287 commits

Author	SHA1	Message	Date
mergify[bot]	9afa387d16	fix: RBAC bypass vulnerabilities in model access (backport #4270) (#4285) ... Closes security gaps where RBAC checks could be bypassed: o Inference router: Added RBAC enforcement in the fallback path to ensure access control is applied consistently. o Model listing: Dynamic models fetched via provider_data were returned without RBAC checks. Added filtering to ensure users only see models they have permission to access. Both fixes create temporary ModelWithOwner objects for RBAC validation, maintaining security through consistent access control enforcement. Closes: #4269 <hr>This is an automatic backport of pull request #4270 done by [Mergify](https://mergify.com). Signed-off-by: Derek Higgins <derekh@redhat.com> Signed-off-by: Charlie Doern <cdoern@redhat.com> Co-authored-by: Derek Higgins <derekh@redhat.com>	2025-12-03 13:02:37 -05:00
mergify[bot]	05b4394cf9	fix: enforce allowed_models during inference requests (backport #4197) (#4228) ... The `allowed_models` configuration was only being applied when listing models via the `/v1/models` endpoint, but the actual inference requests weren't checking this restriction. This meant users could directly request any model the provider supports by specifying it in their inference call, completely bypassing the intended cost controls. The fix adds validation to all three inference methods (chat completions, completions, and embeddings) that checks the requested model against the allowed_models list before making the provider API call. ### Test plan Added unit tests <hr>This is an automatic backport of pull request #4197 done by [Mergify](https://mergify.com). Signed-off-by: Charlie Doern <cdoern@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-11-24 11:31:36 -08:00
mergify[bot]	46bd95e453	fix: Vector store persistence across server restarts (backport #3977) (#4225) ... # What does this PR do? This PR fixes a bug in LlamaStack 0.3.0 where vector stores created via the OpenAI-compatible API (`POST /v1/vector_stores`) would fail with `VectorStoreNotFoundError` after server restart when attempting operations like `vector_io.insert()` or `vector_io.query()`. The bug affected **6 vector IO providers**: `pgvector`, `sqlite_vec`, `chroma`, `milvus`, `qdrant`, and `weaviate`. Created with the assistance of: claude-4.5-sonnet ## Root Cause All affected providers had a broken `_get_and_cache_vector_store_index()` method that: 1. Did not load existing vector stores from persistent storage during initialization 2. Attempted to use `vector_store_table` (which was either `None` or a `KVStore` without the required `get_vector_store()` method) 3. Could not reload vector stores after server restart or cache miss ## Solution This PR implements a consistent pattern across all 6 providers: 1. **Load vector stores during initialization** - Pre-populate the cache from KV store on startup 2. **Fix lazy loading** - Modified `_get_and_cache_vector_store_index()` to load directly from KV store instead of relying on `vector_store_table` 3. **Remove broken dependency** - Eliminated reliance on the `vector_store_table` pattern ## Testing steps ### 1.1 Configure the stack Create or use an existing configuration with a vector IO provider. **Example `run.yaml`:** ```yaml vector_io_store: - provider_id: pgvector provider_type: remote::pgvector config: host: localhost port: 5432 db: llamastack user: llamastack password: llamastack inference: - provider_id: sentence-transformers provider_type: inline::sentence-transformers config: model: sentence-transformers/all-MiniLM-L6-v2 ``` ### 1.2 Start the server ```bash llama stack run run.yaml --port 5000 ``` Wait for the server to fully start. You should see: ``` INFO: Started server process INFO: Application startup complete ``` --- ## Step 2: Create a Vector Store ### 2.1 Create via API ```bash curl -X POST http://localhost:5000/v1/vector_stores \ -H "Content-Type: application/json" \ -d '{ "name": "test-persistence-store", "extra_body": { "embedding_model": "sentence-transformers/all-MiniLM-L6-v2", "embedding_dimension": 384, "provider_id": "pgvector" } }' | jq ``` ### 2.2 Expected Response ```json { "id": "vs_a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d", "object": "vector_store", "name": "test-persistence-store", "status": "completed", "created_at": 1730304000, "file_counts": { "total": 0, "completed": 0, "in_progress": 0, "failed": 0, "cancelled": 0 }, "usage_bytes": 0 } ``` **Save the `id` field** (e.g., `vs_a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d`) — you’ll need it for the next steps. --- ## Step 3: Insert Data (Before Restart) ### 3.1 Insert chunks into the vector store ```bash export VS_ID="vs_a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d" curl -X POST http://localhost:5000/vector-io/insert \ -H "Content-Type: application/json" \ -d "{ \"vector_store_id\": \"$VS_ID\", \"chunks\": [ { \"content\": \"Python is a high-level programming language known for its readability.\", \"metadata\": {\"source\": \"doc1\", \"page\": 1} }, { \"content\": \"Machine learning enables computers to learn from data without explicit programming.\", \"metadata\": {\"source\": \"doc2\", \"page\": 1} }, { \"content\": \"Neural networks are inspired by biological neurons in the brain.\", \"metadata\": {\"source\": \"doc3\", \"page\": 1} } ] }" ``` ### 3.2 Expected Response Status: **200 OK** Response: *Empty or success confirmation* --- ## Step 4: Query Data (Before Restart – Baseline) ### 4.1 Query the vector store ```bash curl -X POST http://localhost:5000/vector-io/query \ -H "Content-Type: application/json" \ -d "{ \"vector_store_id\": \"$VS_ID\", \"query\": \"What is machine learning?\" }" | jq ``` ### 4.2 Expected Response ```json { "chunks": [ { "content": "Machine learning enables computers to learn from data without explicit programming.", "metadata": {"source": "doc2", "page": 1} }, { "content": "Neural networks are inspired by biological neurons in the brain.", "metadata": {"source": "doc3", "page": 1} } ], "scores": [0.85, 0.72] } ``` **Checkpoint:** Works correctly before restart. --- ## Step 5: Restart the Server (Critical Test) ### 5.1 Stop the server In the terminal where it’s running: ``` Ctrl + C ``` Wait for: ``` Shutting down... ``` ### 5.2 Restart the server ```bash llama stack run run.yaml --port 5000 ``` Wait for: ``` INFO: Started server process INFO: Application startup complete ``` The vector store cache is now empty, but data should persist. --- ## Step 6: Verify Vector Store Exists (After Restart) ### 6.1 List vector stores ```bash curl http://localhost:5000/v1/vector_stores | jq ``` ### 6.2 Expected Response ```json { "object": "list", "data": [ { "id": "vs_a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d", "name": "test-persistence-store", "status": "completed" } ] } ``` **Checkpoint:** Vector store should be listed. --- ## Step 7: Insert Data (After Restart – THE BUG TEST) ### 7.1 Insert new chunks ```bash curl -X POST http://localhost:5000/vector-io/insert \ -H "Content-Type: application/json" \ -d "{ \"vector_store_id\": \"$VS_ID\", \"chunks\": [ { \"content\": \"This chunk was inserted AFTER the server restart.\", \"metadata\": {\"source\": \"post-restart\", \"test\": true} } ] }" ``` ### 7.2 Expected Results **With Fix (Correct):** ``` Status: 200 OK Response: Success ``` **Without Fix (Bug):** ```json { "detail": "VectorStoreNotFoundError: Vector Store 'vs_a1b2c3d4-e5f6-4a7b-8c9d-0e1f2a3b4c5d' not found." } ``` **Critical Test:** If insertion succeeds, the fix works. --- ## Step 8: Query Data (After Restart – Verification) ### 8.1 Query all data ```bash curl -X POST http://localhost:5000/vector-io/query \ -H "Content-Type: application/json" \ -d "{ \"vector_store_id\": \"$VS_ID\", \"query\": \"restart\" }" | jq ``` ### 8.2 Expected Response ```json { "chunks": [ { "content": "This chunk was inserted AFTER the server restart.", "metadata": {"source": "post-restart", "test": true} } ], "scores": [0.95] } ``` **Checkpoint:** Both old and new data are queryable. --- ## Step 9: Multiple Restart Test (Extra Verification) ### 9.1 Restart again ```bash Ctrl + C llama stack run run.yaml --port 5000 ``` ### 9.2 Query after restart ```bash curl -X POST http://localhost:5000/vector-io/query \ -H "Content-Type: application/json" \ -d "{ \"vector_store_id\": \"$VS_ID\", \"query\": \"programming\" }" | jq ``` **Expected:** Works correctly across multiple restarts. <hr>This is an automatic backport of pull request #3977 done by [Mergify](https://mergify.com). Signed-off-by: Charlie Doern <cdoern@redhat.com> Co-authored-by: Juan Pérez de Algaba <124347725+jperezdealgaba@users.noreply.github.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>	2025-11-24 11:30:21 -08:00
mergify[bot]	f216eb99be	fix: allowed_models config did not filter models (backport #4030) (#4223) ... # What does this PR do? closes #4022 ## Test Plan ci w/ new tests<hr>This is an automatic backport of pull request #4030 done by [Mergify](https://mergify.com). Co-authored-by: Matthew Farrellee <matt@cs.wisc.edu> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-11-24 11:29:53 -08:00
Ashwin Bharambe	73d70546d4	chore(release-0.3.x): handle missing external_providers_dir (#4011) ... Cherry-pick of #3974 to release-0.3.x branch. ## Summary - Fixes handling of missing external_providers_dir in stack configuration ## Original PR Fixes from #3974 Signed-off-by: Doug Edgar <dedgar@redhat.com> Co-authored-by: Doug Edgar <dedgar@redhat.com>	2025-10-31 12:55:34 -07:00
Ashwin Bharambe	39f33f7f12	feat(cherry-pick): fixes for 0.3.1 release (#3998) ... ## Summary Cherry-picks 5 critical fixes from main to the release-0.3.x branch for the v0.3.1 release, plus CI workflow updates. **Note**: This recreates the cherry-picks from the closed PR #3991, now targeting the renamed `release-0.3.x` branch (previously `release-0.3.x-maint`). ## Commits 1. **2c56a8560** - fix(context): prevent provider data leak between streaming requests (#3924) - **CRITICAL SECURITY FIX**: Prevents provider credentials from leaking between requests - Fixed import path for 0.3.0 compatibility 2. **ddd32b187** - fix(inference): enable routing of models with provider_data alone (#3928) - Enables routing for fully qualified model IDs with provider_data - Resolved merge conflicts, adapted for 0.3.0 structure 3. **f7c2973aa** - fix: Avoid BadRequestError due to invalid max_tokens (#3667) - Fixes failures with Gemini and other providers that reject max_tokens=0 - Non-breaking API change 4. **d7f9da616** - fix(responses): sync conversation before yielding terminal events in streaming (#3888) - Ensures conversation sync executes even when streaming consumers break early 5. **0ffa8658b** - fix(logging): ensure logs go to stderr, loggers obey levels (#3885) - Fixes logging infrastructure 6. **75b49cb3c** - ci: support release branches and match client branch (#3990) - Updates CI workflows to support release-X.Y.x branches - Matches client branch from llama-stack-client-python for release testing - Fixes artifact name collisions ## Adaptations for 0.3.0 - Fixed import paths: `llama_stack.core.telemetry.tracing` → `llama_stack.providers.utils.telemetry.tracing` - Fixed import paths: `llama_stack.core.telemetry.telemetry` → `llama_stack.apis.telemetry` - Changed `self.telemetry_enabled` → `self.telemetry` (0.3.0 attribute name) - Removed `rerank()` method that doesn't exist in 0.3.0 ## Testing All imports verified and tests should pass once CI is set up.	2025-10-30 21:51:42 -07:00
slekkala1	eb2b240594	fix: remove consistency checks (#3881) ... # What does this PR do? metadata is conflicting with the default embedding model set on server side via extra body, removing the check and just letting metadata take precedence over extra body `ValueError: Embedding model inconsistent between metadata ('text-embedding-3-small') and extra_body ('sentence-transformers/nomic-ai/nomic-embed-text-v1.5')` ## Test Plan CI	2025-10-21 14:40:14 -07:00
Ashwin Bharambe	bd3c473208	revert: "chore(cleanup)!: remove tool_runtime.rag_tool" (#3877) ... Reverts llamastack/llama-stack#3871 This PR broke RAG (even from Responses -- there _is_ a dependency)	2025-10-21 11:22:06 -07:00
Ashwin Bharambe	0e96279bee	chore(cleanup)!: remove tool_runtime.rag_tool (#3871) ... Kill the `builtin::rag` tool group completely since it is no longer targeted. We use the Responses implementation for knowledge_search which uses the `openai_vector_stores` pathway. --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2025-10-20 22:26:21 -07:00
Ashwin Bharambe	122de785c4	chore(cleanup)!: kill vector_db references as far as possible (#3864) ... There should not be "vector db" anywhere.	2025-10-20 20:06:16 -07:00
ehhuang	444f6c88f3	chore: remove build.py (#3869) ... # What does this PR do? ## Test Plan CI	2025-10-20 16:28:15 -07:00
Francisco Arceo	48581bf651	chore: Updating how default embedding model is set in stack (#3818) ... # What does this PR do? Refactor setting default vector store provider and embedding model to use an optional `vector_stores` config in the `StackRunConfig` and clean up code to do so (had to add back in some pieces of VectorDB). Also added remote Qdrant and Weaviate to starter distro (based on other PR where inference providers were added for UX). New config is simply (default for Starter distro): ```yaml vector_stores: default_provider_id: faiss default_embedding_model: provider_id: sentence-transformers model_id: nomic-ai/nomic-embed-text-v1.5 ``` ## Test Plan CI and Unit tests. --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-20 14:22:45 -07:00
Ashwin Bharambe	2c43285e22	feat(stores)!: use backend storage references instead of configs (#3697) ... **This PR changes configurations in a backward incompatible way.** Run configs today repeat full SQLite/Postgres snippets everywhere a store is needed, which means duplicated credentials, extra connection pools, and lots of drift between files. This PR introduces named storage backends so the stack and providers can share a single catalog and reference those backends by name. ## Key Changes - Add `storage.backends` to `StackRunConfig`, register each KV/SQL backend once at startup, and validate that references point to the right family. - Move server stores under `storage.stores` with lightweight references (backend + namespace/table) instead of full configs. - Update every provider/config/doc to use the new reference style; docs/codegen now surface the simplified YAML. ## Migration Before: ```yaml metadata_store: type: sqlite db_path: ~/.llama/distributions/foo/registry.db inference_store: type: postgres host: ${env.POSTGRES_HOST} port: ${env.POSTGRES_PORT} db: ${env.POSTGRES_DB} user: ${env.POSTGRES_USER} password: ${env.POSTGRES_PASSWORD} conversations_store: type: postgres host: ${env.POSTGRES_HOST} port: ${env.POSTGRES_PORT} db: ${env.POSTGRES_DB} user: ${env.POSTGRES_USER} password: ${env.POSTGRES_PASSWORD} ``` After: ```yaml storage: backends: kv_default: type: kv_sqlite db_path: ~/.llama/distributions/foo/kvstore.db sql_default: type: sql_postgres host: ${env.POSTGRES_HOST} port: ${env.POSTGRES_PORT} db: ${env.POSTGRES_DB} user: ${env.POSTGRES_USER} password: ${env.POSTGRES_PASSWORD} stores: metadata: backend: kv_default namespace: registry inference: backend: sql_default table_name: inference_store max_write_queue_size: 10000 num_writers: 4 conversations: backend: sql_default table_name: openai_conversations ``` Provider configs follow the same pattern—for example, a Chroma vector adapter switches from: ```yaml providers: vector_io: - provider_id: chromadb provider_type: remote::chromadb config: url: ${env.CHROMADB_URL} kvstore: type: sqlite db_path: ~/.llama/distributions/foo/chroma.db ``` to: ```yaml providers: vector_io: - provider_id: chromadb provider_type: remote::chromadb config: url: ${env.CHROMADB_URL} persistence: backend: kv_default namespace: vector_io::chroma_remote ``` Once the backends are declared, everything else just points at them, so rotating credentials or swapping to Postgres happens in one place and the stack reuses a single connection pool.	2025-10-20 13:20:09 -07:00
Shabana Baig	add64e8e2a	feat: Add instructions parameter in response object (#3741) ... # Problem The current inline provider appends the user provided instructions to messages as a system prompt, but the returned response object does not contain the instructions field (as specified in the OpenAI responses spec). # What does this PR do? This pull request adds the instruction field to the response object definition and updates the inline provider. It also ensures that instructions from previous response is not carried over to the next response (as specified in the openAI spec). Closes #[3566](https://github.com/llamastack/llama-stack/issues/3566) ## Test Plan - Tested manually for change in model response w.r.t supplied instructions field. - Added unit test to check that the instructions from previous response is not carried over to the next response. - Added integration tests to check instructions parameter in the returned response object. - Added new recordings for the integration tests. --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2025-10-20 13:10:37 -07:00
Derek Higgins	1f38359d95	fix: nested claims mapping in OAuth2 token validation (#3814) ... fix: nested claims mapping in OAuth2 token validation The get_attributes_from_claims function was only checking for top-level claim keys, causing token validation to fail when using nested claims like "resource_access.llamastack.roles" (common in Keycloak JWT tokens). Updated the function to support dot notation for traversing nested claim structures. Give precedence to dot notation over literal keys with dots in claims mapping. Added test coverage. Closes: #3812 Signed-off-by: Derek Higgins <derekh@redhat.com>	2025-10-20 12:34:55 -07:00
Charlie Doern	b11bcfde11	refactor(build): rework CLI commands and build process (1/2) (#2974) ... # What does this PR do? This PR does a few things outlined in #2878 namely: 1. adds `llama stack list-deps` a command which simply takes the build logic and instead of executing one of the `build_...` scripts, it displays all of the providers' dependencies using the `module` and `uv`. 2. deprecated `llama stack build` in favor of `llama stack list-deps` 3. updates all tests to use `list-deps` alongside `build`. PR 2/2 will migrate `llama stack run`'s default behavior to be `llama stack build --run` and use the new `list-deps` command under the hood before running the server. examples of `llama stack list-deps starter` ``` llama stack list-deps starter --format json { "name": "starter", "description": "Quick start template for running Llama Stack with several popular providers. This distribution is intended for CPU-only environments.", "apis": [ { "api": "inference", "provider": "remote::cerebras" }, { "api": "inference", "provider": "remote::ollama" }, { "api": "inference", "provider": "remote::vllm" }, { "api": "inference", "provider": "remote::tgi" }, { "api": "inference", "provider": "remote::fireworks" }, { "api": "inference", "provider": "remote::together" }, { "api": "inference", "provider": "remote::bedrock" }, { "api": "inference", "provider": "remote::nvidia" }, { "api": "inference", "provider": "remote::openai" }, { "api": "inference", "provider": "remote::anthropic" }, { "api": "inference", "provider": "remote::gemini" }, { "api": "inference", "provider": "remote::vertexai" }, { "api": "inference", "provider": "remote::groq" }, { "api": "inference", "provider": "remote::sambanova" }, { "api": "inference", "provider": "remote::azure" }, { "api": "inference", "provider": "inline::sentence-transformers" }, { "api": "vector_io", "provider": "inline::faiss" }, { "api": "vector_io", "provider": "inline::sqlite-vec" }, { "api": "vector_io", "provider": "inline::milvus" }, { "api": "vector_io", "provider": "remote::chromadb" }, { "api": "vector_io", "provider": "remote::pgvector" }, { "api": "files", "provider": "inline::localfs" }, { "api": "safety", "provider": "inline::llama-guard" }, { "api": "safety", "provider": "inline::code-scanner" }, { "api": "agents", "provider": "inline::meta-reference" }, { "api": "telemetry", "provider": "inline::meta-reference" }, { "api": "post_training", "provider": "inline::torchtune-cpu" }, { "api": "eval", "provider": "inline::meta-reference" }, { "api": "datasetio", "provider": "remote::huggingface" }, { "api": "datasetio", "provider": "inline::localfs" }, { "api": "scoring", "provider": "inline::basic" }, { "api": "scoring", "provider": "inline::llm-as-judge" }, { "api": "scoring", "provider": "inline::braintrust" }, { "api": "tool_runtime", "provider": "remote::brave-search" }, { "api": "tool_runtime", "provider": "remote::tavily-search" }, { "api": "tool_runtime", "provider": "inline::rag-runtime" }, { "api": "tool_runtime", "provider": "remote::model-context-protocol" }, { "api": "batches", "provider": "inline::reference" } ], "pip_dependencies": [ "pandas", "opentelemetry-exporter-otlp-proto-http", "matplotlib", "opentelemetry-sdk", "sentence-transformers", "datasets", "pymilvus[milvus-lite]>=2.4.10", "codeshield", "scipy", "torchvision", "tree_sitter", "h11>=0.16.0", "aiohttp", "pymongo", "tqdm", "pythainlp", "pillow", "torch", "emoji", "grpcio>=1.67.1,<1.71.0", "fireworks-ai", "langdetect", "psycopg2-binary", "asyncpg", "redis", "together", "torchao>=0.12.0", "openai", "sentencepiece", "aiosqlite", "google-cloud-aiplatform", "faiss-cpu", "numpy", "sqlite-vec", "nltk", "scikit-learn", "mcp>=1.8.1", "transformers", "boto3", "huggingface_hub", "ollama", "autoevals", "sqlalchemy[asyncio]", "torchtune>=0.5.0", "chromadb-client", "pypdf", "requests", "anthropic", "chardet", "aiosqlite", "fastapi", "fire", "httpx", "uvicorn", "opentelemetry-sdk", "opentelemetry-exporter-otlp-proto-http" ] } ``` <img width="1500" height="420" alt="Screenshot 2025-10-16 at 5 53 03 PM" src="https://github.com/user-attachments/assets/765929fb-93e2-44d7-9c3d-8918b70fc721" /> --------- Signed-off-by: Charlie Doern <cdoern@redhat.com>	2025-10-17 19:52:14 -07:00
Charlie Doern	f22aaef42f	chore!: remove telemetry API usage (#3815) ... # What does this PR do? remove telemetry as a providable API from the codebase. This includes removing it from generated distributions but also the provider registry, the router, etc since `setup_logger` is tied pretty strictly to `Api.telemetry` being in impls we still need an "instantiated provider" in our implementations. However it should not be auto-routed or provided. So in validate_and_prepare_providers (called from resolve_impls) I made it so that if run_config.telemetry.enabled, we set up the meta-reference "provider" internally to be used so that log_event will work when called. This is the neatest way I think we can remove telemetry from the provider configs but also not need to rip apart the whole "telemetry is a provider" logic just yet, but we can do it internally later without disrupting users. so telemetry is removed from the registry such that if a user puts `telemetry:` as an API in their build/run config it will err out, but can still be used by us internally as we go through this transition. relates to #3806 Signed-off-by: Charlie Doern <cdoern@redhat.com>	2025-10-16 10:39:32 -07:00
Ashwin Bharambe	185de61d8e	fix(openai_mixin): no yelling for model listing if API keys are not provided (#3826) ... As indicated in the title. Our `starter` distribution enables all remote providers _very intentionally_ because we believe it creates an easier, more welcoming experience to new folks using the software. If we do that, and then slam the logs with errors making them question their life choices, it is not so good :) Note that this fix is limited in scope. If you ever try to actually instantiate the OpenAI client from a code path without an API key being present, you deserve to fail hard. ## Test Plan Run `llama stack run starter` with `OPENAI_API_KEY` set. No more wall of text, just one message saying "listed 96 models".	2025-10-16 10:12:13 -07:00
Ashwin Bharambe	07fc8013eb	fix(tests): reduce some test noise (#3825) ... a bunch of logger.info()s are good for server code to help debug in production, but we don't want them killing our unit test output :) --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2025-10-16 09:52:16 -07:00
Ashwin Bharambe	f70aa99c97	fix(models)!: always prefix models with provider_id when registering (#3822) ... **!!BREAKING CHANGE!!** The lookup is also straightforward -- we always look for this identifier and don't try to find a match for something without the provider_id prefix. Note that, this ideally means we need to update the `register_model()` API also (we should kill "identifier" from there) but I am not doing that as part of this PR. ## Test Plan Existing unit tests	2025-10-16 06:47:39 -07:00
slekkala1	99141c29b1	feat: Add responses and safety impl extra_body (#3781) ... # What does this PR do? Have closed the previous PR due to merge conflicts with multiple PRs Addressed all comments from https://github.com/llamastack/llama-stack/pull/3768 (sorry for carrying over to this one) ## Test Plan Added UTs and integration tests	2025-10-15 15:01:37 -07:00
Sumanth Kamenani	bc8b377a7c	fix(vector-io): handle missing document_id in insert_chunks (#3521) ... Fixed KeyError when chunks don't have document_id in metadata or chunk_metadata. Updated logging to safely extract document_id using getattr and RAG memory to handle different document_id locations. Added test for missing document_id scenarios. Fixes issue #3494 where /v1/vector-io/insert would crash with KeyError. Fixed KeyError when chunks don't have document_id in metadata or chunk_metadata. Updated logging to safely extract document_id using getattr and RAG memory to handle different document_id locations. Added test for missing document_id scenarios. # What does this PR do? Fixes a KeyError crash in `/v1/vector-io/insert` when chunks are missing `document_id` fields. The API was failing even though `document_id` is optional according to the schema. Closes #3494 ## Test Plan **Before fix:** - POST to `/v1/vector-io/insert` with chunks → 500 KeyError - Happened regardless of where `document_id` was placed **After fix:** - Same request works fine → 200 OK - Tested with Postman using FAISS backend - Added unit test covering missing `document_id` scenarios	2025-10-15 11:02:48 -07:00
Ashwin Bharambe	e9b4278a51	feat(responses)!: improve responses + conversations implementations (#3810) ... This PR updates the Conversation item related types and improves a couple critical parts of the implemenation: - it creates a streaming output item for the final assistant message output by the model. until now we only added content parts and included that message in the final response. - rewrites the conversation update code completely to account for items other than messages (tool calls, outputs, etc.) ## Test Plan Used the test script from https://github.com/llamastack/llama-stack-client-python/pull/281 for this ``` TEST_API_BASE_URL=http://localhost:8321/v1 \ pytest tests/integration/test_agent_turn_step_events.py::test_client_side_function_tool -xvs ```	2025-10-15 09:36:11 -07:00
slekkala1	ce8ea2f505	chore: Support embedding params from metadata for Vector Store (#3811) ... # What does this PR do? Support reading embedding model and dimensions from metadata for vector store ## Test Plan Unit Tests	2025-10-15 15:53:36 +02:00
Francisco Arceo	ef4bc70bbe	feat: Enable setting a default embedding model in the stack (#3803) ... # What does this PR do? Enables automatic embedding model detection for vector stores and by using a `default_configured` boolean that can be defined in the `run.yaml`. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan - Unit tests - Integration tests - Simple example below: Spin up the stack: ```bash uv run llama stack build --distro starter --image-type venv --run ``` Then test with OpenAI's client: ```python from openai import OpenAI client = OpenAI(base_url="http://localhost:8321/v1/", api_key="none") vs = client.vector_stores.create() ``` Previously you needed: ```python vs = client.vector_stores.create( extra_body={ "embedding_model": "sentence-transformers/all-MiniLM-L6-v2", "embedding_dimension": 384, } ) ``` The `extra_body` is now unnecessary. --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>	2025-10-14 18:25:13 -07:00
IAN MILLER	007efa6eb5	refactor: replace default all-MiniLM-L6-v2 embedding model by nomic-embed-text-v1.5 in Llama Stack (#3183) ... # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> The purpose of this PR is to replace the Llama Stack's default embedding model by nomic-embed-text-v1.5. These are the key reasons why Llama Stack community decided to switch from all-MiniLM-L6-v2 to nomic-embed-text-v1.5: 1. The training data for [all-MiniLM-L6-v2](https://huggingface.co/sentence-transformers/all-MiniLM-L6-v2#training-data) includes a lot of data sets with various licensing terms, so it is tricky to know when/whether it is appropriate to use this model for commercial applications. 2. The model is not particularly competitive on major benchmarks. For example, if you look at the [MTEB Leaderboard](https://huggingface.co/spaces/mteb/leaderboard) and click on Miscellaneous/BEIR to see English information retrieval accuracy, you see that the top of the leaderboard is dominated by enormous models but also that there are many, many models of relatively modest size whith much higher Retrieval scores. If you want to look closely at the data, I recommend clicking "Download Table" because it is easier to browse that way. More discussion info can be founded [here](https://github.com/llamastack/llama-stack/issues/2418) <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Closes #2418 ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> 1. Run `./scripts/unit-tests.sh` 2. Integration tests via CI wokrflow --------- Signed-off-by: Sébastien Han <seb@redhat.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com> Co-authored-by: Sébastien Han <seb@redhat.com>	2025-10-14 10:44:20 -04:00
Sébastien Han	1136daf310	fix: replace python-jose with PyJWT for JWT handling (#3756) ... # What does this PR do? This commit migrates the authentication system from python-jose to PyJWT to eliminate the dependency on the archived rsa package. The migration includes: - Refactored OAuth2TokenAuthProvider to use PyJWT's PyJWKClient for clean JWKS handling - Removed manual JWKS fetching, caching and key extraction logic in favor of PyJWT's built-in functionality The new implementation is cleaner, more maintainable, and follows PyJWT best practices while maintaining full backward compatibility. ## Test Plan Unit tests. Auth CI. --------- Signed-off-by: Sébastien Han <seb@redhat.com>	2025-10-14 09:35:48 +02:00
Francisco Arceo	968c364a3e	chore: Auto-detect Provider ID when only 1 Vector Store Provider avai… (#3802) ... # What does this PR do? 2 main changes: 1. Remove `provider_id` requirement in call to vector stores and 2. Removes "register first embedding model" logic - Now forces embedding model id as required on Vector Store creation Simplifies the UX for OpenAI to: ```python vs = client.vector_stores.create( name="my_citations_db", extra_body={ "embedding_model": "ollama/nomic-embed-text:latest", } ) ``` <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>	2025-10-13 10:25:36 -07:00
raghotham	b95f095a54	feat: Allow :memory: for kvstore (#3696) ... ## Test Plan added unit tests	2025-10-13 11:19:27 +02:00
Ashwin Bharambe	ecc8a554d2	feat(api)!: support extra_body to embeddings and vector_stores APIs (#3794) ... Applies the same pattern from https://github.com/llamastack/llama-stack/pull/3777 to embeddings and vector_stores.create() endpoints. This should _not_ be a breaking change since (a) our tests were already using the `extra_body` parameter when passing in to the backend (b) but the backend probably wasn't extracting the parameters correctly. This PR will fix that. Updated APIs: `openai_embeddings(), openai_create_vector_store(), openai_create_vector_store_file_batch()`	2025-10-12 19:01:52 -07:00
Francisco Arceo	a165b8b5bb	chore!: BREAKING CHANGE removing VectorDB APIs (#3774) ... # What does this PR do? Removes VectorDBs from API surface and our tests. Moves tests to Vector Stores. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-11 14:07:08 -07:00
ehhuang	06e4cd8e02	feat(api)!: BREAKING CHANGE: support passing extra_body through to providers (#3777) ... # What does this PR do? Allows passing through extra_body parameters to inference providers. With this, we removed the 2 vllm-specific parameters from completions API into `extra_body`. Before/After <img width="1883" height="324" alt="image" src="https://github.com/user-attachments/assets/acb27c08-c748-46c9-b1da-0de64e9908a1" /> closes #2720 ## Test Plan CI and added new test ``` ❯ uv run pytest -s -v tests/integration/ --stack-config=server:starter --inference-mode=record -k 'not( builtin_tool or safety_with_image or code_interpreter or test_rag ) and test_openai_completion_guided_choice' --setup=vllm --suite=base --color=yes Uninstalled 3 packages in 125ms Installed 3 packages in 19ms INFO 2025-10-10 14:29:54,317 tests.integration.conftest:118 tests: Applying setup 'vllm' for suite base INFO 2025-10-10 14:29:54,331 tests.integration.conftest:47 tests: Test stack config type: server (stack_config=server:starter) ============================================================================================================== test session starts ============================================================================================================== platform darwin -- Python 3.12.11, pytest-8.4.2, pluggy-1.6.0 -- /Users/erichuang/projects/llama-stack-1/.venv/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.11', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '8.4.2', 'pluggy': '1.6.0'}, 'Plugins': {'anyio': '4.9.0', 'html': '4.1.1', 'socket': '0.7.0', 'asyncio': '1.1.0', 'json-report': '1.5.0', 'timeout': '2.4.0', 'metadata': '3.1.1', 'cov': '6.2.1', 'nbval': '0.11.0'}} rootdir: /Users/erichuang/projects/llama-stack-1 configfile: pyproject.toml plugins: anyio-4.9.0, html-4.1.1, socket-0.7.0, asyncio-1.1.0, json-report-1.5.0, timeout-2.4.0, metadata-3.1.1, cov-6.2.1, nbval-0.11.0 asyncio: mode=Mode.AUTO, asyncio_default_fixture_loop_scope=None, asyncio_default_test_loop_scope=function collected 285 items / 284 deselected / 1 selected tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B] instantiating llama_stack_client Starting llama stack server with config 'starter' on port 8321... Waiting for server at http://localhost:8321... (0.0s elapsed) Waiting for server at http://localhost:8321... (0.5s elapsed) Waiting for server at http://localhost:8321... (5.1s elapsed) Waiting for server at http://localhost:8321... (5.6s elapsed) Waiting for server at http://localhost:8321... (10.1s elapsed) Waiting for server at http://localhost:8321... (10.6s elapsed) Server is ready at http://localhost:8321 llama_stack_client instantiated in 11.773s PASSEDTerminating llama stack server process... Terminating process 98444 and its group... Server process and children terminated gracefully ============================================================================================================= slowest 10 durations ============================================================================================================== 11.88s setup tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B] 3.02s call tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B] 0.01s teardown tests/integration/inference/test_openai_completion.py::test_openai_completion_guided_choice[txt=vllm/Qwen/Qwen3-0.6B] ================================================================================================ 1 passed, 284 deselected, 3 warnings in 16.21s ================================================================================================= ```	2025-10-10 16:21:44 -07:00
ehhuang	80d58ab519	chore: refactor (chat)completions endpoints to use shared params struct (#3761) ... # What does this PR do? Converts openai(_chat)_completions params to pydantic BaseModel to reduce code duplication across all providers. ## Test Plan CI --- [//]: # (BEGIN SAPLING FOOTER) Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/llamastack/llama-stack/pull/3761). * #3777 * __->__ #3761	2025-10-10 15:46:34 -07:00
Derek Higgins	6954fe2274	fix(auth): allow unauthenticated access to health and version endpoints (#3736) ... The AuthenticationMiddleware was blocking all requests without an Authorization header, including health and version endpoints that are needed by monitoring tools, load balancers, and Kubernetes probes. This commit allows endpoints ending in /health or /version to bypass authentication, enabling operational tooling to function properly without requiring credentials. Closes: #3735 Signed-off-by: Derek Higgins <derekh@redhat.com>	2025-10-10 13:41:43 -07:00
Varsha	32fde8d9a8	feat: Add /v1/embeddings endpoint to batches API (#3384) ... # What does this PR do? This PR extends the Llama Stack Batches API to support the /v1/embeddings endpoint, enabling efficient batch processing of embedding requests alongside the existing /v1/chat/completions and /v1/completions support. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> Closes: https://github.com/llamastack/llama-stack/issues/3145 ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> ``` (stack-client) ➜ llama-stack git:(support/embeddings-api) conda activate stack-client && python -m pytest tests/unit/providers/batches/test_reference.py -v ============================================================================================================================================ test session starts ============================================================================================================================================= platform darwin -- Python 3.12.11, pytest-7.4.4, pluggy-1.5.0 -- /Users/vnarsing/miniconda3/envs/stack-client/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.11', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '7.4.4', 'pluggy': '1.5.0'}, 'Plugins': {'asyncio': '0.23.8', 'cov': '6.0.0', 'timeout': '2.2.0', 'socket': '0.7.0', 'xdist': '3.8.0', 'html': '3.1.1', 'langsmith': '0.3.39', 'anyio': '4.8.0', 'metadata': '3.0.0'}} rootdir: /Users/vnarsing/go/src/github/meta-llama/llama-stack configfile: pyproject.toml plugins: asyncio-0.23.8, cov-6.0.0, timeout-2.2.0, socket-0.7.0, xdist-3.8.0, html-3.1.1, langsmith-0.3.39, anyio-4.8.0, metadata-3.0.0 asyncio: mode=Mode.AUTO collected 46 items tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_and_retrieve_batch_success PASSED [ 2%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_without_metadata PASSED [ 4%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_completion_window PASSED [ 6%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_invalid_endpoints[/v1/invalid/endpoint] PASSED [ 8%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_invalid_endpoints[] PASSED [ 10%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_invalid_metadata PASSED [ 13%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_retrieve_batch_not_found PASSED [ 15%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_success PASSED [ 17%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_invalid_statuses[failed] PASSED [ 19%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_invalid_statuses[expired] PASSED [ 21%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_invalid_statuses[completed] PASSED [ 23%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_cancel_batch_not_found PASSED [ 26%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_empty PASSED [ 28%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_single_batch PASSED [ 30%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_multiple_batches PASSED [ 32%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_with_limit PASSED [ 34%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_with_pagination PASSED [ 36%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_list_batches_invalid_after PASSED [ 39%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_kvstore_persistence PASSED [ 41%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_file_not_found PASSED [ 43%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_file_exists_empty_content PASSED [ 45%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_file_mixed_valid_invalid_json PASSED [ 47%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_model PASSED [ 50%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[custom_id-custom_id-missing_required_parameter-Missing required parameter: custom_id] PASSED [ 52%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[method-method-missing_required_parameter-Missing required parameter: method] PASSED [ 54%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[url-url-missing_required_parameter-Missing required parameter: url] PASSED [ 56%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[body-body-missing_required_parameter-Missing required parameter: body] PASSED [ 58%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[model-body.model-invalid_request-Model parameter is required] PASSED [ 60%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_chat_completions[messages-body.messages-invalid_request-Messages parameter is required] PASSED [ 63%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[custom_id-custom_id-missing_required_parameter-Missing required parameter: custom_id] PASSED [ 65%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[method-method-missing_required_parameter-Missing required parameter: method] PASSED [ 67%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[url-url-missing_required_parameter-Missing required parameter: url] PASSED [ 69%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[body-body-missing_required_parameter-Missing required parameter: body] PASSED [ 71%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[model-body.model-invalid_request-Model parameter is required] PASSED [ 73%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_missing_parameters_completions[prompt-body.prompt-invalid_request-Prompt parameter is required] PASSED [ 76%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_url_mismatch PASSED [ 78%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_multiple_errors_per_request PASSED [ 80%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_request_format PASSED [ 82%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[custom_id-custom_id-12345-Custom_id must be a string] PASSED [ 84%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[url-url-123-URL must be a string] PASSED [ 86%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[method-method-invalid_value2-Method must be a string] PASSED [ 89%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[body-body-invalid_value3-Body must be a JSON dictionary object] PASSED [ 91%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[model-body.model-123-Model must be a string] PASSED [ 93%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_validate_input_invalid_parameter_types[messages-body.messages-invalid messages format-Messages must be an array] PASSED [ 95%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_max_concurrent_batches PASSED [ 97%] tests/unit/providers/batches/test_reference.py::TestReferenceBatchesImpl::test_create_batch_embeddings_endpoint PASSED [100%] ``` --------- Signed-off-by: Varsha Prasad Narsing <varshaprasad96@gmail.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-10 13:25:58 -07:00
Ashwin Bharambe	1394403360	feat(responses): implement usage tracking in streaming responses (#3771) ... Implementats usage accumulation to StreamingResponseOrchestrator. The most important part was to pass `stream_options = { "include_usage": true }` to the chat_completion call. This means I will have to record all responses tests again because request hash will change :) Test changes: - Add usage assertions to streaming and non-streaming tests - Update test recordings with actual usage data from OpenAI	2025-10-10 12:27:03 -07:00
Francisco Arceo	e7d21e1ee3	feat: Add support for Conversations in Responses API (#3743) ... # What does this PR do? This PR adds support for Conversations in Responses. <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan Unit tests Integration tests <Details> <Summary>Manual testing with this script: (click to expand)</Summary> ```python from openai import OpenAI client = OpenAI() client = OpenAI(base_url="http://localhost:8321/v1/", api_key="none") def test_conversation_create(): print("Testing conversation create...") conversation = client.conversations.create( metadata={"topic": "demo"}, items=[ {"type": "message", "role": "user", "content": "Hello!"} ] ) print(f"Created: {conversation}") return conversation def test_conversation_retrieve(conv_id): print(f"Testing conversation retrieve for {conv_id}...") retrieved = client.conversations.retrieve(conv_id) print(f"Retrieved: {retrieved}") return retrieved def test_conversation_update(conv_id): print(f"Testing conversation update for {conv_id}...") updated = client.conversations.update( conv_id, metadata={"topic": "project-x"} ) print(f"Updated: {updated}") return updated def test_conversation_delete(conv_id): print(f"Testing conversation delete for {conv_id}...") deleted = client.conversations.delete(conv_id) print(f"Deleted: {deleted}") return deleted def test_conversation_items_create(conv_id): print(f"Testing conversation items create for {conv_id}...") items = client.conversations.items.create( conv_id, items=[ { "type": "message", "role": "user", "content": [{"type": "input_text", "text": "Hello!"}] }, { "type": "message", "role": "user", "content": [{"type": "input_text", "text": "How are you?"}] } ] ) print(f"Items created: {items}") return items def test_conversation_items_list(conv_id): print(f"Testing conversation items list for {conv_id}...") items = client.conversations.items.list(conv_id, limit=10) print(f"Items list: {items}") return items def test_conversation_item_retrieve(conv_id, item_id): print(f"Testing conversation item retrieve for {conv_id}/{item_id}...") item = client.conversations.items.retrieve(conversation_id=conv_id, item_id=item_id) print(f"Item retrieved: {item}") return item def test_conversation_item_delete(conv_id, item_id): print(f"Testing conversation item delete for {conv_id}/{item_id}...") deleted = client.conversations.items.delete(conversation_id=conv_id, item_id=item_id) print(f"Item deleted: {deleted}") return deleted def test_conversation_responses_create(): print("\nTesting conversation create for a responses example...") conversation = client.conversations.create() print(f"Created: {conversation}") response = client.responses.create( model="gpt-4.1", input=[{"role": "user", "content": "What are the 5 Ds of dodgeball?"}], conversation=conversation.id, ) print(f"Created response: {response} for conversation {conversation.id}") return response, conversation def test_conversations_responses_create_followup( conversation, content="Repeat what you just said but add 'this is my second time saying this'", ): print(f"Using: {conversation.id}") response = client.responses.create( model="gpt-4.1", input=[{"role": "user", "content": content}], conversation=conversation.id, ) print(f"Created response: {response} for conversation {conversation.id}") conv_items = client.conversations.items.list(conversation.id) print(f"\nRetrieving list of items for conversation {conversation.id}:") print(conv_items.model_dump_json(indent=2)) def test_response_with_fake_conv_id(): fake_conv_id = "conv_zzzzzzzzz5dc81908289d62779d2ac510a2b0b602ef00a44" print(f"Using {fake_conv_id}") try: response = client.responses.create( model="gpt-4.1", input=[{"role": "user", "content": "say hello"}], conversation=fake_conv_id, ) print(f"Created response: {response} for conversation {fake_conv_id}") except Exception as e: print(f"failed to create response for conversation {fake_conv_id} with error {e}") def main(): print("Testing OpenAI Conversations API...") # Create conversation conversation = test_conversation_create() conv_id = conversation.id # Retrieve conversation test_conversation_retrieve(conv_id) # Update conversation test_conversation_update(conv_id) # Create items items = test_conversation_items_create(conv_id) # List items items_list = test_conversation_items_list(conv_id) # Retrieve specific item if items_list.data: item_id = items_list.data[0].id test_conversation_item_retrieve(conv_id, item_id) # Delete item test_conversation_item_delete(conv_id, item_id) # Delete conversation test_conversation_delete(conv_id) response, conversation2 = test_conversation_responses_create() print('\ntesting reseponse retrieval') test_conversation_retrieve(conversation2.id) print('\ntesting responses follow up') test_conversations_responses_create_followup(conversation2) print('\ntesting responses follow up x2!') test_conversations_responses_create_followup( conversation2, content="Repeat what you just said but add 'this is my third time saying this'", ) test_response_with_fake_conv_id() print("All tests completed!") if __name__ == "__main__": main() ``` </Details> --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-10 11:57:40 -07:00
grs	8bf07f91cb	feat: reuse previous mcp tool listings where possible (#3710) ... # What does this PR do? This PR checks whether, if a previous response is linked, there are mcp_list_tools objects that can be reused instead of listing the tools explicitly every time. Closes #3106 ## Test Plan Tested manually. Added unit tests to cover new behaviour. --------- Signed-off-by: Gordon Sim <gsim@redhat.com> Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>	2025-10-10 09:28:25 -07:00
Matthew Farrellee	0066d986c5	feat: use SecretStr for inference provider auth credentials (#3724) ... # What does this PR do? use SecretStr for OpenAIMixin providers - RemoteInferenceProviderConfig now has auth_credential: SecretStr - the default alias is api_key (most common name) - some providers override to use api_token (RunPod, vLLM, Databricks) - some providers exclude it (Ollama, TGI, Vertex AI) addresses #3517 ## Test Plan ci w/ new tests	2025-10-10 07:32:50 -07:00
Ashwin Bharambe	e039b61d26	feat(responses)!: add in_progress, failed, content part events (#3765) ... ## Summary - add schema + runtime support for response.in_progress / response.failed / response.incomplete - stream content parts with proper indexes and reasoning slots - align tests + docs with the richer event payloads ## Testing - uv run pytest tests/unit/providers/agents/meta_reference/test_openai_responses.py::test_create_openai_response_with_string_input - uv run pytest tests/unit/providers/agents/meta_reference/test_response_conversion_utils.py	2025-10-10 07:27:34 -07:00
Matthew Farrellee	145b2bcf25	feat: make object registration idempotent (#3752) ... # What does this PR do? objects (vector dbs, models, scoring functions, etc) have an identifier and associated object values. we allow exact duplicate registrations. we reject registrations when the identifier exists and the associated object values differ. note: model are namespaced, i.e. {provider_id}/{identifier}, while other object types are not ## Test Plan ci w/ new tests	2025-10-09 17:04:28 -07:00
Ashwin Bharambe	841d0c3583	fix(testing): improve api_recorder error messages for missing recordings (#3760) ... Replaces opaque error messages when recordings are not found with somewhat better guidance Before: ``` No recorded response found for request hash: abc123... To record this response, run with LLAMA_STACK_TEST_INFERENCE_MODE=record ``` After: ``` Recording not found for request hash: abc123 Model: gpt-4 | Request: POST https://api.openai.com/v1/chat/completions Run './scripts/integration-tests.sh --inference-mode record-if-missing' with required API keys to generate. ```	2025-10-09 15:04:16 -07:00
Ashwin Bharambe	a055a32ee4	fix(tests): remove chroma and qdrant from vector io unit tests (#3759) ... These vector databases are already thoroughly tested in integration tests. Unit tests now focus on sqlite_vec, faiss, and pgvector with mocked dependencies, removing the need for external service dependencies. ## Changes: - Deleted test_qdrant.py unit test file - Removed chroma/qdrant fixtures and parametrization from conftest.py - Fixed SqliteKVStoreConfig import to use correct location - Removed chromadb, qdrant-client, pymilvus, milvus-lite, and weaviate-client from unit test dependencies in pyproject.toml	2025-10-09 14:36:34 -07:00
Ashwin Bharambe	f50ce11a3b	feat(tests): make inference_recorder into api_recorder (include tool_invoke) (#3403) ... Renames `inference_recorder.py` to `api_recorder.py` and extends it to support recording/replaying tool invocations in addition to inference calls. This allows us to record web-search, etc. tool calls and thereafter apply recordings for `tests/integration/responses` ## Test Plan ``` export OPENAI_API_KEY=... export TAVILY_SEARCH_API_KEY=... ./scripts/integration-tests.sh --stack-config ci-tests \ --suite responses --inference-mode record-if-missing ```	2025-10-09 14:27:51 -07:00
Sébastien Han	4b9ebbf6a2	chore: revert "fix: Raising an error message to the user when registering an existing provider." (#3750) ... Reverts llamastack/llama-stack#3624 Causing https://github.com/llamastack/llama-stack/issues/3749	2025-10-09 09:17:37 -04:00
Francisco Arceo	b96640eca3	chore: Removing Weaviate, PGVector, and Milvus from unit tests (#3742) ... # What does this PR do? Removing Weaviate, PostGres, and Milvus unit tests <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>	2025-10-08 12:25:51 -07:00
Bill Murdock	5d711d4bcb	fix: Update watsonx.ai provider to use LiteLLM mixin and list all models (#3674) ... # What does this PR do? - The watsonx.ai provider now uses the LiteLLM mixin instead of using IBM's library, which does not seem to be working (see #3165 for context). - The watsonx.ai provider now lists all the models available by calling the watsonx.ai server instead of having a hard coded list of known models. (That list gets out of date quickly) - An edge case in [llama_stack/core/routers/inference.py](https://github.com/llamastack/llama-stack/pull/3674/files#diff-a34bc966ed9befd9f13d4883c23705dff49be0ad6211c850438cdda6113f3455) is addressed that was causing my manual tests to fail. - Fixes `b64_encode_openai_embeddings_response` which was trying to enumerate over a dictionary and then reference elements of the dictionary using .field instead of ["field"]. That method is called by the LiteLLM mixin for embedding models, so it is needed to get the watsonx.ai embedding models to work. - A unit test along the lines of the one in #3348 is added. A more comprehensive plan for automatically testing the end-to-end functionality for inference providers would be a good idea, but is out of scope for this PR. - Updates to the watsonx distribution. Some were in response to the switch to LiteLLM (e.g., updating the Python packages needed). Others seem to be things that were already broken that I found along the way (e.g., a reference to a watsonx specific doc template that doesn't seem to exist). Closes #3165 Also it is related to a line-item in #3387 but doesn't really address that goal (because it uses the LiteLLM mixin, not the OpenAI one). I tried the OpenAI one and it doesn't work with watsonx.ai, presumably because the watsonx.ai service is not OpenAI compatible. It works with LiteLLM because LiteLLM has a provider implementation for watsonx.ai. ## Test Plan The test script below goes back and forth between the OpenAI and watsonx providers. The idea is that the OpenAI provider shows how it should work and then the watsonx provider output shows that it is also working with watsonx. Note that the result from the MCP test is not as good (the Llama 3.3 70b model does not choose tools as wisely as gpt-4o), but it is still working and providing a valid response. For more details on setup and the MCP server being used for testing, see [the AI Alliance sample notebook](https://github.com/The-AI-Alliance/llama-stack-examples/blob/main/notebooks/01-responses/) that these examples are drawn from. ```python #!/usr/bin/env python3 import json from llama_stack_client import LlamaStackClient from litellm import completion import http.client def print_response(response): """Print response in a nicely formatted way""" print(f"ID: {response.id}") print(f"Status: {response.status}") print(f"Model: {response.model}") print(f"Created at: {response.created_at}") print(f"Output items: {len(response.output)}") for i, output_item in enumerate(response.output): if len(response.output) > 1: print(f"\n--- Output Item {i+1} ---") print(f"Output type: {output_item.type}") if output_item.type in ("text", "message"): print(f"Response content: {output_item.content[0].text}") elif output_item.type == "file_search_call": print(f" Tool Call ID: {output_item.id}") print(f" Tool Status: {output_item.status}") # 'queries' is a list, so we join it for clean printing print(f" Queries: {', '.join(output_item.queries)}") # Display results if they exist, otherwise note they are empty print(f" Results: {output_item.results if output_item.results else 'None'}") elif output_item.type == "mcp_list_tools": print_mcp_list_tools(output_item) elif output_item.type == "mcp_call": print_mcp_call(output_item) else: print(f"Response content: {output_item.content}") def print_mcp_call(mcp_call): """Print MCP call in a nicely formatted way""" print(f"\n🛠️ MCP Tool Call: {mcp_call.name}") print(f" Server: {mcp_call.server_label}") print(f" ID: {mcp_call.id}") print(f" Arguments: {mcp_call.arguments}") if mcp_call.error: print("Error: {mcp_call.error}") elif mcp_call.output: print("Output:") # Try to format JSON output nicely try: parsed_output = json.loads(mcp_call.output) print(json.dumps(parsed_output, indent=4)) except: # If not valid JSON, print as-is print(f" {mcp_call.output}") else: print(" ⏳ No output yet") def print_mcp_list_tools(mcp_list_tools): """Print MCP list tools in a nicely formatted way""" print(f"\n🔧 MCP Server: {mcp_list_tools.server_label}") print(f" ID: {mcp_list_tools.id}") print(f" Available Tools: {len(mcp_list_tools.tools)}") print("=" * 80) for i, tool in enumerate(mcp_list_tools.tools, 1): print(f"\n{i}. {tool.name}") print(f" Description: {tool.description}") # Parse and display input schema schema = tool.input_schema if schema and 'properties' in schema: properties = schema['properties'] required = schema.get('required', []) print(" Parameters:") for param_name, param_info in properties.items(): param_type = param_info.get('type', 'unknown') param_desc = param_info.get('description', 'No description') required_marker = " (required)" if param_name in required else " (optional)" print(f" • {param_name} ({param_type}){required_marker}") if param_desc: print(f" {param_desc}") if i < len(mcp_list_tools.tools): print("-" * 40) def main(): """Main function to run all the tests""" # Configuration LLAMA_STACK_URL = "http://localhost:8321/" LLAMA_STACK_MODEL_IDS = [ "openai/gpt-3.5-turbo", "openai/gpt-4o", "llama-openai-compat/Llama-3.3-70B-Instruct", "watsonx/meta-llama/llama-3-3-70b-instruct" ] # Using gpt-4o for this demo, but feel free to try one of the others or add more to run.yaml. OPENAI_MODEL_ID = LLAMA_STACK_MODEL_IDS[1] WATSONX_MODEL_ID = LLAMA_STACK_MODEL_IDS[-1] NPS_MCP_URL = "http://localhost:3005/sse/" print("=== Llama Stack Testing Script ===") print(f"Using OpenAI model: {OPENAI_MODEL_ID}") print(f"Using WatsonX model: {WATSONX_MODEL_ID}") print(f"MCP URL: {NPS_MCP_URL}") print() # Initialize client print("Initializing LlamaStackClient...") client = LlamaStackClient(base_url="http://localhost:8321") # Test 1: List models print("\n=== Test 1: List Models ===") try: models = client.models.list() print(f"Found {len(models)} models") except Exception as e: print(f"Error listing models: {e}") raise e # Test 2: Basic chat completion with OpenAI print("\n=== Test 2: Basic Chat Completion (OpenAI) ===") try: chat_completion_response = client.chat.completions.create( model=OPENAI_MODEL_ID, messages=[{"role": "user", "content": "What is the capital of France?"}] ) print("OpenAI Response:") for chunk in chat_completion_response.choices[0].message.content: print(chunk, end="", flush=True) print() except Exception as e: print(f"Error with OpenAI chat completion: {e}") raise e # Test 3: Basic chat completion with WatsonX print("\n=== Test 3: Basic Chat Completion (WatsonX) ===") try: chat_completion_response_wxai = client.chat.completions.create( model=WATSONX_MODEL_ID, messages=[{"role": "user", "content": "What is the capital of France?"}], ) print("WatsonX Response:") for chunk in chat_completion_response_wxai.choices[0].message.content: print(chunk, end="", flush=True) print() except Exception as e: print(f"Error with WatsonX chat completion: {e}") raise e # Test 4: Tool calling with OpenAI print("\n=== Test 4: Tool Calling (OpenAI) ===") tools = [ { "type": "function", "function": { "name": "get_current_weather", "description": "Get the current weather for a specific location", "parameters": { "type": "object", "properties": { "location": { "type": "string", "description": "The city and state, e.g., San Francisco, CA", }, "unit": { "type": "string", "enum": ["celsius", "fahrenheit"] }, }, "required": ["location"], }, }, } ] messages = [ {"role": "user", "content": "What's the weather like in Boston, MA?"} ] try: print("--- Initial API Call ---") response = client.chat.completions.create( model=OPENAI_MODEL_ID, messages=messages, tools=tools, tool_choice="auto", # "auto" is the default ) print("OpenAI tool calling response received") except Exception as e: print(f"Error with OpenAI tool calling: {e}") raise e # Test 5: Tool calling with WatsonX print("\n=== Test 5: Tool Calling (WatsonX) ===") try: wxai_response = client.chat.completions.create( model=WATSONX_MODEL_ID, messages=messages, tools=tools, tool_choice="auto", # "auto" is the default ) print("WatsonX tool calling response received") except Exception as e: print(f"Error with WatsonX tool calling: {e}") raise e # Test 6: Streaming with WatsonX print("\n=== Test 6: Streaming Response (WatsonX) ===") try: chat_completion_response_wxai_stream = client.chat.completions.create( model=WATSONX_MODEL_ID, messages=[{"role": "user", "content": "What is the capital of France?"}], stream=True ) print("Model response: ", end="") for chunk in chat_completion_response_wxai_stream: # Each 'chunk' is a ChatCompletionChunk object. # We want the content from the 'delta' attribute. if hasattr(chunk, 'choices') and chunk.choices is not None: content = chunk.choices[0].delta.content # The first few chunks might have None content, so we check for it. if content is not None: print(content, end="", flush=True) print() except Exception as e: print(f"Error with streaming: {e}") raise e # Test 7: MCP with OpenAI print("\n=== Test 7: MCP Integration (OpenAI) ===") try: mcp_llama_stack_client_response = client.responses.create( model=OPENAI_MODEL_ID, input="Tell me about some parks in Rhode Island, and let me know if there are any upcoming events at them.", tools=[ { "type": "mcp", "server_url": NPS_MCP_URL, "server_label": "National Parks Service tools", "allowed_tools": ["search_parks", "get_park_events"], } ] ) print_response(mcp_llama_stack_client_response) except Exception as e: print(f"Error with MCP (OpenAI): {e}") raise e # Test 8: MCP with WatsonX print("\n=== Test 8: MCP Integration (WatsonX) ===") try: mcp_llama_stack_client_response = client.responses.create( model=WATSONX_MODEL_ID, input="What is the capital of France?" ) print_response(mcp_llama_stack_client_response) except Exception as e: print(f"Error with MCP (WatsonX): {e}") raise e # Test 9: MCP with Llama 3.3 print("\n=== Test 9: MCP Integration (Llama 3.3) ===") try: mcp_llama_stack_client_response = client.responses.create( model=WATSONX_MODEL_ID, input="Tell me about some parks in Rhode Island, and let me know if there are any upcoming events at them.", tools=[ { "type": "mcp", "server_url": NPS_MCP_URL, "server_label": "National Parks Service tools", "allowed_tools": ["search_parks", "get_park_events"], } ] ) print_response(mcp_llama_stack_client_response) except Exception as e: print(f"Error with MCP (Llama 3.3): {e}") raise e # Test 10: Embeddings print("\n=== Test 10: Embeddings ===") try: conn = http.client.HTTPConnection("localhost:8321") payload = json.dumps({ "model": "watsonx/ibm/granite-embedding-278m-multilingual", "input": "Hello, world!", }) headers = { 'Content-Type': 'application/json', 'Accept': 'application/json' } conn.request("POST", "/v1/openai/v1/embeddings", payload, headers) res = conn.getresponse() data = res.read() print(data.decode("utf-8")) except Exception as e: print(f"Error with Embeddings: {e}") raise e print("\n=== Testing Complete ===") if __name__ == "__main__": main() ``` --------- Signed-off-by: Bill Murdock <bmurdock@redhat.com> Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com>	2025-10-08 07:29:43 -04:00
Omar Abdelwahab	702fcd1abf	fix: Raising an error message to the user when registering an existing provider. (#3624) ... When the user wants to change the attributes (which could include model name, dimensions,...etc) of an already registered provider, they will get an error message asking that they first unregister the provider before registering a new one. # What does this PR do? This PR updated the register function to raise an error to the user when they attempt to register a provider that was already registered asking them to un-register the existing provider first. <!-- If resolving an issue, uncomment and update the line below --> #2313 ## Test Plan Tested the change with /tests/unit/registry/test_registry.py --------- Co-authored-by: Omar Abdelwahab <omara@fb.com>	2025-10-08 12:09:23 +02:00
slekkala1	c2d97a9db9	chore: fix flaky unit test and add proper shutdown for file batches (#3725) ... # What does this PR do? Have been running into flaky unit test failures: 5217035494 Fixing below 1. Shutting down properly by cancelling any stale file batches tasks running in background. 2. Also, use unique_kvstore_config, so the test dont use same db path and maintain test isolation ## Test Plan Ran unit test locally and CI	2025-10-07 14:23:14 -07:00
Akram Ben Aissi	1970b4aa4b	fix: improve model availability checks: Allows use of unavailable models on startup (#3717) ... - Allows use of unavailable models on startup - Add has_model method to ModelsRoutingTable for checking pre-registered models - Update check_model_availability to check model_store before provider APIs # What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> ## Test Plan <!-- Describe the tests you ran to verify your changes with result summaries. *Provide clear instructions so the plan can be easily re-executed.* --> Start llama stack and point unavailable vLLM ``` VLLM_URL=https://my-unavailable-vllm/v1 MILVUS_DB_PATH=./milvus.db INFERENCE_MODEL=vllm uv run --with llama-stack llama stack build --distro starter --image-type venv --run ``` llama stack will start without crashing but only notifying error. ``` - provider_id: rag-runtime toolgroup_id: builtin::rag vector_dbs: [] version: 2 INFO 2025-10-07 06:40:41,804 llama_stack.providers.utils.inference.inference_store:74 inference: Write queue disabled for SQLite to avoid concurrency issues INFO 2025-10-07 06:40:42,066 llama_stack.providers.utils.responses.responses_store:96 openai_responses: Write queue disabled for SQLite to avoid concurrency issues ERROR 2025-10-07 06:40:58,882 llama_stack.providers.utils.inference.openai_mixin:436 providers::utils: VLLMInferenceAdapter.list_provider_model_ids() failed with: Request timed out. WARNING 2025-10-07 06:40:58,883 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider vllm: Request timed out. [...] INFO 2025-10-07 06:40:59,036 uvicorn.error:216 uncategorized: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit) INFO 2025-10-07 06:41:04,064 openai._base_client:1618 uncategorized: Retrying request to /models in 0.398814 seconds INFO 2025-10-07 06:41:09,497 openai._base_client:1618 uncategorized: Retrying request to /models in 0.781908 seconds ERROR 2025-10-07 06:41:15,282 llama_stack.providers.utils.inference.openai_mixin:436 providers::utils: VLLMInferenceAdapter.list_provider_model_ids() failed with: Request timed out. WARNING 2025-10-07 06:41:15,283 llama_stack.core.routing_tables.models:36 core::routing_tables: Model refresh failed for provider vllm: Request timed out. ```	2025-10-07 14:27:24 -04:00