable from pydantic import BaseModel, Field -from llama_stack.apis.agents.openai_responses import ( +from llama_stack_api.common.tracing import telemetry_traceable +from llama_stack_api.openai_responses import ( OpenAIResponseInputFunctionToolCallOutput, OpenAIResponseMCPApprovalRequest, OpenAIResponseMCPApprovalResponse, @@ -20,9 +21,8 @@ from llama_stack.apis.agents.openai_responses import ( OpenAIResponseOutputMessageMCPListTools, OpenAIResponseOutputMessageWebSearchToolCall, ) -from llama_stack.apis.common.tracing import telemetry_traceable -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.schema_utils import json_schema_type, register_schema, webmethod +from llama_stack_api.schema_utils import json_schema_type, register_schema, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1 Metadata = dict[str, str] diff --git a/src/llama_stack/apis/datasetio/datasetio.py b/src/llama_stack_api/datasetio.py similarity index 89% rename from src/llama_stack/apis/datasetio/datasetio.py rename to src/llama_stack_api/datasetio.py index a0c4a1afc..309a8ff41 100644 --- a/src/llama_stack/apis/datasetio/datasetio.py +++ b/src/llama_stack_api/datasetio.py @@ -6,10 +6,10 @@ from typing import Any, Protocol, runtime_checkable -from llama_stack.apis.common.responses import PaginatedResponse -from llama_stack.apis.datasets import Dataset -from llama_stack.apis.version import LLAMA_STACK_API_V1BETA -from llama_stack.schema_utils import webmethod +from llama_stack_api.common.responses import PaginatedResponse +from llama_stack_api.datasets import Dataset +from llama_stack_api.schema_utils import webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1BETA class DatasetStore(Protocol): diff --git a/src/llama_stack/apis/datasets/datasets.py b/src/llama_stack_api/datasets.py similarity index 97% rename from src/llama_stack/apis/datasets/datasets.py rename to src/llama_stack_api/datasets.py index 9bedc6209..76d787078 100644 --- a/src/llama_stack/apis/datasets/datasets.py +++ b/src/llama_stack_api/datasets.py @@ -9,9 +9,9 @@ from typing import Annotated, Any, Literal, Protocol from pydantic import BaseModel, Field -from llama_stack.apis.resource import Resource, ResourceType -from llama_stack.apis.version import LLAMA_STACK_API_V1BETA -from llama_stack.schema_utils import json_schema_type, register_schema, webmethod +from llama_stack_api.resource import Resource, ResourceType +from llama_stack_api.schema_utils import json_schema_type, register_schema, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1BETA class DatasetPurpose(StrEnum): diff --git a/src/llama_stack/providers/datatypes.py b/src/llama_stack_api/datatypes.py similarity index 51% rename from src/llama_stack/providers/datatypes.py rename to src/llama_stack_api/datatypes.py index 9be3edb8e..f024068f3 100644 --- a/src/llama_stack/providers/datatypes.py +++ b/src/llama_stack_api/datatypes.py @@ -4,21 +4,172 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from enum import StrEnum +from enum import Enum, EnumMeta, StrEnum from typing import Any, Protocol from urllib.parse import urlparse from pydantic import BaseModel, Field -from llama_stack.apis.benchmarks import Benchmark -from llama_stack.apis.datasets import Dataset -from llama_stack.apis.datatypes import Api -from llama_stack.apis.models import Model -from llama_stack.apis.scoring_functions import ScoringFn -from llama_stack.apis.shields import Shield -from llama_stack.apis.tools import ToolGroup -from llama_stack.apis.vector_stores import VectorStore -from llama_stack.schema_utils import json_schema_type +from llama_stack_api.benchmarks import Benchmark +from llama_stack_api.datasets import Dataset +from llama_stack_api.models import Model +from llama_stack_api.schema_utils import json_schema_type +from llama_stack_api.scoring_functions import ScoringFn +from llama_stack_api.shields import Shield +from llama_stack_api.tools import ToolGroup +from llama_stack_api.vector_stores import VectorStore + + +class DynamicApiMeta(EnumMeta): + def __new__(cls, name, bases, namespace): + # Store the original enum values + original_values = {k: v for k, v in namespace.items() if not k.startswith("_")} + + # Create the enum class + cls = super().__new__(cls, name, bases, namespace) + + # Store the original values for reference + cls._original_values = original_values + # Initialize _dynamic_values + cls._dynamic_values = {} + + return cls + + def __call__(cls, value): + try: + return super().__call__(value) + except ValueError as e: + # If this value was already dynamically added, return it + if value in cls._dynamic_values: + return cls._dynamic_values[value] + + # If the value doesn't exist, create a new enum member + # Create a new member name from the value + member_name = value.lower().replace("-", "_") + + # If this member name already exists in the enum, return the existing member + if member_name in cls._member_map_: + return cls._member_map_[member_name] + + # Instead of creating a new member, raise ValueError to force users to use Api.add() to + # register new APIs explicitly + raise ValueError(f"API '{value}' does not exist. Use Api.add() to register new APIs.") from e + + def __iter__(cls): + # Allow iteration over both static and dynamic members + yield from super().__iter__() + if hasattr(cls, "_dynamic_values"): + yield from cls._dynamic_values.values() + + def add(cls, value): + """ + Add a new API to the enum. + Used to register external APIs. + """ + member_name = value.lower().replace("-", "_") + + # If this member name already exists in the enum, return it + if member_name in cls._member_map_: + return cls._member_map_[member_name] + + # Create a new enum member + member = object.__new__(cls) + member._name_ = member_name + member._value_ = value + + # Add it to the enum class + cls._member_map_[member_name] = member + cls._member_names_.append(member_name) + cls._member_type_ = str + + # Store it in our dynamic values + cls._dynamic_values[value] = member + + return member + + +@json_schema_type +class Api(Enum, metaclass=DynamicApiMeta): + """Enumeration of all available APIs in the Llama Stack system. + :cvar providers: Provider management and configuration + :cvar inference: Text generation, chat completions, and embeddings + :cvar safety: Content moderation and safety shields + :cvar agents: Agent orchestration and execution + :cvar batches: Batch processing for asynchronous API requests + :cvar vector_io: Vector database operations and queries + :cvar datasetio: Dataset input/output operations + :cvar scoring: Model output evaluation and scoring + :cvar eval: Model evaluation and benchmarking framework + :cvar post_training: Fine-tuning and model training + :cvar tool_runtime: Tool execution and management + :cvar telemetry: Observability and system monitoring + :cvar models: Model metadata and management + :cvar shields: Safety shield implementations + :cvar datasets: Dataset creation and management + :cvar scoring_functions: Scoring function definitions + :cvar benchmarks: Benchmark suite management + :cvar tool_groups: Tool group organization + :cvar files: File storage and management + :cvar prompts: Prompt versions and management + :cvar inspect: Built-in system inspection and introspection + """ + + providers = "providers" + inference = "inference" + safety = "safety" + agents = "agents" + batches = "batches" + vector_io = "vector_io" + datasetio = "datasetio" + scoring = "scoring" + eval = "eval" + post_training = "post_training" + tool_runtime = "tool_runtime" + + models = "models" + shields = "shields" + vector_stores = "vector_stores" # only used for routing table + datasets = "datasets" + scoring_functions = "scoring_functions" + benchmarks = "benchmarks" + tool_groups = "tool_groups" + files = "files" + prompts = "prompts" + conversations = "conversations" + + # built-in API + inspect = "inspect" + + +@json_schema_type +class Error(BaseModel): + """ + Error response from the API. Roughly follows RFC 7807. + + :param status: HTTP status code + :param title: Error title, a short summary of the error which is invariant for an error type + :param detail: Error detail, a longer human-readable description of the error + :param instance: (Optional) A URL which can be used to retrieve more information about the specific occurrence of the error + """ + + status: int + title: str + detail: str + instance: str | None = None + + +class ExternalApiSpec(BaseModel): + """Specification for an external API implementation.""" + + module: str = Field(..., description="Python module containing the API implementation") + name: str = Field(..., description="Name of the API") + pip_packages: list[str] = Field(default=[], description="List of pip packages to install the API") + protocol: str = Field(..., description="Name of the protocol class for the API") + + +# Provider-related types (merged from providers/datatypes.py) +# NOTE: These imports are forward references to avoid circular dependencies +# They will be resolved at runtime when the classes are used class ModelsProtocolPrivate(Protocol): diff --git a/src/llama_stack/apis/eval/eval.py b/src/llama_stack_api/eval.py similarity index 92% rename from src/llama_stack/apis/eval/eval.py rename to src/llama_stack_api/eval.py index accb04ce1..7a11c221e 100644 --- a/src/llama_stack/apis/eval/eval.py +++ b/src/llama_stack_api/eval.py @@ -8,12 +8,12 @@ from typing import Any, Literal, Protocol from pydantic import BaseModel, Field -from llama_stack.apis.common.job_types import Job -from llama_stack.apis.inference import SamplingParams, SystemMessage -from llama_stack.apis.scoring import ScoringResult -from llama_stack.apis.scoring_functions import ScoringFnParams -from llama_stack.apis.version import LLAMA_STACK_API_V1ALPHA -from llama_stack.schema_utils import json_schema_type, webmethod +from llama_stack_api.common.job_types import Job +from llama_stack_api.inference import SamplingParams, SystemMessage +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.scoring import ScoringResult +from llama_stack_api.scoring_functions import ScoringFnParams +from llama_stack_api.version import LLAMA_STACK_API_V1ALPHA @json_schema_type diff --git a/src/llama_stack/apis/files/files.py b/src/llama_stack_api/files.py similarity index 96% rename from src/llama_stack/apis/files/files.py rename to src/llama_stack_api/files.py index f0ea2f892..8a75a1c39 100644 --- a/src/llama_stack/apis/files/files.py +++ b/src/llama_stack_api/files.py @@ -10,10 +10,10 @@ from typing import Annotated, ClassVar, Literal, Protocol, runtime_checkable from fastapi import File, Form, Response, UploadFile from pydantic import BaseModel, Field -from llama_stack.apis.common.responses import Order -from llama_stack.apis.common.tracing import telemetry_traceable -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.schema_utils import json_schema_type, webmethod +from llama_stack_api.common.responses import Order +from llama_stack_api.common.tracing import telemetry_traceable +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1 # OpenAI Files API Models diff --git a/src/llama_stack/apis/inference/inference.py b/src/llama_stack_api/inference.py similarity index 99% rename from src/llama_stack/apis/inference/inference.py rename to src/llama_stack_api/inference.py index 9f04917c9..b42de95be 100644 --- a/src/llama_stack/apis/inference/inference.py +++ b/src/llama_stack_api/inference.py @@ -18,14 +18,14 @@ from fastapi import Body from pydantic import BaseModel, Field from typing_extensions import TypedDict -from llama_stack.apis.common.content_types import InterleavedContent -from llama_stack.apis.common.responses import ( +from llama_stack_api.common.content_types import InterleavedContent +from llama_stack_api.common.responses import ( Order, ) -from llama_stack.apis.common.tracing import telemetry_traceable -from llama_stack.apis.models import Model -from llama_stack.apis.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA -from llama_stack.schema_utils import json_schema_type, register_schema, webmethod +from llama_stack_api.common.tracing import telemetry_traceable +from llama_stack_api.models import Model +from llama_stack_api.schema_utils import json_schema_type, register_schema, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1, LLAMA_STACK_API_V1ALPHA @json_schema_type diff --git a/src/llama_stack/apis/inspect/inspect.py b/src/llama_stack_api/inspect.py similarity index 94% rename from src/llama_stack/apis/inspect/inspect.py rename to src/llama_stack_api/inspect.py index 235abb124..8326e9e6b 100644 --- a/src/llama_stack/apis/inspect/inspect.py +++ b/src/llama_stack_api/inspect.py @@ -8,11 +8,11 @@ from typing import Literal, Protocol, runtime_checkable from pydantic import BaseModel -from llama_stack.apis.version import ( +from llama_stack_api.datatypes import HealthStatus +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.version import ( LLAMA_STACK_API_V1, ) -from llama_stack.providers.datatypes import HealthStatus -from llama_stack.schema_utils import json_schema_type, webmethod # Valid values for the route filter parameter. # Actual API levels: v1, v1alpha, v1beta (filters by level, excludes deprecated) diff --git a/src/llama_stack/apis/models/models.py b/src/llama_stack_api/models.py similarity index 95% rename from src/llama_stack/apis/models/models.py rename to src/llama_stack_api/models.py index bbb359b51..833864ec2 100644 --- a/src/llama_stack/apis/models/models.py +++ b/src/llama_stack_api/models.py @@ -9,10 +9,10 @@ from typing import Any, Literal, Protocol, runtime_checkable from pydantic import BaseModel, ConfigDict, Field, field_validator -from llama_stack.apis.common.tracing import telemetry_traceable -from llama_stack.apis.resource import Resource, ResourceType -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.schema_utils import json_schema_type, webmethod +from llama_stack_api.common.tracing import telemetry_traceable +from llama_stack_api.resource import Resource, ResourceType +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1 class CommonModelFields(BaseModel): diff --git a/src/llama_stack/apis/agents/openai_responses.py b/src/llama_stack_api/openai_responses.py similarity index 99% rename from src/llama_stack/apis/agents/openai_responses.py rename to src/llama_stack_api/openai_responses.py index 16657ab32..2dd73e90a 100644 --- a/src/llama_stack/apis/agents/openai_responses.py +++ b/src/llama_stack_api/openai_responses.py @@ -10,8 +10,8 @@ from typing import Annotated, Any, Literal from pydantic import BaseModel, Field, model_validator from typing_extensions import TypedDict -from llama_stack.apis.vector_io import SearchRankingOptions as FileSearchRankingOptions -from llama_stack.schema_utils import json_schema_type, register_schema +from llama_stack_api.schema_utils import json_schema_type, register_schema +from llama_stack_api.vector_io import SearchRankingOptions as FileSearchRankingOptions # NOTE(ashwin): this file is literally a copy of the OpenAI responses API schema. We should probably # take their YAML and generate this file automatically. Their YAML is available. @@ -490,6 +490,7 @@ class OpenAIResponseInputToolMCP(BaseModel): :param server_label: Label to identify this MCP server :param server_url: URL endpoint of the MCP server :param headers: (Optional) HTTP headers to include when connecting to the server + :param authorization: (Optional) OAuth access token for authenticating with the MCP server :param require_approval: Approval requirement for tool calls ("always", "never", or filter) :param allowed_tools: (Optional) Restriction on which tools can be used from this server """ @@ -498,6 +499,7 @@ class OpenAIResponseInputToolMCP(BaseModel): server_label: str server_url: str headers: dict[str, Any] | None = None + authorization: str | None = Field(default=None, exclude=True) require_approval: Literal["always"] | Literal["never"] | ApprovalFilter = "never" allowed_tools: list[str] | AllowedToolsFilter | None = None diff --git a/src/llama_stack/apis/post_training/post_training.py b/src/llama_stack_api/post_training.py similarity index 97% rename from src/llama_stack/apis/post_training/post_training.py rename to src/llama_stack_api/post_training.py index 2b7a6222f..0cc9277d9 100644 --- a/src/llama_stack/apis/post_training/post_training.py +++ b/src/llama_stack_api/post_training.py @@ -10,11 +10,11 @@ from typing import Annotated, Any, Literal, Protocol from pydantic import BaseModel, Field -from llama_stack.apis.common.content_types import URL -from llama_stack.apis.common.job_types import JobStatus -from llama_stack.apis.common.training_types import Checkpoint -from llama_stack.apis.version import LLAMA_STACK_API_V1ALPHA -from llama_stack.schema_utils import json_schema_type, register_schema, webmethod +from llama_stack_api.common.content_types import URL +from llama_stack_api.common.job_types import JobStatus +from llama_stack_api.common.training_types import Checkpoint +from llama_stack_api.schema_utils import json_schema_type, register_schema, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1ALPHA @json_schema_type diff --git a/src/llama_stack/apis/prompts/prompts.py b/src/llama_stack_api/prompts.py similarity index 97% rename from src/llama_stack/apis/prompts/prompts.py rename to src/llama_stack_api/prompts.py index 406ae529c..651d03e61 100644 --- a/src/llama_stack/apis/prompts/prompts.py +++ b/src/llama_stack_api/prompts.py @@ -10,9 +10,9 @@ from typing import Protocol, runtime_checkable from pydantic import BaseModel, Field, field_validator, model_validator -from llama_stack.apis.common.tracing import telemetry_traceable -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.schema_utils import json_schema_type, webmethod +from llama_stack_api.common.tracing import telemetry_traceable +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1 @json_schema_type diff --git a/src/llama_stack/apis/providers/providers.py b/src/llama_stack_api/providers.py similarity index 91% rename from src/llama_stack/apis/providers/providers.py rename to src/llama_stack_api/providers.py index e1872571d..5b555b82f 100644 --- a/src/llama_stack/apis/providers/providers.py +++ b/src/llama_stack_api/providers.py @@ -8,9 +8,9 @@ from typing import Any, Protocol, runtime_checkable from pydantic import BaseModel -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.providers.datatypes import HealthResponse -from llama_stack.schema_utils import json_schema_type, webmethod +from llama_stack_api.datatypes import HealthResponse +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1 @json_schema_type diff --git a/src/llama_stack/strong_typing/py.typed b/src/llama_stack_api/py.typed similarity index 100% rename from src/llama_stack/strong_typing/py.typed rename to src/llama_stack_api/py.typed diff --git a/src/llama_stack_api/pyproject.toml b/src/llama_stack_api/pyproject.toml new file mode 100644 index 000000000..0ceb2bb4e --- /dev/null +++ b/src/llama_stack_api/pyproject.toml @@ -0,0 +1,82 @@ +[build-system] +requires = ["setuptools>=61.0"] +build-backend = "setuptools.build_meta" + +[tool.uv] +required-version = ">=0.7.0" + +[project] +name = "llama-stack-api" +version = "0.4.0.dev0" +authors = [{ name = "Meta Llama", email = "llama-oss@meta.com" }] +description = "API and Provider specifications for Llama Stack - lightweight package with protocol definitions and provider specs" +readme = "README.md" +requires-python = ">=3.12" +license = { "text" = "MIT" } +classifiers = [ + "License :: OSI Approved :: MIT License", + "Programming Language :: Python :: 3", + "Operating System :: OS Independent", + "Intended Audience :: Developers", + "Intended Audience :: Information Technology", + "Intended Audience :: Science/Research", + "Topic :: Scientific/Engineering :: Artificial Intelligence", + "Topic :: Scientific/Engineering :: Information Analysis", +] +dependencies = [ + "pydantic>=2.11.9", + "jsonschema", + "opentelemetry-sdk>=1.30.0", + "opentelemetry-exporter-otlp-proto-http>=1.30.0", +] + +[project.urls] +Homepage = "https://github.com/llamastack/llama-stack" + +[tool.setuptools.packages.find] +where = ["."] +include = ["llama_stack_api", "llama_stack_api.*"] + +[tool.setuptools.package-data] +llama_stack_api = ["py.typed"] + +[tool.ruff] +line-length = 120 + +[tool.ruff.lint] +select = [ + "UP", # pyupgrade + "B", # flake8-bugbear + "B9", # flake8-bugbear subset + "C", # comprehensions + "E", # pycodestyle + "F", # Pyflakes + "N", # Naming + "W", # Warnings + "DTZ", # datetime rules + "I", # isort (imports order) + "RUF001", # Checks for ambiguous Unicode characters in strings + "RUF002", # Checks for ambiguous Unicode characters in docstrings + "RUF003", # Checks for ambiguous Unicode characters in comments + "PLC2401", # Checks for the use of non-ASCII characters in variable names +] +ignore = [ + # The following ignores are desired by the project maintainers. + "E402", # Module level import not at top of file + "E501", # Line too long + "F405", # Maybe undefined or defined from star import + "C408", # Ignored because we like the dict keyword argument syntax + "N812", # Ignored because import torch.nn.functional as F is PyTorch convention + + # These are the additional ones we started ignoring after moving to ruff. We should look into each one of them later. + "C901", # Complexity of the function is too high +] +unfixable = [ + "PLE2515", +] # Do not fix this automatically since ruff will replace the zero-width space with \u200b - let's do it manually + +[tool.ruff.lint.per-file-ignores] +"llama_stack_api/apis/**/__init__.py" = ["F403"] + +[tool.ruff.lint.pep8-naming] +classmethod-decorators = ["classmethod", "pydantic.field_validator"] diff --git a/src/llama_stack/apis/tools/rag_tool.py b/src/llama_stack_api/rag_tool.py similarity index 98% rename from src/llama_stack/apis/tools/rag_tool.py rename to src/llama_stack_api/rag_tool.py index 8bcc89bf0..b5edd51af 100644 --- a/src/llama_stack/apis/tools/rag_tool.py +++ b/src/llama_stack_api/rag_tool.py @@ -9,7 +9,7 @@ from typing import Annotated, Any, Literal from pydantic import BaseModel, Field, field_validator -from llama_stack.apis.common.content_types import URL, InterleavedContent +from llama_stack_api.common.content_types import URL, InterleavedContent class RRFRanker(BaseModel): diff --git a/src/llama_stack/apis/resource.py b/src/llama_stack_api/resource.py similarity index 100% rename from src/llama_stack/apis/resource.py rename to src/llama_stack_api/resource.py diff --git a/src/llama_stack/apis/safety/safety.py b/src/llama_stack_api/safety.py similarity index 93% rename from src/llama_stack/apis/safety/safety.py rename to src/llama_stack_api/safety.py index 8872cc518..ef84be2ea 100644 --- a/src/llama_stack/apis/safety/safety.py +++ b/src/llama_stack_api/safety.py @@ -9,11 +9,11 @@ from typing import Any, Protocol, runtime_checkable from pydantic import BaseModel, Field -from llama_stack.apis.common.tracing import telemetry_traceable -from llama_stack.apis.inference import OpenAIMessageParam -from llama_stack.apis.shields import Shield -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.schema_utils import json_schema_type, webmethod +from llama_stack_api.common.tracing import telemetry_traceable +from llama_stack_api.inference import OpenAIMessageParam +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.shields import Shield +from llama_stack_api.version import LLAMA_STACK_API_V1 @json_schema_type diff --git a/src/llama_stack/schema_utils.py b/src/llama_stack_api/schema_utils.py similarity index 100% rename from src/llama_stack/schema_utils.py rename to src/llama_stack_api/schema_utils.py diff --git a/src/llama_stack/apis/scoring/scoring.py b/src/llama_stack_api/scoring.py similarity index 93% rename from src/llama_stack/apis/scoring/scoring.py rename to src/llama_stack_api/scoring.py index 03d943e94..47d144d21 100644 --- a/src/llama_stack/apis/scoring/scoring.py +++ b/src/llama_stack_api/scoring.py @@ -8,9 +8,9 @@ from typing import Any, Protocol, runtime_checkable from pydantic import BaseModel -from llama_stack.apis.scoring_functions import ScoringFn, ScoringFnParams -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.schema_utils import json_schema_type, webmethod +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.scoring_functions import ScoringFn, ScoringFnParams +from llama_stack_api.version import LLAMA_STACK_API_V1 # mapping of metric to value ScoringResultRow = dict[str, Any] diff --git a/src/llama_stack/apis/scoring_functions/scoring_functions.py b/src/llama_stack_api/scoring_functions.py similarity index 96% rename from src/llama_stack/apis/scoring_functions/scoring_functions.py rename to src/llama_stack_api/scoring_functions.py index 78f4a7541..f75336e54 100644 --- a/src/llama_stack/apis/scoring_functions/scoring_functions.py +++ b/src/llama_stack_api/scoring_functions.py @@ -16,10 +16,10 @@ from typing import ( from pydantic import BaseModel, Field -from llama_stack.apis.common.type_system import ParamType -from llama_stack.apis.resource import Resource, ResourceType -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.schema_utils import json_schema_type, register_schema, webmethod +from llama_stack_api.common.type_system import ParamType +from llama_stack_api.resource import Resource, ResourceType +from llama_stack_api.schema_utils import json_schema_type, register_schema, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1 # Perhaps more structure can be imposed on these functions. Maybe they could be associated diff --git a/src/llama_stack/apis/shields/shields.py b/src/llama_stack_api/shields.py similarity index 91% rename from src/llama_stack/apis/shields/shields.py rename to src/llama_stack_api/shields.py index 659ba8b75..2aeb83333 100644 --- a/src/llama_stack/apis/shields/shields.py +++ b/src/llama_stack_api/shields.py @@ -8,10 +8,10 @@ from typing import Any, Literal, Protocol, runtime_checkable from pydantic import BaseModel -from llama_stack.apis.common.tracing import telemetry_traceable -from llama_stack.apis.resource import Resource, ResourceType -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.schema_utils import json_schema_type, webmethod +from llama_stack_api.common.tracing import telemetry_traceable +from llama_stack_api.resource import Resource, ResourceType +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1 class CommonShieldFields(BaseModel): diff --git a/src/llama_stack/strong_typing/__init__.py b/src/llama_stack_api/strong_typing/__init__.py similarity index 100% rename from src/llama_stack/strong_typing/__init__.py rename to src/llama_stack_api/strong_typing/__init__.py diff --git a/src/llama_stack/strong_typing/auxiliary.py b/src/llama_stack_api/strong_typing/auxiliary.py similarity index 100% rename from src/llama_stack/strong_typing/auxiliary.py rename to src/llama_stack_api/strong_typing/auxiliary.py diff --git a/src/llama_stack/strong_typing/classdef.py b/src/llama_stack_api/strong_typing/classdef.py similarity index 100% rename from src/llama_stack/strong_typing/classdef.py rename to src/llama_stack_api/strong_typing/classdef.py diff --git a/src/llama_stack/strong_typing/core.py b/src/llama_stack_api/strong_typing/core.py similarity index 100% rename from src/llama_stack/strong_typing/core.py rename to src/llama_stack_api/strong_typing/core.py diff --git a/src/llama_stack/strong_typing/deserializer.py b/src/llama_stack_api/strong_typing/deserializer.py similarity index 100% rename from src/llama_stack/strong_typing/deserializer.py rename to src/llama_stack_api/strong_typing/deserializer.py diff --git a/src/llama_stack/strong_typing/docstring.py b/src/llama_stack_api/strong_typing/docstring.py similarity index 100% rename from src/llama_stack/strong_typing/docstring.py rename to src/llama_stack_api/strong_typing/docstring.py diff --git a/src/llama_stack/strong_typing/exception.py b/src/llama_stack_api/strong_typing/exception.py similarity index 100% rename from src/llama_stack/strong_typing/exception.py rename to src/llama_stack_api/strong_typing/exception.py diff --git a/src/llama_stack/strong_typing/inspection.py b/src/llama_stack_api/strong_typing/inspection.py similarity index 100% rename from src/llama_stack/strong_typing/inspection.py rename to src/llama_stack_api/strong_typing/inspection.py diff --git a/src/llama_stack/strong_typing/mapping.py b/src/llama_stack_api/strong_typing/mapping.py similarity index 100% rename from src/llama_stack/strong_typing/mapping.py rename to src/llama_stack_api/strong_typing/mapping.py diff --git a/src/llama_stack/strong_typing/name.py b/src/llama_stack_api/strong_typing/name.py similarity index 100% rename from src/llama_stack/strong_typing/name.py rename to src/llama_stack_api/strong_typing/name.py diff --git a/src/llama_stack_api/strong_typing/py.typed b/src/llama_stack_api/strong_typing/py.typed new file mode 100644 index 000000000..e69de29bb diff --git a/src/llama_stack/strong_typing/schema.py b/src/llama_stack_api/strong_typing/schema.py similarity index 100% rename from src/llama_stack/strong_typing/schema.py rename to src/llama_stack_api/strong_typing/schema.py diff --git a/src/llama_stack/strong_typing/serialization.py b/src/llama_stack_api/strong_typing/serialization.py similarity index 100% rename from src/llama_stack/strong_typing/serialization.py rename to src/llama_stack_api/strong_typing/serialization.py diff --git a/src/llama_stack/strong_typing/serializer.py b/src/llama_stack_api/strong_typing/serializer.py similarity index 100% rename from src/llama_stack/strong_typing/serializer.py rename to src/llama_stack_api/strong_typing/serializer.py diff --git a/src/llama_stack/strong_typing/slots.py b/src/llama_stack_api/strong_typing/slots.py similarity index 100% rename from src/llama_stack/strong_typing/slots.py rename to src/llama_stack_api/strong_typing/slots.py diff --git a/src/llama_stack/strong_typing/topological.py b/src/llama_stack_api/strong_typing/topological.py similarity index 100% rename from src/llama_stack/strong_typing/topological.py rename to src/llama_stack_api/strong_typing/topological.py diff --git a/src/llama_stack/apis/tools/tools.py b/src/llama_stack_api/tools.py similarity index 88% rename from src/llama_stack/apis/tools/tools.py rename to src/llama_stack_api/tools.py index 4e7cf2544..81c989f88 100644 --- a/src/llama_stack/apis/tools/tools.py +++ b/src/llama_stack_api/tools.py @@ -10,11 +10,11 @@ from typing import Any, Literal, Protocol from pydantic import BaseModel from typing_extensions import runtime_checkable -from llama_stack.apis.common.content_types import URL, InterleavedContent -from llama_stack.apis.common.tracing import telemetry_traceable -from llama_stack.apis.resource import Resource, ResourceType -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.schema_utils import json_schema_type, webmethod +from llama_stack_api.common.content_types import URL, InterleavedContent +from llama_stack_api.common.tracing import telemetry_traceable +from llama_stack_api.resource import Resource, ResourceType +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.version import LLAMA_STACK_API_V1 @json_schema_type @@ -196,22 +196,32 @@ class ToolRuntime(Protocol): # TODO: This needs to be renamed once OPEN API generator name conflict issue is fixed. @webmethod(route="/tool-runtime/list-tools", method="GET", level=LLAMA_STACK_API_V1) async def list_runtime_tools( - self, tool_group_id: str | None = None, mcp_endpoint: URL | None = None + self, + tool_group_id: str | None = None, + mcp_endpoint: URL | None = None, + authorization: str | None = None, ) -> ListToolDefsResponse: """List all tools in the runtime. :param tool_group_id: The ID of the tool group to list tools for. :param mcp_endpoint: The MCP endpoint to use for the tool group. + :param authorization: (Optional) OAuth access token for authenticating with the MCP server. :returns: A ListToolDefsResponse. """ ... @webmethod(route="/tool-runtime/invoke", method="POST", level=LLAMA_STACK_API_V1) - async def invoke_tool(self, tool_name: str, kwargs: dict[str, Any]) -> ToolInvocationResult: + async def invoke_tool( + self, + tool_name: str, + kwargs: dict[str, Any], + authorization: str | None = None, + ) -> ToolInvocationResult: """Run a tool with the given arguments. :param tool_name: The name of the tool to invoke. :param kwargs: A dictionary of arguments to pass to the tool. + :param authorization: (Optional) OAuth access token for authenticating with the MCP server. :returns: A ToolInvocationResult. """ ... diff --git a/src/llama_stack_api/uv.lock b/src/llama_stack_api/uv.lock new file mode 100644 index 000000000..d61eb9be7 --- /dev/null +++ b/src/llama_stack_api/uv.lock @@ -0,0 +1,498 @@ +version = 1 +revision = 3 +requires-python = ">=3.12" + +[[package]] +name = "annotated-types" +version = "0.7.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/ee/67/531ea369ba64dcff5ec9c3402f9f51bf748cec26dde048a2f973a4eea7f5/annotated_types-0.7.0.tar.gz", hash = "sha256:aff07c09a53a08bc8cfccb9c85b05f1aa9a2a6f23728d790723543408344ce89", size = 16081, upload-time = "2024-05-20T21:33:25.928Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/78/b6/6307fbef88d9b5ee7421e68d78a9f162e0da4900bc5f5793f6d3d0e34fb8/annotated_types-0.7.0-py3-none-any.whl", hash = "sha256:1f02e8b43a8fbbc3f3e0d4f0f4bfc8131bcb4eebe8849b8e5c773f3a1c582a53", size = 13643, upload-time = "2024-05-20T21:33:24.1Z" }, +] + +[[package]] +name = "attrs" +version = "25.4.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/6b/5c/685e6633917e101e5dcb62b9dd76946cbb57c26e133bae9e0cd36033c0a9/attrs-25.4.0.tar.gz", hash = "sha256:16d5969b87f0859ef33a48b35d55ac1be6e42ae49d5e853b597db70c35c57e11", size = 934251, upload-time = "2025-10-06T13:54:44.725Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/3a/2a/7cc015f5b9f5db42b7d48157e23356022889fc354a2813c15934b7cb5c0e/attrs-25.4.0-py3-none-any.whl", hash = "sha256:adcf7e2a1fb3b36ac48d97835bb6d8ade15b8dcce26aba8bf1d14847b57a3373", size = 67615, upload-time = "2025-10-06T13:54:43.17Z" }, +] + +[[package]] +name = "certifi" +version = "2025.11.12" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/a2/8c/58f469717fa48465e4a50c014a0400602d3c437d7c0c468e17ada824da3a/certifi-2025.11.12.tar.gz", hash = "sha256:d8ab5478f2ecd78af242878415affce761ca6bc54a22a27e026d7c25357c3316", size = 160538, upload-time = "2025-11-12T02:54:51.517Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/70/7d/9bc192684cea499815ff478dfcdc13835ddf401365057044fb721ec6bddb/certifi-2025.11.12-py3-none-any.whl", hash = "sha256:97de8790030bbd5c2d96b7ec782fc2f7820ef8dba6db909ccf95449f2d062d4b", size = 159438, upload-time = "2025-11-12T02:54:49.735Z" }, +] + +[[package]] +name = "charset-normalizer" +version = "3.4.4" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/13/69/33ddede1939fdd074bce5434295f38fae7136463422fe4fd3e0e89b98062/charset_normalizer-3.4.4.tar.gz", hash = "sha256:94537985111c35f28720e43603b8e7b43a6ecfb2ce1d3058bbe955b73404e21a", size = 129418, upload-time = "2025-10-14T04:42:32.879Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/f3/85/1637cd4af66fa687396e757dec650f28025f2a2f5a5531a3208dc0ec43f2/charset_normalizer-3.4.4-cp312-cp312-macosx_10_13_universal2.whl", hash = "sha256:0a98e6759f854bd25a58a73fa88833fba3b7c491169f86ce1180c948ab3fd394", size = 208425, upload-time = "2025-10-14T04:40:53.353Z" }, + { url = "https://files.pythonhosted.org/packages/9d/6a/04130023fef2a0d9c62d0bae2649b69f7b7d8d24ea5536feef50551029df/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:b5b290ccc2a263e8d185130284f8501e3e36c5e02750fc6b6bdeb2e9e96f1e25", size = 148162, upload-time = "2025-10-14T04:40:54.558Z" }, + { url = "https://files.pythonhosted.org/packages/78/29/62328d79aa60da22c9e0b9a66539feae06ca0f5a4171ac4f7dc285b83688/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:74bb723680f9f7a6234dcf67aea57e708ec1fbdf5699fb91dfd6f511b0a320ef", size = 144558, upload-time = "2025-10-14T04:40:55.677Z" }, + { url = "https://files.pythonhosted.org/packages/86/bb/b32194a4bf15b88403537c2e120b817c61cd4ecffa9b6876e941c3ee38fe/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:f1e34719c6ed0b92f418c7c780480b26b5d9c50349e9a9af7d76bf757530350d", size = 161497, upload-time = "2025-10-14T04:40:57.217Z" }, + { url = "https://files.pythonhosted.org/packages/19/89/a54c82b253d5b9b111dc74aca196ba5ccfcca8242d0fb64146d4d3183ff1/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:2437418e20515acec67d86e12bf70056a33abdacb5cb1655042f6538d6b085a8", size = 159240, upload-time = "2025-10-14T04:40:58.358Z" }, + { url = "https://files.pythonhosted.org/packages/c0/10/d20b513afe03acc89ec33948320a5544d31f21b05368436d580dec4e234d/charset_normalizer-3.4.4-cp312-cp312-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:11d694519d7f29d6cd09f6ac70028dba10f92f6cdd059096db198c283794ac86", size = 153471, upload-time = "2025-10-14T04:40:59.468Z" }, + { url = "https://files.pythonhosted.org/packages/61/fa/fbf177b55bdd727010f9c0a3c49eefa1d10f960e5f09d1d887bf93c2e698/charset_normalizer-3.4.4-cp312-cp312-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:ac1c4a689edcc530fc9d9aa11f5774b9e2f33f9a0c6a57864e90908f5208d30a", size = 150864, upload-time = "2025-10-14T04:41:00.623Z" }, + { url = "https://files.pythonhosted.org/packages/05/12/9fbc6a4d39c0198adeebbde20b619790e9236557ca59fc40e0e3cebe6f40/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:21d142cc6c0ec30d2efee5068ca36c128a30b0f2c53c1c07bd78cb6bc1d3be5f", size = 150647, upload-time = "2025-10-14T04:41:01.754Z" }, + { url = "https://files.pythonhosted.org/packages/ad/1f/6a9a593d52e3e8c5d2b167daf8c6b968808efb57ef4c210acb907c365bc4/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_armv7l.whl", hash = "sha256:5dbe56a36425d26d6cfb40ce79c314a2e4dd6211d51d6d2191c00bed34f354cc", size = 145110, upload-time = "2025-10-14T04:41:03.231Z" }, + { url = "https://files.pythonhosted.org/packages/30/42/9a52c609e72471b0fc54386dc63c3781a387bb4fe61c20231a4ebcd58bdd/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_ppc64le.whl", hash = "sha256:5bfbb1b9acf3334612667b61bd3002196fe2a1eb4dd74d247e0f2a4d50ec9bbf", size = 162839, upload-time = "2025-10-14T04:41:04.715Z" }, + { url = "https://files.pythonhosted.org/packages/c4/5b/c0682bbf9f11597073052628ddd38344a3d673fda35a36773f7d19344b23/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_riscv64.whl", hash = "sha256:d055ec1e26e441f6187acf818b73564e6e6282709e9bcb5b63f5b23068356a15", size = 150667, upload-time = "2025-10-14T04:41:05.827Z" }, + { url = "https://files.pythonhosted.org/packages/e4/24/a41afeab6f990cf2daf6cb8c67419b63b48cf518e4f56022230840c9bfb2/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_s390x.whl", hash = "sha256:af2d8c67d8e573d6de5bc30cdb27e9b95e49115cd9baad5ddbd1a6207aaa82a9", size = 160535, upload-time = "2025-10-14T04:41:06.938Z" }, + { url = "https://files.pythonhosted.org/packages/2a/e5/6a4ce77ed243c4a50a1fecca6aaaab419628c818a49434be428fe24c9957/charset_normalizer-3.4.4-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:780236ac706e66881f3b7f2f32dfe90507a09e67d1d454c762cf642e6e1586e0", size = 154816, upload-time = "2025-10-14T04:41:08.101Z" }, + { url = "https://files.pythonhosted.org/packages/a8/ef/89297262b8092b312d29cdb2517cb1237e51db8ecef2e9af5edbe7b683b1/charset_normalizer-3.4.4-cp312-cp312-win32.whl", hash = "sha256:5833d2c39d8896e4e19b689ffc198f08ea58116bee26dea51e362ecc7cd3ed26", size = 99694, upload-time = "2025-10-14T04:41:09.23Z" }, + { url = "https://files.pythonhosted.org/packages/3d/2d/1e5ed9dd3b3803994c155cd9aacb60c82c331bad84daf75bcb9c91b3295e/charset_normalizer-3.4.4-cp312-cp312-win_amd64.whl", hash = "sha256:a79cfe37875f822425b89a82333404539ae63dbdddf97f84dcbc3d339aae9525", size = 107131, upload-time = "2025-10-14T04:41:10.467Z" }, + { url = "https://files.pythonhosted.org/packages/d0/d9/0ed4c7098a861482a7b6a95603edce4c0d9db2311af23da1fb2b75ec26fc/charset_normalizer-3.4.4-cp312-cp312-win_arm64.whl", hash = "sha256:376bec83a63b8021bb5c8ea75e21c4ccb86e7e45ca4eb81146091b56599b80c3", size = 100390, upload-time = "2025-10-14T04:41:11.915Z" }, + { url = "https://files.pythonhosted.org/packages/97/45/4b3a1239bbacd321068ea6e7ac28875b03ab8bc0aa0966452db17cd36714/charset_normalizer-3.4.4-cp313-cp313-macosx_10_13_universal2.whl", hash = "sha256:e1f185f86a6f3403aa2420e815904c67b2f9ebc443f045edd0de921108345794", size = 208091, upload-time = "2025-10-14T04:41:13.346Z" }, + { url = "https://files.pythonhosted.org/packages/7d/62/73a6d7450829655a35bb88a88fca7d736f9882a27eacdca2c6d505b57e2e/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:6b39f987ae8ccdf0d2642338faf2abb1862340facc796048b604ef14919e55ed", size = 147936, upload-time = "2025-10-14T04:41:14.461Z" }, + { url = "https://files.pythonhosted.org/packages/89/c5/adb8c8b3d6625bef6d88b251bbb0d95f8205831b987631ab0c8bb5d937c2/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:3162d5d8ce1bb98dd51af660f2121c55d0fa541b46dff7bb9b9f86ea1d87de72", size = 144180, upload-time = "2025-10-14T04:41:15.588Z" }, + { url = "https://files.pythonhosted.org/packages/91/ed/9706e4070682d1cc219050b6048bfd293ccf67b3d4f5a4f39207453d4b99/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:81d5eb2a312700f4ecaa977a8235b634ce853200e828fbadf3a9c50bab278328", size = 161346, upload-time = "2025-10-14T04:41:16.738Z" }, + { url = "https://files.pythonhosted.org/packages/d5/0d/031f0d95e4972901a2f6f09ef055751805ff541511dc1252ba3ca1f80cf5/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:5bd2293095d766545ec1a8f612559f6b40abc0eb18bb2f5d1171872d34036ede", size = 158874, upload-time = "2025-10-14T04:41:17.923Z" }, + { url = "https://files.pythonhosted.org/packages/f5/83/6ab5883f57c9c801ce5e5677242328aa45592be8a00644310a008d04f922/charset_normalizer-3.4.4-cp313-cp313-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:a8a8b89589086a25749f471e6a900d3f662d1d3b6e2e59dcecf787b1cc3a1894", size = 153076, upload-time = "2025-10-14T04:41:19.106Z" }, + { url = "https://files.pythonhosted.org/packages/75/1e/5ff781ddf5260e387d6419959ee89ef13878229732732ee73cdae01800f2/charset_normalizer-3.4.4-cp313-cp313-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:bc7637e2f80d8530ee4a78e878bce464f70087ce73cf7c1caf142416923b98f1", size = 150601, upload-time = "2025-10-14T04:41:20.245Z" }, + { url = "https://files.pythonhosted.org/packages/d7/57/71be810965493d3510a6ca79b90c19e48696fb1ff964da319334b12677f0/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:f8bf04158c6b607d747e93949aa60618b61312fe647a6369f88ce2ff16043490", size = 150376, upload-time = "2025-10-14T04:41:21.398Z" }, + { url = "https://files.pythonhosted.org/packages/e5/d5/c3d057a78c181d007014feb7e9f2e65905a6c4ef182c0ddf0de2924edd65/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_armv7l.whl", hash = "sha256:554af85e960429cf30784dd47447d5125aaa3b99a6f0683589dbd27e2f45da44", size = 144825, upload-time = "2025-10-14T04:41:22.583Z" }, + { url = "https://files.pythonhosted.org/packages/e6/8c/d0406294828d4976f275ffbe66f00266c4b3136b7506941d87c00cab5272/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_ppc64le.whl", hash = "sha256:74018750915ee7ad843a774364e13a3db91682f26142baddf775342c3f5b1133", size = 162583, upload-time = "2025-10-14T04:41:23.754Z" }, + { url = "https://files.pythonhosted.org/packages/d7/24/e2aa1f18c8f15c4c0e932d9287b8609dd30ad56dbe41d926bd846e22fb8d/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_riscv64.whl", hash = "sha256:c0463276121fdee9c49b98908b3a89c39be45d86d1dbaa22957e38f6321d4ce3", size = 150366, upload-time = "2025-10-14T04:41:25.27Z" }, + { url = "https://files.pythonhosted.org/packages/e4/5b/1e6160c7739aad1e2df054300cc618b06bf784a7a164b0f238360721ab86/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_s390x.whl", hash = "sha256:362d61fd13843997c1c446760ef36f240cf81d3ebf74ac62652aebaf7838561e", size = 160300, upload-time = "2025-10-14T04:41:26.725Z" }, + { url = "https://files.pythonhosted.org/packages/7a/10/f882167cd207fbdd743e55534d5d9620e095089d176d55cb22d5322f2afd/charset_normalizer-3.4.4-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:9a26f18905b8dd5d685d6d07b0cdf98a79f3c7a918906af7cc143ea2e164c8bc", size = 154465, upload-time = "2025-10-14T04:41:28.322Z" }, + { url = "https://files.pythonhosted.org/packages/89/66/c7a9e1b7429be72123441bfdbaf2bc13faab3f90b933f664db506dea5915/charset_normalizer-3.4.4-cp313-cp313-win32.whl", hash = "sha256:9b35f4c90079ff2e2edc5b26c0c77925e5d2d255c42c74fdb70fb49b172726ac", size = 99404, upload-time = "2025-10-14T04:41:29.95Z" }, + { url = "https://files.pythonhosted.org/packages/c4/26/b9924fa27db384bdcd97ab83b4f0a8058d96ad9626ead570674d5e737d90/charset_normalizer-3.4.4-cp313-cp313-win_amd64.whl", hash = "sha256:b435cba5f4f750aa6c0a0d92c541fb79f69a387c91e61f1795227e4ed9cece14", size = 107092, upload-time = "2025-10-14T04:41:31.188Z" }, + { url = "https://files.pythonhosted.org/packages/af/8f/3ed4bfa0c0c72a7ca17f0380cd9e4dd842b09f664e780c13cff1dcf2ef1b/charset_normalizer-3.4.4-cp313-cp313-win_arm64.whl", hash = "sha256:542d2cee80be6f80247095cc36c418f7bddd14f4a6de45af91dfad36d817bba2", size = 100408, upload-time = "2025-10-14T04:41:32.624Z" }, + { url = "https://files.pythonhosted.org/packages/2a/35/7051599bd493e62411d6ede36fd5af83a38f37c4767b92884df7301db25d/charset_normalizer-3.4.4-cp314-cp314-macosx_10_13_universal2.whl", hash = "sha256:da3326d9e65ef63a817ecbcc0df6e94463713b754fe293eaa03da99befb9a5bd", size = 207746, upload-time = "2025-10-14T04:41:33.773Z" }, + { url = "https://files.pythonhosted.org/packages/10/9a/97c8d48ef10d6cd4fcead2415523221624bf58bcf68a802721a6bc807c8f/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_aarch64.manylinux_2_17_aarch64.manylinux_2_28_aarch64.whl", hash = "sha256:8af65f14dc14a79b924524b1e7fffe304517b2bff5a58bf64f30b98bbc5079eb", size = 147889, upload-time = "2025-10-14T04:41:34.897Z" }, + { url = "https://files.pythonhosted.org/packages/10/bf/979224a919a1b606c82bd2c5fa49b5c6d5727aa47b4312bb27b1734f53cd/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_armv7l.manylinux_2_17_armv7l.manylinux_2_31_armv7l.whl", hash = "sha256:74664978bb272435107de04e36db5a9735e78232b85b77d45cfb38f758efd33e", size = 143641, upload-time = "2025-10-14T04:41:36.116Z" }, + { url = "https://files.pythonhosted.org/packages/ba/33/0ad65587441fc730dc7bd90e9716b30b4702dc7b617e6ba4997dc8651495/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_ppc64le.manylinux_2_17_ppc64le.manylinux_2_28_ppc64le.whl", hash = "sha256:752944c7ffbfdd10c074dc58ec2d5a8a4cd9493b314d367c14d24c17684ddd14", size = 160779, upload-time = "2025-10-14T04:41:37.229Z" }, + { url = "https://files.pythonhosted.org/packages/67/ed/331d6b249259ee71ddea93f6f2f0a56cfebd46938bde6fcc6f7b9a3d0e09/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_s390x.manylinux_2_17_s390x.manylinux_2_28_s390x.whl", hash = "sha256:d1f13550535ad8cff21b8d757a3257963e951d96e20ec82ab44bc64aeb62a191", size = 159035, upload-time = "2025-10-14T04:41:38.368Z" }, + { url = "https://files.pythonhosted.org/packages/67/ff/f6b948ca32e4f2a4576aa129d8bed61f2e0543bf9f5f2b7fc3758ed005c9/charset_normalizer-3.4.4-cp314-cp314-manylinux2014_x86_64.manylinux_2_17_x86_64.manylinux_2_28_x86_64.whl", hash = "sha256:ecaae4149d99b1c9e7b88bb03e3221956f68fd6d50be2ef061b2381b61d20838", size = 152542, upload-time = "2025-10-14T04:41:39.862Z" }, + { url = "https://files.pythonhosted.org/packages/16/85/276033dcbcc369eb176594de22728541a925b2632f9716428c851b149e83/charset_normalizer-3.4.4-cp314-cp314-manylinux_2_31_riscv64.manylinux_2_39_riscv64.whl", hash = "sha256:cb6254dc36b47a990e59e1068afacdcd02958bdcce30bb50cc1700a8b9d624a6", size = 149524, upload-time = "2025-10-14T04:41:41.319Z" }, + { url = "https://files.pythonhosted.org/packages/9e/f2/6a2a1f722b6aba37050e626530a46a68f74e63683947a8acff92569f979a/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:c8ae8a0f02f57a6e61203a31428fa1d677cbe50c93622b4149d5c0f319c1d19e", size = 150395, upload-time = "2025-10-14T04:41:42.539Z" }, + { url = "https://files.pythonhosted.org/packages/60/bb/2186cb2f2bbaea6338cad15ce23a67f9b0672929744381e28b0592676824/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_armv7l.whl", hash = "sha256:47cc91b2f4dd2833fddaedd2893006b0106129d4b94fdb6af1f4ce5a9965577c", size = 143680, upload-time = "2025-10-14T04:41:43.661Z" }, + { url = "https://files.pythonhosted.org/packages/7d/a5/bf6f13b772fbb2a90360eb620d52ed8f796f3c5caee8398c3b2eb7b1c60d/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_ppc64le.whl", hash = "sha256:82004af6c302b5d3ab2cfc4cc5f29db16123b1a8417f2e25f9066f91d4411090", size = 162045, upload-time = "2025-10-14T04:41:44.821Z" }, + { url = "https://files.pythonhosted.org/packages/df/c5/d1be898bf0dc3ef9030c3825e5d3b83f2c528d207d246cbabe245966808d/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_riscv64.whl", hash = "sha256:2b7d8f6c26245217bd2ad053761201e9f9680f8ce52f0fcd8d0755aeae5b2152", size = 149687, upload-time = "2025-10-14T04:41:46.442Z" }, + { url = "https://files.pythonhosted.org/packages/a5/42/90c1f7b9341eef50c8a1cb3f098ac43b0508413f33affd762855f67a410e/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_s390x.whl", hash = "sha256:799a7a5e4fb2d5898c60b640fd4981d6a25f1c11790935a44ce38c54e985f828", size = 160014, upload-time = "2025-10-14T04:41:47.631Z" }, + { url = "https://files.pythonhosted.org/packages/76/be/4d3ee471e8145d12795ab655ece37baed0929462a86e72372fd25859047c/charset_normalizer-3.4.4-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:99ae2cffebb06e6c22bdc25801d7b30f503cc87dbd283479e7b606f70aff57ec", size = 154044, upload-time = "2025-10-14T04:41:48.81Z" }, + { url = "https://files.pythonhosted.org/packages/b0/6f/8f7af07237c34a1defe7defc565a9bc1807762f672c0fde711a4b22bf9c0/charset_normalizer-3.4.4-cp314-cp314-win32.whl", hash = "sha256:f9d332f8c2a2fcbffe1378594431458ddbef721c1769d78e2cbc06280d8155f9", size = 99940, upload-time = "2025-10-14T04:41:49.946Z" }, + { url = "https://files.pythonhosted.org/packages/4b/51/8ade005e5ca5b0d80fb4aff72a3775b325bdc3d27408c8113811a7cbe640/charset_normalizer-3.4.4-cp314-cp314-win_amd64.whl", hash = "sha256:8a6562c3700cce886c5be75ade4a5db4214fda19fede41d9792d100288d8f94c", size = 107104, upload-time = "2025-10-14T04:41:51.051Z" }, + { url = "https://files.pythonhosted.org/packages/da/5f/6b8f83a55bb8278772c5ae54a577f3099025f9ade59d0136ac24a0df4bde/charset_normalizer-3.4.4-cp314-cp314-win_arm64.whl", hash = "sha256:de00632ca48df9daf77a2c65a484531649261ec9f25489917f09e455cb09ddb2", size = 100743, upload-time = "2025-10-14T04:41:52.122Z" }, + { url = "https://files.pythonhosted.org/packages/0a/4c/925909008ed5a988ccbb72dcc897407e5d6d3bd72410d69e051fc0c14647/charset_normalizer-3.4.4-py3-none-any.whl", hash = "sha256:7a32c560861a02ff789ad905a2fe94e3f840803362c84fecf1851cb4cf3dc37f", size = 53402, upload-time = "2025-10-14T04:42:31.76Z" }, +] + +[[package]] +name = "googleapis-common-protos" +version = "1.72.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "protobuf" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/e5/7b/adfd75544c415c487b33061fe7ae526165241c1ea133f9a9125a56b39fd8/googleapis_common_protos-1.72.0.tar.gz", hash = "sha256:e55a601c1b32b52d7a3e65f43563e2aa61bcd737998ee672ac9b951cd49319f5", size = 147433, upload-time = "2025-11-06T18:29:24.087Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/c4/ab/09169d5a4612a5f92490806649ac8d41e3ec9129c636754575b3553f4ea4/googleapis_common_protos-1.72.0-py3-none-any.whl", hash = "sha256:4299c5a82d5ae1a9702ada957347726b167f9f8d1fc352477702a1e851ff4038", size = 297515, upload-time = "2025-11-06T18:29:13.14Z" }, +] + +[[package]] +name = "idna" +version = "3.11" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/6f/6d/0703ccc57f3a7233505399edb88de3cbd678da106337b9fcde432b65ed60/idna-3.11.tar.gz", hash = "sha256:795dafcc9c04ed0c1fb032c2aa73654d8e8c5023a7df64a53f39190ada629902", size = 194582, upload-time = "2025-10-12T14:55:20.501Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/0e/61/66938bbb5fc52dbdf84594873d5b51fb1f7c7794e9c0f5bd885f30bc507b/idna-3.11-py3-none-any.whl", hash = "sha256:771a87f49d9defaf64091e6e6fe9c18d4833f140bd19464795bc32d966ca37ea", size = 71008, upload-time = "2025-10-12T14:55:18.883Z" }, +] + +[[package]] +name = "importlib-metadata" +version = "8.7.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "zipp" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/76/66/650a33bd90f786193e4de4b3ad86ea60b53c89b669a5c7be931fac31cdb0/importlib_metadata-8.7.0.tar.gz", hash = "sha256:d13b81ad223b890aa16c5471f2ac3056cf76c5f10f82d6f9292f0b415f389000", size = 56641, upload-time = "2025-04-27T15:29:01.736Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/20/b0/36bd937216ec521246249be3bf9855081de4c5e06a0c9b4219dbeda50373/importlib_metadata-8.7.0-py3-none-any.whl", hash = "sha256:e5dd1551894c77868a30651cef00984d50e1002d06942a7101d34870c5f02afd", size = 27656, upload-time = "2025-04-27T15:29:00.214Z" }, +] + +[[package]] +name = "jsonschema" +version = "4.25.1" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "attrs" }, + { name = "jsonschema-specifications" }, + { name = "referencing" }, + { name = "rpds-py" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/74/69/f7185de793a29082a9f3c7728268ffb31cb5095131a9c139a74078e27336/jsonschema-4.25.1.tar.gz", hash = "sha256:e4a9655ce0da0c0b67a085847e00a3a51449e1157f4f75e9fb5aa545e122eb85", size = 357342, upload-time = "2025-08-18T17:03:50.038Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/bf/9c/8c95d856233c1f82500c2450b8c68576b4cf1c871db3afac5c34ff84e6fd/jsonschema-4.25.1-py3-none-any.whl", hash = "sha256:3fba0169e345c7175110351d456342c364814cfcf3b964ba4587f22915230a63", size = 90040, upload-time = "2025-08-18T17:03:48.373Z" }, +] + +[[package]] +name = "jsonschema-specifications" +version = "2025.9.1" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "referencing" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/19/74/a633ee74eb36c44aa6d1095e7cc5569bebf04342ee146178e2d36600708b/jsonschema_specifications-2025.9.1.tar.gz", hash = "sha256:b540987f239e745613c7a9176f3edb72b832a4ac465cf02712288397832b5e8d", size = 32855, upload-time = "2025-09-08T01:34:59.186Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/41/45/1a4ed80516f02155c51f51e8cedb3c1902296743db0bbc66608a0db2814f/jsonschema_specifications-2025.9.1-py3-none-any.whl", hash = "sha256:98802fee3a11ee76ecaca44429fda8a41bff98b00a0f2838151b113f210cc6fe", size = 18437, upload-time = "2025-09-08T01:34:57.871Z" }, +] + +[[package]] +name = "llama-stack-api" +version = "0.4.0.dev0" +source = { editable = "." } +dependencies = [ + { name = "jsonschema" }, + { name = "opentelemetry-exporter-otlp-proto-http" }, + { name = "opentelemetry-sdk" }, + { name = "pydantic" }, +] + +[package.metadata] +requires-dist = [ + { name = "jsonschema" }, + { name = "opentelemetry-exporter-otlp-proto-http", specifier = ">=1.30.0" }, + { name = "opentelemetry-sdk", specifier = ">=1.30.0" }, + { name = "pydantic", specifier = ">=2.11.9" }, +] + +[[package]] +name = "opentelemetry-api" +version = "1.38.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "importlib-metadata" }, + { name = "typing-extensions" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/08/d8/0f354c375628e048bd0570645b310797299754730079853095bf000fba69/opentelemetry_api-1.38.0.tar.gz", hash = "sha256:f4c193b5e8acb0912b06ac5b16321908dd0843d75049c091487322284a3eea12", size = 65242, upload-time = "2025-10-16T08:35:50.25Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/ae/a2/d86e01c28300bd41bab8f18afd613676e2bd63515417b77636fc1add426f/opentelemetry_api-1.38.0-py3-none-any.whl", hash = "sha256:2891b0197f47124454ab9f0cf58f3be33faca394457ac3e09daba13ff50aa582", size = 65947, upload-time = "2025-10-16T08:35:30.23Z" }, +] + +[[package]] +name = "opentelemetry-exporter-otlp-proto-common" +version = "1.38.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "opentelemetry-proto" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/19/83/dd4660f2956ff88ed071e9e0e36e830df14b8c5dc06722dbde1841accbe8/opentelemetry_exporter_otlp_proto_common-1.38.0.tar.gz", hash = "sha256:e333278afab4695aa8114eeb7bf4e44e65c6607d54968271a249c180b2cb605c", size = 20431, upload-time = "2025-10-16T08:35:53.285Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/a7/9e/55a41c9601191e8cd8eb626b54ee6827b9c9d4a46d736f32abc80d8039fc/opentelemetry_exporter_otlp_proto_common-1.38.0-py3-none-any.whl", hash = "sha256:03cb76ab213300fe4f4c62b7d8f17d97fcfd21b89f0b5ce38ea156327ddda74a", size = 18359, upload-time = "2025-10-16T08:35:34.099Z" }, +] + +[[package]] +name = "opentelemetry-exporter-otlp-proto-http" +version = "1.38.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "googleapis-common-protos" }, + { name = "opentelemetry-api" }, + { name = "opentelemetry-exporter-otlp-proto-common" }, + { name = "opentelemetry-proto" }, + { name = "opentelemetry-sdk" }, + { name = "requests" }, + { name = "typing-extensions" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/81/0a/debcdfb029fbd1ccd1563f7c287b89a6f7bef3b2902ade56797bfd020854/opentelemetry_exporter_otlp_proto_http-1.38.0.tar.gz", hash = "sha256:f16bd44baf15cbe07633c5112ffc68229d0edbeac7b37610be0b2def4e21e90b", size = 17282, upload-time = "2025-10-16T08:35:54.422Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/e5/77/154004c99fb9f291f74aa0822a2f5bbf565a72d8126b3a1b63ed8e5f83c7/opentelemetry_exporter_otlp_proto_http-1.38.0-py3-none-any.whl", hash = "sha256:84b937305edfc563f08ec69b9cb2298be8188371217e867c1854d77198d0825b", size = 19579, upload-time = "2025-10-16T08:35:36.269Z" }, +] + +[[package]] +name = "opentelemetry-proto" +version = "1.38.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "protobuf" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/51/14/f0c4f0f6371b9cb7f9fa9ee8918bfd59ac7040c7791f1e6da32a1839780d/opentelemetry_proto-1.38.0.tar.gz", hash = "sha256:88b161e89d9d372ce723da289b7da74c3a8354a8e5359992be813942969ed468", size = 46152, upload-time = "2025-10-16T08:36:01.612Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/b6/6a/82b68b14efca5150b2632f3692d627afa76b77378c4999f2648979409528/opentelemetry_proto-1.38.0-py3-none-any.whl", hash = "sha256:b6ebe54d3217c42e45462e2a1ae28c3e2bf2ec5a5645236a490f55f45f1a0a18", size = 72535, upload-time = "2025-10-16T08:35:45.749Z" }, +] + +[[package]] +name = "opentelemetry-sdk" +version = "1.38.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "opentelemetry-api" }, + { name = "opentelemetry-semantic-conventions" }, + { name = "typing-extensions" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/85/cb/f0eee1445161faf4c9af3ba7b848cc22a50a3d3e2515051ad8628c35ff80/opentelemetry_sdk-1.38.0.tar.gz", hash = "sha256:93df5d4d871ed09cb4272305be4d996236eedb232253e3ab864c8620f051cebe", size = 171942, upload-time = "2025-10-16T08:36:02.257Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/2f/2e/e93777a95d7d9c40d270a371392b6d6f1ff170c2a3cb32d6176741b5b723/opentelemetry_sdk-1.38.0-py3-none-any.whl", hash = "sha256:1c66af6564ecc1553d72d811a01df063ff097cdc82ce188da9951f93b8d10f6b", size = 132349, upload-time = "2025-10-16T08:35:46.995Z" }, +] + +[[package]] +name = "opentelemetry-semantic-conventions" +version = "0.59b0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "opentelemetry-api" }, + { name = "typing-extensions" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/40/bc/8b9ad3802cd8ac6583a4eb7de7e5d7db004e89cb7efe7008f9c8a537ee75/opentelemetry_semantic_conventions-0.59b0.tar.gz", hash = "sha256:7a6db3f30d70202d5bf9fa4b69bc866ca6a30437287de6c510fb594878aed6b0", size = 129861, upload-time = "2025-10-16T08:36:03.346Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/24/7d/c88d7b15ba8fe5c6b8f93be50fc11795e9fc05386c44afaf6b76fe191f9b/opentelemetry_semantic_conventions-0.59b0-py3-none-any.whl", hash = "sha256:35d3b8833ef97d614136e253c1da9342b4c3c083bbaf29ce31d572a1c3825eed", size = 207954, upload-time = "2025-10-16T08:35:48.054Z" }, +] + +[[package]] +name = "protobuf" +version = "6.33.1" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/0a/03/a1440979a3f74f16cab3b75b0da1a1a7f922d56a8ddea96092391998edc0/protobuf-6.33.1.tar.gz", hash = "sha256:97f65757e8d09870de6fd973aeddb92f85435607235d20b2dfed93405d00c85b", size = 443432, upload-time = "2025-11-13T16:44:18.895Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/06/f1/446a9bbd2c60772ca36556bac8bfde40eceb28d9cc7838755bc41e001d8f/protobuf-6.33.1-cp310-abi3-win32.whl", hash = "sha256:f8d3fdbc966aaab1d05046d0240dd94d40f2a8c62856d41eaa141ff64a79de6b", size = 425593, upload-time = "2025-11-13T16:44:06.275Z" }, + { url = "https://files.pythonhosted.org/packages/a6/79/8780a378c650e3df849b73de8b13cf5412f521ca2ff9b78a45c247029440/protobuf-6.33.1-cp310-abi3-win_amd64.whl", hash = "sha256:923aa6d27a92bf44394f6abf7ea0500f38769d4b07f4be41cb52bd8b1123b9ed", size = 436883, upload-time = "2025-11-13T16:44:09.222Z" }, + { url = "https://files.pythonhosted.org/packages/cd/93/26213ff72b103ae55bb0d73e7fb91ea570ef407c3ab4fd2f1f27cac16044/protobuf-6.33.1-cp39-abi3-macosx_10_9_universal2.whl", hash = "sha256:fe34575f2bdde76ac429ec7b570235bf0c788883e70aee90068e9981806f2490", size = 427522, upload-time = "2025-11-13T16:44:10.475Z" }, + { url = "https://files.pythonhosted.org/packages/c2/32/df4a35247923393aa6b887c3b3244a8c941c32a25681775f96e2b418f90e/protobuf-6.33.1-cp39-abi3-manylinux2014_aarch64.whl", hash = "sha256:f8adba2e44cde2d7618996b3fc02341f03f5bc3f2748be72dc7b063319276178", size = 324445, upload-time = "2025-11-13T16:44:11.869Z" }, + { url = "https://files.pythonhosted.org/packages/8e/d0/d796e419e2ec93d2f3fa44888861c3f88f722cde02b7c3488fcc6a166820/protobuf-6.33.1-cp39-abi3-manylinux2014_s390x.whl", hash = "sha256:0f4cf01222c0d959c2b399142deb526de420be8236f22c71356e2a544e153c53", size = 339161, upload-time = "2025-11-13T16:44:12.778Z" }, + { url = "https://files.pythonhosted.org/packages/1d/2a/3c5f05a4af06649547027d288747f68525755de692a26a7720dced3652c0/protobuf-6.33.1-cp39-abi3-manylinux2014_x86_64.whl", hash = "sha256:8fd7d5e0eb08cd5b87fd3df49bc193f5cfd778701f47e11d127d0afc6c39f1d1", size = 323171, upload-time = "2025-11-13T16:44:14.035Z" }, + { url = "https://files.pythonhosted.org/packages/08/b4/46310463b4f6ceef310f8348786f3cff181cea671578e3d9743ba61a459e/protobuf-6.33.1-py3-none-any.whl", hash = "sha256:d595a9fd694fdeb061a62fbe10eb039cc1e444df81ec9bb70c7fc59ebcb1eafa", size = 170477, upload-time = "2025-11-13T16:44:17.633Z" }, +] + +[[package]] +name = "pydantic" +version = "2.12.4" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "annotated-types" }, + { name = "pydantic-core" }, + { name = "typing-extensions" }, + { name = "typing-inspection" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/96/ad/a17bc283d7d81837c061c49e3eaa27a45991759a1b7eae1031921c6bd924/pydantic-2.12.4.tar.gz", hash = "sha256:0f8cb9555000a4b5b617f66bfd2566264c4984b27589d3b845685983e8ea85ac", size = 821038, upload-time = "2025-11-05T10:50:08.59Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/82/2f/e68750da9b04856e2a7ec56fc6f034a5a79775e9b9a81882252789873798/pydantic-2.12.4-py3-none-any.whl", hash = "sha256:92d3d202a745d46f9be6df459ac5a064fdaa3c1c4cd8adcfa332ccf3c05f871e", size = 463400, upload-time = "2025-11-05T10:50:06.732Z" }, +] + +[[package]] +name = "pydantic-core" +version = "2.41.5" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "typing-extensions" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/71/70/23b021c950c2addd24ec408e9ab05d59b035b39d97cdc1130e1bce647bb6/pydantic_core-2.41.5.tar.gz", hash = "sha256:08daa51ea16ad373ffd5e7606252cc32f07bc72b28284b6bc9c6df804816476e", size = 460952, upload-time = "2025-11-04T13:43:49.098Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/5f/5d/5f6c63eebb5afee93bcaae4ce9a898f3373ca23df3ccaef086d0233a35a7/pydantic_core-2.41.5-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:f41a7489d32336dbf2199c8c0a215390a751c5b014c2c1c5366e817202e9cdf7", size = 2110990, upload-time = "2025-11-04T13:39:58.079Z" }, + { url = "https://files.pythonhosted.org/packages/aa/32/9c2e8ccb57c01111e0fd091f236c7b371c1bccea0fa85247ac55b1e2b6b6/pydantic_core-2.41.5-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:070259a8818988b9a84a449a2a7337c7f430a22acc0859c6b110aa7212a6d9c0", size = 1896003, upload-time = "2025-11-04T13:39:59.956Z" }, + { url = "https://files.pythonhosted.org/packages/68/b8/a01b53cb0e59139fbc9e4fda3e9724ede8de279097179be4ff31f1abb65a/pydantic_core-2.41.5-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e96cea19e34778f8d59fe40775a7a574d95816eb150850a85a7a4c8f4b94ac69", size = 1919200, upload-time = "2025-11-04T13:40:02.241Z" }, + { url = "https://files.pythonhosted.org/packages/38/de/8c36b5198a29bdaade07b5985e80a233a5ac27137846f3bc2d3b40a47360/pydantic_core-2.41.5-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:ed2e99c456e3fadd05c991f8f437ef902e00eedf34320ba2b0842bd1c3ca3a75", size = 2052578, upload-time = "2025-11-04T13:40:04.401Z" }, + { url = "https://files.pythonhosted.org/packages/00/b5/0e8e4b5b081eac6cb3dbb7e60a65907549a1ce035a724368c330112adfdd/pydantic_core-2.41.5-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:65840751b72fbfd82c3c640cff9284545342a4f1eb1586ad0636955b261b0b05", size = 2208504, upload-time = "2025-11-04T13:40:06.072Z" }, + { url = "https://files.pythonhosted.org/packages/77/56/87a61aad59c7c5b9dc8caad5a41a5545cba3810c3e828708b3d7404f6cef/pydantic_core-2.41.5-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:e536c98a7626a98feb2d3eaf75944ef6f3dbee447e1f841eae16f2f0a72d8ddc", size = 2335816, upload-time = "2025-11-04T13:40:07.835Z" }, + { url = "https://files.pythonhosted.org/packages/0d/76/941cc9f73529988688a665a5c0ecff1112b3d95ab48f81db5f7606f522d3/pydantic_core-2.41.5-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:eceb81a8d74f9267ef4081e246ffd6d129da5d87e37a77c9bde550cb04870c1c", size = 2075366, upload-time = "2025-11-04T13:40:09.804Z" }, + { url = "https://files.pythonhosted.org/packages/d3/43/ebef01f69baa07a482844faaa0a591bad1ef129253ffd0cdaa9d8a7f72d3/pydantic_core-2.41.5-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d38548150c39b74aeeb0ce8ee1d8e82696f4a4e16ddc6de7b1d8823f7de4b9b5", size = 2171698, upload-time = "2025-11-04T13:40:12.004Z" }, + { url = "https://files.pythonhosted.org/packages/b1/87/41f3202e4193e3bacfc2c065fab7706ebe81af46a83d3e27605029c1f5a6/pydantic_core-2.41.5-cp312-cp312-musllinux_1_1_aarch64.whl", hash = "sha256:c23e27686783f60290e36827f9c626e63154b82b116d7fe9adba1fda36da706c", size = 2132603, upload-time = "2025-11-04T13:40:13.868Z" }, + { url = "https://files.pythonhosted.org/packages/49/7d/4c00df99cb12070b6bccdef4a195255e6020a550d572768d92cc54dba91a/pydantic_core-2.41.5-cp312-cp312-musllinux_1_1_armv7l.whl", hash = "sha256:482c982f814460eabe1d3bb0adfdc583387bd4691ef00b90575ca0d2b6fe2294", size = 2329591, upload-time = "2025-11-04T13:40:15.672Z" }, + { url = "https://files.pythonhosted.org/packages/cc/6a/ebf4b1d65d458f3cda6a7335d141305dfa19bdc61140a884d165a8a1bbc7/pydantic_core-2.41.5-cp312-cp312-musllinux_1_1_x86_64.whl", hash = "sha256:bfea2a5f0b4d8d43adf9d7b8bf019fb46fdd10a2e5cde477fbcb9d1fa08c68e1", size = 2319068, upload-time = "2025-11-04T13:40:17.532Z" }, + { url = "https://files.pythonhosted.org/packages/49/3b/774f2b5cd4192d5ab75870ce4381fd89cf218af999515baf07e7206753f0/pydantic_core-2.41.5-cp312-cp312-win32.whl", hash = "sha256:b74557b16e390ec12dca509bce9264c3bbd128f8a2c376eaa68003d7f327276d", size = 1985908, upload-time = "2025-11-04T13:40:19.309Z" }, + { url = "https://files.pythonhosted.org/packages/86/45/00173a033c801cacf67c190fef088789394feaf88a98a7035b0e40d53dc9/pydantic_core-2.41.5-cp312-cp312-win_amd64.whl", hash = "sha256:1962293292865bca8e54702b08a4f26da73adc83dd1fcf26fbc875b35d81c815", size = 2020145, upload-time = "2025-11-04T13:40:21.548Z" }, + { url = "https://files.pythonhosted.org/packages/f9/22/91fbc821fa6d261b376a3f73809f907cec5ca6025642c463d3488aad22fb/pydantic_core-2.41.5-cp312-cp312-win_arm64.whl", hash = "sha256:1746d4a3d9a794cacae06a5eaaccb4b8643a131d45fbc9af23e353dc0a5ba5c3", size = 1976179, upload-time = "2025-11-04T13:40:23.393Z" }, + { url = "https://files.pythonhosted.org/packages/87/06/8806241ff1f70d9939f9af039c6c35f2360cf16e93c2ca76f184e76b1564/pydantic_core-2.41.5-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:941103c9be18ac8daf7b7adca8228f8ed6bb7a1849020f643b3a14d15b1924d9", size = 2120403, upload-time = "2025-11-04T13:40:25.248Z" }, + { url = "https://files.pythonhosted.org/packages/94/02/abfa0e0bda67faa65fef1c84971c7e45928e108fe24333c81f3bfe35d5f5/pydantic_core-2.41.5-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:112e305c3314f40c93998e567879e887a3160bb8689ef3d2c04b6cc62c33ac34", size = 1896206, upload-time = "2025-11-04T13:40:27.099Z" }, + { url = "https://files.pythonhosted.org/packages/15/df/a4c740c0943e93e6500f9eb23f4ca7ec9bf71b19e608ae5b579678c8d02f/pydantic_core-2.41.5-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:0cbaad15cb0c90aa221d43c00e77bb33c93e8d36e0bf74760cd00e732d10a6a0", size = 1919307, upload-time = "2025-11-04T13:40:29.806Z" }, + { url = "https://files.pythonhosted.org/packages/9a/e3/6324802931ae1d123528988e0e86587c2072ac2e5394b4bc2bc34b61ff6e/pydantic_core-2.41.5-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:03ca43e12fab6023fc79d28ca6b39b05f794ad08ec2feccc59a339b02f2b3d33", size = 2063258, upload-time = "2025-11-04T13:40:33.544Z" }, + { url = "https://files.pythonhosted.org/packages/c9/d4/2230d7151d4957dd79c3044ea26346c148c98fbf0ee6ebd41056f2d62ab5/pydantic_core-2.41.5-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:dc799088c08fa04e43144b164feb0c13f9a0bc40503f8df3e9fde58a3c0c101e", size = 2214917, upload-time = "2025-11-04T13:40:35.479Z" }, + { url = "https://files.pythonhosted.org/packages/e6/9f/eaac5df17a3672fef0081b6c1bb0b82b33ee89aa5cec0d7b05f52fd4a1fa/pydantic_core-2.41.5-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:97aeba56665b4c3235a0e52b2c2f5ae9cd071b8a8310ad27bddb3f7fb30e9aa2", size = 2332186, upload-time = "2025-11-04T13:40:37.436Z" }, + { url = "https://files.pythonhosted.org/packages/cf/4e/35a80cae583a37cf15604b44240e45c05e04e86f9cfd766623149297e971/pydantic_core-2.41.5-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:406bf18d345822d6c21366031003612b9c77b3e29ffdb0f612367352aab7d586", size = 2073164, upload-time = "2025-11-04T13:40:40.289Z" }, + { url = "https://files.pythonhosted.org/packages/bf/e3/f6e262673c6140dd3305d144d032f7bd5f7497d3871c1428521f19f9efa2/pydantic_core-2.41.5-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:b93590ae81f7010dbe380cdeab6f515902ebcbefe0b9327cc4804d74e93ae69d", size = 2179146, upload-time = "2025-11-04T13:40:42.809Z" }, + { url = "https://files.pythonhosted.org/packages/75/c7/20bd7fc05f0c6ea2056a4565c6f36f8968c0924f19b7d97bbfea55780e73/pydantic_core-2.41.5-cp313-cp313-musllinux_1_1_aarch64.whl", hash = "sha256:01a3d0ab748ee531f4ea6c3e48ad9dac84ddba4b0d82291f87248f2f9de8d740", size = 2137788, upload-time = "2025-11-04T13:40:44.752Z" }, + { url = "https://files.pythonhosted.org/packages/3a/8d/34318ef985c45196e004bc46c6eab2eda437e744c124ef0dbe1ff2c9d06b/pydantic_core-2.41.5-cp313-cp313-musllinux_1_1_armv7l.whl", hash = "sha256:6561e94ba9dacc9c61bce40e2d6bdc3bfaa0259d3ff36ace3b1e6901936d2e3e", size = 2340133, upload-time = "2025-11-04T13:40:46.66Z" }, + { url = "https://files.pythonhosted.org/packages/9c/59/013626bf8c78a5a5d9350d12e7697d3d4de951a75565496abd40ccd46bee/pydantic_core-2.41.5-cp313-cp313-musllinux_1_1_x86_64.whl", hash = "sha256:915c3d10f81bec3a74fbd4faebe8391013ba61e5a1a8d48c4455b923bdda7858", size = 2324852, upload-time = "2025-11-04T13:40:48.575Z" }, + { url = "https://files.pythonhosted.org/packages/1a/d9/c248c103856f807ef70c18a4f986693a46a8ffe1602e5d361485da502d20/pydantic_core-2.41.5-cp313-cp313-win32.whl", hash = "sha256:650ae77860b45cfa6e2cdafc42618ceafab3a2d9a3811fcfbd3bbf8ac3c40d36", size = 1994679, upload-time = "2025-11-04T13:40:50.619Z" }, + { url = "https://files.pythonhosted.org/packages/9e/8b/341991b158ddab181cff136acd2552c9f35bd30380422a639c0671e99a91/pydantic_core-2.41.5-cp313-cp313-win_amd64.whl", hash = "sha256:79ec52ec461e99e13791ec6508c722742ad745571f234ea6255bed38c6480f11", size = 2019766, upload-time = "2025-11-04T13:40:52.631Z" }, + { url = "https://files.pythonhosted.org/packages/73/7d/f2f9db34af103bea3e09735bb40b021788a5e834c81eedb541991badf8f5/pydantic_core-2.41.5-cp313-cp313-win_arm64.whl", hash = "sha256:3f84d5c1b4ab906093bdc1ff10484838aca54ef08de4afa9de0f5f14d69639cd", size = 1981005, upload-time = "2025-11-04T13:40:54.734Z" }, + { url = "https://files.pythonhosted.org/packages/ea/28/46b7c5c9635ae96ea0fbb779e271a38129df2550f763937659ee6c5dbc65/pydantic_core-2.41.5-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:3f37a19d7ebcdd20b96485056ba9e8b304e27d9904d233d7b1015db320e51f0a", size = 2119622, upload-time = "2025-11-04T13:40:56.68Z" }, + { url = "https://files.pythonhosted.org/packages/74/1a/145646e5687e8d9a1e8d09acb278c8535ebe9e972e1f162ed338a622f193/pydantic_core-2.41.5-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:1d1d9764366c73f996edd17abb6d9d7649a7eb690006ab6adbda117717099b14", size = 1891725, upload-time = "2025-11-04T13:40:58.807Z" }, + { url = "https://files.pythonhosted.org/packages/23/04/e89c29e267b8060b40dca97bfc64a19b2a3cf99018167ea1677d96368273/pydantic_core-2.41.5-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:25e1c2af0fce638d5f1988b686f3b3ea8cd7de5f244ca147c777769e798a9cd1", size = 1915040, upload-time = "2025-11-04T13:41:00.853Z" }, + { url = "https://files.pythonhosted.org/packages/84/a3/15a82ac7bd97992a82257f777b3583d3e84bdb06ba6858f745daa2ec8a85/pydantic_core-2.41.5-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:506d766a8727beef16b7adaeb8ee6217c64fc813646b424d0804d67c16eddb66", size = 2063691, upload-time = "2025-11-04T13:41:03.504Z" }, + { url = "https://files.pythonhosted.org/packages/74/9b/0046701313c6ef08c0c1cf0e028c67c770a4e1275ca73131563c5f2a310a/pydantic_core-2.41.5-cp314-cp314-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:4819fa52133c9aa3c387b3328f25c1facc356491e6135b459f1de698ff64d869", size = 2213897, upload-time = "2025-11-04T13:41:05.804Z" }, + { url = "https://files.pythonhosted.org/packages/8a/cd/6bac76ecd1b27e75a95ca3a9a559c643b3afcd2dd62086d4b7a32a18b169/pydantic_core-2.41.5-cp314-cp314-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:2b761d210c9ea91feda40d25b4efe82a1707da2ef62901466a42492c028553a2", size = 2333302, upload-time = "2025-11-04T13:41:07.809Z" }, + { url = "https://files.pythonhosted.org/packages/4c/d2/ef2074dc020dd6e109611a8be4449b98cd25e1b9b8a303c2f0fca2f2bcf7/pydantic_core-2.41.5-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:22f0fb8c1c583a3b6f24df2470833b40207e907b90c928cc8d3594b76f874375", size = 2064877, upload-time = "2025-11-04T13:41:09.827Z" }, + { url = "https://files.pythonhosted.org/packages/18/66/e9db17a9a763d72f03de903883c057b2592c09509ccfe468187f2a2eef29/pydantic_core-2.41.5-cp314-cp314-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:2782c870e99878c634505236d81e5443092fba820f0373997ff75f90f68cd553", size = 2180680, upload-time = "2025-11-04T13:41:12.379Z" }, + { url = "https://files.pythonhosted.org/packages/d3/9e/3ce66cebb929f3ced22be85d4c2399b8e85b622db77dad36b73c5387f8f8/pydantic_core-2.41.5-cp314-cp314-musllinux_1_1_aarch64.whl", hash = "sha256:0177272f88ab8312479336e1d777f6b124537d47f2123f89cb37e0accea97f90", size = 2138960, upload-time = "2025-11-04T13:41:14.627Z" }, + { url = "https://files.pythonhosted.org/packages/a6/62/205a998f4327d2079326b01abee48e502ea739d174f0a89295c481a2272e/pydantic_core-2.41.5-cp314-cp314-musllinux_1_1_armv7l.whl", hash = "sha256:63510af5e38f8955b8ee5687740d6ebf7c2a0886d15a6d65c32814613681bc07", size = 2339102, upload-time = "2025-11-04T13:41:16.868Z" }, + { url = "https://files.pythonhosted.org/packages/3c/0d/f05e79471e889d74d3d88f5bd20d0ed189ad94c2423d81ff8d0000aab4ff/pydantic_core-2.41.5-cp314-cp314-musllinux_1_1_x86_64.whl", hash = "sha256:e56ba91f47764cc14f1daacd723e3e82d1a89d783f0f5afe9c364b8bb491ccdb", size = 2326039, upload-time = "2025-11-04T13:41:18.934Z" }, + { url = "https://files.pythonhosted.org/packages/ec/e1/e08a6208bb100da7e0c4b288eed624a703f4d129bde2da475721a80cab32/pydantic_core-2.41.5-cp314-cp314-win32.whl", hash = "sha256:aec5cf2fd867b4ff45b9959f8b20ea3993fc93e63c7363fe6851424c8a7e7c23", size = 1995126, upload-time = "2025-11-04T13:41:21.418Z" }, + { url = "https://files.pythonhosted.org/packages/48/5d/56ba7b24e9557f99c9237e29f5c09913c81eeb2f3217e40e922353668092/pydantic_core-2.41.5-cp314-cp314-win_amd64.whl", hash = "sha256:8e7c86f27c585ef37c35e56a96363ab8de4e549a95512445b85c96d3e2f7c1bf", size = 2015489, upload-time = "2025-11-04T13:41:24.076Z" }, + { url = "https://files.pythonhosted.org/packages/4e/bb/f7a190991ec9e3e0ba22e4993d8755bbc4a32925c0b5b42775c03e8148f9/pydantic_core-2.41.5-cp314-cp314-win_arm64.whl", hash = "sha256:e672ba74fbc2dc8eea59fb6d4aed6845e6905fc2a8afe93175d94a83ba2a01a0", size = 1977288, upload-time = "2025-11-04T13:41:26.33Z" }, + { url = "https://files.pythonhosted.org/packages/92/ed/77542d0c51538e32e15afe7899d79efce4b81eee631d99850edc2f5e9349/pydantic_core-2.41.5-cp314-cp314t-macosx_10_12_x86_64.whl", hash = "sha256:8566def80554c3faa0e65ac30ab0932b9e3a5cd7f8323764303d468e5c37595a", size = 2120255, upload-time = "2025-11-04T13:41:28.569Z" }, + { url = "https://files.pythonhosted.org/packages/bb/3d/6913dde84d5be21e284439676168b28d8bbba5600d838b9dca99de0fad71/pydantic_core-2.41.5-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:b80aa5095cd3109962a298ce14110ae16b8c1aece8b72f9dafe81cf597ad80b3", size = 1863760, upload-time = "2025-11-04T13:41:31.055Z" }, + { url = "https://files.pythonhosted.org/packages/5a/f0/e5e6b99d4191da102f2b0eb9687aaa7f5bea5d9964071a84effc3e40f997/pydantic_core-2.41.5-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:3006c3dd9ba34b0c094c544c6006cc79e87d8612999f1a5d43b769b89181f23c", size = 1878092, upload-time = "2025-11-04T13:41:33.21Z" }, + { url = "https://files.pythonhosted.org/packages/71/48/36fb760642d568925953bcc8116455513d6e34c4beaa37544118c36aba6d/pydantic_core-2.41.5-cp314-cp314t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:72f6c8b11857a856bcfa48c86f5368439f74453563f951e473514579d44aa612", size = 2053385, upload-time = "2025-11-04T13:41:35.508Z" }, + { url = "https://files.pythonhosted.org/packages/20/25/92dc684dd8eb75a234bc1c764b4210cf2646479d54b47bf46061657292a8/pydantic_core-2.41.5-cp314-cp314t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5cb1b2f9742240e4bb26b652a5aeb840aa4b417c7748b6f8387927bc6e45e40d", size = 2218832, upload-time = "2025-11-04T13:41:37.732Z" }, + { url = "https://files.pythonhosted.org/packages/e2/09/f53e0b05023d3e30357d82eb35835d0f6340ca344720a4599cd663dca599/pydantic_core-2.41.5-cp314-cp314t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bd3d54f38609ff308209bd43acea66061494157703364ae40c951f83ba99a1a9", size = 2327585, upload-time = "2025-11-04T13:41:40Z" }, + { url = "https://files.pythonhosted.org/packages/aa/4e/2ae1aa85d6af35a39b236b1b1641de73f5a6ac4d5a7509f77b814885760c/pydantic_core-2.41.5-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:2ff4321e56e879ee8d2a879501c8e469414d948f4aba74a2d4593184eb326660", size = 2041078, upload-time = "2025-11-04T13:41:42.323Z" }, + { url = "https://files.pythonhosted.org/packages/cd/13/2e215f17f0ef326fc72afe94776edb77525142c693767fc347ed6288728d/pydantic_core-2.41.5-cp314-cp314t-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d0d2568a8c11bf8225044aa94409e21da0cb09dcdafe9ecd10250b2baad531a9", size = 2173914, upload-time = "2025-11-04T13:41:45.221Z" }, + { url = "https://files.pythonhosted.org/packages/02/7a/f999a6dcbcd0e5660bc348a3991c8915ce6599f4f2c6ac22f01d7a10816c/pydantic_core-2.41.5-cp314-cp314t-musllinux_1_1_aarch64.whl", hash = "sha256:a39455728aabd58ceabb03c90e12f71fd30fa69615760a075b9fec596456ccc3", size = 2129560, upload-time = "2025-11-04T13:41:47.474Z" }, + { url = "https://files.pythonhosted.org/packages/3a/b1/6c990ac65e3b4c079a4fb9f5b05f5b013afa0f4ed6780a3dd236d2cbdc64/pydantic_core-2.41.5-cp314-cp314t-musllinux_1_1_armv7l.whl", hash = "sha256:239edca560d05757817c13dc17c50766136d21f7cd0fac50295499ae24f90fdf", size = 2329244, upload-time = "2025-11-04T13:41:49.992Z" }, + { url = "https://files.pythonhosted.org/packages/d9/02/3c562f3a51afd4d88fff8dffb1771b30cfdfd79befd9883ee094f5b6c0d8/pydantic_core-2.41.5-cp314-cp314t-musllinux_1_1_x86_64.whl", hash = "sha256:2a5e06546e19f24c6a96a129142a75cee553cc018ffee48a460059b1185f4470", size = 2331955, upload-time = "2025-11-04T13:41:54.079Z" }, + { url = "https://files.pythonhosted.org/packages/5c/96/5fb7d8c3c17bc8c62fdb031c47d77a1af698f1d7a406b0f79aaa1338f9ad/pydantic_core-2.41.5-cp314-cp314t-win32.whl", hash = "sha256:b4ececa40ac28afa90871c2cc2b9ffd2ff0bf749380fbdf57d165fd23da353aa", size = 1988906, upload-time = "2025-11-04T13:41:56.606Z" }, + { url = "https://files.pythonhosted.org/packages/22/ed/182129d83032702912c2e2d8bbe33c036f342cc735737064668585dac28f/pydantic_core-2.41.5-cp314-cp314t-win_amd64.whl", hash = "sha256:80aa89cad80b32a912a65332f64a4450ed00966111b6615ca6816153d3585a8c", size = 1981607, upload-time = "2025-11-04T13:41:58.889Z" }, + { url = "https://files.pythonhosted.org/packages/9f/ed/068e41660b832bb0b1aa5b58011dea2a3fe0ba7861ff38c4d4904c1c1a99/pydantic_core-2.41.5-cp314-cp314t-win_arm64.whl", hash = "sha256:35b44f37a3199f771c3eaa53051bc8a70cd7b54f333531c59e29fd4db5d15008", size = 1974769, upload-time = "2025-11-04T13:42:01.186Z" }, + { url = "https://files.pythonhosted.org/packages/09/32/59b0c7e63e277fa7911c2fc70ccfb45ce4b98991e7ef37110663437005af/pydantic_core-2.41.5-graalpy312-graalpy250_312_native-macosx_10_12_x86_64.whl", hash = "sha256:7da7087d756b19037bc2c06edc6c170eeef3c3bafcb8f532ff17d64dc427adfd", size = 2110495, upload-time = "2025-11-04T13:42:49.689Z" }, + { url = "https://files.pythonhosted.org/packages/aa/81/05e400037eaf55ad400bcd318c05bb345b57e708887f07ddb2d20e3f0e98/pydantic_core-2.41.5-graalpy312-graalpy250_312_native-macosx_11_0_arm64.whl", hash = "sha256:aabf5777b5c8ca26f7824cb4a120a740c9588ed58df9b2d196ce92fba42ff8dc", size = 1915388, upload-time = "2025-11-04T13:42:52.215Z" }, + { url = "https://files.pythonhosted.org/packages/6e/0d/e3549b2399f71d56476b77dbf3cf8937cec5cd70536bdc0e374a421d0599/pydantic_core-2.41.5-graalpy312-graalpy250_312_native-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:c007fe8a43d43b3969e8469004e9845944f1a80e6acd47c150856bb87f230c56", size = 1942879, upload-time = "2025-11-04T13:42:56.483Z" }, + { url = "https://files.pythonhosted.org/packages/f7/07/34573da085946b6a313d7c42f82f16e8920bfd730665de2d11c0c37a74b5/pydantic_core-2.41.5-graalpy312-graalpy250_312_native-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:76d0819de158cd855d1cbb8fcafdf6f5cf1eb8e470abe056d5d161106e38062b", size = 2139017, upload-time = "2025-11-04T13:42:59.471Z" }, +] + +[[package]] +name = "referencing" +version = "0.37.0" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "attrs" }, + { name = "rpds-py" }, + { name = "typing-extensions", marker = "python_full_version < '3.13'" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/22/f5/df4e9027acead3ecc63e50fe1e36aca1523e1719559c499951bb4b53188f/referencing-0.37.0.tar.gz", hash = "sha256:44aefc3142c5b842538163acb373e24cce6632bd54bdb01b21ad5863489f50d8", size = 78036, upload-time = "2025-10-13T15:30:48.871Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/2c/58/ca301544e1fa93ed4f80d724bf5b194f6e4b945841c5bfd555878eea9fcb/referencing-0.37.0-py3-none-any.whl", hash = "sha256:381329a9f99628c9069361716891d34ad94af76e461dcb0335825aecc7692231", size = 26766, upload-time = "2025-10-13T15:30:47.625Z" }, +] + +[[package]] +name = "requests" +version = "2.32.5" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "certifi" }, + { name = "charset-normalizer" }, + { name = "idna" }, + { name = "urllib3" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/c9/74/b3ff8e6c8446842c3f5c837e9c3dfcfe2018ea6ecef224c710c85ef728f4/requests-2.32.5.tar.gz", hash = "sha256:dbba0bac56e100853db0ea71b82b4dfd5fe2bf6d3754a8893c3af500cec7d7cf", size = 134517, upload-time = "2025-08-18T20:46:02.573Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/1e/db/4254e3eabe8020b458f1a747140d32277ec7a271daf1d235b70dc0b4e6e3/requests-2.32.5-py3-none-any.whl", hash = "sha256:2462f94637a34fd532264295e186976db0f5d453d1cdd31473c85a6a161affb6", size = 64738, upload-time = "2025-08-18T20:46:00.542Z" }, +] + +[[package]] +name = "rpds-py" +version = "0.28.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/48/dc/95f074d43452b3ef5d06276696ece4b3b5d696e7c9ad7173c54b1390cd70/rpds_py-0.28.0.tar.gz", hash = "sha256:abd4df20485a0983e2ca334a216249b6186d6e3c1627e106651943dbdb791aea", size = 27419, upload-time = "2025-10-22T22:24:29.327Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/b8/5c/6c3936495003875fe7b14f90ea812841a08fca50ab26bd840e924097d9c8/rpds_py-0.28.0-cp312-cp312-macosx_10_12_x86_64.whl", hash = "sha256:6b4f28583a4f247ff60cd7bdda83db8c3f5b05a7a82ff20dd4b078571747708f", size = 366439, upload-time = "2025-10-22T22:22:04.525Z" }, + { url = "https://files.pythonhosted.org/packages/56/f9/a0f1ca194c50aa29895b442771f036a25b6c41a35e4f35b1a0ea713bedae/rpds_py-0.28.0-cp312-cp312-macosx_11_0_arm64.whl", hash = "sha256:d678e91b610c29c4b3d52a2c148b641df2b4676ffe47c59f6388d58b99cdc424", size = 348170, upload-time = "2025-10-22T22:22:06.397Z" }, + { url = "https://files.pythonhosted.org/packages/18/ea/42d243d3a586beb72c77fa5def0487daf827210069a95f36328e869599ea/rpds_py-0.28.0-cp312-cp312-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e819e0e37a44a78e1383bf1970076e2ccc4dc8c2bbaa2f9bd1dc987e9afff628", size = 378838, upload-time = "2025-10-22T22:22:07.932Z" }, + { url = "https://files.pythonhosted.org/packages/e7/78/3de32e18a94791af8f33601402d9d4f39613136398658412a4e0b3047327/rpds_py-0.28.0-cp312-cp312-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:5ee514e0f0523db5d3fb171f397c54875dbbd69760a414dccf9d4d7ad628b5bd", size = 393299, upload-time = "2025-10-22T22:22:09.435Z" }, + { url = "https://files.pythonhosted.org/packages/13/7e/4bdb435afb18acea2eb8a25ad56b956f28de7c59f8a1d32827effa0d4514/rpds_py-0.28.0-cp312-cp312-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:5f3fa06d27fdcee47f07a39e02862da0100cb4982508f5ead53ec533cd5fe55e", size = 518000, upload-time = "2025-10-22T22:22:11.326Z" }, + { url = "https://files.pythonhosted.org/packages/31/d0/5f52a656875cdc60498ab035a7a0ac8f399890cc1ee73ebd567bac4e39ae/rpds_py-0.28.0-cp312-cp312-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:46959ef2e64f9e4a41fc89aa20dbca2b85531f9a72c21099a3360f35d10b0d5a", size = 408746, upload-time = "2025-10-22T22:22:13.143Z" }, + { url = "https://files.pythonhosted.org/packages/3e/cd/49ce51767b879cde77e7ad9fae164ea15dce3616fe591d9ea1df51152706/rpds_py-0.28.0-cp312-cp312-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8455933b4bcd6e83fde3fefc987a023389c4b13f9a58c8d23e4b3f6d13f78c84", size = 386379, upload-time = "2025-10-22T22:22:14.602Z" }, + { url = "https://files.pythonhosted.org/packages/6a/99/e4e1e1ee93a98f72fc450e36c0e4d99c35370220e815288e3ecd2ec36a2a/rpds_py-0.28.0-cp312-cp312-manylinux_2_31_riscv64.whl", hash = "sha256:ad50614a02c8c2962feebe6012b52f9802deec4263946cddea37aaf28dd25a66", size = 401280, upload-time = "2025-10-22T22:22:16.063Z" }, + { url = "https://files.pythonhosted.org/packages/61/35/e0c6a57488392a8b319d2200d03dad2b29c0db9996f5662c3b02d0b86c02/rpds_py-0.28.0-cp312-cp312-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:e5deca01b271492553fdb6c7fd974659dce736a15bae5dad7ab8b93555bceb28", size = 412365, upload-time = "2025-10-22T22:22:17.504Z" }, + { url = "https://files.pythonhosted.org/packages/ff/6a/841337980ea253ec797eb084665436007a1aad0faac1ba097fb906c5f69c/rpds_py-0.28.0-cp312-cp312-musllinux_1_2_aarch64.whl", hash = "sha256:735f8495a13159ce6a0d533f01e8674cec0c57038c920495f87dcb20b3ddb48a", size = 559573, upload-time = "2025-10-22T22:22:19.108Z" }, + { url = "https://files.pythonhosted.org/packages/e7/5e/64826ec58afd4c489731f8b00729c5f6afdb86f1df1df60bfede55d650bb/rpds_py-0.28.0-cp312-cp312-musllinux_1_2_i686.whl", hash = "sha256:961ca621ff10d198bbe6ba4957decca61aa2a0c56695384c1d6b79bf61436df5", size = 583973, upload-time = "2025-10-22T22:22:20.768Z" }, + { url = "https://files.pythonhosted.org/packages/b6/ee/44d024b4843f8386a4eeaa4c171b3d31d55f7177c415545fd1a24c249b5d/rpds_py-0.28.0-cp312-cp312-musllinux_1_2_x86_64.whl", hash = "sha256:2374e16cc9131022e7d9a8f8d65d261d9ba55048c78f3b6e017971a4f5e6353c", size = 553800, upload-time = "2025-10-22T22:22:22.25Z" }, + { url = "https://files.pythonhosted.org/packages/7d/89/33e675dccff11a06d4d85dbb4d1865f878d5020cbb69b2c1e7b2d3f82562/rpds_py-0.28.0-cp312-cp312-win32.whl", hash = "sha256:d15431e334fba488b081d47f30f091e5d03c18527c325386091f31718952fe08", size = 216954, upload-time = "2025-10-22T22:22:24.105Z" }, + { url = "https://files.pythonhosted.org/packages/af/36/45f6ebb3210887e8ee6dbf1bc710ae8400bb417ce165aaf3024b8360d999/rpds_py-0.28.0-cp312-cp312-win_amd64.whl", hash = "sha256:a410542d61fc54710f750d3764380b53bf09e8c4edbf2f9141a82aa774a04f7c", size = 227844, upload-time = "2025-10-22T22:22:25.551Z" }, + { url = "https://files.pythonhosted.org/packages/57/91/f3fb250d7e73de71080f9a221d19bd6a1c1eb0d12a1ea26513f6c1052ad6/rpds_py-0.28.0-cp312-cp312-win_arm64.whl", hash = "sha256:1f0cfd1c69e2d14f8c892b893997fa9a60d890a0c8a603e88dca4955f26d1edd", size = 217624, upload-time = "2025-10-22T22:22:26.914Z" }, + { url = "https://files.pythonhosted.org/packages/d3/03/ce566d92611dfac0085c2f4b048cd53ed7c274a5c05974b882a908d540a2/rpds_py-0.28.0-cp313-cp313-macosx_10_12_x86_64.whl", hash = "sha256:e9e184408a0297086f880556b6168fa927d677716f83d3472ea333b42171ee3b", size = 366235, upload-time = "2025-10-22T22:22:28.397Z" }, + { url = "https://files.pythonhosted.org/packages/00/34/1c61da1b25592b86fd285bd7bd8422f4c9d748a7373b46126f9ae792a004/rpds_py-0.28.0-cp313-cp313-macosx_11_0_arm64.whl", hash = "sha256:edd267266a9b0448f33dc465a97cfc5d467594b600fe28e7fa2f36450e03053a", size = 348241, upload-time = "2025-10-22T22:22:30.171Z" }, + { url = "https://files.pythonhosted.org/packages/fc/00/ed1e28616848c61c493a067779633ebf4b569eccaacf9ccbdc0e7cba2b9d/rpds_py-0.28.0-cp313-cp313-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:85beb8b3f45e4e32f6802fb6cd6b17f615ef6c6a52f265371fb916fae02814aa", size = 378079, upload-time = "2025-10-22T22:22:31.644Z" }, + { url = "https://files.pythonhosted.org/packages/11/b2/ccb30333a16a470091b6e50289adb4d3ec656fd9951ba8c5e3aaa0746a67/rpds_py-0.28.0-cp313-cp313-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:d2412be8d00a1b895f8ad827cc2116455196e20ed994bb704bf138fe91a42724", size = 393151, upload-time = "2025-10-22T22:22:33.453Z" }, + { url = "https://files.pythonhosted.org/packages/8c/d0/73e2217c3ee486d555cb84920597480627d8c0240ff3062005c6cc47773e/rpds_py-0.28.0-cp313-cp313-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:cf128350d384b777da0e68796afdcebc2e9f63f0e9f242217754e647f6d32491", size = 517520, upload-time = "2025-10-22T22:22:34.949Z" }, + { url = "https://files.pythonhosted.org/packages/c4/91/23efe81c700427d0841a4ae7ea23e305654381831e6029499fe80be8a071/rpds_py-0.28.0-cp313-cp313-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:a2036d09b363aa36695d1cc1a97b36865597f4478470b0697b5ee9403f4fe399", size = 408699, upload-time = "2025-10-22T22:22:36.584Z" }, + { url = "https://files.pythonhosted.org/packages/ca/ee/a324d3198da151820a326c1f988caaa4f37fc27955148a76fff7a2d787a9/rpds_py-0.28.0-cp313-cp313-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:b8e1e9be4fa6305a16be628959188e4fd5cd6f1b0e724d63c6d8b2a8adf74ea6", size = 385720, upload-time = "2025-10-22T22:22:38.014Z" }, + { url = "https://files.pythonhosted.org/packages/19/ad/e68120dc05af8b7cab4a789fccd8cdcf0fe7e6581461038cc5c164cd97d2/rpds_py-0.28.0-cp313-cp313-manylinux_2_31_riscv64.whl", hash = "sha256:0a403460c9dd91a7f23fc3188de6d8977f1d9603a351d5db6cf20aaea95b538d", size = 401096, upload-time = "2025-10-22T22:22:39.869Z" }, + { url = "https://files.pythonhosted.org/packages/99/90/c1e070620042459d60df6356b666bb1f62198a89d68881816a7ed121595a/rpds_py-0.28.0-cp313-cp313-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:d7366b6553cdc805abcc512b849a519167db8f5e5c3472010cd1228b224265cb", size = 411465, upload-time = "2025-10-22T22:22:41.395Z" }, + { url = "https://files.pythonhosted.org/packages/68/61/7c195b30d57f1b8d5970f600efee72a4fad79ec829057972e13a0370fd24/rpds_py-0.28.0-cp313-cp313-musllinux_1_2_aarch64.whl", hash = "sha256:5b43c6a3726efd50f18d8120ec0551241c38785b68952d240c45ea553912ac41", size = 558832, upload-time = "2025-10-22T22:22:42.871Z" }, + { url = "https://files.pythonhosted.org/packages/b0/3d/06f3a718864773f69941d4deccdf18e5e47dd298b4628062f004c10f3b34/rpds_py-0.28.0-cp313-cp313-musllinux_1_2_i686.whl", hash = "sha256:0cb7203c7bc69d7c1585ebb33a2e6074492d2fc21ad28a7b9d40457ac2a51ab7", size = 583230, upload-time = "2025-10-22T22:22:44.877Z" }, + { url = "https://files.pythonhosted.org/packages/66/df/62fc783781a121e77fee9a21ead0a926f1b652280a33f5956a5e7833ed30/rpds_py-0.28.0-cp313-cp313-musllinux_1_2_x86_64.whl", hash = "sha256:7a52a5169c664dfb495882adc75c304ae1d50df552fbd68e100fdc719dee4ff9", size = 553268, upload-time = "2025-10-22T22:22:46.441Z" }, + { url = "https://files.pythonhosted.org/packages/84/85/d34366e335140a4837902d3dea89b51f087bd6a63c993ebdff59e93ee61d/rpds_py-0.28.0-cp313-cp313-win32.whl", hash = "sha256:2e42456917b6687215b3e606ab46aa6bca040c77af7df9a08a6dcfe8a4d10ca5", size = 217100, upload-time = "2025-10-22T22:22:48.342Z" }, + { url = "https://files.pythonhosted.org/packages/3c/1c/f25a3f3752ad7601476e3eff395fe075e0f7813fbb9862bd67c82440e880/rpds_py-0.28.0-cp313-cp313-win_amd64.whl", hash = "sha256:e0a0311caedc8069d68fc2bf4c9019b58a2d5ce3cd7cb656c845f1615b577e1e", size = 227759, upload-time = "2025-10-22T22:22:50.219Z" }, + { url = "https://files.pythonhosted.org/packages/e0/d6/5f39b42b99615b5bc2f36ab90423ea404830bdfee1c706820943e9a645eb/rpds_py-0.28.0-cp313-cp313-win_arm64.whl", hash = "sha256:04c1b207ab8b581108801528d59ad80aa83bb170b35b0ddffb29c20e411acdc1", size = 217326, upload-time = "2025-10-22T22:22:51.647Z" }, + { url = "https://files.pythonhosted.org/packages/5c/8b/0c69b72d1cee20a63db534be0df271effe715ef6c744fdf1ff23bb2b0b1c/rpds_py-0.28.0-cp313-cp313t-macosx_10_12_x86_64.whl", hash = "sha256:f296ea3054e11fc58ad42e850e8b75c62d9a93a9f981ad04b2e5ae7d2186ff9c", size = 355736, upload-time = "2025-10-22T22:22:53.211Z" }, + { url = "https://files.pythonhosted.org/packages/f7/6d/0c2ee773cfb55c31a8514d2cece856dd299170a49babd50dcffb15ddc749/rpds_py-0.28.0-cp313-cp313t-macosx_11_0_arm64.whl", hash = "sha256:5a7306c19b19005ad98468fcefeb7100b19c79fc23a5f24a12e06d91181193fa", size = 342677, upload-time = "2025-10-22T22:22:54.723Z" }, + { url = "https://files.pythonhosted.org/packages/e2/1c/22513ab25a27ea205144414724743e305e8153e6abe81833b5e678650f5a/rpds_py-0.28.0-cp313-cp313t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:e5d9b86aa501fed9862a443c5c3116f6ead8bc9296185f369277c42542bd646b", size = 371847, upload-time = "2025-10-22T22:22:56.295Z" }, + { url = "https://files.pythonhosted.org/packages/60/07/68e6ccdb4b05115ffe61d31afc94adef1833d3a72f76c9632d4d90d67954/rpds_py-0.28.0-cp313-cp313t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e5bbc701eff140ba0e872691d573b3d5d30059ea26e5785acba9132d10c8c31d", size = 381800, upload-time = "2025-10-22T22:22:57.808Z" }, + { url = "https://files.pythonhosted.org/packages/73/bf/6d6d15df80781d7f9f368e7c1a00caf764436518c4877fb28b029c4624af/rpds_py-0.28.0-cp313-cp313t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:9a5690671cd672a45aa8616d7374fdf334a1b9c04a0cac3c854b1136e92374fe", size = 518827, upload-time = "2025-10-22T22:22:59.826Z" }, + { url = "https://files.pythonhosted.org/packages/7b/d3/2decbb2976cc452cbf12a2b0aaac5f1b9dc5dd9d1f7e2509a3ee00421249/rpds_py-0.28.0-cp313-cp313t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:9f1d92ecea4fa12f978a367c32a5375a1982834649cdb96539dcdc12e609ab1a", size = 399471, upload-time = "2025-10-22T22:23:01.968Z" }, + { url = "https://files.pythonhosted.org/packages/b1/2c/f30892f9e54bd02e5faca3f6a26d6933c51055e67d54818af90abed9748e/rpds_py-0.28.0-cp313-cp313t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:8d252db6b1a78d0a3928b6190156042d54c93660ce4d98290d7b16b5296fb7cc", size = 377578, upload-time = "2025-10-22T22:23:03.52Z" }, + { url = "https://files.pythonhosted.org/packages/f0/5d/3bce97e5534157318f29ac06bf2d279dae2674ec12f7cb9c12739cee64d8/rpds_py-0.28.0-cp313-cp313t-manylinux_2_31_riscv64.whl", hash = "sha256:d61b355c3275acb825f8777d6c4505f42b5007e357af500939d4a35b19177259", size = 390482, upload-time = "2025-10-22T22:23:05.391Z" }, + { url = "https://files.pythonhosted.org/packages/e3/f0/886bd515ed457b5bd93b166175edb80a0b21a210c10e993392127f1e3931/rpds_py-0.28.0-cp313-cp313t-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:acbe5e8b1026c0c580d0321c8aae4b0a1e1676861d48d6e8c6586625055b606a", size = 402447, upload-time = "2025-10-22T22:23:06.93Z" }, + { url = "https://files.pythonhosted.org/packages/42/b5/71e8777ac55e6af1f4f1c05b47542a1eaa6c33c1cf0d300dca6a1c6e159a/rpds_py-0.28.0-cp313-cp313t-musllinux_1_2_aarch64.whl", hash = "sha256:8aa23b6f0fc59b85b4c7d89ba2965af274346f738e8d9fc2455763602e62fd5f", size = 552385, upload-time = "2025-10-22T22:23:08.557Z" }, + { url = "https://files.pythonhosted.org/packages/5d/cb/6ca2d70cbda5a8e36605e7788c4aa3bea7c17d71d213465a5a675079b98d/rpds_py-0.28.0-cp313-cp313t-musllinux_1_2_i686.whl", hash = "sha256:7b14b0c680286958817c22d76fcbca4800ddacef6f678f3a7c79a1fe7067fe37", size = 575642, upload-time = "2025-10-22T22:23:10.348Z" }, + { url = "https://files.pythonhosted.org/packages/4a/d4/407ad9960ca7856d7b25c96dcbe019270b5ffdd83a561787bc682c797086/rpds_py-0.28.0-cp313-cp313t-musllinux_1_2_x86_64.whl", hash = "sha256:bcf1d210dfee61a6c86551d67ee1031899c0fdbae88b2d44a569995d43797712", size = 544507, upload-time = "2025-10-22T22:23:12.434Z" }, + { url = "https://files.pythonhosted.org/packages/51/31/2f46fe0efcac23fbf5797c6b6b7e1c76f7d60773e525cb65fcbc582ee0f2/rpds_py-0.28.0-cp313-cp313t-win32.whl", hash = "sha256:3aa4dc0fdab4a7029ac63959a3ccf4ed605fee048ba67ce89ca3168da34a1342", size = 205376, upload-time = "2025-10-22T22:23:13.979Z" }, + { url = "https://files.pythonhosted.org/packages/92/e4/15947bda33cbedfc134490a41841ab8870a72a867a03d4969d886f6594a2/rpds_py-0.28.0-cp313-cp313t-win_amd64.whl", hash = "sha256:7b7d9d83c942855e4fdcfa75d4f96f6b9e272d42fffcb72cd4bb2577db2e2907", size = 215907, upload-time = "2025-10-22T22:23:15.5Z" }, + { url = "https://files.pythonhosted.org/packages/08/47/ffe8cd7a6a02833b10623bf765fbb57ce977e9a4318ca0e8cf97e9c3d2b3/rpds_py-0.28.0-cp314-cp314-macosx_10_12_x86_64.whl", hash = "sha256:dcdcb890b3ada98a03f9f2bb108489cdc7580176cb73b4f2d789e9a1dac1d472", size = 353830, upload-time = "2025-10-22T22:23:17.03Z" }, + { url = "https://files.pythonhosted.org/packages/f9/9f/890f36cbd83a58491d0d91ae0db1702639edb33fb48eeb356f80ecc6b000/rpds_py-0.28.0-cp314-cp314-macosx_11_0_arm64.whl", hash = "sha256:f274f56a926ba2dc02976ca5b11c32855cbd5925534e57cfe1fda64e04d1add2", size = 341819, upload-time = "2025-10-22T22:23:18.57Z" }, + { url = "https://files.pythonhosted.org/packages/09/e3/921eb109f682aa24fb76207698fbbcf9418738f35a40c21652c29053f23d/rpds_py-0.28.0-cp314-cp314-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:4fe0438ac4a29a520ea94c8c7f1754cdd8feb1bc490dfda1bfd990072363d527", size = 373127, upload-time = "2025-10-22T22:23:20.216Z" }, + { url = "https://files.pythonhosted.org/packages/23/13/bce4384d9f8f4989f1a9599c71b7a2d877462e5fd7175e1f69b398f729f4/rpds_py-0.28.0-cp314-cp314-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:8a358a32dd3ae50e933347889b6af9a1bdf207ba5d1a3f34e1a38cd3540e6733", size = 382767, upload-time = "2025-10-22T22:23:21.787Z" }, + { url = "https://files.pythonhosted.org/packages/23/e1/579512b2d89a77c64ccef5a0bc46a6ef7f72ae0cf03d4b26dcd52e57ee0a/rpds_py-0.28.0-cp314-cp314-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e80848a71c78aa328fefaba9c244d588a342c8e03bda518447b624ea64d1ff56", size = 517585, upload-time = "2025-10-22T22:23:23.699Z" }, + { url = "https://files.pythonhosted.org/packages/62/3c/ca704b8d324a2591b0b0adcfcaadf9c862375b11f2f667ac03c61b4fd0a6/rpds_py-0.28.0-cp314-cp314-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:f586db2e209d54fe177e58e0bc4946bea5fb0102f150b1b2f13de03e1f0976f8", size = 399828, upload-time = "2025-10-22T22:23:25.713Z" }, + { url = "https://files.pythonhosted.org/packages/da/37/e84283b9e897e3adc46b4c88bb3f6ec92a43bd4d2f7ef5b13459963b2e9c/rpds_py-0.28.0-cp314-cp314-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:5ae8ee156d6b586e4292491e885d41483136ab994e719a13458055bec14cf370", size = 375509, upload-time = "2025-10-22T22:23:27.32Z" }, + { url = "https://files.pythonhosted.org/packages/1a/c2/a980beab869d86258bf76ec42dec778ba98151f253a952b02fe36d72b29c/rpds_py-0.28.0-cp314-cp314-manylinux_2_31_riscv64.whl", hash = "sha256:a805e9b3973f7e27f7cab63a6b4f61d90f2e5557cff73b6e97cd5b8540276d3d", size = 392014, upload-time = "2025-10-22T22:23:29.332Z" }, + { url = "https://files.pythonhosted.org/packages/da/b5/b1d3c5f9d3fa5aeef74265f9c64de3c34a0d6d5cd3c81c8b17d5c8f10ed4/rpds_py-0.28.0-cp314-cp314-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:5d3fd16b6dc89c73a4da0b4ac8b12a7ecc75b2864b95c9e5afed8003cb50a728", size = 402410, upload-time = "2025-10-22T22:23:31.14Z" }, + { url = "https://files.pythonhosted.org/packages/74/ae/cab05ff08dfcc052afc73dcb38cbc765ffc86f94e966f3924cd17492293c/rpds_py-0.28.0-cp314-cp314-musllinux_1_2_aarch64.whl", hash = "sha256:6796079e5d24fdaba6d49bda28e2c47347e89834678f2bc2c1b4fc1489c0fb01", size = 553593, upload-time = "2025-10-22T22:23:32.834Z" }, + { url = "https://files.pythonhosted.org/packages/70/80/50d5706ea2a9bfc9e9c5f401d91879e7c790c619969369800cde202da214/rpds_py-0.28.0-cp314-cp314-musllinux_1_2_i686.whl", hash = "sha256:76500820c2af232435cbe215e3324c75b950a027134e044423f59f5b9a1ba515", size = 576925, upload-time = "2025-10-22T22:23:34.47Z" }, + { url = "https://files.pythonhosted.org/packages/ab/12/85a57d7a5855a3b188d024b099fd09c90db55d32a03626d0ed16352413ff/rpds_py-0.28.0-cp314-cp314-musllinux_1_2_x86_64.whl", hash = "sha256:bbdc5640900a7dbf9dd707fe6388972f5bbd883633eb68b76591044cfe346f7e", size = 542444, upload-time = "2025-10-22T22:23:36.093Z" }, + { url = "https://files.pythonhosted.org/packages/6c/65/10643fb50179509150eb94d558e8837c57ca8b9adc04bd07b98e57b48f8c/rpds_py-0.28.0-cp314-cp314-win32.whl", hash = "sha256:adc8aa88486857d2b35d75f0640b949759f79dc105f50aa2c27816b2e0dd749f", size = 207968, upload-time = "2025-10-22T22:23:37.638Z" }, + { url = "https://files.pythonhosted.org/packages/b4/84/0c11fe4d9aaea784ff4652499e365963222481ac647bcd0251c88af646eb/rpds_py-0.28.0-cp314-cp314-win_amd64.whl", hash = "sha256:66e6fa8e075b58946e76a78e69e1a124a21d9a48a5b4766d15ba5b06869d1fa1", size = 218876, upload-time = "2025-10-22T22:23:39.179Z" }, + { url = "https://files.pythonhosted.org/packages/0f/e0/3ab3b86ded7bb18478392dc3e835f7b754cd446f62f3fc96f4fe2aca78f6/rpds_py-0.28.0-cp314-cp314-win_arm64.whl", hash = "sha256:a6fe887c2c5c59413353b7c0caff25d0e566623501ccfff88957fa438a69377d", size = 212506, upload-time = "2025-10-22T22:23:40.755Z" }, + { url = "https://files.pythonhosted.org/packages/51/ec/d5681bb425226c3501eab50fc30e9d275de20c131869322c8a1729c7b61c/rpds_py-0.28.0-cp314-cp314t-macosx_10_12_x86_64.whl", hash = "sha256:7a69df082db13c7070f7b8b1f155fa9e687f1d6aefb7b0e3f7231653b79a067b", size = 355433, upload-time = "2025-10-22T22:23:42.259Z" }, + { url = "https://files.pythonhosted.org/packages/be/ec/568c5e689e1cfb1ea8b875cffea3649260955f677fdd7ddc6176902d04cd/rpds_py-0.28.0-cp314-cp314t-macosx_11_0_arm64.whl", hash = "sha256:b1cde22f2c30ebb049a9e74c5374994157b9b70a16147d332f89c99c5960737a", size = 342601, upload-time = "2025-10-22T22:23:44.372Z" }, + { url = "https://files.pythonhosted.org/packages/32/fe/51ada84d1d2a1d9d8f2c902cfddd0133b4a5eb543196ab5161d1c07ed2ad/rpds_py-0.28.0-cp314-cp314t-manylinux_2_17_aarch64.manylinux2014_aarch64.whl", hash = "sha256:5338742f6ba7a51012ea470bd4dc600a8c713c0c72adaa0977a1b1f4327d6592", size = 372039, upload-time = "2025-10-22T22:23:46.025Z" }, + { url = "https://files.pythonhosted.org/packages/07/c1/60144a2f2620abade1a78e0d91b298ac2d9b91bc08864493fa00451ef06e/rpds_py-0.28.0-cp314-cp314t-manylinux_2_17_armv7l.manylinux2014_armv7l.whl", hash = "sha256:e1460ebde1bcf6d496d80b191d854adedcc619f84ff17dc1c6d550f58c9efbba", size = 382407, upload-time = "2025-10-22T22:23:48.098Z" }, + { url = "https://files.pythonhosted.org/packages/45/ed/091a7bbdcf4038a60a461df50bc4c82a7ed6d5d5e27649aab61771c17585/rpds_py-0.28.0-cp314-cp314t-manylinux_2_17_ppc64le.manylinux2014_ppc64le.whl", hash = "sha256:e3eb248f2feba84c692579257a043a7699e28a77d86c77b032c1d9fbb3f0219c", size = 518172, upload-time = "2025-10-22T22:23:50.16Z" }, + { url = "https://files.pythonhosted.org/packages/54/dd/02cc90c2fd9c2ef8016fd7813bfacd1c3a1325633ec8f244c47b449fc868/rpds_py-0.28.0-cp314-cp314t-manylinux_2_17_s390x.manylinux2014_s390x.whl", hash = "sha256:bd3bbba5def70b16cd1c1d7255666aad3b290fbf8d0fe7f9f91abafb73611a91", size = 399020, upload-time = "2025-10-22T22:23:51.81Z" }, + { url = "https://files.pythonhosted.org/packages/ab/81/5d98cc0329bbb911ccecd0b9e19fbf7f3a5de8094b4cda5e71013b2dd77e/rpds_py-0.28.0-cp314-cp314t-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3114f4db69ac5a1f32e7e4d1cbbe7c8f9cf8217f78e6e002cedf2d54c2a548ed", size = 377451, upload-time = "2025-10-22T22:23:53.711Z" }, + { url = "https://files.pythonhosted.org/packages/b4/07/4d5bcd49e3dfed2d38e2dcb49ab6615f2ceb9f89f5a372c46dbdebb4e028/rpds_py-0.28.0-cp314-cp314t-manylinux_2_31_riscv64.whl", hash = "sha256:4b0cb8a906b1a0196b863d460c0222fb8ad0f34041568da5620f9799b83ccf0b", size = 390355, upload-time = "2025-10-22T22:23:55.299Z" }, + { url = "https://files.pythonhosted.org/packages/3f/79/9f14ba9010fee74e4f40bf578735cfcbb91d2e642ffd1abe429bb0b96364/rpds_py-0.28.0-cp314-cp314t-manylinux_2_5_i686.manylinux1_i686.whl", hash = "sha256:cf681ac76a60b667106141e11a92a3330890257e6f559ca995fbb5265160b56e", size = 403146, upload-time = "2025-10-22T22:23:56.929Z" }, + { url = "https://files.pythonhosted.org/packages/39/4c/f08283a82ac141331a83a40652830edd3a4a92c34e07e2bbe00baaea2f5f/rpds_py-0.28.0-cp314-cp314t-musllinux_1_2_aarch64.whl", hash = "sha256:1e8ee6413cfc677ce8898d9cde18cc3a60fc2ba756b0dec5b71eb6eb21c49fa1", size = 552656, upload-time = "2025-10-22T22:23:58.62Z" }, + { url = "https://files.pythonhosted.org/packages/61/47/d922fc0666f0dd8e40c33990d055f4cc6ecff6f502c2d01569dbed830f9b/rpds_py-0.28.0-cp314-cp314t-musllinux_1_2_i686.whl", hash = "sha256:b3072b16904d0b5572a15eb9d31c1954e0d3227a585fc1351aa9878729099d6c", size = 576782, upload-time = "2025-10-22T22:24:00.312Z" }, + { url = "https://files.pythonhosted.org/packages/d3/0c/5bafdd8ccf6aa9d3bfc630cfece457ff5b581af24f46a9f3590f790e3df2/rpds_py-0.28.0-cp314-cp314t-musllinux_1_2_x86_64.whl", hash = "sha256:b670c30fd87a6aec281c3c9896d3bae4b205fd75d79d06dc87c2503717e46092", size = 544671, upload-time = "2025-10-22T22:24:02.297Z" }, + { url = "https://files.pythonhosted.org/packages/2c/37/dcc5d8397caa924988693519069d0beea077a866128719351a4ad95e82fc/rpds_py-0.28.0-cp314-cp314t-win32.whl", hash = "sha256:8014045a15b4d2b3476f0a287fcc93d4f823472d7d1308d47884ecac9e612be3", size = 205749, upload-time = "2025-10-22T22:24:03.848Z" }, + { url = "https://files.pythonhosted.org/packages/d7/69/64d43b21a10d72b45939a28961216baeb721cc2a430f5f7c3bfa21659a53/rpds_py-0.28.0-cp314-cp314t-win_amd64.whl", hash = "sha256:7a4e59c90d9c27c561eb3160323634a9ff50b04e4f7820600a2beb0ac90db578", size = 216233, upload-time = "2025-10-22T22:24:05.471Z" }, +] + +[[package]] +name = "typing-extensions" +version = "4.15.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/72/94/1a15dd82efb362ac84269196e94cf00f187f7ed21c242792a923cdb1c61f/typing_extensions-4.15.0.tar.gz", hash = "sha256:0cea48d173cc12fa28ecabc3b837ea3cf6f38c6d1136f85cbaaf598984861466", size = 109391, upload-time = "2025-08-25T13:49:26.313Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/18/67/36e9267722cc04a6b9f15c7f3441c2363321a3ea07da7ae0c0707beb2a9c/typing_extensions-4.15.0-py3-none-any.whl", hash = "sha256:f0fa19c6845758ab08074a0cfa8b7aecb71c999ca73d62883bc25cc018c4e548", size = 44614, upload-time = "2025-08-25T13:49:24.86Z" }, +] + +[[package]] +name = "typing-inspection" +version = "0.4.2" +source = { registry = "https://pypi.org/simple" } +dependencies = [ + { name = "typing-extensions" }, +] +sdist = { url = "https://files.pythonhosted.org/packages/55/e3/70399cb7dd41c10ac53367ae42139cf4b1ca5f36bb3dc6c9d33acdb43655/typing_inspection-0.4.2.tar.gz", hash = "sha256:ba561c48a67c5958007083d386c3295464928b01faa735ab8547c5692e87f464", size = 75949, upload-time = "2025-10-01T02:14:41.687Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/dc/9b/47798a6c91d8bdb567fe2698fe81e0c6b7cb7ef4d13da4114b41d239f65d/typing_inspection-0.4.2-py3-none-any.whl", hash = "sha256:4ed1cacbdc298c220f1bd249ed5287caa16f34d44ef4e9c3d0cbad5b521545e7", size = 14611, upload-time = "2025-10-01T02:14:40.154Z" }, +] + +[[package]] +name = "urllib3" +version = "2.5.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/15/22/9ee70a2574a4f4599c47dd506532914ce044817c7752a79b6a51286319bc/urllib3-2.5.0.tar.gz", hash = "sha256:3fc47733c7e419d4bc3f6b3dc2b4f890bb743906a30d56ba4a5bfa4bbff92760", size = 393185, upload-time = "2025-06-18T14:07:41.644Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/a7/c2/fe1e52489ae3122415c51f387e221dd0773709bad6c6cdaa599e8a2c5185/urllib3-2.5.0-py3-none-any.whl", hash = "sha256:e6b01673c0fa6a13e374b50871808eb3bf7046c4b125b216f6bf1cc604cff0dc", size = 129795, upload-time = "2025-06-18T14:07:40.39Z" }, +] + +[[package]] +name = "zipp" +version = "3.23.0" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/e3/02/0f2892c661036d50ede074e376733dca2ae7c6eb617489437771209d4180/zipp-3.23.0.tar.gz", hash = "sha256:a07157588a12518c9d4034df3fbbee09c814741a33ff63c05fa29d26a2404166", size = 25547, upload-time = "2025-06-08T17:06:39.4Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/2e/54/647ade08bf0db230bfea292f893923872fd20be6ac6f53b2b936ba839d75/zipp-3.23.0-py3-none-any.whl", hash = "sha256:071652d6115ed432f5ce1d34c336c0adfd6a884660d1e9712a256d3d3bd4b14e", size = 10276, upload-time = "2025-06-08T17:06:38.034Z" }, +] diff --git a/src/llama_stack/apis/vector_io/vector_io.py b/src/llama_stack_api/vector_io.py similarity index 98% rename from src/llama_stack/apis/vector_io/vector_io.py rename to src/llama_stack_api/vector_io.py index 699241128..053e569f4 100644 --- a/src/llama_stack/apis/vector_io/vector_io.py +++ b/src/llama_stack_api/vector_io.py @@ -13,12 +13,12 @@ from typing import Annotated, Any, Literal, Protocol, runtime_checkable from fastapi import Body, Query from pydantic import BaseModel, Field -from llama_stack.apis.common.tracing import telemetry_traceable -from llama_stack.apis.inference import InterleavedContent -from llama_stack.apis.vector_stores import VectorStore -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.schema_utils import json_schema_type, webmethod -from llama_stack.strong_typing.schema import register_schema +from llama_stack_api.common.tracing import telemetry_traceable +from llama_stack_api.inference import InterleavedContent +from llama_stack_api.schema_utils import json_schema_type, webmethod +from llama_stack_api.strong_typing.schema import register_schema +from llama_stack_api.vector_stores import VectorStore +from llama_stack_api.version import LLAMA_STACK_API_V1 @json_schema_type diff --git a/src/llama_stack/apis/vector_stores/vector_stores.py b/src/llama_stack_api/vector_stores.py similarity index 96% rename from src/llama_stack/apis/vector_stores/vector_stores.py rename to src/llama_stack_api/vector_stores.py index 524624028..0a1e6c53c 100644 --- a/src/llama_stack/apis/vector_stores/vector_stores.py +++ b/src/llama_stack_api/vector_stores.py @@ -8,7 +8,7 @@ from typing import Literal from pydantic import BaseModel -from llama_stack.apis.resource import Resource, ResourceType +from llama_stack_api.resource import Resource, ResourceType # Internal resource type for storing the vector store routing and other information diff --git a/src/llama_stack/apis/version.py b/src/llama_stack_api/version.py similarity index 100% rename from src/llama_stack/apis/version.py rename to src/llama_stack_api/version.py diff --git a/tests/common/mcp.py b/tests/common/mcp.py index 644becd2d..085575ec0 100644 --- a/tests/common/mcp.py +++ b/tests/common/mcp.py @@ -244,8 +244,14 @@ def make_mcp_server(required_auth_token: str | None = None, tools: dict[str, Cal timeout = 2 start_time = time.time() - server_url = f"http://localhost:{port}/sse" - logger.debug(f"Waiting for MCP server thread to start on port {port}") + # Determine the appropriate host for the server URL based on test environment + # - For library client and server mode: use localhost (both on same host) + # - For docker mode: use host.docker.internal (container needs to reach host) + import os + + mcp_host = os.environ.get("LLAMA_STACK_TEST_MCP_HOST", "localhost") + server_url = f"http://{mcp_host}:{port}/sse" + logger.debug(f"Waiting for MCP server thread to start on port {port} (accessible via {mcp_host})") while time.time() - start_time < timeout: if server_thread.is_alive(): diff --git a/tests/external/llama-stack-api-weather/src/llama_stack_api_weather/weather.py b/tests/external/llama-stack-api-weather/src/llama_stack_api_weather/weather.py index e97a9d8fb..9c399b7bf 100644 --- a/tests/external/llama-stack-api-weather/src/llama_stack_api_weather/weather.py +++ b/tests/external/llama-stack-api-weather/src/llama_stack_api_weather/weather.py @@ -6,9 +6,7 @@ from typing import Protocol -from llama_stack.apis.version import LLAMA_STACK_API_V1 -from llama_stack.providers.datatypes import Api, ProviderSpec, RemoteProviderSpec -from llama_stack.schema_utils import webmethod +from llama_stack_api import LLAMA_STACK_API_V1, Api, ProviderSpec, RemoteProviderSpec, webmethod def available_providers() -> list[ProviderSpec]: diff --git a/tests/integration/batches/conftest.py b/tests/integration/batches/conftest.py index 3ab8df3d9..4dc5b7993 100644 --- a/tests/integration/batches/conftest.py +++ b/tests/integration/batches/conftest.py @@ -14,7 +14,7 @@ from io import BytesIO import pytest -from llama_stack.apis.files import OpenAIFilePurpose +from llama_stack_api import OpenAIFilePurpose class BatchHelper: diff --git a/tests/integration/files/test_files.py b/tests/integration/files/test_files.py index d9e8dd501..1f19c88c5 100644 --- a/tests/integration/files/test_files.py +++ b/tests/integration/files/test_files.py @@ -10,8 +10,8 @@ from unittest.mock import patch import pytest import requests -from llama_stack.apis.files import OpenAIFilePurpose from llama_stack.core.datatypes import User +from llama_stack_api import OpenAIFilePurpose purpose = OpenAIFilePurpose.ASSISTANTS diff --git a/tests/integration/inference/test_provider_data_routing.py b/tests/integration/inference/test_provider_data_routing.py index 99aa75395..e4a0a24b5 100644 --- a/tests/integration/inference/test_provider_data_routing.py +++ b/tests/integration/inference/test_provider_data_routing.py @@ -16,15 +16,15 @@ from unittest.mock import AsyncMock, patch import pytest -from llama_stack.apis.datatypes import Api -from llama_stack.apis.inference.inference import ( +from llama_stack.core.library_client import LlamaStackAsLibraryClient +from llama_stack.core.telemetry.telemetry import MetricEvent +from llama_stack_api import ( + Api, OpenAIAssistantMessageParam, OpenAIChatCompletion, OpenAIChatCompletionUsage, OpenAIChoice, ) -from llama_stack.core.library_client import LlamaStackAsLibraryClient -from llama_stack.core.telemetry.telemetry import MetricEvent class OpenAIChatCompletionWithMetrics(OpenAIChatCompletion): diff --git a/tests/integration/inference/test_tools_with_schemas.py b/tests/integration/inference/test_tools_with_schemas.py index f30e9ece5..5b6e69ae3 100644 --- a/tests/integration/inference/test_tools_with_schemas.py +++ b/tests/integration/inference/test_tools_with_schemas.py @@ -193,7 +193,14 @@ class TestMCPToolsInChatCompletion: mcp_endpoint=dict(uri=uri), ) - provider_data = {"mcp_headers": {uri: {"Authorization": f"Bearer {AUTH_TOKEN}"}}} + # Use old header-based approach for Phase 1 (backward compatibility) + provider_data = { + "mcp_headers": { + uri: { + "Authorization": f"Bearer {AUTH_TOKEN}", + }, + }, + } auth_headers = { "X-LlamaStack-Provider-Data": json.dumps(provider_data), } diff --git a/tests/integration/post_training/test_post_training.py b/tests/integration/post_training/test_post_training.py index b5be71c7c..e6868019a 100644 --- a/tests/integration/post_training/test_post_training.py +++ b/tests/integration/post_training/test_post_training.py @@ -10,7 +10,8 @@ import uuid import pytest -from llama_stack.apis.post_training import ( +from llama_stack.log import get_logger +from llama_stack_api import ( DataConfig, DatasetFormat, DPOAlignmentConfig, @@ -18,7 +19,6 @@ from llama_stack.apis.post_training import ( LoraFinetuningConfig, TrainingConfig, ) -from llama_stack.log import get_logger # Configure logging logger = get_logger(name=__name__, category="post_training") diff --git a/tests/integration/responses/conftest.py b/tests/integration/responses/conftest.py new file mode 100644 index 000000000..c29575072 --- /dev/null +++ b/tests/integration/responses/conftest.py @@ -0,0 +1,17 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the terms described in the LICENSE file in +# the root directory of this source tree. + +import pytest + +from llama_stack.core.library_client import LlamaStackAsLibraryClient + + +@pytest.fixture +def responses_client(compat_client): + """Provide a client for responses tests, skipping library client mode.""" + if isinstance(compat_client, LlamaStackAsLibraryClient): + pytest.skip("Responses API tests are not supported in library client mode") + return compat_client diff --git a/tests/integration/responses/recordings/0a4aca0cd075369aaf6133ee82d9d940455cb083c0fd1330c666a12d74df6f89.json b/tests/integration/responses/recordings/0a4aca0cd075369aaf6133ee82d9d940455cb083c0fd1330c666a12d74df6f89.json new file mode 100644 index 000000000..9b432130b --- /dev/null +++ b/tests/integration/responses/recordings/0a4aca0cd075369aaf6133ee82d9d940455cb083c0fd1330c666a12d74df6f89.json @@ -0,0 +1,549 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-experiment_analysis_streaming]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "I need a complete analysis: First, get the experiment ID for 'chemical_reaction', then get the results for that experiment, and tell me if the yield was above 80%. Return only one tool call per step. Please stream your analysis process." + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_Q9Gcxub7UbQsxJWVkiy4FETr", + "type": "function", + "function": { + "name": "get_experiment_id", + "arguments": "{\"experiment_name\":\"chemical_reaction\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_Q9Gcxub7UbQsxJWVkiy4FETr", + "content": [ + { + "type": "text", + "text": "exp_003" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-0a4aca0cd075", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_yTMuQEKu7x115q8XvhqelRub", + "function": { + "arguments": "", + "name": "get_experiment_results" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "9CSOZwfG5M7nid" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-0a4aca0cd075", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Wss" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-0a4aca0cd075", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "experiment", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "5AmVsa0S6NBy" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-0a4aca0cd075", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_id", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "2Sf" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-0a4aca0cd075", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "z" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-0a4aca0cd075", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "exp", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "leu" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-0a4aca0cd075", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "omxpR" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-0a4aca0cd075", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "003", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "kW6" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-0a4aca0cd075", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Zm6" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-0a4aca0cd075", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "aXvC" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-0a4aca0cd075", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 19, + "prompt_tokens": 457, + "total_tokens": 476, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "s13YHOCCaCDcJ" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/2bd4c8dc08b3ee3ffce696864f0bd9f35d82223c7d1cab613ab2e818d79d6f9b.json b/tests/integration/responses/recordings/2bd4c8dc08b3ee3ffce696864f0bd9f35d82223c7d1cab613ab2e818d79d6f9b.json new file mode 100644 index 000000000..5aebcd841 --- /dev/null +++ b/tests/integration/responses/recordings/2bd4c8dc08b3ee3ffce696864f0bd9f35d82223c7d1cab613ab2e818d79d6f9b.json @@ -0,0 +1,295 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_non_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-user_file_access_check]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "I need to check if user 'alice' can access the file 'document.txt'. First, get alice's user ID, then check if that user ID can access the file 'document.txt'. Do this as a series of steps, where each step is a separate message. Return only one tool call per step. Summarize the final result with a single 'yes' or 'no' response." + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_EsVvmBUqtJb42kNkYnK19QkJ", + "type": "function", + "function": { + "name": "get_user_id", + "arguments": "{\"username\":\"alice\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_EsVvmBUqtJb42kNkYnK19QkJ", + "content": [ + { + "type": "text", + "text": "user_12345" + } + ] + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_kCmSE8ORKfQoiEsW2UCYr5Sh", + "type": "function", + "function": { + "name": "check_file_access", + "arguments": "{\"user_id\":\"user_12345\",\"filename\":\"document.txt\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_kCmSE8ORKfQoiEsW2UCYr5Sh", + "content": [ + { + "type": "text", + "text": "yes" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2bd4c8dc08b3", + "choices": [ + { + "delta": { + "content": "", + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "UxHf8fChwO3CUY" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2bd4c8dc08b3", + "choices": [ + { + "delta": { + "content": "yes", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "GOexNEhopELIg" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2bd4c8dc08b3", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "stop", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "O41d8hC8zD" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2bd4c8dc08b3", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 2, + "prompt_tokens": 516, + "total_tokens": 518, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "9VQklZAZMYAfa0" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/2ed23a4289840f93202f94e7e7027118869d34d768ad87ba072e92e8a43a52f2.json b/tests/integration/responses/recordings/2ed23a4289840f93202f94e7e7027118869d34d768ad87ba072e92e8a43a52f2.json new file mode 100644 index 000000000..c39483a7c --- /dev/null +++ b/tests/integration/responses/recordings/2ed23a4289840f93202f94e7e7027118869d34d768ad87ba072e92e8a43a52f2.json @@ -0,0 +1,833 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-user_permissions_workflow]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "Help me with this security check: First, get the user ID for 'charlie', then get the permissions for that user ID, and finally check if that user can access 'secret_file.txt'. Stream your progress as you work through each step. Return only one tool call per step. Summarize the final result with a single 'yes' or 'no' response." + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_fsxGbKmceUbLSXCe4sx9WLXO", + "type": "function", + "function": { + "name": "get_user_id", + "arguments": "{\"username\":\"charlie\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_fsxGbKmceUbLSXCe4sx9WLXO", + "content": [ + { + "type": "text", + "text": "user_11111" + } + ] + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_moRBxqnBJ48EWTSEoQ1llgib", + "type": "function", + "function": { + "name": "get_user_permissions", + "arguments": "{\"user_id\":\"user_11111\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_moRBxqnBJ48EWTSEoQ1llgib", + "content": [ + { + "type": "text", + "text": "admin" + } + ] + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_ybUqAP9oQn3rwQqVdOLs5Wb4", + "type": "function", + "function": { + "name": "check_file_access", + "arguments": "{\"user_id\":\"user_11111\",\"filename\":\"secret_file.txt\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_ybUqAP9oQn3rwQqVdOLs5Wb4", + "content": [ + { + "type": "text", + "text": "no" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": "", + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "WLGSIGDbuImIc2" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": "The", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "tOPrT8GpCzqCn" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": " user", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ViOvVDT7owF" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": " '", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "EkiYJGYtRb2KCr" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": "char", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ioC2G58DuWTx" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": "lie", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "A5rxByl55APwi" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": "'", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "kmDNWRqOyy2r3ST" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": " cannot", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "JHGD4XKFC" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": " access", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "6IPkFhs93" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": " '", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "LGHjKnVq2lF1DS" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": "secret", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "1nGoXVjnK0" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": "_file", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "OeR7YlvZQLa" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": ".txt", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "yLKHaSgjE64R" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": "'.", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "waZY1Js7DPWtoN" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": " The", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "km3Gr5HspErW" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": " final", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Mvzf8AUstX" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": " result", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "660CrCPne" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": " is", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "lq7NyKvIo8UEO" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": ":", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "qjIz07y1RQsKqTo" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": " no", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "xhcVwxM4RaQcN" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": ".", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "dPxBJZ3WUesIy8T" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "stop", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Z9wFfcEaK2" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-2ed23a428984", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 21, + "prompt_tokens": 542, + "total_tokens": 563, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "fSoZk1lrb3nJt" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/3177a984c900c2bdc2785b502bded6791b1054ce0f36e967eb3793b5608344f3.json b/tests/integration/responses/recordings/3177a984c900c2bdc2785b502bded6791b1054ce0f36e967eb3793b5608344f3.json new file mode 100644 index 000000000..d86ca8cc9 --- /dev/null +++ b/tests/integration/responses/recordings/3177a984c900c2bdc2785b502bded6791b1054ce0f36e967eb3793b5608344f3.json @@ -0,0 +1,759 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_mcp_tool_approval[openai_client-txt=openai/gpt-4o-True-boiling_point_tool]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid in Celsius?" + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_bL84OWNnE1s75GJEqGLAK35W", + "function": { + "arguments": "", + "name": "get_boiling_point" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ptE" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "UEV" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "li", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "hMko" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "nr" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_name", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "x" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "D" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "my", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "aLLC" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "aw", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "EZdr" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "esom", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "yV" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "eli", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "0bj" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "5J" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\",\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "z" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "c", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "7dZEY" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "elsius", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "AqP" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "true", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "X8" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "oa7h2" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "1Is8" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-3177a984c900", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 27, + "prompt_tokens": 156, + "total_tokens": 183, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "DfwHMdbjUVww7" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/318c5361647df0245c074cd2c7d6f50e862aeddbbeaeb256ef1add34de7c1dc8.json b/tests/integration/responses/recordings/318c5361647df0245c074cd2c7d6f50e862aeddbbeaeb256ef1add34de7c1dc8.json new file mode 100644 index 000000000..025246ebe --- /dev/null +++ b/tests/integration/responses/recordings/318c5361647df0245c074cd2c7d6f50e862aeddbbeaeb256ef1add34de7c1dc8.json @@ -0,0 +1,549 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_non_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-experiment_results_lookup]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "I need to get the results for the 'boiling_point' experiment. First, get the experiment ID for 'boiling_point', then use that ID to get the experiment results. Tell me the boiling point in Celsius." + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_dZwjBxH3aTRhnaS0bJVPqRcz", + "type": "function", + "function": { + "name": "get_experiment_id", + "arguments": "{\"experiment_name\":\"boiling_point\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_dZwjBxH3aTRhnaS0bJVPqRcz", + "content": [ + { + "type": "text", + "text": "exp_004" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-318c5361647d", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_skNUKbERbtdoADH834U9OE91", + "function": { + "arguments": "", + "name": "get_experiment_results" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "5aHvu2xes6Amy8" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-318c5361647d", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "9HQ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-318c5361647d", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "experiment", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ckAh5OXg9JIe" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-318c5361647d", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_id", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "avh" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-318c5361647d", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "x" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-318c5361647d", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "exp", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "f75" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-318c5361647d", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Nini1" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-318c5361647d", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "004", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "MXB" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-318c5361647d", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Vc4" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-318c5361647d", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "rnph" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-318c5361647d", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 19, + "prompt_tokens": 450, + "total_tokens": 469, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "nUptVmnQlQZrH" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/42c357284497af596ae6c9341b0c189daa31e88b25d0381a985f24203b7a5a38.json b/tests/integration/responses/recordings/42c357284497af596ae6c9341b0c189daa31e88b25d0381a985f24203b7a5a38.json index 7ec2ac931..4e80e1cdd 100644 --- a/tests/integration/responses/recordings/42c357284497af596ae6c9341b0c189daa31e88b25d0381a985f24203b7a5a38.json +++ b/tests/integration/responses/recordings/42c357284497af596ae6c9341b0c189daa31e88b25d0381a985f24203b7a5a38.json @@ -10,7 +10,7 @@ }, "response": { "body": { - "__type__": "llama_stack.apis.tools.tools.ToolInvocationResult", + "__type__": "llama_stack_api.tools.ToolInvocationResult", "__data__": { "content": "{\"query\": \"Llama 4 Maverick model experts\", \"top_k\": [{\"url\": \"https://console.groq.com/docs/model/meta-llama/llama-4-maverick-17b-128e-instruct\", \"title\": \"Llama 4 Maverick 17B 128E\", \"content\": \"Llama 4 Maverick is Meta's natively multimodal model that enables text and image understanding. With a 17 billion parameter mixture-of-experts architecture (128 experts), this model offers industry-leading performance for multimodal tasks like natural assistant-like chat, image recognition, and coding tasks. Llama 4 Maverick features an auto-regressive language model that uses a mixture-of-experts (MoE) architecture with 17B activated parameters (400B total) and incorporates early fusion for native multimodality. The model uses 128 experts to efficiently handle both text and image inputs while maintaining high performance across chat, knowledge, and code generation tasks, with a knowledge cutoff of August 2024. * For multimodal applications, this model supports up to 5 image inputs create( model =\\\"meta-llama/llama-4-maverick-17b-128e-instruct\\\", messages =[ { \\\"role\\\": \\\"user\\\", \\\"content\\\": \\\"Explain why fast inference is critical for reasoning models\\\" } ] ) print(completion.\", \"score\": 0.9170729, \"raw_content\": null}, {\"url\": \"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E\", \"title\": \"meta-llama/Llama-4-Maverick-17B-128E - Hugging Face\", \"content\": \"Model Architecture: The Llama 4 models are auto-regressive language models that use a mixture-of-experts (MoE) architecture and incorporate\", \"score\": 0.8021998, \"raw_content\": null}, {\"url\": \"https://www.ibm.com/new/announcements/meta-llama-4-maverick-and-llama-4-scout-now-available-in-watsonx-ai\", \"title\": \"Meta Llama 4 Maverick and Llama 4 Scout now available in watsonx ...\", \"content\": \"# Meta Llama 4 Maverick and Llama 4 Scout now available in watsonx.ai **IBM is excited to announce the addition of Meta\\u2019s latest generation of open models, Llama 4, to** **watsonx.ai****.** Llama 4 Scout and Llama 4 Maverick, the first mixture of experts (MoE) models released by Meta, provide frontier multimodal performance, high speeds, low cost, and industry leading context length. With the introduction of these latest offerings from Meta, IBM now supports a total of 13 Meta models in the expansive library of \\u00a0foundation models available in watsonx.ai. Trained on 40 trillion tokens of data, Llama 4 Scout offers performance rivalling or exceeding that of models with significantly larger active parameter counts while keeping costs and latency low. ## Llama 4 models on IBM watsonx\", \"score\": 0.78194773, \"raw_content\": null}, {\"url\": \"https://medium.com/@divyanshbhatiajm19/metas-llama-4-family-the-complete-guide-to-scout-maverick-and-behemoth-ai-models-in-2025-21a90c882e8a\", \"title\": \"Meta's Llama 4 Family: The Complete Guide to Scout, Maverick, and ...\", \"content\": \"# Meta\\u2019s Llama 4 Family: The Complete Guide to Scout, Maverick, and Behemoth AI Models in 2025 Feature Llama 4 Scout Llama 4 Maverick Llama 4 Behemoth **Total Parameters** 109B 400B ~2T **Active Parameters** 17B 17B 288B **Expert Count** 16 128 16 **Context Window** 10M tokens 1M tokens Not specified **Hardware Requirements** Single H100 GPU Single H100 DGX host Multiple GPUs **Inference Cost** Not specified $0.19-$0.49 per 1M tokens Not specified **Release Status** Available now Available now In training **Primary Use Cases** Long-context analysis, code processing High-performance multimodal applications Research, STEM reasoning The Llama 4 family represents Meta\\u2019s most significant AI development to date, with each model offering distinct advantages for different use cases:\", \"score\": 0.69672287, \"raw_content\": null}, {\"url\": \"https://www.llama.com/models/llama-4/\", \"title\": \"Unmatched Performance and Efficiency | Llama 4\", \"content\": \"# Llama 4 # Llama 4 Llama 4 Scout Class-leading natively multimodal model that offers superior text and visual intelligence, single H100 GPU efficiency, and a 10M context window for seamless long document analysis. Llama 4 MaverickIndustry-leading natively multimodal model for image and text understanding with groundbreaking intelligence and fast responses at a low cost. We evaluated model performance on a suite of common benchmarks across a wide range of languages, testing for coding, reasoning, knowledge, vision understanding, multilinguality, and long context. 4. Specialized long context evals are not traditionally reported for generalist models, so we share internal runs to showcase llama's frontier performance. 4. Specialized long context evals are not traditionally reported for generalist models, so we share internal runs to showcase llama's frontier performance.\", \"score\": 0.629889, \"raw_content\": null}]}", "error_message": null, diff --git a/tests/integration/responses/recordings/430a49246c97c29bd958f383627f53ec795fd77ef818827e16691689151bf17c.json b/tests/integration/responses/recordings/430a49246c97c29bd958f383627f53ec795fd77ef818827e16691689151bf17c.json new file mode 100644 index 000000000..b26cd985e --- /dev/null +++ b/tests/integration/responses/recordings/430a49246c97c29bd958f383627f53ec795fd77ef818827e16691689151bf17c.json @@ -0,0 +1,413 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_non_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-user_file_access_check]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "I need to check if user 'alice' can access the file 'document.txt'. First, get alice's user ID, then check if that user ID can access the file 'document.txt'. Do this as a series of steps, where each step is a separate message. Return only one tool call per step. Summarize the final result with a single 'yes' or 'no' response." + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-430a49246c97", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_EsVvmBUqtJb42kNkYnK19QkJ", + "function": { + "arguments": "", + "name": "get_user_id" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Ma7aiZxSs" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-430a49246c97", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "DXu" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-430a49246c97", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "username", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "rtfrl7gxu80vmN" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-430a49246c97", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "r" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-430a49246c97", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "alice", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "M" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-430a49246c97", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "vSu" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-430a49246c97", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "sXfh" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-430a49246c97", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 15, + "prompt_tokens": 454, + "total_tokens": 469, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "bEe7hWJ6U62YQ" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/51e3ddbc9d23c614ead9a8fd6ad30294237eb43063c00efc83b8a1202c1cc20c.json b/tests/integration/responses/recordings/51e3ddbc9d23c614ead9a8fd6ad30294237eb43063c00efc83b8a1202c1cc20c.json new file mode 100644 index 000000000..464de788f --- /dev/null +++ b/tests/integration/responses/recordings/51e3ddbc9d23c614ead9a8fd6ad30294237eb43063c00efc83b8a1202c1cc20c.json @@ -0,0 +1,614 @@ +{ + "test_id": "tests/integration/responses/test_mcp_authentication.py::test_mcp_authorization_backward_compatibility[openai_client-txt=openai/gpt-4o]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid?" + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_UeAsx9M8mAXo1F1LZj6TsEV9", + "type": "function", + "function": { + "name": "get_boiling_point", + "arguments": "{\"liquid_name\":\"myawesomeliquid\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_UeAsx9M8mAXo1F1LZj6TsEV9", + "content": [ + { + "type": "text", + "text": "-100" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": "", + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "c5g42LQpiBwmVH" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": "The", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "MEmQFjCKEsNDL" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": " boiling", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "dF3UemYO" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": " point", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ENDOmjG37D" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": " of", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "6kb5u2d4ILV59" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": " \"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Y6Dp6rbT9OdBG" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": "my", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "EN0ShAkdxF2jIs" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": "aw", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "1NHavCOT2fSI63" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": "esom", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "VTwbnRFtKY2W" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": "eli", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "VJuNhLeGK43e6" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": "quid", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "bFgxcYCjU42I" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": "\"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "5KR4mGTP0Rpu0O" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": " is", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "KCeY3i4Qo9L1j" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": " -", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "GgtT2kqCUk8jGH" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": "100", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "H3E18AkuuATh3" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": "\u00b0C", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "5kuUoomGw6aPf0" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": ".", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "CKIiDxWMV3zzcNj" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "stop", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "9KZoS4rawE" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-51e3ddbc9d23", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 17, + "prompt_tokens": 188, + "total_tokens": 205, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "iq2ecCxqopvPO" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/5236eb1d546e5a1bd0712891d8b4866a73cc04ce93db40346beb070f30fafee1.json b/tests/integration/responses/recordings/5236eb1d546e5a1bd0712891d8b4866a73cc04ce93db40346beb070f30fafee1.json new file mode 100644 index 000000000..66c87e3bb --- /dev/null +++ b/tests/integration/responses/recordings/5236eb1d546e5a1bd0712891d8b4866a73cc04ce93db40346beb070f30fafee1.json @@ -0,0 +1,614 @@ +{ + "test_id": "tests/integration/responses/test_mcp_authentication.py::test_mcp_authorization_bearer[client_with_models-txt=openai/gpt-4o]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid?" + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_mitVYvmPaFfoSmKjzKo5xmZp", + "type": "function", + "function": { + "name": "get_boiling_point", + "arguments": "{\"liquid_name\":\"myawesomeliquid\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_mitVYvmPaFfoSmKjzKo5xmZp", + "content": [ + { + "type": "text", + "text": "-100" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": "", + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "veiGKPHTdRNcOX" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": "The", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "u9RK8eZYDguJs" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": " boiling", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "U0L1RjHF" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": " point", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "TMS6QVLJfj" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": " of", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "5zokjwZ0nBNlD" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": " \"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "CmOp3DQRu0AqZ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": "my", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "OlnZU0jlGyE2mD" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": "aw", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "PGCsCfw8zUqRAj" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": "esom", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "8P65fJ4x3QVF" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": "eli", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "HVTNGb62o54Ol" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": "quid", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "bdRgQioKQZM6" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": "\"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "5djjyePEzwsPID" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": " is", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "xoN3TaCEum6A9" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": " -", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "UmU8LCL6WJIDrf" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": "100", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "FFXxvyme7JKyc" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": "\u00b0C", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "8BpDPmgFmIBJQQ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": ".", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Mey7rwshfBQbVlP" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "stop", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "IXaz4vn8As" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-5236eb1d546e", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 17, + "prompt_tokens": 188, + "total_tokens": 205, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "9ebnd6bFXcdOY" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/52a2b96781961e252aa3a7b0a5ff77eb5d0989d312e929ed59dda07738487d09.json b/tests/integration/responses/recordings/52a2b96781961e252aa3a7b0a5ff77eb5d0989d312e929ed59dda07738487d09.json new file mode 100644 index 000000000..fef5f0a62 --- /dev/null +++ b/tests/integration/responses/recordings/52a2b96781961e252aa3a7b0a5ff77eb5d0989d312e929ed59dda07738487d09.json @@ -0,0 +1,586 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-user_permissions_workflow]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "Help me with this security check: First, get the user ID for 'charlie', then get the permissions for that user ID, and finally check if that user can access 'secret_file.txt'. Stream your progress as you work through each step. Return only one tool call per step. Summarize the final result with a single 'yes' or 'no' response." + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_fsxGbKmceUbLSXCe4sx9WLXO", + "type": "function", + "function": { + "name": "get_user_id", + "arguments": "{\"username\":\"charlie\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_fsxGbKmceUbLSXCe4sx9WLXO", + "content": [ + { + "type": "text", + "text": "user_11111" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-52a2b9678196", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_moRBxqnBJ48EWTSEoQ1llgib", + "function": { + "arguments": "", + "name": "get_user_permissions" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-52a2b9678196", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "00p" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-52a2b9678196", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "user", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Y0" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-52a2b9678196", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_id", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "i2I" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-52a2b9678196", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "P" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-52a2b9678196", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "user", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "IG" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-52a2b9678196", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "QY61l" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-52a2b9678196", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "111", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "YAZ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-52a2b9678196", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "11", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Nw7U" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-52a2b9678196", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Ev7" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-52a2b9678196", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "CSaD" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-52a2b9678196", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 19, + "prompt_tokens": 478, + "total_tokens": 497, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "kMNEyeKFT75vK" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/541b5db7789e61d2400b70bd41c2ff7145784d249c3216c34299c38c28118328.json b/tests/integration/responses/recordings/541b5db7789e61d2400b70bd41c2ff7145784d249c3216c34299c38c28118328.json new file mode 100644 index 000000000..6b7e5bc49 --- /dev/null +++ b/tests/integration/responses/recordings/541b5db7789e61d2400b70bd41c2ff7145784d249c3216c34299c38c28118328.json @@ -0,0 +1,524 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_non_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-experiment_results_lookup]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "I need to get the results for the 'boiling_point' experiment. First, get the experiment ID for 'boiling_point', then use that ID to get the experiment results. Tell me the boiling point in Celsius." + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-541b5db7789e", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_dZwjBxH3aTRhnaS0bJVPqRcz", + "function": { + "arguments": "", + "name": "get_experiment_id" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "W3B" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-541b5db7789e", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "L7n" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-541b5db7789e", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "experiment", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "lXUc0FKJkRea" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-541b5db7789e", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_name", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "0" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-541b5db7789e", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "D" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-541b5db7789e", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "bo", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "3dUQ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-541b5db7789e", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "iling", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "1" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-541b5db7789e", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_point", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-541b5db7789e", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "48i" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-541b5db7789e", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "eQyU" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-541b5db7789e", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 19, + "prompt_tokens": 418, + "total_tokens": 437, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "5tVrc5IEigum8" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/54aa690e31b5c33a0488a5d7403393e5712917253462292829b37b9320d6df82.json b/tests/integration/responses/recordings/54aa690e31b5c33a0488a5d7403393e5712917253462292829b37b9320d6df82.json index a6c31dc72..a8e1e8611 100644 --- a/tests/integration/responses/recordings/54aa690e31b5c33a0488a5d7403393e5712917253462292829b37b9320d6df82.json +++ b/tests/integration/responses/recordings/54aa690e31b5c33a0488a5d7403393e5712917253462292829b37b9320d6df82.json @@ -10,7 +10,7 @@ }, "response": { "body": { - "__type__": "llama_stack.apis.tools.tools.ToolInvocationResult", + "__type__": "llama_stack_api.tools.ToolInvocationResult", "__data__": { "content": "{\"query\": \"Llama 4 Maverick model number of experts\", \"top_k\": [{\"url\": \"https://console.groq.com/docs/model/meta-llama/llama-4-maverick-17b-128e-instruct\", \"title\": \"Llama 4 Maverick 17B 128E\", \"content\": \"Llama 4 Maverick is Meta's natively multimodal model that enables text and image understanding. With a 17 billion parameter mixture-of-experts architecture (128 experts), this model offers industry-leading performance for multimodal tasks like natural assistant-like chat, image recognition, and coding tasks. Llama 4 Maverick features an auto-regressive language model that uses a mixture-of-experts (MoE) architecture with 17B activated parameters (400B total) and incorporates early fusion for native multimodality. The model uses 128 experts to efficiently handle both text and image inputs while maintaining high performance across chat, knowledge, and code generation tasks, with a knowledge cutoff of August 2024. * For multimodal applications, this model supports up to 5 image inputs create( model =\\\"meta-llama/llama-4-maverick-17b-128e-instruct\\\", messages =[ { \\\"role\\\": \\\"user\\\", \\\"content\\\": \\\"Explain why fast inference is critical for reasoning models\\\" } ] ) print(completion.\", \"score\": 0.9287263, \"raw_content\": null}, {\"url\": \"https://huggingface.co/meta-llama/Llama-4-Maverick-17B-128E\", \"title\": \"meta-llama/Llama-4-Maverick-17B-128E\", \"content\": \"... model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts. Model developer: Meta. Model Architecture: The\", \"score\": 0.9183121, \"raw_content\": null}, {\"url\": \"https://build.nvidia.com/meta/llama-4-maverick-17b-128e-instruct/modelcard\", \"title\": \"llama-4-maverick-17b-128e-instruct Model by Meta\", \"content\": \"... model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts. Third-Party Community Consideration. This model\", \"score\": 0.91399205, \"raw_content\": null}, {\"url\": \"https://replicate.com/meta/llama-4-maverick-instruct\", \"title\": \"meta/llama-4-maverick-instruct | Run with an API on ...\", \"content\": \"... model with 16 experts, and Llama 4 Maverick, a 17 billion parameter model with 128 experts. All services are online \\u00b7 Home \\u00b7 About \\u00b7 Changelog\", \"score\": 0.9073207, \"raw_content\": null}, {\"url\": \"https://openrouter.ai/meta-llama/llama-4-maverick\", \"title\": \"Llama 4 Maverick - API, Providers, Stats\", \"content\": \"# Meta: Llama 4 Maverick ### meta-llama/llama-4-maverick Llama 4 Maverick 17B Instruct (128E) is a high-capacity multimodal language model from Meta, built on a mixture-of-experts (MoE) architecture with 128 experts and 17 billion active parameters per forward pass (400B total). Released on April 5, 2025 under the Llama 4 Community License, Maverick is suited for research and commercial applications requiring advanced multimodal understanding and high model throughput. Llama 4 Maverick - API, Providers, Stats | OpenRouter ## Providers for Llama 4 Maverick ## Performance for Llama 4 Maverick ## Apps using Llama 4 Maverick ## Recent activity on Llama 4 Maverick ## Uptime stats for Llama 4 Maverick ## Sample code and API for Llama 4 Maverick\", \"score\": 0.8958969, \"raw_content\": null}]}", "error_message": null, diff --git a/tests/integration/responses/recordings/56ddb450d81590f461113ec5a55d0532e8f5b9418b22e5f874afff695601da16.json b/tests/integration/responses/recordings/56ddb450d81590f461113ec5a55d0532e8f5b9418b22e5f874afff695601da16.json new file mode 100644 index 000000000..bacefe818 --- /dev/null +++ b/tests/integration/responses/recordings/56ddb450d81590f461113ec5a55d0532e8f5b9418b22e5f874afff695601da16.json @@ -0,0 +1,574 @@ +{ + "test_id": "tests/integration/responses/test_mcp_authentication.py::test_mcp_authorization_backward_compatibility[openai_client-txt=openai/gpt-4o]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid?" + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_UeAsx9M8mAXo1F1LZj6TsEV9", + "function": { + "arguments": "", + "name": "get_boiling_point" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "bKe" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "kxw" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "li", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "cKkF" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "md" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_name", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "O" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "o" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "my", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "nRfv" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "aw", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "1M8i" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "esom", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "7q" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "eli", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "R2Q" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "lB" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "MDi" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "7KwE" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-56ddb450d815", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 22, + "prompt_tokens": 154, + "total_tokens": 176, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "9IipvPESur5Y7" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/59faeeca84b137e9b2c7d310ea47dc01025aeb2ee6203ef478133313e0a0e250.json b/tests/integration/responses/recordings/59faeeca84b137e9b2c7d310ea47dc01025aeb2ee6203ef478133313e0a0e250.json new file mode 100644 index 000000000..7ab319fb8 --- /dev/null +++ b/tests/integration/responses/recordings/59faeeca84b137e9b2c7d310ea47dc01025aeb2ee6203ef478133313e0a0e250.json @@ -0,0 +1,614 @@ +{ + "test_id": "tests/integration/responses/test_mcp_authentication.py::test_mcp_authorization_bearer[openai_client-txt=openai/gpt-4o]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid?" + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_2lYntxgdJV66JFvD6OuICQCB", + "type": "function", + "function": { + "name": "get_boiling_point", + "arguments": "{\"liquid_name\":\"myawesomeliquid\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_2lYntxgdJV66JFvD6OuICQCB", + "content": [ + { + "type": "text", + "text": "-100" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": "", + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "BNpFmbWkpYEjZX" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": "The", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "HdnyHcq2CLvjn" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": " boiling", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "gOMuwgrp" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": " point", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "OTfqq7Yggw" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": " of", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "cwJMhZJyf5PIp" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": " \"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "54NR7IGiuBTw5" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": "my", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "q1x9cVVPTflQti" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": "aw", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "vcudLe3yaadkvB" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": "esom", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "uql1pBt4elRL" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": "eli", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "M2kzUEkJctjYp" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": "quid", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Waet2ux2zs9P" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": "\"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "KjbjxdGYUZDuiI" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": " is", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Fg8IXJhJv8iAI" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": " -", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "wiAqPLAoinVhQq" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": "100", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "vJnb9sE969jph" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": "\u00b0C", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "5Hgi5CU0aV0sPw" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": ".", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "RDfKhuQo4E4TLXU" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "stop", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "oN1EYVkDbW" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-59faeeca84b1", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 17, + "prompt_tokens": 188, + "total_tokens": 205, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "OfhOTT3VdJ2s7" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/6a05cad89f138e215047fd44d21803c4a397f772ad8b1cb90ec44527ce964a45.json b/tests/integration/responses/recordings/6a05cad89f138e215047fd44d21803c4a397f772ad8b1cb90ec44527ce964a45.json new file mode 100644 index 000000000..adae894b3 --- /dev/null +++ b/tests/integration/responses/recordings/6a05cad89f138e215047fd44d21803c4a397f772ad8b1cb90ec44527ce964a45.json @@ -0,0 +1,614 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_non_streaming_mcp_tool[openai_client-txt=openai/gpt-4o-boiling_point_tool]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid in Celsius?" + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_8kf8fNIDcWOelbCmUEcretON", + "type": "function", + "function": { + "name": "get_boiling_point", + "arguments": "{\"liquid_name\":\"myawesomeliquid\",\"celsius\":true}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_8kf8fNIDcWOelbCmUEcretON", + "content": [ + { + "type": "text", + "text": "-100" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": "", + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "QvigjcdULEdran" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": "The", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "sIHyVud88f1Ri" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": " boiling", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "L46IcJeM" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": " point", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "j0afpRCRBL" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": " of", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "tuzBzZB7jURPj" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": " \"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "iq6vUNVBRuRH5" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": "my", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Nkkz9uUPfhHdqZ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": "aw", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "oR3PEQpsXLwYOJ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": "esom", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "VBFf1ewix1rj" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": "eli", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "yEx3rYoaZjsTw" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": "quid", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "I6VR8wzPmnpa" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": "\"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "xld69F07KIb2Yc" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": " is", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "GKgtQZJiWLVKj" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": " -", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "1by4tgiJqNgaI1" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": "100", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "2RdP6HDQApUpN" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": "\u00b0C", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "21ABialEpJBCcX" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": ".", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "uoaaRgmiGLD815k" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "stop", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "QKEKTjUUam" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6a05cad89f13", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 17, + "prompt_tokens": 195, + "total_tokens": 212, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "ceWQr6uzZRuj3" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/6d7f54b7be4845c31ae64498e8018a218bb7f4b8363998abc34ec9bb7ba3a03d.json b/tests/integration/responses/recordings/6d7f54b7be4845c31ae64498e8018a218bb7f4b8363998abc34ec9bb7ba3a03d.json new file mode 100644 index 000000000..997e18bec --- /dev/null +++ b/tests/integration/responses/recordings/6d7f54b7be4845c31ae64498e8018a218bb7f4b8363998abc34ec9bb7ba3a03d.json @@ -0,0 +1,574 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_mcp_tool_approval[openai_client-txt=openai/gpt-4o-False-boiling_point_tool]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid in Celsius?" + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_4ldOwO71od1E0lrdgYQCoe2e", + "function": { + "arguments": "", + "name": "get_boiling_point" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "TdV" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "L5f" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "li", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "qo3z" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "i3" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_name", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Z" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Z" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "my", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "QdX5" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "aw", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "sJYi" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "esom", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Yk" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "eli", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "pnS" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "y5" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Tjs" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Cx0I" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-6d7f54b7be48", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 22, + "prompt_tokens": 156, + "total_tokens": 178, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "bmRrd4XLuhmCv" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/73c9287059db75cd80dc56cff905fe3ff21e6c39189ab93778335439f288158f.json b/tests/integration/responses/recordings/73c9287059db75cd80dc56cff905fe3ff21e6c39189ab93778335439f288158f.json new file mode 100644 index 000000000..53f1a8125 --- /dev/null +++ b/tests/integration/responses/recordings/73c9287059db75cd80dc56cff905fe3ff21e6c39189ab93778335439f288158f.json @@ -0,0 +1,771 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_non_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-user_file_access_check]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "I need to check if user 'alice' can access the file 'document.txt'. First, get alice's user ID, then check if that user ID can access the file 'document.txt'. Do this as a series of steps, where each step is a separate message. Return only one tool call per step. Summarize the final result with a single 'yes' or 'no' response." + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_EsVvmBUqtJb42kNkYnK19QkJ", + "type": "function", + "function": { + "name": "get_user_id", + "arguments": "{\"username\":\"alice\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_EsVvmBUqtJb42kNkYnK19QkJ", + "content": [ + { + "type": "text", + "text": "user_12345" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_kCmSE8ORKfQoiEsW2UCYr5Sh", + "function": { + "arguments": "", + "name": "check_file_access" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "sCU" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "iHp" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "user", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "3b" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_id", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "4hG" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "z" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "user", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "zX" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "WRFf5" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "123", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "PvE" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "45", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "xak8" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\",\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "v" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "filename", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "l7Rfy5le49BJu0" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "p" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "document", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "EpFPZH128OUIsw" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": ".txt", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Zg" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "jH3" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "UubI" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-73c9287059db", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 24, + "prompt_tokens": 482, + "total_tokens": 506, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "GITY7sf69sAJd" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/775a161a318a252454fd44f9850b37c6ec15eb17dfaa95f015dcc6f65fa10c94.json b/tests/integration/responses/recordings/775a161a318a252454fd44f9850b37c6ec15eb17dfaa95f015dcc6f65fa10c94.json new file mode 100644 index 000000000..c2c8bbd80 --- /dev/null +++ b/tests/integration/responses/recordings/775a161a318a252454fd44f9850b37c6ec15eb17dfaa95f015dcc6f65fa10c94.json @@ -0,0 +1,574 @@ +{ + "test_id": "tests/integration/responses/test_mcp_authentication.py::test_mcp_authorization_bearer[openai_client-txt=openai/gpt-4o]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid?" + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_2lYntxgdJV66JFvD6OuICQCB", + "function": { + "arguments": "", + "name": "get_boiling_point" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "UmB" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ejb" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "li", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Loxj" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "IQ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_name", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "8" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "G" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "my", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "lo9p" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "aw", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "YWPA" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "esom", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "vV" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "eli", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "e0t" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "kv" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "h2F" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "B9QY" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-775a161a318a", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 22, + "prompt_tokens": 154, + "total_tokens": 176, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "MH88zIptmy2Xs" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/77ad6e42c34823ac51a784cfe4fa0ee18d09bd413189a7c03b24bf3871e3d8d7.json b/tests/integration/responses/recordings/77ad6e42c34823ac51a784cfe4fa0ee18d09bd413189a7c03b24bf3871e3d8d7.json index b92c67940..dd7884012 100644 --- a/tests/integration/responses/recordings/77ad6e42c34823ac51a784cfe4fa0ee18d09bd413189a7c03b24bf3871e3d8d7.json +++ b/tests/integration/responses/recordings/77ad6e42c34823ac51a784cfe4fa0ee18d09bd413189a7c03b24bf3871e3d8d7.json @@ -10,7 +10,7 @@ }, "response": { "body": { - "__type__": "llama_stack.apis.tools.tools.ToolInvocationResult", + "__type__": "llama_stack_api.tools.ToolInvocationResult", "__data__": { "content": "{\"query\": \"latest version of Python\", \"top_k\": [{\"url\": \"https://www.liquidweb.com/blog/latest-python-version/\", \"title\": \"The latest Python version: Python 3.14 - Liquid Web\", \"content\": \"The latest major version, Python 3.14 was officially released on October 7, 2025. Let's explore the key features of Python's current version, how to download\", \"score\": 0.890761, \"raw_content\": null}, {\"url\": \"https://docs.python.org/3/whatsnew/3.14.html\", \"title\": \"What's new in Python 3.14 \\u2014 Python 3.14.0 documentation\", \"content\": \"Python 3.14 is the latest stable release of the Python programming language, with a mix of changes to the language, the implementation, and the standard\", \"score\": 0.8124067, \"raw_content\": null}, {\"url\": \"https://devguide.python.org/versions/\", \"title\": \"Status of Python versions - Python Developer's Guide\", \"content\": \"The main branch is currently the future Python 3.15, and is the only branch that accepts new features. The latest release for each Python version can be found\", \"score\": 0.80089486, \"raw_content\": null}, {\"url\": \"https://www.python.org/doc/versions/\", \"title\": \"Python documentation by version\", \"content\": \"Python 3.12.4, documentation released on 6 June 2024. Python 3.12.3, documentation released on 9 April 2024. Python 3.12.2, documentation released on 6 February\", \"score\": 0.74563974, \"raw_content\": null}, {\"url\": \"https://www.python.org/downloads/\", \"title\": \"Download Python | Python.org\", \"content\": \"Active Python Releases \\u00b7 3.15 pre-release 2026-10-07 (planned) 2031-10 PEP 790 \\u00b7 3.14 bugfix 2025-10-07 2030-10 PEP 745 \\u00b7 3.13 bugfix 2024-10-07 2029-10 PEP 719\", \"score\": 0.6551821, \"raw_content\": null}]}", "error_message": null, diff --git a/tests/integration/responses/recordings/9f10c42f1338ae4b535cb877851520db560af78e9bc38159e526b68b8daa168e.json b/tests/integration/responses/recordings/9f10c42f1338ae4b535cb877851520db560af78e9bc38159e526b68b8daa168e.json new file mode 100644 index 000000000..5c9d6ee91 --- /dev/null +++ b/tests/integration/responses/recordings/9f10c42f1338ae4b535cb877851520db560af78e9bc38159e526b68b8daa168e.json @@ -0,0 +1,759 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_sequential_mcp_tool[openai_client-txt=openai/gpt-4o-boiling_point_tool]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid in Celsius?" + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_b5k2yeqIi5ucElnnrVPyYU4x", + "function": { + "arguments": "", + "name": "get_boiling_point" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "AhH" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "SMa" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "li", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "fBD0" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "LL" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_name", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "h" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "5" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "my", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ySpU" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "aw", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "fra1" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "esom", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Hb" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "eli", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "INi" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "jF" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\",\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "i" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "c", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "2dDeK" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "elsius", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "DSb" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "true", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "vP" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "9boiy" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ZZRa" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-9f10c42f1338", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 27, + "prompt_tokens": 156, + "total_tokens": 183, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "HoutUcx6gZI1g" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/a97d8a2f2fd75b4a5ca732e632b981ca011dd1b6c29df530d12726b1cf7989e5.json b/tests/integration/responses/recordings/a97d8a2f2fd75b4a5ca732e632b981ca011dd1b6c29df530d12726b1cf7989e5.json new file mode 100644 index 000000000..3ba6af144 --- /dev/null +++ b/tests/integration/responses/recordings/a97d8a2f2fd75b4a5ca732e632b981ca011dd1b6c29df530d12726b1cf7989e5.json @@ -0,0 +1,833 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-user_permissions_workflow]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "Help me with this security check: First, get the user ID for 'charlie', then get the permissions for that user ID, and finally check if that user can access 'secret_file.txt'. Stream your progress as you work through each step. Return only one tool call per step. Summarize the final result with a single 'yes' or 'no' response." + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_fsxGbKmceUbLSXCe4sx9WLXO", + "type": "function", + "function": { + "name": "get_user_id", + "arguments": "{\"username\":\"charlie\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_fsxGbKmceUbLSXCe4sx9WLXO", + "content": [ + { + "type": "text", + "text": "user_11111" + } + ] + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_moRBxqnBJ48EWTSEoQ1llgib", + "type": "function", + "function": { + "name": "get_user_permissions", + "arguments": "{\"user_id\":\"user_11111\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_moRBxqnBJ48EWTSEoQ1llgib", + "content": [ + { + "type": "text", + "text": "admin" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_ybUqAP9oQn3rwQqVdOLs5Wb4", + "function": { + "arguments": "", + "name": "check_file_access" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "xpc" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "xXs" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "user", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "XY" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_id", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "HbC" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "f" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "user", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Ds" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Osfy3" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "111", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ioI" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "11", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "GQg6" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\",\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "2" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "filename", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "b2qqKbGC68nHMB" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "H" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "secret", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_file", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "6" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": ".txt", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Wz" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ImW" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "nRAE" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-a97d8a2f2fd7", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 25, + "prompt_tokens": 507, + "total_tokens": 532, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "rgbYyZ54cN8La" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/b30da63114770b8c975bf66e24aee40546a0658db3df58b9b4d948e4e95b0961.json b/tests/integration/responses/recordings/b30da63114770b8c975bf66e24aee40546a0658db3df58b9b4d948e4e95b0961.json new file mode 100644 index 000000000..80cce1358 --- /dev/null +++ b/tests/integration/responses/recordings/b30da63114770b8c975bf66e24aee40546a0658db3df58b9b4d948e4e95b0961.json @@ -0,0 +1,524 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-experiment_analysis_streaming]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "I need a complete analysis: First, get the experiment ID for 'chemical_reaction', then get the results for that experiment, and tell me if the yield was above 80%. Return only one tool call per step. Please stream your analysis process." + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b30da6311477", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_Q9Gcxub7UbQsxJWVkiy4FETr", + "function": { + "arguments": "", + "name": "get_experiment_id" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "c8d" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b30da6311477", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "QoE" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b30da6311477", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "experiment", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "1krtmewG8p36" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b30da6311477", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_name", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "P" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b30da6311477", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "D" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b30da6311477", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "chemical", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "FoS4ov7pi99K5h" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b30da6311477", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_re", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "BhD" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b30da6311477", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "action", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b30da6311477", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "KWC" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b30da6311477", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "PFmv" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b30da6311477", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 19, + "prompt_tokens": 425, + "total_tokens": 444, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "NYdC3zepOXLsO" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/b6b7282ca0ad5a3c59321d2b045a91ebca1cbaeb4f7aab22c5b9e246b476272f.json b/tests/integration/responses/recordings/b6b7282ca0ad5a3c59321d2b045a91ebca1cbaeb4f7aab22c5b9e246b476272f.json new file mode 100644 index 000000000..040998a3b --- /dev/null +++ b/tests/integration/responses/recordings/b6b7282ca0ad5a3c59321d2b045a91ebca1cbaeb4f7aab22c5b9e246b476272f.json @@ -0,0 +1,649 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_sequential_mcp_tool[openai_client-txt=openai/gpt-4o-boiling_point_tool]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid in Celsius?" + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_b5k2yeqIi5ucElnnrVPyYU4x", + "type": "function", + "function": { + "name": "get_boiling_point", + "arguments": "{\"liquid_name\":\"myawesomeliquid\",\"celsius\":true}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_b5k2yeqIi5ucElnnrVPyYU4x", + "content": [ + { + "type": "text", + "text": "-100" + } + ] + }, + { + "role": "assistant", + "content": "The boiling point of \"myawesomeliquid\" is -100 degrees Celsius." + }, + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid in Celsius?" + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": "", + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "7S5XpbMeFTTZba" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": "The", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "G4KYajpQCgm5p" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": " boiling", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "krw8d3Np" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": " point", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "sOEsvVtCEV" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": " of", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "5eAw89OUrx7VT" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": " \"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "PFghmTocqCYea" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": "my", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "IRJRbKIoXwNh0e" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": "aw", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "wuoL6MoA21KfMP" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": "esom", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "DLRS3D5YVekk" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": "eli", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "PQZQlOncwl01F" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": "quid", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "TVfNNxYtZgXQ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": "\"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "LscPqJGnbMf6Qw" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": " is", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "X8NSrxHcpYYXL" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": " -", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "5nfdb4DuFapoeT" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": "100", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "K2qXQYFAd591w" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": " degrees", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "b0rvHdF1" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": " Celsius", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "kFoGt52c" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": ".", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "SJjhJwz2zgz693C" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "stop", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "MityMxFgBz" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-b6b7282ca0ad", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 18, + "prompt_tokens": 234, + "total_tokens": 252, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "qf0j6dzuNPifV" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/c27df465b2996c4d7c909e9ccfac53deb1ac47d064a1b5c70a78b7436438818f.json b/tests/integration/responses/recordings/c27df465b2996c4d7c909e9ccfac53deb1ac47d064a1b5c70a78b7436438818f.json new file mode 100644 index 000000000..c79ed1010 --- /dev/null +++ b/tests/integration/responses/recordings/c27df465b2996c4d7c909e9ccfac53deb1ac47d064a1b5c70a78b7436438818f.json @@ -0,0 +1,450 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-user_permissions_workflow]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "Help me with this security check: First, get the user ID for 'charlie', then get the permissions for that user ID, and finally check if that user can access 'secret_file.txt'. Stream your progress as you work through each step. Return only one tool call per step. Summarize the final result with a single 'yes' or 'no' response." + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c27df465b299", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_fsxGbKmceUbLSXCe4sx9WLXO", + "function": { + "arguments": "", + "name": "get_user_id" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "sOa6fZEKZ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c27df465b299", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "HBO" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c27df465b299", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "username", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "7kcXlaglccmA8a" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c27df465b299", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "a" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c27df465b299", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "char", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "bS" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c27df465b299", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "lie", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "d2e" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c27df465b299", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "fhE" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c27df465b299", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "SlsZ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c27df465b299", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 16, + "prompt_tokens": 449, + "total_tokens": 465, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "fjMWRTbF1Ni06" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/c84e894f47a6d7f4d4556829d24ea14cd2869c77972c33e66d9b42438e2165cd.json b/tests/integration/responses/recordings/c84e894f47a6d7f4d4556829d24ea14cd2869c77972c33e66d9b42438e2165cd.json new file mode 100644 index 000000000..37a29324e --- /dev/null +++ b/tests/integration/responses/recordings/c84e894f47a6d7f4d4556829d24ea14cd2869c77972c33e66d9b42438e2165cd.json @@ -0,0 +1,574 @@ +{ + "test_id": "tests/integration/responses/test_mcp_authentication.py::test_mcp_authorization_bearer[client_with_models-txt=openai/gpt-4o]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid?" + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_mitVYvmPaFfoSmKjzKo5xmZp", + "function": { + "arguments": "", + "name": "get_boiling_point" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "5Y1" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "QzQ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "li", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "4NPm" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Lh" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_name", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "r" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "w" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "my", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "GSVa" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "aw", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "AWZm" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "esom", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "DG" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "eli", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "1Bw" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Oq" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "cI8" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "kKqh" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c84e894f47a6", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 22, + "prompt_tokens": 154, + "total_tokens": 176, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "etTUytEvlkJ99" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/c9c723cd01233311d9033f55d6db610b38555bb86f93c507ede8752af47cda6a.json b/tests/integration/responses/recordings/c9c723cd01233311d9033f55d6db610b38555bb86f93c507ede8752af47cda6a.json new file mode 100644 index 000000000..e98f64b93 --- /dev/null +++ b/tests/integration/responses/recordings/c9c723cd01233311d9033f55d6db610b38555bb86f93c507ede8752af47cda6a.json @@ -0,0 +1,574 @@ +{ + "test_id": "tests/integration/responses/test_mcp_authentication.py::test_mcp_authorization_backward_compatibility[client_with_models-txt=openai/gpt-4o]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid?" + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_wnbihJuwYAfnI8uxy84Yl48j", + "function": { + "arguments": "", + "name": "get_boiling_point" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "TC0" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "hDL" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "li", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "4G8Z" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ow" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_name", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "P" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "M" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "my", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "yhAk" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "aw", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "SdIN" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "esom", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "2z" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "eli", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "nEC" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "2B" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\"}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "DoL" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "cSRf" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-c9c723cd0123", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 22, + "prompt_tokens": 154, + "total_tokens": 176, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "ejlSF0NzXFFso" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/d35c1244fbbe9898da3958113c1d054d5f5dd6bdd3c4333db6cef7361fb32feb.json b/tests/integration/responses/recordings/d35c1244fbbe9898da3958113c1d054d5f5dd6bdd3c4333db6cef7361fb32feb.json new file mode 100644 index 000000000..a41104fd5 --- /dev/null +++ b/tests/integration/responses/recordings/d35c1244fbbe9898da3958113c1d054d5f5dd6bdd3c4333db6cef7361fb32feb.json @@ -0,0 +1,759 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_non_streaming_mcp_tool[openai_client-txt=openai/gpt-4o-boiling_point_tool]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid in Celsius?" + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": [ + { + "index": 0, + "id": "call_8kf8fNIDcWOelbCmUEcretON", + "function": { + "arguments": "", + "name": "get_boiling_point" + }, + "type": "function" + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "1xG" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "{\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "RQj" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "li", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "XncI" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "86" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "_name", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "L" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "8" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "my", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "lnSu" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "aw", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ksr1" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "esom", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "CU" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "eli", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "hrv" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "quid", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "K9" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\",\"", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "a" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "c", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "LKw52" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "elsius", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "\":", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "yGY" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "true", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "wC" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": [ + { + "index": 0, + "id": null, + "function": { + "arguments": "}", + "name": null + }, + "type": null + } + ] + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "8fF8B" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "tool_calls", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "bbwp" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d35c1244fbbe", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 27, + "prompt_tokens": 156, + "total_tokens": 183, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "k0bo4JwUfLNKW" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/d42e1020edee86d9f6da7df909c2a453cb8f2e11e80beb8e5506439345c428eb.json b/tests/integration/responses/recordings/d42e1020edee86d9f6da7df909c2a453cb8f2e11e80beb8e5506439345c428eb.json new file mode 100644 index 000000000..610fe96b1 --- /dev/null +++ b/tests/integration/responses/recordings/d42e1020edee86d9f6da7df909c2a453cb8f2e11e80beb8e5506439345c428eb.json @@ -0,0 +1,808 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-experiment_analysis_streaming]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "I need a complete analysis: First, get the experiment ID for 'chemical_reaction', then get the results for that experiment, and tell me if the yield was above 80%. Return only one tool call per step. Please stream your analysis process." + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_Q9Gcxub7UbQsxJWVkiy4FETr", + "type": "function", + "function": { + "name": "get_experiment_id", + "arguments": "{\"experiment_name\":\"chemical_reaction\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_Q9Gcxub7UbQsxJWVkiy4FETr", + "content": [ + { + "type": "text", + "text": "exp_003" + } + ] + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_yTMuQEKu7x115q8XvhqelRub", + "type": "function", + "function": { + "name": "get_experiment_results", + "arguments": "{\"experiment_id\":\"exp_003\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_yTMuQEKu7x115q8XvhqelRub", + "content": [ + { + "type": "text", + "text": "Yield: 85%, Status: Complete" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": "", + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "7yA3503fehs27D" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": "The", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "T95BeWrgJQMHt" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": " yield", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "VveNEnHuMQ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": " for", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "KupSssWahehO" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": " the", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Ogot8KLW0IXw" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": " '", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "dYKJ6jPstuAso4" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": "chemical", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "wcSKhZVd" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": "_re", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "6ZlTlRGLyclHo" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": "action", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "WpYqOmrhXr" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": "'", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "qUhq7HrrwdFEyuY" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": " experiment", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "WWO2y" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": " is", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "pFVMO1BRN37n4" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": " ", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "TtQlcHeU2mPl830" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": "85", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "zyw8OdA0pXZCp5" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": "%,", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "VcHVTGGXrqvev1" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": " which", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "FI9FAA2rX6" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": " is", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Cc65gPYGA6Xfd" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": " above", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "T7BlLMIQGs" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": " ", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "2oKThCybRdG8MzZ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": "80", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "QHWdJWXK6hzQVS" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": "%.", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "lJnplmQYyl0SL3" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "stop", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "NPaAVrOB4J" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-d42e1020edee", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 21, + "prompt_tokens": 494, + "total_tokens": 515, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "ngidabPDDHECm" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/db81127157a8364ce8f7a81e10d9b84bf814950e3c8f11eed7ed9f11d4462237.json b/tests/integration/responses/recordings/db81127157a8364ce8f7a81e10d9b84bf814950e3c8f11eed7ed9f11d4462237.json new file mode 100644 index 000000000..67c78f3ed --- /dev/null +++ b/tests/integration/responses/recordings/db81127157a8364ce8f7a81e10d9b84bf814950e3c8f11eed7ed9f11d4462237.json @@ -0,0 +1,614 @@ +{ + "test_id": "tests/integration/responses/test_mcp_authentication.py::test_mcp_authorization_backward_compatibility[client_with_models-txt=openai/gpt-4o]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid?" + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_wnbihJuwYAfnI8uxy84Yl48j", + "type": "function", + "function": { + "name": "get_boiling_point", + "arguments": "{\"liquid_name\":\"myawesomeliquid\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_wnbihJuwYAfnI8uxy84Yl48j", + "content": [ + { + "type": "text", + "text": "-100" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": "", + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Usdowqbd6beiYB" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": "The", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "nVevItSH27TBR" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": " boiling", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "HWyYtVAl" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": " point", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "kvvcut6Eib" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": " of", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "E0osAbGBpCPvy" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": " \"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "GmH7m44fmv0Mk" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": "my", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "oJ4DV7z5GiqJqX" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": "aw", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "8AmNNAYPXMNrEr" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": "esom", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "JEzK8X8AD9hP" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": "eli", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "8EGj5LyQzpZMt" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": "quid", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "wQG19uBuvC7j" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": "\"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "8Wyenb7E997f9E" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": " is", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "SVXiel7RHA6f3" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": " -", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ynScunJEjmOWBo" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": "100", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "po2PLlPavc9TN" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": "\u00b0C", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "mt2jiL22pWkH93" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": ".", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "32gJJ61zmjmftOn" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "stop", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "HszNIiCJ12" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-db81127157a8", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 17, + "prompt_tokens": 188, + "total_tokens": 205, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "cAx3IDg7toBDJ" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/e2dc09dc546d9b8b99096804fe75fae1f1eb09efe6e4f86c115a78a3db5a59bc.json b/tests/integration/responses/recordings/e2dc09dc546d9b8b99096804fe75fae1f1eb09efe6e4f86c115a78a3db5a59bc.json new file mode 100644 index 000000000..ce771f24e --- /dev/null +++ b/tests/integration/responses/recordings/e2dc09dc546d9b8b99096804fe75fae1f1eb09efe6e4f86c115a78a3db5a59bc.json @@ -0,0 +1,668 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_mcp_tool_approval[openai_client-txt=openai/gpt-4o-True-boiling_point_tool]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid in Celsius?" + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_bL84OWNnE1s75GJEqGLAK35W", + "type": "function", + "function": { + "name": "get_boiling_point", + "arguments": "{\"liquid_name\":\"myawesomeliquid\",\"celsius\":true}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_bL84OWNnE1s75GJEqGLAK35W", + "content": [ + { + "type": "text", + "text": "-100" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": "", + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "STnb1nbwTsG4JZ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": "The", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "aEUUYMIYjnZpH" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": " boiling", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "2QzI8Zau" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": " point", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "gZw7vp0bnu" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": " of", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "TYru3DcfZVc6B" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": " \"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "h5P3cluszFa21" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": "my", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ggSDGSgtWOR3d9" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": "aw", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "lm72CS5Lt7lW76" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": "esom", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "fKXRsLB1CG0e" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": "eli", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "JxZBNjkfyXquH" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": "quid", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "egtKHFRBAqZn" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": "\"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "R7MdHaS5Rj2mMV" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": " in", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "LydsYLrAIj6PU" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": " Celsius", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "4MmAUDk0" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": " is", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Ivlu4M0VfRH8b" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": " -", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "OfTmU32oCtMsuo" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": "100", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "IUbbHa5oyIPjr" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": "\u00b0C", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "llluAF0LBNJIwi" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": ".", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "LnUC3LPx43OfUbC" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "stop", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ULfebGmmMn" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e2dc09dc546d", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 19, + "prompt_tokens": 195, + "total_tokens": 214, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "w11BVXjZVXRtg" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/e9f1cc3da4297f143b7b2a4b21b34cf2f55727b67c1e1854a106b9d8c7c64b70.json b/tests/integration/responses/recordings/e9f1cc3da4297f143b7b2a4b21b34cf2f55727b67c1e1854a106b9d8c7c64b70.json new file mode 100644 index 000000000..f8472055f --- /dev/null +++ b/tests/integration/responses/recordings/e9f1cc3da4297f143b7b2a4b21b34cf2f55727b67c1e1854a106b9d8c7c64b70.json @@ -0,0 +1,700 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_non_streaming_multi_turn_tool_execution[openai_client-txt=openai/gpt-4o-experiment_results_lookup]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "I need to get the results for the 'boiling_point' experiment. First, get the experiment ID for 'boiling_point', then use that ID to get the experiment results. Tell me the boiling point in Celsius." + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_dZwjBxH3aTRhnaS0bJVPqRcz", + "type": "function", + "function": { + "name": "get_experiment_id", + "arguments": "{\"experiment_name\":\"boiling_point\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_dZwjBxH3aTRhnaS0bJVPqRcz", + "content": [ + { + "type": "text", + "text": "exp_004" + } + ] + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_skNUKbERbtdoADH834U9OE91", + "type": "function", + "function": { + "name": "get_experiment_results", + "arguments": "{\"experiment_id\":\"exp_004\"}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_skNUKbERbtdoADH834U9OE91", + "content": [ + { + "type": "text", + "text": "Boiling Point: 100\u00b0C, Status: Verified" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "get_user_id", + "description": "\n Get the user ID for a given username. This ID is needed for other operations.\n\n :param username: The username to look up\n :return: The user ID for the username\n ", + "parameters": { + "properties": { + "username": { + "title": "Username", + "type": "string" + } + }, + "required": [ + "username" + ], + "title": "get_user_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_user_permissions", + "description": "\n Get the permissions for a user ID. Requires a valid user ID from get_user_id.\n\n :param user_id: The user ID to check permissions for\n :return: The permissions for the user\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + } + }, + "required": [ + "user_id" + ], + "title": "get_user_permissionsArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "check_file_access", + "description": "\n Check if a user can access a specific file. Requires a valid user ID.\n\n :param user_id: The user ID to check access for\n :param filename: The filename to check access to\n :return: Whether the user can access the file (yes/no)\n ", + "parameters": { + "properties": { + "user_id": { + "title": "User Id", + "type": "string" + }, + "filename": { + "title": "Filename", + "type": "string" + } + }, + "required": [ + "user_id", + "filename" + ], + "title": "check_file_accessArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_id", + "description": "\n Get the experiment ID for a given experiment name. This ID is needed to get results.\n\n :param experiment_name: The name of the experiment\n :return: The experiment ID\n ", + "parameters": { + "properties": { + "experiment_name": { + "title": "Experiment Name", + "type": "string" + } + }, + "required": [ + "experiment_name" + ], + "title": "get_experiment_idArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_experiment_results", + "description": "\n Get the results for an experiment ID. Requires a valid experiment ID from get_experiment_id.\n\n :param experiment_id: The experiment ID to get results for\n :return: The experiment results\n ", + "parameters": { + "properties": { + "experiment_id": { + "title": "Experiment Id", + "type": "string" + } + }, + "required": [ + "experiment_id" + ], + "title": "get_experiment_resultsArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": "", + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "OzNg5nfMI5VouN" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": "The", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "EBvjjqFPfytPb" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": " boiling", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "HhEiLgKg" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": " point", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "hLc2aAgg1D" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": " for", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "q3AsmJJ6Rvyt" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": " the", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "4QJrcjxcuFLd" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": " experiment", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "BQQJ8" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": " '", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "nj2SOixVU5KocZ" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": "bo", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ookLm9qkLqQQ3M" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": "iling", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "J4axWnSRvQU" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": "_point", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "QG6jvQWF8t" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": "'", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "veUGdbLd3d8r2yU" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": " is", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "ZOCkbhGksYmsF" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": " ", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "fbNuaYkAA8gREQ7" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": "100", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "3rdZxDq7QoXcl" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": "\u00b0C", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "upjHViB9dUBWAd" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": ".", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "hBZNqRjyLGCIMjg" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "stop", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "PrtgvDwRZp" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-e9f1cc3da429", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 17, + "prompt_tokens": 490, + "total_tokens": 507, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "euYYBnLE4Mj0Z" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/recordings/ed89b57fec937fa8602b4911a21a9a1a9488fb2347bf73d6e3bc2203a9a47a61.json b/tests/integration/responses/recordings/ed89b57fec937fa8602b4911a21a9a1a9488fb2347bf73d6e3bc2203a9a47a61.json new file mode 100644 index 000000000..d8d87a16e --- /dev/null +++ b/tests/integration/responses/recordings/ed89b57fec937fa8602b4911a21a9a1a9488fb2347bf73d6e3bc2203a9a47a61.json @@ -0,0 +1,641 @@ +{ + "test_id": "tests/integration/responses/test_tool_responses.py::test_response_sequential_mcp_tool[openai_client-txt=openai/gpt-4o-boiling_point_tool]", + "request": { + "method": "POST", + "url": "https://api.openai.com/v1/v1/chat/completions", + "headers": {}, + "body": { + "model": "gpt-4o", + "messages": [ + { + "role": "user", + "content": "What is the boiling point of myawesomeliquid in Celsius?" + }, + { + "role": "assistant", + "content": "", + "tool_calls": [ + { + "index": 0, + "id": "call_b5k2yeqIi5ucElnnrVPyYU4x", + "type": "function", + "function": { + "name": "get_boiling_point", + "arguments": "{\"liquid_name\":\"myawesomeliquid\",\"celsius\":true}" + } + } + ] + }, + { + "role": "tool", + "tool_call_id": "call_b5k2yeqIi5ucElnnrVPyYU4x", + "content": [ + { + "type": "text", + "text": "-100" + } + ] + } + ], + "stream": true, + "stream_options": { + "include_usage": true + }, + "tools": [ + { + "type": "function", + "function": { + "name": "greet_everyone", + "parameters": { + "properties": { + "url": { + "title": "Url", + "type": "string" + } + }, + "required": [ + "url" + ], + "title": "greet_everyoneArguments", + "type": "object" + } + } + }, + { + "type": "function", + "function": { + "name": "get_boiling_point", + "description": "\n Returns the boiling point of a liquid in Celsius or Fahrenheit.\n\n :param liquid_name: The name of the liquid\n :param celsius: Whether to return the boiling point in Celsius\n :return: The boiling point of the liquid in Celcius or Fahrenheit\n ", + "parameters": { + "properties": { + "liquid_name": { + "title": "Liquid Name", + "type": "string" + }, + "celsius": { + "default": true, + "title": "Celsius", + "type": "boolean" + } + }, + "required": [ + "liquid_name" + ], + "title": "get_boiling_pointArguments", + "type": "object" + } + } + } + ] + }, + "endpoint": "/v1/chat/completions", + "model": "gpt-4o" + }, + "response": { + "body": [ + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": "", + "function_call": null, + "refusal": null, + "role": "assistant", + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "WGXCgkwfwMDUCG" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": "The", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "pkdvw6gGNrtXN" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": " boiling", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "RO5YJeZc" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": " point", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "riZZHSDEz0" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": " of", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "1zjk8zIdt2Y2b" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": " \"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "XGHv0dlif7IrC" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": "my", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Ii2KeTyV3U0uiU" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": "aw", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "3OyYvSytdOYhpT" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": "esom", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "zCnXbjW4JE6l" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": "eli", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "0bwcz2K91q7EO" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": "quid", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Um0jFlJegpXI" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": "\"", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "4OllZlS2JmoD3l" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": " is", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "x4jApO80AyXpX" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": " -", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "wq0D3Wzc1l3h6S" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": "100", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Dn78V58iZ9wKK" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": " degrees", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "fjHDBTqT" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": " Celsius", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "Cnp6KULL" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": ".", + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": null, + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "grbygHexDT4JwGx" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [ + { + "delta": { + "content": null, + "function_call": null, + "refusal": null, + "role": null, + "tool_calls": null + }, + "finish_reason": "stop", + "index": 0, + "logprobs": null + } + ], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": null, + "obfuscation": "upSRpiQQKE" + } + }, + { + "__type__": "openai.types.chat.chat_completion_chunk.ChatCompletionChunk", + "__data__": { + "id": "rec-ed89b57fec93", + "choices": [], + "created": 0, + "model": "gpt-4o-2024-08-06", + "object": "chat.completion.chunk", + "service_tier": "default", + "system_fingerprint": "fp_cbf1785567", + "usage": { + "completion_tokens": 18, + "prompt_tokens": 195, + "total_tokens": 213, + "completion_tokens_details": { + "accepted_prediction_tokens": 0, + "audio_tokens": 0, + "reasoning_tokens": 0, + "rejected_prediction_tokens": 0 + }, + "prompt_tokens_details": { + "audio_tokens": 0, + "cached_tokens": 0 + } + }, + "obfuscation": "psE6Es6zZ2Kz4" + } + } + ], + "is_streaming": true + }, + "id_normalization_mapping": {} +} diff --git a/tests/integration/responses/test_basic_responses.py b/tests/integration/responses/test_basic_responses.py index a764084af..d72a43375 100644 --- a/tests/integration/responses/test_basic_responses.py +++ b/tests/integration/responses/test_basic_responses.py @@ -13,8 +13,8 @@ from .streaming_assertions import StreamingValidator @pytest.mark.parametrize("case", basic_test_cases) -def test_response_non_streaming_basic(compat_client, text_model_id, case): - response = compat_client.responses.create( +def test_response_non_streaming_basic(responses_client, text_model_id, case): + response = responses_client.responses.create( model=text_model_id, input=case.input, stream=False, @@ -31,10 +31,10 @@ def test_response_non_streaming_basic(compat_client, text_model_id, case): "Total tokens should equal input + output tokens" ) - retrieved_response = compat_client.responses.retrieve(response_id=response.id) + retrieved_response = responses_client.responses.retrieve(response_id=response.id) assert retrieved_response.output_text == response.output_text - next_response = compat_client.responses.create( + next_response = responses_client.responses.create( model=text_model_id, input="Repeat your previous response in all caps.", previous_response_id=response.id, @@ -44,8 +44,8 @@ def test_response_non_streaming_basic(compat_client, text_model_id, case): @pytest.mark.parametrize("case", basic_test_cases) -def test_response_streaming_basic(compat_client, text_model_id, case): - response = compat_client.responses.create( +def test_response_streaming_basic(responses_client, text_model_id, case): + response = responses_client.responses.create( model=text_model_id, input=case.input, stream=True, @@ -98,15 +98,15 @@ def test_response_streaming_basic(compat_client, text_model_id, case): validator.assert_response_consistency() # Verify stored response matches streamed response - retrieved_response = compat_client.responses.retrieve(response_id=response_id) + retrieved_response = responses_client.responses.retrieve(response_id=response_id) final_event = events[-1] assert retrieved_response.output_text == final_event.response.output_text @pytest.mark.parametrize("case", basic_test_cases) -def test_response_streaming_incremental_content(compat_client, text_model_id, case): +def test_response_streaming_incremental_content(responses_client, text_model_id, case): """Test that streaming actually delivers content incrementally, not just at the end.""" - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input=case.input, stream=True, @@ -170,10 +170,10 @@ def test_response_streaming_incremental_content(compat_client, text_model_id, ca @pytest.mark.parametrize("case", multi_turn_test_cases) -def test_response_non_streaming_multi_turn(compat_client, text_model_id, case): +def test_response_non_streaming_multi_turn(responses_client, text_model_id, case): previous_response_id = None for turn_input, turn_expected in case.turns: - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input=turn_input, previous_response_id=previous_response_id, @@ -184,8 +184,8 @@ def test_response_non_streaming_multi_turn(compat_client, text_model_id, case): @pytest.mark.parametrize("case", image_test_cases) -def test_response_non_streaming_image(compat_client, text_model_id, case): - response = compat_client.responses.create( +def test_response_non_streaming_image(responses_client, text_model_id, case): + response = responses_client.responses.create( model=text_model_id, input=case.input, stream=False, @@ -195,10 +195,10 @@ def test_response_non_streaming_image(compat_client, text_model_id, case): @pytest.mark.parametrize("case", multi_turn_image_test_cases) -def test_response_non_streaming_multi_turn_image(compat_client, text_model_id, case): +def test_response_non_streaming_multi_turn_image(responses_client, text_model_id, case): previous_response_id = None for turn_input, turn_expected in case.turns: - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input=turn_input, previous_response_id=previous_response_id, diff --git a/tests/integration/responses/test_conversation_responses.py b/tests/integration/responses/test_conversation_responses.py index babb77793..ce249f6a0 100644 --- a/tests/integration/responses/test_conversation_responses.py +++ b/tests/integration/responses/test_conversation_responses.py @@ -88,6 +88,7 @@ class TestConversationResponses: assert "apple" in response.output_text.lower() + @pytest.mark.timeout(60, method="thread") def test_conversation_error_handling(self, openai_client, text_model_id): """Test error handling for invalid and nonexistent conversations.""" # Invalid conversation ID format @@ -131,18 +132,18 @@ class TestConversationResponses: assert len(response.output_text.strip()) > 0 # this is not ready yet - # def test_conversation_compat_client(self, compat_client, text_model_id): + # def test_conversation_compat_client(self, responses_client, text_model_id): # """Test conversation parameter works with compatibility client.""" - # if not hasattr(compat_client, "conversations"): - # pytest.skip("compat_client does not support conversations API") + # if not hasattr(responses_client, "conversations"): + # pytest.skip("responses_client does not support conversations API") # - # conversation = compat_client.conversations.create() - # response = compat_client.responses.create( + # conversation = responses_client.conversations.create() + # response = responses_client.responses.create( # model=text_model_id, input="Tell me a joke", conversation=conversation.id # ) # # assert response is not None # assert len(response.output_text.strip()) > 0 # - # conversation_items = compat_client.conversations.items.list(conversation.id) + # conversation_items = responses_client.conversations.items.list(conversation.id) # assert len(conversation_items.data) >= 2 diff --git a/tests/integration/responses/test_file_search.py b/tests/integration/responses/test_file_search.py index dde5fd7f6..b2a634fb0 100644 --- a/tests/integration/responses/test_file_search.py +++ b/tests/integration/responses/test_file_search.py @@ -9,8 +9,6 @@ import time import pytest -from llama_stack.core.library_client import LlamaStackAsLibraryClient - from .helpers import new_vector_store, upload_file @@ -28,12 +26,9 @@ from .helpers import new_vector_store, upload_file }, ], ) -def test_response_text_format(compat_client, text_model_id, text_format): - if isinstance(compat_client, LlamaStackAsLibraryClient): - pytest.skip("Responses API text format is not yet supported in library client.") - +def test_response_text_format(responses_client, text_model_id, text_format): stream = False - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input="What is the capital of France?", stream=stream, @@ -47,13 +42,10 @@ def test_response_text_format(compat_client, text_model_id, text_format): @pytest.fixture -def vector_store_with_filtered_files(compat_client, embedding_model_id, embedding_dimension, tmp_path_factory): +def vector_store_with_filtered_files(responses_client, embedding_model_id, embedding_dimension, tmp_path_factory): # """Create a vector store with multiple files that have different attributes for filtering tests.""" - if isinstance(compat_client, LlamaStackAsLibraryClient): - pytest.skip("upload_file() is not yet supported in library client somehow?") - vector_store = new_vector_store( - compat_client, "test_vector_store_with_filters", embedding_model_id, embedding_dimension + responses_client, "test_vector_store_with_filters", embedding_model_id, embedding_dimension ) tmp_path = tmp_path_factory.mktemp("filter_test_files") @@ -104,11 +96,11 @@ def vector_store_with_filtered_files(compat_client, embedding_model_id, embeddin file_path.write_text(file_data["content"]) # Upload file - file_response = upload_file(compat_client, file_data["name"], str(file_path)) + file_response = upload_file(responses_client, file_data["name"], str(file_path)) file_ids.append(file_response.id) # Attach file to vector store with attributes - file_attach_response = compat_client.vector_stores.files.create( + file_attach_response = responses_client.vector_stores.files.create( vector_store_id=vector_store.id, file_id=file_response.id, attributes=file_data["attributes"], @@ -117,7 +109,7 @@ def vector_store_with_filtered_files(compat_client, embedding_model_id, embeddin # Wait for attachment while file_attach_response.status == "in_progress": time.sleep(0.1) - file_attach_response = compat_client.vector_stores.files.retrieve( + file_attach_response = responses_client.vector_stores.files.retrieve( vector_store_id=vector_store.id, file_id=file_response.id, ) @@ -127,17 +119,17 @@ def vector_store_with_filtered_files(compat_client, embedding_model_id, embeddin # Cleanup: delete vector store and files try: - compat_client.vector_stores.delete(vector_store_id=vector_store.id) + responses_client.vector_stores.delete(vector_store_id=vector_store.id) for file_id in file_ids: try: - compat_client.files.delete(file_id=file_id) + responses_client.files.delete(file_id=file_id) except Exception: pass # File might already be deleted except Exception: pass # Best effort cleanup -def test_response_file_search_filter_by_region(compat_client, text_model_id, vector_store_with_filtered_files): +def test_response_file_search_filter_by_region(responses_client, text_model_id, vector_store_with_filtered_files): """Test file search with region equality filter.""" tools = [ { @@ -147,7 +139,7 @@ def test_response_file_search_filter_by_region(compat_client, text_model_id, vec } ] - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input="What are the updates from the US region?", tools=tools, @@ -168,7 +160,7 @@ def test_response_file_search_filter_by_region(compat_client, text_model_id, vec assert "asia" not in result.text.lower() -def test_response_file_search_filter_by_category(compat_client, text_model_id, vector_store_with_filtered_files): +def test_response_file_search_filter_by_category(responses_client, text_model_id, vector_store_with_filtered_files): """Test file search with category equality filter.""" tools = [ { @@ -178,7 +170,7 @@ def test_response_file_search_filter_by_category(compat_client, text_model_id, v } ] - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input="Show me all marketing reports", tools=tools, @@ -198,7 +190,7 @@ def test_response_file_search_filter_by_category(compat_client, text_model_id, v assert "revenue figures" not in result.text.lower() -def test_response_file_search_filter_by_date_range(compat_client, text_model_id, vector_store_with_filtered_files): +def test_response_file_search_filter_by_date_range(responses_client, text_model_id, vector_store_with_filtered_files): """Test file search with date range filter using compound AND.""" tools = [ { @@ -222,7 +214,7 @@ def test_response_file_search_filter_by_date_range(compat_client, text_model_id, } ] - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input="What happened in Q1 2023?", tools=tools, @@ -241,7 +233,7 @@ def test_response_file_search_filter_by_date_range(compat_client, text_model_id, assert "q3" not in result.text.lower() -def test_response_file_search_filter_compound_and(compat_client, text_model_id, vector_store_with_filtered_files): +def test_response_file_search_filter_compound_and(responses_client, text_model_id, vector_store_with_filtered_files): """Test file search with compound AND filter (region AND category).""" tools = [ { @@ -257,7 +249,7 @@ def test_response_file_search_filter_compound_and(compat_client, text_model_id, } ] - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input="What are the engineering updates from the US?", tools=tools, @@ -277,7 +269,7 @@ def test_response_file_search_filter_compound_and(compat_client, text_model_id, assert "promotional" not in result.text.lower() and "revenue" not in result.text.lower() -def test_response_file_search_filter_compound_or(compat_client, text_model_id, vector_store_with_filtered_files): +def test_response_file_search_filter_compound_or(responses_client, text_model_id, vector_store_with_filtered_files): """Test file search with compound OR filter (marketing OR sales).""" tools = [ { @@ -293,7 +285,7 @@ def test_response_file_search_filter_compound_or(compat_client, text_model_id, v } ] - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input="Show me marketing and sales documents", tools=tools, @@ -320,7 +312,7 @@ def test_response_file_search_filter_compound_or(compat_client, text_model_id, v assert categories_found.issubset({"marketing", "sales"}), f"Found unexpected categories: {categories_found}" -def test_response_file_search_streaming_events(compat_client, text_model_id, vector_store_with_filtered_files): +def test_response_file_search_streaming_events(responses_client, text_model_id, vector_store_with_filtered_files): """Test that file search emits proper streaming events (in_progress, searching, completed).""" tools = [ { @@ -329,7 +321,7 @@ def test_response_file_search_streaming_events(compat_client, text_model_id, vec } ] - stream = compat_client.responses.create( + stream = responses_client.responses.create( model=text_model_id, input="What are the marketing updates?", tools=tools, diff --git a/tests/integration/responses/test_mcp_authentication.py b/tests/integration/responses/test_mcp_authentication.py new file mode 100644 index 000000000..5c990ff6a --- /dev/null +++ b/tests/integration/responses/test_mcp_authentication.py @@ -0,0 +1,105 @@ +# Copyright (c) Meta Platforms, Inc. and affiliates. +# All rights reserved. +# +# This source code is licensed under the terms described in the LICENSE file in +# the root directory of this source tree. + + +import pytest + +from tests.common.mcp import make_mcp_server + +from .helpers import setup_mcp_tools + +# MCP authentication tests with recordings +# Tests for bearer token authorization support in MCP tool configurations + + +def test_mcp_authorization_bearer(responses_client, text_model_id): + """Test that bearer authorization is correctly applied to MCP requests.""" + test_token = "test-bearer-token-789" + with make_mcp_server(required_auth_token=test_token) as mcp_server_info: + tools = setup_mcp_tools( + [ + { + "type": "mcp", + "server_label": "auth-mcp", + "server_url": "", + "authorization": test_token, # Just the token, not "Bearer " + } + ], + mcp_server_info, + ) + + # Create response - authorization should be applied + response = responses_client.responses.create( + model=text_model_id, + input="What is the boiling point of myawesomeliquid?", + tools=tools, + stream=False, + ) + + # Verify list_tools succeeded (requires auth) + assert len(response.output) >= 3 + assert response.output[0].type == "mcp_list_tools" + assert len(response.output[0].tools) == 2 + + # Verify tool invocation succeeded (requires auth) + assert response.output[1].type == "mcp_call" + assert response.output[1].error is None + + +def test_mcp_authorization_error_when_header_provided(responses_client, text_model_id): + """Test that providing Authorization in headers raises a security error.""" + test_token = "test-token-123" + with make_mcp_server(required_auth_token=test_token) as mcp_server_info: + tools = setup_mcp_tools( + [ + { + "type": "mcp", + "server_label": "header-auth-mcp", + "server_url": "", + "headers": {"Authorization": f"Bearer {test_token}"}, # Security risk - should be rejected + } + ], + mcp_server_info, + ) + + # Create response - should raise BadRequestError for security reasons + with pytest.raises((ValueError, Exception), match="Authorization header cannot be passed via 'headers'"): + responses_client.responses.create( + model=text_model_id, + input="What is the boiling point of myawesomeliquid?", + tools=tools, + stream=False, + ) + + +def test_mcp_authorization_backward_compatibility(responses_client, text_model_id): + """Test that MCP tools work without authorization (backward compatibility).""" + # No authorization required + with make_mcp_server(required_auth_token=None) as mcp_server_info: + tools = setup_mcp_tools( + [ + { + "type": "mcp", + "server_label": "noauth-mcp", + "server_url": "", + } + ], + mcp_server_info, + ) + + # Create response without authorization + response = responses_client.responses.create( + model=text_model_id, + input="What is the boiling point of myawesomeliquid?", + tools=tools, + stream=False, + ) + + # Verify operations succeeded without auth + assert len(response.output) >= 3 + assert response.output[0].type == "mcp_list_tools" + assert response.output[1].type == "mcp_call" + assert response.output[1].error is None diff --git a/tests/integration/responses/test_tool_responses.py b/tests/integration/responses/test_tool_responses.py index 9bf58c6ff..742d45f8b 100644 --- a/tests/integration/responses/test_tool_responses.py +++ b/tests/integration/responses/test_tool_responses.py @@ -9,6 +9,7 @@ import logging # allow-direct-logging import os import httpx +import llama_stack_client import openai import pytest @@ -29,8 +30,8 @@ from .streaming_assertions import StreamingValidator @pytest.mark.parametrize("case", web_search_test_cases) -def test_response_non_streaming_web_search(compat_client, text_model_id, case): - response = compat_client.responses.create( +def test_response_non_streaming_web_search(responses_client, text_model_id, case): + response = responses_client.responses.create( model=text_model_id, input=case.input, tools=case.tools, @@ -48,12 +49,9 @@ def test_response_non_streaming_web_search(compat_client, text_model_id, case): @pytest.mark.parametrize("case", file_search_test_cases) def test_response_non_streaming_file_search( - compat_client, text_model_id, embedding_model_id, embedding_dimension, tmp_path, case + responses_client, text_model_id, embedding_model_id, embedding_dimension, tmp_path, case ): - if isinstance(compat_client, LlamaStackAsLibraryClient): - pytest.skip("Responses API file search is not yet supported in library client.") - - vector_store = new_vector_store(compat_client, "test_vector_store", embedding_model_id, embedding_dimension) + vector_store = new_vector_store(responses_client, "test_vector_store", embedding_model_id, embedding_dimension) if case.file_content: file_name = "test_response_non_streaming_file_search.txt" @@ -65,16 +63,16 @@ def test_response_non_streaming_file_search( else: raise ValueError("No file content or path provided for case") - file_response = upload_file(compat_client, file_name, file_path) + file_response = upload_file(responses_client, file_name, file_path) # Attach our file to the vector store - compat_client.vector_stores.files.create( + responses_client.vector_stores.files.create( vector_store_id=vector_store.id, file_id=file_response.id, ) # Wait for the file to be attached - wait_for_file_attachment(compat_client, vector_store.id, file_response.id) + wait_for_file_attachment(responses_client, vector_store.id, file_response.id) # Update our tools with the right vector store id tools = case.tools @@ -83,7 +81,7 @@ def test_response_non_streaming_file_search( tool["vector_store_ids"] = [vector_store.id] # Create the response request, which should query our vector store - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input=case.input, tools=tools, @@ -105,15 +103,12 @@ def test_response_non_streaming_file_search( def test_response_non_streaming_file_search_empty_vector_store( - compat_client, text_model_id, embedding_model_id, embedding_dimension + responses_client, text_model_id, embedding_model_id, embedding_dimension ): - if isinstance(compat_client, LlamaStackAsLibraryClient): - pytest.skip("Responses API file search is not yet supported in library client.") - - vector_store = new_vector_store(compat_client, "test_vector_store", embedding_model_id, embedding_dimension) + vector_store = new_vector_store(responses_client, "test_vector_store", embedding_model_id, embedding_dimension) # Create the response request, which should query our vector store - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input="How many experts does the Llama 4 Maverick model have?", tools=[{"type": "file_search", "vector_store_ids": [vector_store.id]}], @@ -133,13 +128,10 @@ def test_response_non_streaming_file_search_empty_vector_store( def test_response_sequential_file_search( - compat_client, text_model_id, embedding_model_id, embedding_dimension, tmp_path + responses_client, text_model_id, embedding_model_id, embedding_dimension, tmp_path ): """Test file search with sequential responses using previous_response_id.""" - if isinstance(compat_client, LlamaStackAsLibraryClient): - pytest.skip("Responses API file search is not yet supported in library client.") - - vector_store = new_vector_store(compat_client, "test_vector_store", embedding_model_id, embedding_dimension) + vector_store = new_vector_store(responses_client, "test_vector_store", embedding_model_id, embedding_dimension) # Create a test file with content file_content = "The Llama 4 Maverick model has 128 experts in its mixture of experts architecture." @@ -147,21 +139,21 @@ def test_response_sequential_file_search( file_path = tmp_path / file_name file_path.write_text(file_content) - file_response = upload_file(compat_client, file_name, file_path) + file_response = upload_file(responses_client, file_name, file_path) # Attach the file to the vector store - compat_client.vector_stores.files.create( + responses_client.vector_stores.files.create( vector_store_id=vector_store.id, file_id=file_response.id, ) # Wait for the file to be attached - wait_for_file_attachment(compat_client, vector_store.id, file_response.id) + wait_for_file_attachment(responses_client, vector_store.id, file_response.id) tools = [{"type": "file_search", "vector_store_ids": [vector_store.id]}] # First response request with file search - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input="How many experts does the Llama 4 Maverick model have?", tools=tools, @@ -178,7 +170,7 @@ def test_response_sequential_file_search( assert "128" in response.output_text or "experts" in response.output_text.lower() # Second response request using previous_response_id - response2 = compat_client.responses.create( + response2 = responses_client.responses.create( model=text_model_id, input="Can you tell me more about the architecture?", tools=tools, @@ -199,14 +191,11 @@ def test_response_sequential_file_search( @pytest.mark.parametrize("case", mcp_tool_test_cases) -def test_response_non_streaming_mcp_tool(compat_client, text_model_id, case, caplog): - if not isinstance(compat_client, LlamaStackAsLibraryClient): - pytest.skip("in-process MCP server is only supported in library client") - +def test_response_non_streaming_mcp_tool(responses_client, text_model_id, case, caplog): with make_mcp_server() as mcp_server_info: tools = setup_mcp_tools(case.tools, mcp_server_info) - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input=case.input, tools=tools, @@ -243,15 +232,15 @@ def test_response_non_streaming_mcp_tool(compat_client, text_model_id, case, cap exc_type = ( AuthenticationRequiredError - if isinstance(compat_client, LlamaStackAsLibraryClient) - else (httpx.HTTPStatusError, openai.AuthenticationError) + if isinstance(responses_client, LlamaStackAsLibraryClient) + else (httpx.HTTPStatusError, openai.AuthenticationError, llama_stack_client.AuthenticationError) ) # Suppress expected auth error logs only for the failing auth attempt with caplog.at_level( logging.CRITICAL, logger="llama_stack.providers.inline.agents.meta_reference.responses.streaming" ): with pytest.raises(exc_type): - compat_client.responses.create( + responses_client.responses.create( model=text_model_id, input=case.input, tools=tools, @@ -260,9 +249,9 @@ def test_response_non_streaming_mcp_tool(compat_client, text_model_id, case, cap for tool in tools: if tool["type"] == "mcp": - tool["headers"] = {"Authorization": "Bearer test-token"} + tool["authorization"] = "test-token" - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input=case.input, tools=tools, @@ -272,14 +261,11 @@ def test_response_non_streaming_mcp_tool(compat_client, text_model_id, case, cap @pytest.mark.parametrize("case", mcp_tool_test_cases) -def test_response_sequential_mcp_tool(compat_client, text_model_id, case): - if not isinstance(compat_client, LlamaStackAsLibraryClient): - pytest.skip("in-process MCP server is only supported in library client") - +def test_response_sequential_mcp_tool(responses_client, text_model_id, case): with make_mcp_server() as mcp_server_info: tools = setup_mcp_tools(case.tools, mcp_server_info) - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input=case.input, tools=tools, @@ -311,7 +297,7 @@ def test_response_sequential_mcp_tool(compat_client, text_model_id, case): text_content = message.content[0].text assert "boiling point" in text_content.lower() - response2 = compat_client.responses.create( + response2 = responses_client.responses.create( model=text_model_id, input=case.input, tools=tools, stream=False, previous_response_id=response.id ) @@ -323,16 +309,13 @@ def test_response_sequential_mcp_tool(compat_client, text_model_id, case): @pytest.mark.parametrize("case", mcp_tool_test_cases) @pytest.mark.parametrize("approve", [True, False]) -def test_response_mcp_tool_approval(compat_client, text_model_id, case, approve): - if not isinstance(compat_client, LlamaStackAsLibraryClient): - pytest.skip("in-process MCP server is only supported in library client") - +def test_response_mcp_tool_approval(responses_client, text_model_id, case, approve): with make_mcp_server() as mcp_server_info: tools = setup_mcp_tools(case.tools, mcp_server_info) for tool in tools: tool["require_approval"] = "always" - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input=case.input, tools=tools, @@ -352,13 +335,13 @@ def test_response_mcp_tool_approval(compat_client, text_model_id, case, approve) approval_request = response.output[1] assert approval_request.type == "mcp_approval_request" assert approval_request.name == "get_boiling_point" - assert json.loads(approval_request.arguments) == { - "liquid_name": "myawesomeliquid", - "celsius": True, - } + args = json.loads(approval_request.arguments) + assert args["liquid_name"] == "myawesomeliquid" + # celsius has a default value of True, so it may be omitted or explicitly set + assert args.get("celsius", True) is True # send approval response - response = compat_client.responses.create( + response = responses_client.responses.create( previous_response_id=response.id, model=text_model_id, input=[{"type": "mcp_approval_response", "approval_request_id": approval_request.id, "approve": approve}], @@ -398,8 +381,8 @@ def test_response_mcp_tool_approval(compat_client, text_model_id, case, approve) @pytest.mark.parametrize("case", custom_tool_test_cases) -def test_response_non_streaming_custom_tool(compat_client, text_model_id, case): - response = compat_client.responses.create( +def test_response_non_streaming_custom_tool(responses_client, text_model_id, case): + response = responses_client.responses.create( model=text_model_id, input=case.input, tools=case.tools, @@ -412,8 +395,8 @@ def test_response_non_streaming_custom_tool(compat_client, text_model_id, case): @pytest.mark.parametrize("case", custom_tool_test_cases) -def test_response_function_call_ordering_1(compat_client, text_model_id, case): - response = compat_client.responses.create( +def test_response_function_call_ordering_1(responses_client, text_model_id, case): + response = responses_client.responses.create( model=text_model_id, input=case.input, tools=case.tools, @@ -437,13 +420,13 @@ def test_response_function_call_ordering_1(compat_client, text_model_id, case): "call_id": response.output[0].call_id, } ) - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input=inputs, tools=case.tools, stream=False, previous_response_id=response.id ) assert len(response.output) == 1 -def test_response_function_call_ordering_2(compat_client, text_model_id): +def test_response_function_call_ordering_2(responses_client, text_model_id): tools = [ { "type": "function", @@ -468,7 +451,7 @@ def test_response_function_call_ordering_2(compat_client, text_model_id): "content": "Is the weather better in San Francisco or Los Angeles?", } ] - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input=inputs, tools=tools, @@ -489,7 +472,7 @@ def test_response_function_call_ordering_2(compat_client, text_model_id): "call_id": output.call_id, } ) - response = compat_client.responses.create( + response = responses_client.responses.create( model=text_model_id, input=inputs, tools=tools, @@ -500,15 +483,12 @@ def test_response_function_call_ordering_2(compat_client, text_model_id): @pytest.mark.parametrize("case", multi_turn_tool_execution_test_cases) -def test_response_non_streaming_multi_turn_tool_execution(compat_client, text_model_id, case): +def test_response_non_streaming_multi_turn_tool_execution(responses_client, text_model_id, case): """Test multi-turn tool execution where multiple MCP tool calls are performed in sequence.""" - if not isinstance(compat_client, LlamaStackAsLibraryClient): - pytest.skip("in-process MCP server is only supported in library client") - with make_mcp_server(tools=dependency_tools()) as mcp_server_info: tools = setup_mcp_tools(case.tools, mcp_server_info) - response = compat_client.responses.create( + response = responses_client.responses.create( input=case.input, model=text_model_id, tools=tools, @@ -550,15 +530,12 @@ def test_response_non_streaming_multi_turn_tool_execution(compat_client, text_mo @pytest.mark.parametrize("case", multi_turn_tool_execution_streaming_test_cases) -def test_response_streaming_multi_turn_tool_execution(compat_client, text_model_id, case): +def test_response_streaming_multi_turn_tool_execution(responses_client, text_model_id, case): """Test streaming multi-turn tool execution where multiple MCP tool calls are performed in sequence.""" - if not isinstance(compat_client, LlamaStackAsLibraryClient): - pytest.skip("in-process MCP server is only supported in library client") - with make_mcp_server(tools=dependency_tools()) as mcp_server_info: tools = setup_mcp_tools(case.tools, mcp_server_info) - stream = compat_client.responses.create( + stream = responses_client.responses.create( input=case.input, model=text_model_id, tools=tools, diff --git a/tests/integration/safety/test_llama_guard.py b/tests/integration/safety/test_llama_guard.py index 5a73bb044..a554752cd 100644 --- a/tests/integration/safety/test_llama_guard.py +++ b/tests/integration/safety/test_llama_guard.py @@ -13,8 +13,8 @@ from collections.abc import Generator import pytest -from llama_stack.apis.safety import ViolationLevel from llama_stack.models.llama.sku_types import CoreModelId +from llama_stack_api import ViolationLevel # Llama Guard models available for text and vision shields LLAMA_GUARD_TEXT_MODELS = [CoreModelId.llama_guard_4_12b.value] diff --git a/tests/integration/safety/test_safety.py b/tests/integration/safety/test_safety.py index 6337abc9c..857ff2f81 100644 --- a/tests/integration/safety/test_safety.py +++ b/tests/integration/safety/test_safety.py @@ -8,7 +8,7 @@ import mimetypes import pytest -from llama_stack.apis.safety import ViolationLevel +from llama_stack_api import ViolationLevel CODE_SCANNER_ENABLED_PROVIDERS = {"ollama", "together", "fireworks"} diff --git a/tests/integration/safety/test_vision_safety.py b/tests/integration/safety/test_vision_safety.py index 7b3779e9e..dc7b7e1ad 100644 --- a/tests/integration/safety/test_vision_safety.py +++ b/tests/integration/safety/test_vision_safety.py @@ -10,7 +10,7 @@ import os import pytest -from llama_stack.apis.safety import ViolationLevel +from llama_stack_api import ViolationLevel VISION_SHIELD_ENABLED_PROVIDERS = {"together"} diff --git a/tests/integration/tool_runtime/test_mcp.py b/tests/integration/tool_runtime/test_mcp.py index 3a8fde37f..1b7f509d2 100644 --- a/tests/integration/tool_runtime/test_mcp.py +++ b/tests/integration/tool_runtime/test_mcp.py @@ -10,8 +10,6 @@ import pytest from llama_stack_client.lib.agents.agent import Agent from llama_stack_client.lib.agents.turn_events import StepCompleted, StepProgress, ToolCallIssuedDelta -from llama_stack.core.library_client import LlamaStackAsLibraryClient - AUTH_TOKEN = "test-token" from tests.common.mcp import MCP_TOOLGROUP_ID, make_mcp_server @@ -24,9 +22,6 @@ def mcp_server(): def test_mcp_invocation(llama_stack_client, text_model_id, mcp_server): - if not isinstance(llama_stack_client, LlamaStackAsLibraryClient): - pytest.skip("The local MCP server only reliably reachable from library client.") - test_toolgroup_id = MCP_TOOLGROUP_ID uri = mcp_server["server_url"] @@ -42,6 +37,7 @@ def test_mcp_invocation(llama_stack_client, text_model_id, mcp_server): mcp_endpoint=dict(uri=uri), ) + # Use old header-based approach for Phase 1 (backward compatibility) provider_data = { "mcp_headers": { uri: { @@ -58,7 +54,7 @@ def test_mcp_invocation(llama_stack_client, text_model_id, mcp_server): tools_list = llama_stack_client.tools.list( toolgroup_id=test_toolgroup_id, - extra_headers=auth_headers, + extra_headers=auth_headers, # Use old header-based approach ) assert len(tools_list) == 2 assert {t.name for t in tools_list} == {"greet_everyone", "get_boiling_point"} @@ -66,7 +62,7 @@ def test_mcp_invocation(llama_stack_client, text_model_id, mcp_server): response = llama_stack_client.tool_runtime.invoke_tool( tool_name="greet_everyone", kwargs=dict(url="https://www.google.com"), - extra_headers=auth_headers, + extra_headers=auth_headers, # Use old header-based approach ) content = response.content assert len(content) == 1 @@ -81,9 +77,7 @@ def test_mcp_invocation(llama_stack_client, text_model_id, mcp_server): "server_label": test_toolgroup_id, "require_approval": "never", "allowed_tools": [tool.name for tool in tools_list], - "headers": { - "Authorization": f"Bearer {AUTH_TOKEN}", - }, + "authorization": AUTH_TOKEN, } ] agent = Agent( @@ -109,7 +103,6 @@ def test_mcp_invocation(llama_stack_client, text_model_id, mcp_server): } ], stream=True, - extra_headers=auth_headers, ) ) events = [chunk.event for chunk in chunks] diff --git a/tests/integration/tool_runtime/test_mcp_json_schema.py b/tests/integration/tool_runtime/test_mcp_json_schema.py index def0b27b8..719588c7f 100644 --- a/tests/integration/tool_runtime/test_mcp_json_schema.py +++ b/tests/integration/tool_runtime/test_mcp_json_schema.py @@ -4,8 +4,7 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -""" -Integration tests for MCP tools with complex JSON Schema support. +"""Integration tests for MCP tools with complex JSON Schema support. Tests $ref, $defs, and other JSON Schema features through MCP integration. """ @@ -123,7 +122,14 @@ class TestMCPSchemaPreservation: mcp_endpoint=dict(uri=uri), ) - provider_data = {"mcp_headers": {uri: {"Authorization": f"Bearer {AUTH_TOKEN}"}}} + # Use old header-based approach for Phase 1 (backward compatibility) + provider_data = { + "mcp_headers": { + uri: { + "Authorization": f"Bearer {AUTH_TOKEN}", + }, + }, + } auth_headers = { "X-LlamaStack-Provider-Data": json.dumps(provider_data), } @@ -166,7 +172,15 @@ class TestMCPSchemaPreservation: provider_id="model-context-protocol", mcp_endpoint=dict(uri=uri), ) - provider_data = {"mcp_headers": {uri: {"Authorization": f"Bearer {AUTH_TOKEN}"}}} + + # Use old header-based approach for Phase 1 (backward compatibility) + provider_data = { + "mcp_headers": { + uri: { + "Authorization": f"Bearer {AUTH_TOKEN}", + }, + }, + } auth_headers = { "X-LlamaStack-Provider-Data": json.dumps(provider_data), } @@ -216,7 +230,14 @@ class TestMCPSchemaPreservation: mcp_endpoint=dict(uri=uri), ) - provider_data = {"mcp_headers": {uri: {"Authorization": f"Bearer {AUTH_TOKEN}"}}} + # Use old header-based approach for Phase 1 (backward compatibility) + provider_data = { + "mcp_headers": { + uri: { + "Authorization": f"Bearer {AUTH_TOKEN}", + }, + }, + } auth_headers = { "X-LlamaStack-Provider-Data": json.dumps(provider_data), } @@ -263,7 +284,14 @@ class TestMCPToolInvocation: mcp_endpoint=dict(uri=uri), ) - provider_data = {"mcp_headers": {uri: {"Authorization": f"Bearer {AUTH_TOKEN}"}}} + # Use old header-based approach for Phase 1 (backward compatibility) + provider_data = { + "mcp_headers": { + uri: { + "Authorization": f"Bearer {AUTH_TOKEN}", + }, + }, + } auth_headers = { "X-LlamaStack-Provider-Data": json.dumps(provider_data), } @@ -309,7 +337,14 @@ class TestMCPToolInvocation: mcp_endpoint=dict(uri=uri), ) - provider_data = {"mcp_headers": {uri: {"Authorization": f"Bearer {AUTH_TOKEN}"}}} + # Use old header-based approach for Phase 1 (backward compatibility) + provider_data = { + "mcp_headers": { + uri: { + "Authorization": f"Bearer {AUTH_TOKEN}", + }, + }, + } auth_headers = { "X-LlamaStack-Provider-Data": json.dumps(provider_data), } @@ -365,7 +400,14 @@ class TestAgentWithMCPTools: mcp_endpoint=dict(uri=uri), ) - provider_data = {"mcp_headers": {uri: {"Authorization": f"Bearer {AUTH_TOKEN}"}}} + # Use old header-based approach for Phase 1 (backward compatibility) + provider_data = { + "mcp_headers": { + uri: { + "Authorization": f"Bearer {AUTH_TOKEN}", + }, + }, + } auth_headers = { "X-LlamaStack-Provider-Data": json.dumps(provider_data), } @@ -381,6 +423,7 @@ class TestAgentWithMCPTools: "server_label": test_toolgroup_id, "require_approval": "never", "allowed_tools": [tool.name for tool in tools_list], + "authorization": AUTH_TOKEN, } ] @@ -389,7 +432,6 @@ class TestAgentWithMCPTools: model=text_model_id, instructions="You are a helpful assistant that can process orders and book flights.", tools=tool_defs, - extra_headers=auth_headers, ) session_id = agent.create_session("test-session-complex") @@ -411,7 +453,6 @@ class TestAgentWithMCPTools: } ], stream=True, - extra_headers=auth_headers, ) ) diff --git a/tests/integration/tool_runtime/test_registration.py b/tests/integration/tool_runtime/test_registration.py index 4d532ed87..036a5f018 100644 --- a/tests/integration/tool_runtime/test_registration.py +++ b/tests/integration/tool_runtime/test_registration.py @@ -8,8 +8,8 @@ import re import pytest -from llama_stack.apis.common.errors import ToolGroupNotFoundError from llama_stack.core.library_client import LlamaStackAsLibraryClient +from llama_stack_api import ToolGroupNotFoundError from tests.common.mcp import MCP_TOOLGROUP_ID, make_mcp_server diff --git a/tests/integration/vector_io/test_openai_vector_stores.py b/tests/integration/vector_io/test_openai_vector_stores.py index 1043d4903..102f3f00c 100644 --- a/tests/integration/vector_io/test_openai_vector_stores.py +++ b/tests/integration/vector_io/test_openai_vector_stores.py @@ -11,10 +11,9 @@ import pytest from llama_stack_client import BadRequestError from openai import BadRequestError as OpenAIBadRequestError -from llama_stack.apis.files import ExpiresAfter -from llama_stack.apis.vector_io import Chunk from llama_stack.core.library_client import LlamaStackAsLibraryClient from llama_stack.log import get_logger +from llama_stack_api import Chunk, ExpiresAfter from ..conftest import vector_provider_wrapper @@ -646,7 +645,7 @@ def test_openai_vector_store_attach_file( ): """Test OpenAI vector store attach file.""" skip_if_provider_doesnt_support_openai_vector_stores(client_with_models) - from llama_stack.apis.files import ExpiresAfter + from llama_stack_api import ExpiresAfter compat_client = compat_client_with_empty_stores @@ -710,7 +709,7 @@ def test_openai_vector_store_attach_files_on_creation( skip_if_provider_doesnt_support_openai_vector_stores(client_with_models) compat_client = compat_client_with_empty_stores - from llama_stack.apis.files import ExpiresAfter + from llama_stack_api import ExpiresAfter # Create some files and attach them to the vector store valid_file_ids = [] @@ -775,7 +774,7 @@ def test_openai_vector_store_list_files( skip_if_provider_doesnt_support_openai_vector_stores(client_with_models) compat_client = compat_client_with_empty_stores - from llama_stack.apis.files import ExpiresAfter + from llama_stack_api import ExpiresAfter # Create a vector store vector_store = compat_client.vector_stores.create( @@ -867,7 +866,7 @@ def test_openai_vector_store_retrieve_file_contents( skip_if_provider_doesnt_support_openai_vector_stores(client_with_models) compat_client = compat_client_with_empty_stores - from llama_stack.apis.files import ExpiresAfter + from llama_stack_api import ExpiresAfter # Create a vector store vector_store = compat_client.vector_stores.create( @@ -928,7 +927,7 @@ def test_openai_vector_store_delete_file( skip_if_provider_doesnt_support_openai_vector_stores(client_with_models) compat_client = compat_client_with_empty_stores - from llama_stack.apis.files import ExpiresAfter + from llama_stack_api import ExpiresAfter # Create a vector store vector_store = compat_client.vector_stores.create( @@ -994,7 +993,7 @@ def test_openai_vector_store_delete_file_removes_from_vector_store( skip_if_provider_doesnt_support_openai_vector_stores(client_with_models) compat_client = compat_client_with_empty_stores - from llama_stack.apis.files import ExpiresAfter + from llama_stack_api import ExpiresAfter # Create a vector store vector_store = compat_client.vector_stores.create( @@ -1046,7 +1045,7 @@ def test_openai_vector_store_update_file( skip_if_provider_doesnt_support_openai_vector_stores(client_with_models) compat_client = compat_client_with_empty_stores - from llama_stack.apis.files import ExpiresAfter + from llama_stack_api import ExpiresAfter # Create a vector store vector_store = compat_client.vector_stores.create( @@ -1103,7 +1102,7 @@ def test_create_vector_store_files_duplicate_vector_store_name( This test confirms that client.vector_stores.create() creates a unique ID """ skip_if_provider_doesnt_support_openai_vector_stores(client_with_models) - from llama_stack.apis.files import ExpiresAfter + from llama_stack_api import ExpiresAfter compat_client = compat_client_with_empty_stores diff --git a/tests/integration/vector_io/test_vector_io.py b/tests/integration/vector_io/test_vector_io.py index 1b2099069..29dbd3e56 100644 --- a/tests/integration/vector_io/test_vector_io.py +++ b/tests/integration/vector_io/test_vector_io.py @@ -6,7 +6,7 @@ import pytest -from llama_stack.apis.vector_io import Chunk +from llama_stack_api import Chunk from ..conftest import vector_provider_wrapper diff --git a/tests/unit/conversations/test_api_models.py b/tests/unit/conversations/test_api_models.py index 8416cba0b..f8576f076 100644 --- a/tests/unit/conversations/test_api_models.py +++ b/tests/unit/conversations/test_api_models.py @@ -5,11 +5,7 @@ # the root directory of this source tree. -from llama_stack.apis.conversations.conversations import ( - Conversation, - ConversationItem, - ConversationItemList, -) +from llama_stack_api import Conversation, ConversationItem, ConversationItemList def test_conversation_model_defaults(): diff --git a/tests/unit/conversations/test_conversations.py b/tests/unit/conversations/test_conversations.py index 3f0175831..95c54d379 100644 --- a/tests/unit/conversations/test_conversations.py +++ b/tests/unit/conversations/test_conversations.py @@ -12,10 +12,6 @@ from openai.types.conversations.conversation import Conversation as OpenAIConver from openai.types.conversations.conversation_item import ConversationItem as OpenAIConversationItem from pydantic import TypeAdapter -from llama_stack.apis.agents.openai_responses import ( - OpenAIResponseInputMessageContentText, - OpenAIResponseMessage, -) from llama_stack.core.conversations.conversations import ( ConversationServiceConfig, ConversationServiceImpl, @@ -28,6 +24,7 @@ from llama_stack.core.storage.datatypes import ( StorageConfig, ) from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends +from llama_stack_api import OpenAIResponseInputMessageContentText, OpenAIResponseMessage @pytest.fixture diff --git a/tests/unit/core/routers/test_safety_router.py b/tests/unit/core/routers/test_safety_router.py index bf195ff33..1b24a59a2 100644 --- a/tests/unit/core/routers/test_safety_router.py +++ b/tests/unit/core/routers/test_safety_router.py @@ -6,10 +6,9 @@ from unittest.mock import AsyncMock -from llama_stack.apis.safety.safety import ModerationObject, ModerationObjectResults -from llama_stack.apis.shields import ListShieldsResponse, Shield from llama_stack.core.datatypes import SafetyConfig from llama_stack.core.routers.safety import SafetyRouter +from llama_stack_api import ListShieldsResponse, ModerationObject, ModerationObjectResults, Shield async def test_run_moderation_uses_default_shield_when_model_missing(): diff --git a/tests/unit/core/routers/test_vector_io.py b/tests/unit/core/routers/test_vector_io.py index f9bd84a37..a6df0694b 100644 --- a/tests/unit/core/routers/test_vector_io.py +++ b/tests/unit/core/routers/test_vector_io.py @@ -8,8 +8,13 @@ from unittest.mock import AsyncMock, Mock import pytest -from llama_stack.apis.vector_io import OpenAICreateVectorStoreRequestWithExtraBody from llama_stack.core.routers.vector_io import VectorIORouter +from llama_stack_api import ( + ModelNotFoundError, + ModelType, + ModelTypeError, + OpenAICreateVectorStoreRequestWithExtraBody, +) async def test_single_provider_auto_selection(): @@ -21,6 +26,7 @@ async def test_single_provider_auto_selection(): Mock(identifier="all-MiniLM-L6-v2", model_type="embedding", metadata={"embedding_dimension": 384}) ] ) + mock_routing_table.get_object_by_identifier = AsyncMock(return_value=Mock(model_type=ModelType.embedding)) mock_routing_table.register_vector_store = AsyncMock( return_value=Mock(identifier="vs_123", provider_id="inline::faiss", provider_resource_id="vs_123") ) @@ -48,6 +54,7 @@ async def test_create_vector_stores_multiple_providers_missing_provider_id_error Mock(identifier="all-MiniLM-L6-v2", model_type="embedding", metadata={"embedding_dimension": 384}) ] ) + mock_routing_table.get_object_by_identifier = AsyncMock(return_value=Mock(model_type=ModelType.embedding)) router = VectorIORouter(mock_routing_table) request = OpenAICreateVectorStoreRequestWithExtraBody.model_validate( {"name": "test_store", "embedding_model": "all-MiniLM-L6-v2"} @@ -117,3 +124,32 @@ async def test_update_vector_store_same_provider_id_succeeds(): provider.openai_update_vector_store.assert_called_once_with( vector_store_id="vs_123", name="updated_name", expires_after=None, metadata={"provider_id": "inline::faiss"} ) + + +async def test_create_vector_store_with_unknown_embedding_model_raises_error(): + """Test that creating a vector store with an unknown embedding model raises + FoundError.""" + mock_routing_table = Mock(impls_by_provider_id={"provider": "mock"}) + mock_routing_table.get_object_by_identifier = AsyncMock(return_value=None) + + router = VectorIORouter(mock_routing_table) + request = OpenAICreateVectorStoreRequestWithExtraBody.model_validate( + {"embedding_model": "unknown-model", "embedding_dimension": 384} + ) + + with pytest.raises(ModelNotFoundError, match="Model 'unknown-model' not found"): + await router.openai_create_vector_store(request) + + +async def test_create_vector_store_with_wrong_model_type_raises_error(): + """Test that creating a vector store with a non-embedding model raises ModelTypeError.""" + mock_routing_table = Mock(impls_by_provider_id={"provider": "mock"}) + mock_routing_table.get_object_by_identifier = AsyncMock(return_value=Mock(model_type=ModelType.llm)) + + router = VectorIORouter(mock_routing_table) + request = OpenAICreateVectorStoreRequestWithExtraBody.model_validate( + {"embedding_model": "text-model", "embedding_dimension": 384} + ) + + with pytest.raises(ModelTypeError, match="Model 'text-model' is of type"): + await router.openai_create_vector_store(request) diff --git a/tests/unit/core/test_stack_validation.py b/tests/unit/core/test_stack_validation.py index d28803006..462a25c8b 100644 --- a/tests/unit/core/test_stack_validation.py +++ b/tests/unit/core/test_stack_validation.py @@ -10,11 +10,9 @@ from unittest.mock import AsyncMock import pytest -from llama_stack.apis.models import ListModelsResponse, Model, ModelType -from llama_stack.apis.shields import ListShieldsResponse, Shield from llama_stack.core.datatypes import QualifiedModel, SafetyConfig, StackRunConfig, StorageConfig, VectorStoresConfig from llama_stack.core.stack import validate_safety_config, validate_vector_stores_config -from llama_stack.providers.datatypes import Api +from llama_stack_api import Api, ListModelsResponse, ListShieldsResponse, Model, ModelType, Shield class TestVectorStoresValidation: diff --git a/tests/unit/distribution/routers/test_routing_tables.py b/tests/unit/distribution/routers/test_routing_tables.py index 8c1838ba3..292ee8384 100644 --- a/tests/unit/distribution/routers/test_routing_tables.py +++ b/tests/unit/distribution/routers/test_routing_tables.py @@ -10,14 +10,6 @@ from unittest.mock import AsyncMock import pytest -from llama_stack.apis.common.content_types import URL -from llama_stack.apis.common.errors import ModelNotFoundError -from llama_stack.apis.common.type_system import NumberType -from llama_stack.apis.datasets.datasets import Dataset, DatasetPurpose, URIDataSource -from llama_stack.apis.datatypes import Api -from llama_stack.apis.models import Model, ModelType -from llama_stack.apis.shields.shields import Shield -from llama_stack.apis.tools import ListToolDefsResponse, ToolDef, ToolGroup from llama_stack.core.datatypes import RegistryEntrySource from llama_stack.core.routing_tables.benchmarks import BenchmarksRoutingTable from llama_stack.core.routing_tables.datasets import DatasetsRoutingTable @@ -25,6 +17,21 @@ from llama_stack.core.routing_tables.models import ModelsRoutingTable from llama_stack.core.routing_tables.scoring_functions import ScoringFunctionsRoutingTable from llama_stack.core.routing_tables.shields import ShieldsRoutingTable from llama_stack.core.routing_tables.toolgroups import ToolGroupsRoutingTable +from llama_stack_api import ( + URL, + Api, + Dataset, + DatasetPurpose, + ListToolDefsResponse, + Model, + ModelNotFoundError, + ModelType, + NumberType, + Shield, + ToolDef, + ToolGroup, + URIDataSource, +) class Impl: @@ -130,7 +137,7 @@ class ToolGroupsImpl(Impl): async def unregister_toolgroup(self, toolgroup_id: str): return toolgroup_id - async def list_runtime_tools(self, toolgroup_id, mcp_endpoint): + async def list_runtime_tools(self, toolgroup_id, mcp_endpoint, authorization=None): return ListToolDefsResponse( data=[ ToolDef( diff --git a/tests/unit/distribution/test_api_recordings.py b/tests/unit/distribution/test_api_recordings.py index 2b7ce5c4e..889f063e6 100644 --- a/tests/unit/distribution/test_api_recordings.py +++ b/tests/unit/distribution/test_api_recordings.py @@ -11,8 +11,15 @@ from unittest.mock import patch import pytest from openai import AsyncOpenAI +from llama_stack.testing.api_recorder import ( + APIRecordingMode, + ResponseStorage, + api_recording, + normalize_inference_request, +) + # Import the real Pydantic response types instead of using Mocks -from llama_stack.apis.inference import ( +from llama_stack_api import ( OpenAIAssistantMessageParam, OpenAIChatCompletion, OpenAIChoice, @@ -20,12 +27,6 @@ from llama_stack.apis.inference import ( OpenAIEmbeddingsResponse, OpenAIEmbeddingUsage, ) -from llama_stack.testing.api_recorder import ( - APIRecordingMode, - ResponseStorage, - api_recording, - normalize_inference_request, -) @pytest.fixture diff --git a/tests/unit/distribution/test_distribution.py b/tests/unit/distribution/test_distribution.py index 11f55cfdb..b8d6ba55d 100644 --- a/tests/unit/distribution/test_distribution.py +++ b/tests/unit/distribution/test_distribution.py @@ -22,7 +22,7 @@ from llama_stack.core.storage.datatypes import ( SqlStoreReference, StorageConfig, ) -from llama_stack.providers.datatypes import ProviderSpec +from llama_stack_api import ProviderSpec class SampleConfig(BaseModel): @@ -312,7 +312,7 @@ pip_packages: """Test loading an external provider from a module (success path).""" from types import SimpleNamespace - from llama_stack.providers.datatypes import Api, ProviderSpec + from llama_stack_api import Api, ProviderSpec # Simulate a provider module with get_provider_spec fake_spec = ProviderSpec( @@ -396,7 +396,7 @@ pip_packages: def test_external_provider_from_module_building(self, mock_providers): """Test loading an external provider from a module during build (building=True, partial spec).""" from llama_stack.core.datatypes import BuildConfig, BuildProvider, DistributionSpec - from llama_stack.providers.datatypes import Api + from llama_stack_api import Api # No importlib patch needed, should not import module when type of `config` is BuildConfig or DistributionSpec build_config = BuildConfig( @@ -457,7 +457,7 @@ class TestGetExternalProvidersFromModule: from types import SimpleNamespace from llama_stack.core.distribution import get_external_providers_from_module - from llama_stack.providers.datatypes import ProviderSpec + from llama_stack_api import ProviderSpec fake_spec = ProviderSpec( api=Api.inference, @@ -594,7 +594,7 @@ class TestGetExternalProvidersFromModule: from types import SimpleNamespace from llama_stack.core.distribution import get_external_providers_from_module - from llama_stack.providers.datatypes import ProviderSpec + from llama_stack_api import ProviderSpec spec1 = ProviderSpec( api=Api.inference, @@ -642,7 +642,7 @@ class TestGetExternalProvidersFromModule: from types import SimpleNamespace from llama_stack.core.distribution import get_external_providers_from_module - from llama_stack.providers.datatypes import ProviderSpec + from llama_stack_api import ProviderSpec spec1 = ProviderSpec( api=Api.inference, @@ -690,7 +690,7 @@ class TestGetExternalProvidersFromModule: from types import SimpleNamespace from llama_stack.core.distribution import get_external_providers_from_module - from llama_stack.providers.datatypes import ProviderSpec + from llama_stack_api import ProviderSpec # Module returns both inline and remote variants spec1 = ProviderSpec( @@ -829,7 +829,7 @@ class TestGetExternalProvidersFromModule: from types import SimpleNamespace from llama_stack.core.distribution import get_external_providers_from_module - from llama_stack.providers.datatypes import ProviderSpec + from llama_stack_api import ProviderSpec inference_spec = ProviderSpec( api=Api.inference, diff --git a/tests/unit/files/test_files.py b/tests/unit/files/test_files.py index 426e2cf64..793f4edd3 100644 --- a/tests/unit/files/test_files.py +++ b/tests/unit/files/test_files.py @@ -7,9 +7,6 @@ import pytest -from llama_stack.apis.common.errors import ResourceNotFoundError -from llama_stack.apis.common.responses import Order -from llama_stack.apis.files import OpenAIFilePurpose from llama_stack.core.access_control.access_control import default_policy from llama_stack.core.storage.datatypes import SqliteSqlStoreConfig, SqlStoreReference from llama_stack.providers.inline.files.localfs import ( @@ -17,6 +14,7 @@ from llama_stack.providers.inline.files.localfs import ( LocalfsFilesImplConfig, ) from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends +from llama_stack_api import OpenAIFilePurpose, Order, ResourceNotFoundError class MockUploadFile: diff --git a/tests/unit/providers/batches/test_reference.py b/tests/unit/providers/batches/test_reference.py index 89cb1af9d..32d59234d 100644 --- a/tests/unit/providers/batches/test_reference.py +++ b/tests/unit/providers/batches/test_reference.py @@ -59,8 +59,7 @@ from unittest.mock import AsyncMock, MagicMock import pytest -from llama_stack.apis.batches import BatchObject -from llama_stack.apis.common.errors import ConflictError, ResourceNotFoundError +from llama_stack_api import BatchObject, ConflictError, ResourceNotFoundError class TestReferenceBatchesImpl: diff --git a/tests/unit/providers/batches/test_reference_idempotency.py b/tests/unit/providers/batches/test_reference_idempotency.py index e6cb29b9b..acb7ca01c 100644 --- a/tests/unit/providers/batches/test_reference_idempotency.py +++ b/tests/unit/providers/batches/test_reference_idempotency.py @@ -44,7 +44,7 @@ import asyncio import pytest -from llama_stack.apis.common.errors import ConflictError +from llama_stack_api import ConflictError class TestReferenceBatchesIdempotency: diff --git a/tests/unit/providers/files/test_s3_files.py b/tests/unit/providers/files/test_s3_files.py index 92a45a9f2..de6c92e9c 100644 --- a/tests/unit/providers/files/test_s3_files.py +++ b/tests/unit/providers/files/test_s3_files.py @@ -9,8 +9,7 @@ from unittest.mock import patch import pytest from botocore.exceptions import ClientError -from llama_stack.apis.common.errors import ResourceNotFoundError -from llama_stack.apis.files import OpenAIFilePurpose +from llama_stack_api import OpenAIFilePurpose, ResourceNotFoundError class TestS3FilesImpl: @@ -228,7 +227,7 @@ class TestS3FilesImpl: mock_now.return_value = 0 - from llama_stack.apis.files import ExpiresAfter + from llama_stack_api import ExpiresAfter sample_text_file.filename = "test_expired_file" uploaded = await s3_provider.openai_upload_file( @@ -260,7 +259,7 @@ class TestS3FilesImpl: async def test_unsupported_expires_after_anchor(self, s3_provider, sample_text_file): """Unsupported anchor value should raise ValueError.""" - from llama_stack.apis.files import ExpiresAfter + from llama_stack_api import ExpiresAfter sample_text_file.filename = "test_unsupported_expires_after_anchor" @@ -273,7 +272,7 @@ class TestS3FilesImpl: async def test_nonint_expires_after_seconds(self, s3_provider, sample_text_file): """Non-integer seconds in expires_after should raise ValueError.""" - from llama_stack.apis.files import ExpiresAfter + from llama_stack_api import ExpiresAfter sample_text_file.filename = "test_nonint_expires_after_seconds" @@ -286,7 +285,7 @@ class TestS3FilesImpl: async def test_expires_after_seconds_out_of_bounds(self, s3_provider, sample_text_file): """Seconds outside allowed range should raise ValueError.""" - from llama_stack.apis.files import ExpiresAfter + from llama_stack_api import ExpiresAfter with pytest.raises(ValueError, match="greater than or equal to 3600"): await s3_provider.openai_upload_file( diff --git a/tests/unit/providers/files/test_s3_files_auth.py b/tests/unit/providers/files/test_s3_files_auth.py index 6097f2808..e113611bd 100644 --- a/tests/unit/providers/files/test_s3_files_auth.py +++ b/tests/unit/providers/files/test_s3_files_auth.py @@ -8,10 +8,9 @@ from unittest.mock import patch import pytest -from llama_stack.apis.common.errors import ResourceNotFoundError -from llama_stack.apis.files import OpenAIFilePurpose from llama_stack.core.datatypes import User from llama_stack.providers.remote.files.s3.files import S3FilesImpl +from llama_stack_api import OpenAIFilePurpose, ResourceNotFoundError async def test_listing_hides_other_users_file(s3_provider, sample_text_file): diff --git a/tests/unit/providers/inference/test_bedrock_adapter.py b/tests/unit/providers/inference/test_bedrock_adapter.py index fdd07c032..a20f2860a 100644 --- a/tests/unit/providers/inference/test_bedrock_adapter.py +++ b/tests/unit/providers/inference/test_bedrock_adapter.py @@ -10,9 +10,9 @@ from unittest.mock import AsyncMock, MagicMock import pytest from openai import AuthenticationError -from llama_stack.apis.inference import OpenAIChatCompletionRequestWithExtraBody from llama_stack.providers.remote.inference.bedrock.bedrock import BedrockInferenceAdapter from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig +from llama_stack_api import OpenAIChatCompletionRequestWithExtraBody def test_adapter_initialization(): diff --git a/tests/unit/providers/inference/test_remote_vllm.py b/tests/unit/providers/inference/test_remote_vllm.py index ffd45798e..958895cc4 100644 --- a/tests/unit/providers/inference/test_remote_vllm.py +++ b/tests/unit/providers/inference/test_remote_vllm.py @@ -10,7 +10,13 @@ from unittest.mock import AsyncMock, MagicMock, PropertyMock, patch import pytest -from llama_stack.apis.inference import ( +from llama_stack.core.routers.inference import InferenceRouter +from llama_stack.core.routing_tables.models import ModelsRoutingTable +from llama_stack.providers.remote.inference.vllm.config import VLLMInferenceAdapterConfig +from llama_stack.providers.remote.inference.vllm.vllm import VLLMInferenceAdapter +from llama_stack_api import ( + HealthStatus, + Model, OpenAIAssistantMessageParam, OpenAIChatCompletion, OpenAIChatCompletionRequestWithExtraBody, @@ -20,12 +26,6 @@ from llama_stack.apis.inference import ( OpenAICompletionRequestWithExtraBody, ToolChoice, ) -from llama_stack.apis.models import Model -from llama_stack.core.routers.inference import InferenceRouter -from llama_stack.core.routing_tables.models import ModelsRoutingTable -from llama_stack.providers.datatypes import HealthStatus -from llama_stack.providers.remote.inference.vllm.config import VLLMInferenceAdapterConfig -from llama_stack.providers.remote.inference.vllm.vllm import VLLMInferenceAdapter # These are unit test for the remote vllm provider # implementation. This should only contain tests which are specific to diff --git a/tests/unit/providers/inline/agents/meta_reference/responses/test_streaming.py b/tests/unit/providers/inline/agents/meta_reference/responses/test_streaming.py index fff29928c..658132340 100644 --- a/tests/unit/providers/inline/agents/meta_reference/responses/test_streaming.py +++ b/tests/unit/providers/inline/agents/meta_reference/responses/test_streaming.py @@ -8,11 +8,11 @@ from unittest.mock import AsyncMock import pytest -from llama_stack.apis.tools import ToolDef from llama_stack.providers.inline.agents.meta_reference.responses.streaming import ( convert_tooldef_to_chat_tool, ) from llama_stack.providers.inline.agents.meta_reference.responses.types import ChatCompletionContext +from llama_stack_api import ToolDef @pytest.fixture diff --git a/tests/unit/providers/nvidia/test_datastore.py b/tests/unit/providers/nvidia/test_datastore.py index b59636f7b..36006cc39 100644 --- a/tests/unit/providers/nvidia/test_datastore.py +++ b/tests/unit/providers/nvidia/test_datastore.py @@ -9,10 +9,9 @@ from unittest.mock import patch import pytest -from llama_stack.apis.datasets import Dataset, DatasetPurpose, URIDataSource -from llama_stack.apis.resource import ResourceType from llama_stack.providers.remote.datasetio.nvidia.config import NvidiaDatasetIOConfig from llama_stack.providers.remote.datasetio.nvidia.datasetio import NvidiaDatasetIOAdapter +from llama_stack_api import Dataset, DatasetPurpose, ResourceType, URIDataSource @pytest.fixture diff --git a/tests/unit/providers/nvidia/test_eval.py b/tests/unit/providers/nvidia/test_eval.py index 86e005b76..783d664bf 100644 --- a/tests/unit/providers/nvidia/test_eval.py +++ b/tests/unit/providers/nvidia/test_eval.py @@ -9,14 +9,20 @@ from unittest.mock import MagicMock, patch import pytest -from llama_stack.apis.benchmarks import Benchmark -from llama_stack.apis.common.job_types import Job, JobStatus -from llama_stack.apis.eval.eval import BenchmarkConfig, EvaluateResponse, ModelCandidate, SamplingParams -from llama_stack.apis.inference.inference import TopPSamplingStrategy -from llama_stack.apis.resource import ResourceType from llama_stack.models.llama.sku_types import CoreModelId from llama_stack.providers.remote.eval.nvidia.config import NVIDIAEvalConfig from llama_stack.providers.remote.eval.nvidia.eval import NVIDIAEvalImpl +from llama_stack_api import ( + Benchmark, + BenchmarkConfig, + EvaluateResponse, + Job, + JobStatus, + ModelCandidate, + ResourceType, + SamplingParams, + TopPSamplingStrategy, +) MOCK_DATASET_ID = "default/test-dataset" MOCK_BENCHMARK_ID = "test-benchmark" diff --git a/tests/unit/providers/nvidia/test_parameters.py b/tests/unit/providers/nvidia/test_parameters.py index ad381da26..b714fc607 100644 --- a/tests/unit/providers/nvidia/test_parameters.py +++ b/tests/unit/providers/nvidia/test_parameters.py @@ -10,7 +10,12 @@ from unittest.mock import patch import pytest -from llama_stack.apis.post_training.post_training import ( +from llama_stack.core.library_client import convert_pydantic_to_json_value +from llama_stack.providers.remote.post_training.nvidia.post_training import ( + NvidiaPostTrainingAdapter, + NvidiaPostTrainingConfig, +) +from llama_stack_api import ( DataConfig, DatasetFormat, EfficiencyConfig, @@ -19,11 +24,6 @@ from llama_stack.apis.post_training.post_training import ( OptimizerType, TrainingConfig, ) -from llama_stack.core.library_client import convert_pydantic_to_json_value -from llama_stack.providers.remote.post_training.nvidia.post_training import ( - NvidiaPostTrainingAdapter, - NvidiaPostTrainingConfig, -) class TestNvidiaParameters: diff --git a/tests/unit/providers/nvidia/test_rerank_inference.py b/tests/unit/providers/nvidia/test_rerank_inference.py index 2793b5f44..ee62910b8 100644 --- a/tests/unit/providers/nvidia/test_rerank_inference.py +++ b/tests/unit/providers/nvidia/test_rerank_inference.py @@ -9,10 +9,10 @@ from unittest.mock import AsyncMock, MagicMock, patch import aiohttp import pytest -from llama_stack.apis.models import ModelType from llama_stack.providers.remote.inference.nvidia.config import NVIDIAConfig from llama_stack.providers.remote.inference.nvidia.nvidia import NVIDIAInferenceAdapter from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import ModelType class MockResponse: diff --git a/tests/unit/providers/nvidia/test_safety.py b/tests/unit/providers/nvidia/test_safety.py index 622302630..07e04ddea 100644 --- a/tests/unit/providers/nvidia/test_safety.py +++ b/tests/unit/providers/nvidia/test_safety.py @@ -10,15 +10,16 @@ from unittest.mock import AsyncMock, MagicMock, patch import pytest -from llama_stack.apis.inference import ( - OpenAIAssistantMessageParam, - OpenAIUserMessageParam, -) -from llama_stack.apis.resource import ResourceType -from llama_stack.apis.safety import RunShieldResponse, ViolationLevel -from llama_stack.apis.shields import Shield from llama_stack.providers.remote.safety.nvidia.config import NVIDIASafetyConfig from llama_stack.providers.remote.safety.nvidia.nvidia import NVIDIASafetyAdapter +from llama_stack_api import ( + OpenAIAssistantMessageParam, + OpenAIUserMessageParam, + ResourceType, + RunShieldResponse, + Shield, + ViolationLevel, +) class FakeNVIDIASafetyAdapter(NVIDIASafetyAdapter): diff --git a/tests/unit/providers/nvidia/test_supervised_fine_tuning.py b/tests/unit/providers/nvidia/test_supervised_fine_tuning.py index 91148605d..94948da41 100644 --- a/tests/unit/providers/nvidia/test_supervised_fine_tuning.py +++ b/tests/unit/providers/nvidia/test_supervised_fine_tuning.py @@ -10,15 +10,6 @@ from unittest.mock import patch import pytest -from llama_stack.apis.post_training.post_training import ( - DataConfig, - DatasetFormat, - LoraFinetuningConfig, - OptimizerConfig, - OptimizerType, - QATFinetuningConfig, - TrainingConfig, -) from llama_stack.core.library_client import convert_pydantic_to_json_value from llama_stack.providers.remote.post_training.nvidia.post_training import ( ListNvidiaPostTrainingJobs, @@ -27,6 +18,15 @@ from llama_stack.providers.remote.post_training.nvidia.post_training import ( NvidiaPostTrainingJob, NvidiaPostTrainingJobStatusResponse, ) +from llama_stack_api import ( + DataConfig, + DatasetFormat, + LoraFinetuningConfig, + OptimizerConfig, + OptimizerType, + QATFinetuningConfig, + TrainingConfig, +) @pytest.fixture diff --git a/tests/unit/providers/test_bedrock.py b/tests/unit/providers/test_bedrock.py index 684fcf262..7126e1b69 100644 --- a/tests/unit/providers/test_bedrock.py +++ b/tests/unit/providers/test_bedrock.py @@ -7,9 +7,9 @@ from types import SimpleNamespace from unittest.mock import AsyncMock, PropertyMock, patch -from llama_stack.apis.inference import OpenAIChatCompletionRequestWithExtraBody from llama_stack.providers.remote.inference.bedrock.bedrock import BedrockInferenceAdapter from llama_stack.providers.remote.inference.bedrock.config import BedrockConfig +from llama_stack_api import OpenAIChatCompletionRequestWithExtraBody def test_can_create_adapter(): diff --git a/tests/unit/providers/utils/inference/test_openai_mixin.py b/tests/unit/providers/utils/inference/test_openai_mixin.py index 0b5ea078b..5b13a75f4 100644 --- a/tests/unit/providers/utils/inference/test_openai_mixin.py +++ b/tests/unit/providers/utils/inference/test_openai_mixin.py @@ -12,11 +12,10 @@ from unittest.mock import AsyncMock, MagicMock, Mock, PropertyMock, patch import pytest from pydantic import BaseModel, Field -from llama_stack.apis.inference import Model, OpenAIChatCompletionRequestWithExtraBody, OpenAIUserMessageParam -from llama_stack.apis.models import ModelType from llama_stack.core.request_headers import request_provider_data_context from llama_stack.providers.utils.inference.model_registry import RemoteInferenceProviderConfig from llama_stack.providers.utils.inference.openai_mixin import OpenAIMixin +from llama_stack_api import Model, ModelType, OpenAIChatCompletionRequestWithExtraBody, OpenAIUserMessageParam class OpenAIMixinImpl(OpenAIMixin): diff --git a/tests/unit/providers/utils/inference/test_prompt_adapter.py b/tests/unit/providers/utils/inference/test_prompt_adapter.py index 62c8db74d..ab5736ac5 100644 --- a/tests/unit/providers/utils/inference/test_prompt_adapter.py +++ b/tests/unit/providers/utils/inference/test_prompt_adapter.py @@ -4,14 +4,11 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.inference import ( - OpenAIAssistantMessageParam, - OpenAIUserMessageParam, -) from llama_stack.models.llama.datatypes import RawTextItem from llama_stack.providers.utils.inference.prompt_adapter import ( convert_openai_message_to_raw_message, ) +from llama_stack_api import OpenAIAssistantMessageParam, OpenAIUserMessageParam class TestConvertOpenAIMessageToRawMessage: diff --git a/tests/unit/providers/utils/memory/test_vector_store.py b/tests/unit/providers/utils/memory/test_vector_store.py index 590bdd1d2..f3241ba20 100644 --- a/tests/unit/providers/utils/memory/test_vector_store.py +++ b/tests/unit/providers/utils/memory/test_vector_store.py @@ -8,9 +8,8 @@ from unittest.mock import AsyncMock, MagicMock, patch import pytest -from llama_stack.apis.common.content_types import URL, TextContentItem -from llama_stack.apis.tools import RAGDocument from llama_stack.providers.utils.memory.vector_store import content_from_data_and_mime_type, content_from_doc +from llama_stack_api import URL, RAGDocument, TextContentItem async def test_content_from_doc_with_url(): diff --git a/tests/unit/providers/utils/test_model_registry.py b/tests/unit/providers/utils/test_model_registry.py index 04e75aa82..1e3efafa1 100644 --- a/tests/unit/providers/utils/test_model_registry.py +++ b/tests/unit/providers/utils/test_model_registry.py @@ -35,8 +35,8 @@ import pytest -from llama_stack.apis.models import Model from llama_stack.providers.utils.inference.model_registry import ModelRegistryHelper, ProviderModelEntry +from llama_stack_api import Model @pytest.fixture diff --git a/tests/unit/providers/vector_io/conftest.py b/tests/unit/providers/vector_io/conftest.py index 5e56ea417..6408e25ab 100644 --- a/tests/unit/providers/vector_io/conftest.py +++ b/tests/unit/providers/vector_io/conftest.py @@ -10,8 +10,6 @@ from unittest.mock import AsyncMock, MagicMock, patch import numpy as np import pytest -from llama_stack.apis.vector_io import Chunk, ChunkMetadata, QueryChunksResponse -from llama_stack.apis.vector_stores import VectorStore from llama_stack.core.storage.datatypes import KVStoreReference, SqliteKVStoreConfig from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.providers.inline.vector_io.faiss.faiss import FaissIndex, FaissVectorIOAdapter @@ -20,6 +18,7 @@ from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import SQLiteV from llama_stack.providers.remote.vector_io.pgvector.config import PGVectorVectorIOConfig from llama_stack.providers.remote.vector_io.pgvector.pgvector import PGVectorIndex, PGVectorVectorIOAdapter from llama_stack.providers.utils.kvstore import register_kvstore_backends +from llama_stack_api import Chunk, ChunkMetadata, QueryChunksResponse, VectorStore EMBEDDING_DIMENSION = 768 COLLECTION_PREFIX = "test_collection" diff --git a/tests/unit/providers/vector_io/test_faiss.py b/tests/unit/providers/vector_io/test_faiss.py index 44bcd0cfd..075296cbb 100644 --- a/tests/unit/providers/vector_io/test_faiss.py +++ b/tests/unit/providers/vector_io/test_faiss.py @@ -10,15 +10,12 @@ from unittest.mock import MagicMock, patch import numpy as np import pytest -from llama_stack.apis.files import Files -from llama_stack.apis.vector_io import Chunk, QueryChunksResponse -from llama_stack.apis.vector_stores import VectorStore -from llama_stack.providers.datatypes import HealthStatus from llama_stack.providers.inline.vector_io.faiss.config import FaissVectorIOConfig from llama_stack.providers.inline.vector_io.faiss.faiss import ( FaissIndex, FaissVectorIOAdapter, ) +from llama_stack_api import Chunk, Files, HealthStatus, QueryChunksResponse, VectorStore # This test is a unit test for the FaissVectorIOAdapter class. This should only contain # tests which are specific to this class. More general (API-level) tests should be placed in diff --git a/tests/unit/providers/vector_io/test_sqlite_vec.py b/tests/unit/providers/vector_io/test_sqlite_vec.py index 5ee62cd63..d1548cf37 100644 --- a/tests/unit/providers/vector_io/test_sqlite_vec.py +++ b/tests/unit/providers/vector_io/test_sqlite_vec.py @@ -9,12 +9,12 @@ import asyncio import numpy as np import pytest -from llama_stack.apis.vector_io import Chunk, QueryChunksResponse from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import ( SQLiteVecIndex, SQLiteVecVectorIOAdapter, _create_sqlite_connection, ) +from llama_stack_api import Chunk, QueryChunksResponse # This test is a unit test for the SQLiteVecVectorIOAdapter class. This should only contain # tests which are specific to this class. More general (API-level) tests should be placed in diff --git a/tests/unit/providers/vector_io/test_vector_io_openai_vector_stores.py b/tests/unit/providers/vector_io/test_vector_io_openai_vector_stores.py index 121623e1b..3797abb2c 100644 --- a/tests/unit/providers/vector_io/test_vector_io_openai_vector_stores.py +++ b/tests/unit/providers/vector_io/test_vector_io_openai_vector_stores.py @@ -11,17 +11,17 @@ from unittest.mock import AsyncMock, patch import numpy as np import pytest -from llama_stack.apis.common.errors import VectorStoreNotFoundError -from llama_stack.apis.vector_io import ( +from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import VECTOR_DBS_PREFIX +from llama_stack_api import ( Chunk, OpenAICreateVectorStoreFileBatchRequestWithExtraBody, OpenAICreateVectorStoreRequestWithExtraBody, QueryChunksResponse, + VectorStore, VectorStoreChunkingStrategyAuto, VectorStoreFileObject, + VectorStoreNotFoundError, ) -from llama_stack.apis.vector_stores import VectorStore -from llama_stack.providers.inline.vector_io.sqlite_vec.sqlite_vec import VECTOR_DBS_PREFIX # This test is a unit test for the inline VectorIO providers. This should only contain # tests which are specific to this class. More general (API-level) tests should be placed in @@ -222,7 +222,7 @@ async def test_insert_chunks_missing_db_raises(vector_io_adapter): async def test_insert_chunks_with_missing_document_id(vector_io_adapter): """Ensure no KeyError when document_id is missing or in different places.""" - from llama_stack.apis.vector_io import Chunk, ChunkMetadata + from llama_stack_api import Chunk, ChunkMetadata fake_index = AsyncMock() vector_io_adapter.cache["db1"] = fake_index @@ -255,10 +255,9 @@ async def test_insert_chunks_with_missing_document_id(vector_io_adapter): async def test_document_id_with_invalid_type_raises_error(): """Ensure TypeError is raised when document_id is not a string.""" - from llama_stack.apis.vector_io import Chunk - # Integer document_id should raise TypeError from llama_stack.providers.utils.vector_io.vector_utils import generate_chunk_id + from llama_stack_api import Chunk chunk = Chunk(content="test", chunk_id=generate_chunk_id("test", "test"), metadata={"document_id": 12345}) with pytest.raises(TypeError) as exc_info: diff --git a/tests/unit/providers/vector_io/test_vector_utils.py b/tests/unit/providers/vector_io/test_vector_utils.py index 1ca753a44..7f6b4af79 100644 --- a/tests/unit/providers/vector_io/test_vector_utils.py +++ b/tests/unit/providers/vector_io/test_vector_utils.py @@ -4,8 +4,8 @@ # This source code is licensed under the terms described in the LICENSE file in # the root directory of this source tree. -from llama_stack.apis.vector_io import Chunk, ChunkMetadata from llama_stack.providers.utils.vector_io.vector_utils import generate_chunk_id +from llama_stack_api import Chunk, ChunkMetadata # This test is a unit test for the chunk_utils.py helpers. This should only contain # tests which are specific to this file. More general (API-level) tests should be placed in diff --git a/tests/unit/rag/test_rag_query.py b/tests/unit/rag/test_rag_query.py index 8563d0d53..7eb17b74b 100644 --- a/tests/unit/rag/test_rag_query.py +++ b/tests/unit/rag/test_rag_query.py @@ -8,13 +8,8 @@ from unittest.mock import AsyncMock, MagicMock import pytest -from llama_stack.apis.tools.rag_tool import RAGQueryConfig -from llama_stack.apis.vector_io import ( - Chunk, - ChunkMetadata, - QueryChunksResponse, -) from llama_stack.providers.inline.tool_runtime.rag.memory import MemoryToolRuntimeImpl +from llama_stack_api import Chunk, ChunkMetadata, QueryChunksResponse, RAGQueryConfig class TestRagQuery: diff --git a/tests/unit/rag/test_vector_store.py b/tests/unit/rag/test_vector_store.py index 1f73fdb8e..2562df8d6 100644 --- a/tests/unit/rag/test_vector_store.py +++ b/tests/unit/rag/test_vector_store.py @@ -13,12 +13,6 @@ from unittest.mock import AsyncMock, MagicMock import numpy as np import pytest -from llama_stack.apis.inference.inference import ( - OpenAIEmbeddingData, - OpenAIEmbeddingsRequestWithExtraBody, -) -from llama_stack.apis.tools import RAGDocument -from llama_stack.apis.vector_io import Chunk from llama_stack.providers.utils.memory.vector_store import ( URL, VectorStoreWithIndex, @@ -27,6 +21,7 @@ from llama_stack.providers.utils.memory.vector_store import ( make_overlapped_chunks, ) from llama_stack.providers.utils.vector_io.vector_utils import generate_chunk_id +from llama_stack_api import Chunk, OpenAIEmbeddingData, OpenAIEmbeddingsRequestWithExtraBody, RAGDocument DUMMY_PDF_PATH = Path(os.path.abspath(__file__)).parent / "fixtures" / "dummy.pdf" # Depending on the machine, this can get parsed a couple of ways diff --git a/tests/unit/registry/test_registry.py b/tests/unit/registry/test_registry.py index d4c9786d1..1b5032782 100644 --- a/tests/unit/registry/test_registry.py +++ b/tests/unit/registry/test_registry.py @@ -7,8 +7,6 @@ import pytest -from llama_stack.apis.inference import Model -from llama_stack.apis.vector_stores import VectorStore from llama_stack.core.datatypes import VectorStoreWithOwner from llama_stack.core.storage.datatypes import KVStoreReference, SqliteKVStoreConfig from llama_stack.core.store.registry import ( @@ -17,6 +15,7 @@ from llama_stack.core.store.registry import ( DiskDistributionRegistry, ) from llama_stack.providers.utils.kvstore import kvstore_impl, register_kvstore_backends +from llama_stack_api import Model, VectorStore @pytest.fixture @@ -304,8 +303,8 @@ async def test_double_registration_different_objects(disk_dist_registry): async def test_double_registration_with_cache(cached_disk_dist_registry): """Test double registration behavior with caching enabled.""" - from llama_stack.apis.models import ModelType from llama_stack.core.datatypes import ModelWithOwner + from llama_stack_api import ModelType model1 = ModelWithOwner( identifier="test_model", diff --git a/tests/unit/registry/test_registry_acl.py b/tests/unit/registry/test_registry_acl.py index 09b9a3cfb..a09d2a30d 100644 --- a/tests/unit/registry/test_registry_acl.py +++ b/tests/unit/registry/test_registry_acl.py @@ -5,9 +5,9 @@ # the root directory of this source tree. -from llama_stack.apis.models import ModelType from llama_stack.core.datatypes import ModelWithOwner, User from llama_stack.core.store.registry import CachedDiskDistributionRegistry +from llama_stack_api import ModelType async def test_registry_cache_with_acl(cached_disk_dist_registry): diff --git a/tests/unit/server/test_access_control.py b/tests/unit/server/test_access_control.py index ea4f9b8b2..23a9636d5 100644 --- a/tests/unit/server/test_access_control.py +++ b/tests/unit/server/test_access_control.py @@ -10,11 +10,10 @@ import pytest import yaml from pydantic import TypeAdapter, ValidationError -from llama_stack.apis.datatypes import Api -from llama_stack.apis.models import ModelType from llama_stack.core.access_control.access_control import AccessDeniedError, is_action_allowed from llama_stack.core.datatypes import AccessRule, ModelWithOwner, User from llama_stack.core.routing_tables.models import ModelsRoutingTable +from llama_stack_api import Api, ModelType class AsyncMock(MagicMock): diff --git a/tests/unit/server/test_auth.py b/tests/unit/server/test_auth.py index cc9397f07..57a552514 100644 --- a/tests/unit/server/test_auth.py +++ b/tests/unit/server/test_auth.py @@ -144,7 +144,7 @@ def middleware_with_mocks(mock_auth_endpoint): middleware = AuthenticationMiddleware(mock_app, auth_config, {}) # Mock the route_impls to simulate finding routes with required scopes - from llama_stack.schema_utils import WebMethod + from llama_stack_api import WebMethod routes = { ("POST", "/test/scoped"): WebMethod(route="/test/scoped", method="POST", required_scope="test.read"), diff --git a/tests/unit/server/test_resolver.py b/tests/unit/server/test_resolver.py index b44f12f7e..8f8a61ea7 100644 --- a/tests/unit/server/test_resolver.py +++ b/tests/unit/server/test_resolver.py @@ -11,7 +11,6 @@ from unittest.mock import AsyncMock, MagicMock from pydantic import BaseModel, Field -from llama_stack.apis.inference import Inference from llama_stack.core.datatypes import Api, Provider, StackRunConfig from llama_stack.core.resolver import resolve_impls from llama_stack.core.routers.inference import InferenceRouter @@ -25,9 +24,9 @@ from llama_stack.core.storage.datatypes import ( SqlStoreReference, StorageConfig, ) -from llama_stack.providers.datatypes import InlineProviderSpec, ProviderSpec from llama_stack.providers.utils.kvstore import register_kvstore_backends from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends +from llama_stack_api import Inference, InlineProviderSpec, ProviderSpec def add_protocol_methods(cls: type, protocol: type[Protocol]) -> None: diff --git a/tests/unit/server/test_server.py b/tests/unit/server/test_server.py index d6d4f4f23..53f193672 100644 --- a/tests/unit/server/test_server.py +++ b/tests/unit/server/test_server.py @@ -12,7 +12,7 @@ from pydantic import ValidationError from llama_stack.core.access_control.access_control import AccessDeniedError from llama_stack.core.datatypes import AuthenticationRequiredError -from llama_stack.core.server.server import translate_exception +from llama_stack.core.server.server import remove_disabled_providers, translate_exception class TestTranslateException: @@ -194,3 +194,70 @@ class TestTranslateException: assert isinstance(result3, HTTPException) assert result3.status_code == 403 assert result3.detail == "Permission denied: Access denied" + + +class TestRemoveDisabledProviders: + """Test cases for the remove_disabled_providers function.""" + + def test_remove_explicitly_disabled_provider(self): + """Test that providers with provider_id='__disabled__' are removed.""" + config = { + "providers": { + "inference": [ + {"provider_id": "openai", "provider_type": "remote::openai", "config": {}}, + {"provider_id": "__disabled__", "provider_type": "remote::vllm", "config": {}}, + ] + } + } + result = remove_disabled_providers(config) + assert len(result["providers"]["inference"]) == 1 + assert result["providers"]["inference"][0]["provider_id"] == "openai" + + def test_remove_empty_provider_id(self): + """Test that providers with empty provider_id are removed.""" + config = { + "providers": { + "inference": [ + {"provider_id": "openai", "provider_type": "remote::openai", "config": {}}, + {"provider_id": "", "provider_type": "remote::vllm", "config": {}}, + ] + } + } + result = remove_disabled_providers(config) + assert len(result["providers"]["inference"]) == 1 + assert result["providers"]["inference"][0]["provider_id"] == "openai" + + def test_keep_models_with_none_provider_model_id(self): + """Test that models with None provider_model_id are NOT removed.""" + config = { + "registered_resources": { + "models": [ + { + "model_id": "llama-3-2-3b", + "provider_id": "vllm-inference", + "model_type": "llm", + "provider_model_id": None, + "metadata": {}, + }, + { + "model_id": "gpt-4o-mini", + "provider_id": "openai", + "model_type": "llm", + "provider_model_id": None, + "metadata": {}, + }, + { + "model_id": "granite-embedding-125m", + "provider_id": "sentence-transformers", + "model_type": "embedding", + "provider_model_id": "ibm-granite/granite-embedding-125m-english", + "metadata": {"embedding_dimension": 768}, + }, + ] + } + } + result = remove_disabled_providers(config) + assert len(result["registered_resources"]["models"]) == 3 + assert result["registered_resources"]["models"][0]["model_id"] == "llama-3-2-3b" + assert result["registered_resources"]["models"][1]["model_id"] == "gpt-4o-mini" + assert result["registered_resources"]["models"][2]["model_id"] == "granite-embedding-125m" diff --git a/tests/unit/server/test_sse.py b/tests/unit/server/test_sse.py index 0303a6ded..d82743c80 100644 --- a/tests/unit/server/test_sse.py +++ b/tests/unit/server/test_sse.py @@ -10,8 +10,8 @@ from unittest.mock import AsyncMock, MagicMock import pytest -from llama_stack.apis.common.responses import PaginatedResponse from llama_stack.core.server.server import create_dynamic_typed_route, create_sse_event, sse_generator +from llama_stack_api import PaginatedResponse @pytest.fixture diff --git a/tests/unit/tools/test_tools_json_schema.py b/tests/unit/tools/test_tools_json_schema.py index 8fe3103bc..623955984 100644 --- a/tests/unit/tools/test_tools_json_schema.py +++ b/tests/unit/tools/test_tools_json_schema.py @@ -11,8 +11,8 @@ Tests the new input_schema and output_schema fields. from pydantic import ValidationError -from llama_stack.apis.tools import ToolDef from llama_stack.models.llama.datatypes import BuiltinTool, ToolDefinition +from llama_stack_api import ToolDef class TestToolDefValidation: diff --git a/tests/unit/utils/inference/test_inference_store.py b/tests/unit/utils/inference/test_inference_store.py index d2de1c759..bdcc529ce 100644 --- a/tests/unit/utils/inference/test_inference_store.py +++ b/tests/unit/utils/inference/test_inference_store.py @@ -8,16 +8,16 @@ import time import pytest -from llama_stack.apis.inference import ( +from llama_stack.core.storage.datatypes import InferenceStoreReference, SqliteSqlStoreConfig +from llama_stack.providers.utils.inference.inference_store import InferenceStore +from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends +from llama_stack_api import ( OpenAIAssistantMessageParam, OpenAIChatCompletion, OpenAIChoice, OpenAIUserMessageParam, Order, ) -from llama_stack.core.storage.datatypes import InferenceStoreReference, SqliteSqlStoreConfig -from llama_stack.providers.utils.inference.inference_store import InferenceStore -from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends @pytest.fixture(autouse=True) diff --git a/tests/unit/utils/responses/test_responses_store.py b/tests/unit/utils/responses/test_responses_store.py index 34cff3d3f..8c108d9c1 100644 --- a/tests/unit/utils/responses/test_responses_store.py +++ b/tests/unit/utils/responses/test_responses_store.py @@ -10,15 +10,10 @@ from uuid import uuid4 import pytest -from llama_stack.apis.agents import Order -from llama_stack.apis.agents.openai_responses import ( - OpenAIResponseInput, - OpenAIResponseObject, -) -from llama_stack.apis.inference import OpenAIMessageParam, OpenAIUserMessageParam from llama_stack.core.storage.datatypes import ResponsesStoreReference, SqliteSqlStoreConfig from llama_stack.providers.utils.responses.responses_store import ResponsesStore from llama_stack.providers.utils.sqlstore.sqlstore import register_sqlstore_backends +from llama_stack_api import OpenAIMessageParam, OpenAIResponseInput, OpenAIResponseObject, OpenAIUserMessageParam, Order def build_store(db_path: str, policy: list | None = None) -> ResponsesStore: @@ -46,7 +41,7 @@ def create_test_response_object( def create_test_response_input(content: str, input_id: str) -> OpenAIResponseInput: """Helper to create a test response input.""" - from llama_stack.apis.agents.openai_responses import OpenAIResponseMessage + from llama_stack_api import OpenAIResponseMessage return OpenAIResponseMessage( id=input_id, diff --git a/uv.lock b/uv.lock index f1808f005..8f45f0564 100644 --- a/uv.lock +++ b/uv.lock @@ -139,6 +139,15 @@ wheels = [ { url = "https://files.pythonhosted.org/packages/aa/f3/0b6ced594e51cc95d8c1fc1640d3623770d01e4969d29c0bd09945fafefa/altair-5.5.0-py3-none-any.whl", hash = "sha256:91a310b926508d560fe0148d02a194f38b824122641ef528113d029fcd129f8c", size = 731200, upload-time = "2024-11-23T23:39:56.4Z" }, ] +[[package]] +name = "annotated-doc" +version = "0.0.4" +source = { registry = "https://pypi.org/simple" } +sdist = { url = "https://files.pythonhosted.org/packages/57/ba/046ceea27344560984e26a590f90bc7f4a75b06701f653222458922b558c/annotated_doc-0.0.4.tar.gz", hash = "sha256:fbcda96e87e9c92ad167c2e53839e57503ecfda18804ea28102353485033faa4", size = 7288, upload-time = "2025-11-10T22:07:42.062Z" } +wheels = [ + { url = "https://files.pythonhosted.org/packages/1e/d3/26bf1008eb3d2daa8ef4cacc7f3bfdc11818d111f7e2d0201bc6e3b49d45/annotated_doc-0.0.4-py3-none-any.whl", hash = "sha256:571ac1dc6991c450b25a9c2d84a3705e2ae7a53467b5d111c24fa8baabbed320", size = 5303, upload-time = "2025-11-10T22:07:40.673Z" }, +] + [[package]] name = "annotated-types" version = "0.7.0" @@ -1037,16 +1046,17 @@ wheels = [ [[package]] name = "fastapi" -version = "0.119.0" +version = "0.121.2" source = { registry = "https://pypi.org/simple" } dependencies = [ + { name = "annotated-doc" }, { name = "pydantic" }, { name = "starlette" }, { name = "typing-extensions" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/0a/f9/5c5bcce82a7997cc0eb8c47b7800f862f6b56adc40486ed246e5010d443b/fastapi-0.119.0.tar.gz", hash = "sha256:451082403a2c1f0b99c6bd57c09110ed5463856804c8078d38e5a1f1035dbbb7", size = 336756, upload-time = "2025-10-11T17:13:40.53Z" } +sdist = { url = "https://files.pythonhosted.org/packages/fb/48/f08f264da34cf160db82c62ffb335e838b1fc16cbcc905f474c7d4c815db/fastapi-0.121.2.tar.gz", hash = "sha256:ca8e932b2b823ec1721c641e3669472c855ad9564a2854c9899d904c2848b8b9", size = 342944, upload-time = "2025-11-13T17:05:54.692Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/ce/70/584c4d7cad80f5e833715c0a29962d7c93b4d18eed522a02981a6d1b6ee5/fastapi-0.119.0-py3-none-any.whl", hash = "sha256:90a2e49ed19515320abb864df570dd766be0662c5d577688f1600170f7f73cf2", size = 107095, upload-time = "2025-10-11T17:13:39.048Z" }, + { url = "https://files.pythonhosted.org/packages/eb/23/dfb161e91db7c92727db505dc72a384ee79681fe0603f706f9f9f52c2901/fastapi-0.121.2-py3-none-any.whl", hash = "sha256:f2d80b49a86a846b70cc3a03eb5ea6ad2939298bf6a7fe377aa9cd3dd079d358", size = 109201, upload-time = "2025-11-13T17:05:52.718Z" }, ] [[package]] @@ -1945,6 +1955,7 @@ dependencies = [ { name = "httpx" }, { name = "jinja2" }, { name = "jsonschema" }, + { name = "llama-stack-api" }, { name = "openai" }, { name = "opentelemetry-exporter-otlp-proto-http" }, { name = "opentelemetry-sdk" }, @@ -2094,6 +2105,7 @@ requires-dist = [ { name = "httpx" }, { name = "jinja2", specifier = ">=3.1.6" }, { name = "jsonschema" }, + { name = "llama-stack-api", editable = "src/llama_stack_api" }, { name = "llama-stack-client", marker = "extra == 'client'", specifier = ">=0.3.0" }, { name = "openai", specifier = ">=2.5.0" }, { name = "opentelemetry-exporter-otlp-proto-http", specifier = ">=1.30.0" }, @@ -2108,6 +2120,7 @@ requires-dist = [ { name = "rich" }, { name = "sqlalchemy", extras = ["asyncio"], specifier = ">=2.0.41" }, { name = "starlette" }, + { name = "starlette", specifier = ">=0.49.1" }, { name = "termcolor" }, { name = "tiktoken" }, { name = "uvicorn", specifier = ">=0.34.0" }, @@ -2125,7 +2138,7 @@ dev = [ { name = "black" }, { name = "mypy" }, { name = "nbval" }, - { name = "pre-commit" }, + { name = "pre-commit", specifier = ">=4.4.0" }, { name = "pytest", specifier = ">=8.4" }, { name = "pytest-asyncio", specifier = ">=1.0" }, { name = "pytest-cov" }, @@ -2226,6 +2239,25 @@ unit = [ { name = "together" }, ] +[[package]] +name = "llama-stack-api" +version = "0.4.0.dev0" +source = { editable = "src/llama_stack_api" } +dependencies = [ + { name = "jsonschema" }, + { name = "opentelemetry-exporter-otlp-proto-http" }, + { name = "opentelemetry-sdk" }, + { name = "pydantic" }, +] + +[package.metadata] +requires-dist = [ + { name = "jsonschema" }, + { name = "opentelemetry-exporter-otlp-proto-http", specifier = ">=1.30.0" }, + { name = "opentelemetry-sdk", specifier = ">=1.30.0" }, + { name = "pydantic", specifier = ">=2.11.9" }, +] + [[package]] name = "llama-stack-client" version = "0.3.0" @@ -3403,7 +3435,7 @@ wheels = [ [[package]] name = "pre-commit" -version = "4.2.0" +version = "4.4.0" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "cfgv" }, @@ -3412,9 +3444,9 @@ dependencies = [ { name = "pyyaml" }, { name = "virtualenv" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/08/39/679ca9b26c7bb2999ff122d50faa301e49af82ca9c066ec061cfbc0c6784/pre_commit-4.2.0.tar.gz", hash = "sha256:601283b9757afd87d40c4c4a9b2b5de9637a8ea02eaff7adc2d0fb4e04841146", size = 193424, upload-time = "2025-03-18T21:35:20.987Z" } +sdist = { url = "https://files.pythonhosted.org/packages/a6/49/7845c2d7bf6474efd8e27905b51b11e6ce411708c91e829b93f324de9929/pre_commit-4.4.0.tar.gz", hash = "sha256:f0233ebab440e9f17cabbb558706eb173d19ace965c68cdce2c081042b4fab15", size = 197501, upload-time = "2025-11-08T21:12:11.607Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/88/74/a88bf1b1efeae488a0c0b7bdf71429c313722d1fc0f377537fbe554e6180/pre_commit-4.2.0-py2.py3-none-any.whl", hash = "sha256:a009ca7205f1eb497d10b845e52c838a98b6cdd2102a6c8e4540e94ee75c58bd", size = 220707, upload-time = "2025-03-18T21:35:19.343Z" }, + { url = "https://files.pythonhosted.org/packages/27/11/574fe7d13acf30bfd0a8dd7fa1647040f2b8064f13f43e8c963b1e65093b/pre_commit-4.4.0-py2.py3-none-any.whl", hash = "sha256:b35ea52957cbf83dcc5d8ee636cbead8624e3a15fbfa61a370e42158ac8a5813", size = 226049, upload-time = "2025-11-08T21:12:10.228Z" }, ] [[package]] @@ -5039,15 +5071,15 @@ wheels = [ [[package]] name = "starlette" -version = "0.47.2" +version = "0.49.3" source = { registry = "https://pypi.org/simple" } dependencies = [ { name = "anyio" }, { name = "typing-extensions", marker = "python_full_version < '3.13'" }, ] -sdist = { url = "https://files.pythonhosted.org/packages/04/57/d062573f391d062710d4088fa1369428c38d51460ab6fedff920efef932e/starlette-0.47.2.tar.gz", hash = "sha256:6ae9aa5db235e4846decc1e7b79c4f346adf41e9777aebeb49dfd09bbd7023d8", size = 2583948, upload-time = "2025-07-20T17:31:58.522Z" } +sdist = { url = "https://files.pythonhosted.org/packages/de/1a/608df0b10b53b0beb96a37854ee05864d182ddd4b1156a22f1ad3860425a/starlette-0.49.3.tar.gz", hash = "sha256:1c14546f299b5901a1ea0e34410575bc33bbd741377a10484a54445588d00284", size = 2655031, upload-time = "2025-11-01T15:12:26.13Z" } wheels = [ - { url = "https://files.pythonhosted.org/packages/f7/1f/b876b1f83aef204198a42dc101613fefccb32258e5428b5f9259677864b4/starlette-0.47.2-py3-none-any.whl", hash = "sha256:c5847e96134e5c5371ee9fac6fdf1a67336d5815e09eb2a01fdb57a351ef915b", size = 72984, upload-time = "2025-07-20T17:31:56.738Z" }, + { url = "https://files.pythonhosted.org/packages/a3/e0/021c772d6a662f43b63044ab481dc6ac7592447605b5b35a957785363122/starlette-0.49.3-py3-none-any.whl", hash = "sha256:b579b99715fdc2980cf88c8ec96d3bf1ce16f5a8051a7c2b84ef9b1cdecaea2f", size = 74340, upload-time = "2025-11-01T15:12:24.387Z" }, ] [[package]]