mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 18:00:36 +00:00
3075 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Nathan Weinberg
|
b6bb8fbf64
|
ci: add pre-commit check ensuring FIPS compliance (#3899)
# What does this PR do? this commit adds a new pre-commit hook to scan for non-FIPS compliant function usage within llama-stack Closes #3427 ## Test Plan Ran locally Signed-off-by: Nathan Weinberg <nweinber@redhat.com> |
||
Ashwin Bharambe
|
e809d21357
|
feat: add backward compatibility tests for run.yaml (#3952)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 1s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Python Package Build Test / build (3.12) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.13) (push) Failing after 1s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Test External API and Providers / test-external (venv) (push) Failing after 42s
Vector IO Integration Tests / test-matrix (push) Failing after 45s
API Conformance Tests / check-schema-compatibility (push) Successful in 54s
UI Tests / ui-tests (22) (push) Successful in 52s
Pre-commit / pre-commit (push) Successful in 3m28s
This adds automated backward compatibility testing for `run.yaml` files. As we evolve `StackRunConfig`, changes can inadvertently break existing user configurations. This workflow catches those breaks before merge. We test old run.yaml files (from main and the latest release) against the PR's new code. If configs that worked before now fail, the PR is blocked unless explicitly acknowledged as a breaking change. **Two test layers:** - Schema validation: Quick pytest checks that configs parse without errors - Integration tests: Full test suite execution to catch runtime semantic issues (cross-field validations, provider initialization, etc.) **What we test against:** - main branch: Breaking changes here block the PR (this is the gate) - Latest release: Informational only - shows if we've drifted from what users have If tests fail, the PR author must acknowledge the breaking change by adding `!:` to the PR title (e.g., `feat!: change xyz`) or including `BREAKING CHANGE:` in a commit message. Once acknowledged, the check passes with a warning. These jobs are run: 1. `check-main-compatibility` - Schema validation of all distribution run.yaml files from main 2. `test-integration-main` - Full integration test suite using main's ci-tests run.yaml 3. `test-integration-release` - Integration tests with latest release config (informational) 4. `check-schema-release-compatibility` - Schema checks against release (informational) The integration tests catch issues that schema validation alone would miss, like assertion failures in `StackRunConfig.validate_server_stores()` or provider-specific runtime logic. Resolves #3311 Related to #3237 |
||
Derek Higgins
|
c678682cdd
|
chore: remove unused methods from InferenceRouter (#3953)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Test Llama Stack Build / generate-matrix (push) Successful in 3s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 6s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Test Llama Stack Build / build-single-provider (push) Failing after 4s
Python Package Build Test / build (3.12) (push) Failing after 2s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 4s
Test llama stack list-deps / show-single-provider (push) Failing after 3s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Unit Tests / unit-tests (3.12) (push) Failing after 5s
Test llama stack list-deps / list-deps-from-config (push) Failing after 24s
Test llama stack list-deps / generate-matrix (push) Successful in 25s
Python Package Build Test / build (3.13) (push) Failing after 25s
Unit Tests / unit-tests (3.13) (push) Failing after 25s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 29s
Vector IO Integration Tests / test-matrix (push) Failing after 32s
Test llama stack list-deps / list-deps (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 40s
UI Tests / ui-tests (22) (push) Successful in 59s
Test Llama Stack Build / build (push) Failing after 1m1s
Pre-commit / pre-commit (push) Successful in 5m23s
Remove unused methods that became obsolete after
|
||
ehhuang
|
1aa8979050
|
test: enable telemetry tests in server mode (#3927)
# What does this PR do? - added a server-based test OLTP collector ## Test Plan CI |
||
|
ehhuang
|
1f9d48cd54
|
feat: openai files provider (#3946)
# What does this PR do? - Adds OpenAI files provider - Note that file content retrieval is pretty limited by `purpose` https://community.openai.com/t/file-uploads-error-why-can-t-i-download-files-with-purpose-user-data/1357013?utm_source=chatgpt.com ## Test Plan Modify run yaml to use openai files provider: ``` files: - provider_id: openai provider_type: remote::openai config: api_key: ${env.OPENAI_API_KEY:=} metadata_store: backend: sql_default table_name: openai_files_metadata # Then run files tests ❯ uv run --no-sync ./scripts/integration-tests.sh --stack-config server:ci-tests --inference-mode replay --setup ollama --suite base --pattern test_files ``` |
||
raghotham
|
feabcdd67b
|
docs: add documentation on how to use custom run yaml in docker (#3949)
as title
test plan:
```yaml
# custom-ollama-run.yaml
version: 2
image_name: starter
external_providers_dir: /.llama/providers.d
apis:
- inference
- vector_io
- files
- safety
- tool_runtime
- agents
providers:
inference:
# Single Ollama provider for all models
- provider_id: ollama
provider_type: remote::ollama
config:
url: ${env.OLLAMA_URL:=http://localhost:11434}
vector_io:
- provider_id: faiss
provider_type: inline::faiss
config:
persistence:
namespace: vector_io::faiss
backend: kv_default
files:
- provider_id: meta-reference-files
provider_type: inline::localfs
config:
storage_dir: /.llama/files
metadata_store:
table_name: files_metadata
backend: sql_default
safety:
- provider_id: llama-guard
provider_type: inline::llama-guard
config:
excluded_categories: []
tool_runtime:
- provider_id: rag-runtime
provider_type: inline::rag-runtime
agents:
- provider_id: meta-reference
provider_type: inline::meta-reference
config:
persistence:
agent_state:
namespace: agents
backend: kv_default
responses:
table_name: responses
backend: sql_default
max_write_queue_size: 10000
num_writers: 4
storage:
backends:
kv_default:
type: kv_sqlite
db_path: /.llama/kvstore.db
sql_default:
type: sql_sqlite
db_path: /.llama/sql_store.db
stores:
metadata:
namespace: registry
backend: kv_default
inference:
table_name: inference_store
backend: sql_default
max_write_queue_size: 10000
num_writers: 4
conversations:
table_name: openai_conversations
backend: sql_default
registered_resources:
models:
# All models use the same 'ollama' provider
- model_id: llama3.2-vision:latest
provider_id: ollama
provider_model_id: llama3.2-vision:latest
model_type: llm
- model_id: llama3.2:3b
provider_id: ollama
provider_model_id: llama3.2:3b
model_type: llm
# Embedding models
- model_id: nomic-embed-text-v2-moe
provider_id: ollama
provider_model_id: toshk0/nomic-embed-text-v2-moe:Q6_K
model_type: embedding
metadata:
embedding_dimension: 768
shields: []
vector_dbs: []
datasets: []
scoring_fns: []
benchmarks: []
tool_groups: []
server:
port: 8321
telemetry:
enabled: true
vector_stores:
default_provider_id: faiss
default_embedding_model:
provider_id: ollama
model_id: toshk0/nomic-embed-text-v2-moe:Q6_K
```
```bash
docker run
-it
--pull always
-p $LLAMA_STACK_PORT:$LLAMA_STACK_PORT
-v ~/.llama:/root/.llama
-v $CUSTOM_RUN_CONFIG:/app/custom-run.yaml
-e RUN_CONFIG_PATH=/app/custom-run.yaml
-e OLLAMA_URL=http://host.docker.internal:11434/
llamastack/distribution-starter:0.3.0
--port $LLAMA_STACK_PORT
```
|
||
|
Ashwin Bharambe
|
f88416ef87
|
fix(inference): enable routing of models with provider_data alone (#3928)
This PR enables routing of fully qualified model IDs of the form `provider_id/model_id` even when the models are not registered with the Stack. Here's the situation: assume a remote inference provider which works only when users provide their own API keys via `X-LlamaStack-Provider-Data` header. By definition, we cannot list models and hence update our routing registry. But because we _require_ a provider ID in the models now, we can identify which provider to route to and let that provider decide. Note that we still try to look up our registry since it may have a pre-registered alias. Just that we don't outright fail when we are not able to look it up. Also, updated inference router so that the responses have the _exact_ model that the request had. ## Test Plan Added an integration test Closes #3929 --------- Co-authored-by: ehhuang <ehhuang@users.noreply.github.com> |
||
|
Ashwin Bharambe
|
94b0592240
|
fix(mypy): add type stubs and fix typing issues (#3938)
Adds type stubs and fixes mypy errors for better type coverage. Changes: - Added type_checking dependency group with type stubs (torchtune, trl, etc.) - Added lm-format-enforcer to pre-commit hook - Created HFAutoModel Protocol for type-safe HuggingFace model handling - Added mypy.overrides for untyped libraries (torchtune, fairscale, etc.) - Fixed type issues in post-training providers, databricks, and api_recorder Note: ~1,200 errors remain in excluded files (see pyproject.toml exclude list). --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Ashwin Bharambe
|
1d385b5b75
|
fix(mypy): resolve OpenAI SDK and provider type issues (#3936)
## Summary - Fix OpenAI SDK NotGiven/Omit type mismatches in embeddings calls - Fix incorrect OpenAIChatCompletionChunk import in vllm provider - Refactor to avoid type:ignore comments by using conditional kwargs ## Changes **openai_mixin.py (9 errors fixed):** - Build kwargs conditionally for embeddings.create() to avoid NotGiven/Omit mismatch - Only include parameters when they have actual values (not None) **gemini.py (9 errors fixed):** - Apply same conditional kwargs pattern - Add missing Any import **vllm.py (2 errors fixed):** - Use correct OpenAIChatCompletionChunk from llama_stack.apis.inference - Remove incorrect alias from openai package ## Technical Notes The OpenAI SDK has a type system quirk where `NOT_GIVEN` has type `NotGiven` but parameter signatures expect `Omit`. By only passing parameters with actual values, we avoid this mismatch entirely without needing `# type: ignore` comments. 🤖 Generated with [Claude Code](https://claude.com/claude-code) --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Ashwin Bharambe
|
d009dc29f7
|
fix(mypy): resolve provider utility and testing type issues (#3935)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Test Llama Stack Build / generate-matrix (push) Successful in 3s
Vector IO Integration Tests / test-matrix (push) Failing after 5s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.12) (push) Failing after 2s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 4s
Test Llama Stack Build / build-single-provider (push) Failing after 4s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 4s
Python Package Build Test / build (3.13) (push) Failing after 3s
Test llama stack list-deps / generate-matrix (push) Successful in 4s
Test llama stack list-deps / show-single-provider (push) Failing after 3s
API Conformance Tests / check-schema-compatibility (push) Successful in 11s
Test llama stack list-deps / list-deps-from-config (push) Failing after 4s
Test External API and Providers / test-external (venv) (push) Failing after 3s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Test llama stack list-deps / list-deps (push) Failing after 4s
Test Llama Stack Build / build (push) Failing after 7s
UI Tests / ui-tests (22) (push) Successful in 51s
Pre-commit / pre-commit (push) Successful in 2m0s
Fixes mypy type errors in provider utilities and testing infrastructure: - `mcp.py`: Cast incompatible client types, wrap image data properly - `batches.py`: Rename walrus variable to avoid shadowing - `api_recorder.py`: Use cast for Pydantic field annotation No functional changes. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Ashwin Bharambe
|
fcf07790c8
|
fix(mypy): resolve model implementation typing issues (#3934)
## Summary Fixes mypy type errors across 4 model implementation files (Phase 2d of mypy suppression removal plan): - `src/llama_stack/models/llama/llama3/multimodal/image_transform.py` (10 errors fixed) - `src/llama_stack/models/llama/checkpoint.py` (2 errors fixed) - `src/llama_stack/models/llama/hadamard_utils.py` (1 error fixed) - `src/llama_stack/models/llama/llama3/multimodal/encoder_utils.py` (1 error fixed) ## Changes ### image_transform.py - Fixed return type annotation for `find_supported_resolutions` from `Tensor` to `list[tuple[int, int]]` - Fixed parameter and return type annotations for `resize_without_distortion` from `Tensor` to `Image.Image` - Resolved variable shadowing by using separate names: `possible_resolutions_list` for the list and `possible_resolutions_tensor` for the tensor ### checkpoint.py - Replaced deprecated `torch.BFloat16Tensor` and `torch.cuda.BFloat16Tensor` with `torch.set_default_dtype(torch.bfloat16)` - Fixed variable shadowing by renaming numpy array to `ckpt_paths_array` to distinguish from the parameter `ckpt_paths: list[Path]` ### hadamard_utils.py - Added `isinstance` assertion to narrow type from `nn.Module` to `nn.Linear` before accessing `in_features` attribute ### encoder_utils.py - Fixed variable shadowing by using `masks_list` for list accumulation and `masks` for the final Tensor result ## Test plan - Verified all files pass mypy type checking (only optional dependency import warnings remain) - No functional changes - only type annotations and variable naming improvements Stacks on PR #3933 Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Ashwin Bharambe
|
6ce59b5df8
|
fix(mypy): resolve type issues in MongoDB, batches, and auth providers (#3933)
Fixes mypy type errors in provider utilities: - MongoDB: Fix AsyncMongoClient parameters, use async iteration for cursor - Batches: Handle memoryview|bytes union for file decoding - Auth: Add missing imports, validate JWKS URI, conditionally pass parameters Fixes 11 type errors. No functional changes. |
||
|
Ashwin Bharambe
|
4a2ea278c5
|
fix(mypy): resolve OpenTelemetry typing issues in telemetry.py (#3943)
Fixes mypy type errors in OpenTelemetry integration: - Add type aliases for AttributeValue and Attributes - Add helper to filter None values from attributes (OpenTelemetry doesn't accept None) - Cast metric and tracer objects to proper types - Update imports after refactoring No functional changes. |
||
|
Ashwin Bharambe
|
85887d724f |
Revert "fix(mypy): resolve OpenTelemetry typing issues in telemetry.py (#3931)"
This reverts commit
|
||
|
Ashwin Bharambe
|
9afc52a36a
|
fix(mypy): resolve OpenTelemetry typing issues in telemetry.py (#3931)
## Summary Fix all 11 mypy type checking errors in `telemetry.py` without using any type suppressions. **Changes:** - Add type aliases for OpenTelemetry attribute types (`AttributeValue`, `Attributes`) - Create `_clean_attributes()` helper to filter None values from attribute dicts - Use `cast()` for TracerProvider methods (`add_span_processor`, `force_flush`) - Use `cast()` for metric creation methods returning from global storage - Fix variable reuse by renaming `span` to `end_span` in SpanEndPayload branch - Add None check for `parent_span` before `set_span_in_context` **Errors Fixed:** - TracerProvider attribute access: 2 errors - Counter/UpDownCounter/ObservableGauge return types: 3 errors - Attribute dict type mismatches: 4 errors - Span assignment type conflicts: 2 errors **Testing:** ```bash uv run mypy src/llama_stack/core/telemetry/telemetry.py # Success: no issues found ``` **Part of:** Mypy suppression removal plan (Phase 2a/4) **Stack:** - [Phase 1] Add type stubs (#3930) - [Phase 2a] Fix OpenTelemetry types (this PR) - [Phase 2b+] Fix remaining errors (upcoming) - [Phase 3] Remove inline suppressions (upcoming) - [Phase 4] Un-exclude files from mypy (upcoming) |
||
Ian Miller
|
5598f61e12
|
feat(responses)!: introduce OpenAI compatible prompts to Responses API (#3942)
# What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> This PR is responsible for making changes to Responses API scheme to introduce OpenAI compatible prompts there. Change to the API only, therefore currently no implementation at all. However, the follow up PR with actual implementation will be submitted after current PR lands. The need of this functionality was initiated in #3514. > Note, #3514 is divided on three separate PRs. Current PR is the second of three. <!-- 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.* --> CI |
||
|
Ashwin Bharambe
|
e5ca7e6450
|
chore(mypy): add mypy and type stub packages to dev deps (#3930)
## Summary This PR adds mypy and essential type stub packages to dev dependencies as Phase 1 of the mypy suppression removal plan. **Changes:** - Add `mypy` to dev dependencies - Add type stubs: `types-jsonschema`, `pandas-stubs`, `types-psutil`, `types-tqdm`, `boto3-stubs` **Impact:** - Enables static type checking across the codebase - Eliminates ~30 type checking errors related to missing type information for third-party packages - Provides foundation for subsequent PRs to remove type suppressions **Part of:** Mypy suppression removal plan (Phase 1/4) **Testing:** ```bash uv sync --group dev uv run mypy ``` |
||
Sébastien Han
|
d10bfb5121
|
chore: remove leftover llama_stack directory (#3940)
# What does this PR do? Followup on https://github.com/llamastack/llama-stack/pull/3920 where the llama_stack directory was moved under src. Signed-off-by: Sébastien Han <seb@redhat.com> |
||
|
Sébastien Han
|
b47afac7c2
|
chore: bump openai package version (#3918)
Some checks failed
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 5s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.12) (push) Failing after 2s
Test Llama Stack Build / generate-matrix (push) Successful in 4s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 4s
Test Llama Stack Build / build-single-provider (push) Failing after 4s
Test llama stack list-deps / list-deps-from-config (push) Failing after 5s
Unit Tests / unit-tests (3.12) (push) Failing after 3s
Test llama stack list-deps / show-single-provider (push) Failing after 10s
Test External API and Providers / test-external (venv) (push) Failing after 10s
Python Package Build Test / build (3.13) (push) Failing after 24s
Test llama stack list-deps / generate-matrix (push) Successful in 26s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 28s
Unit Tests / unit-tests (3.13) (push) Failing after 25s
Vector IO Integration Tests / test-matrix (push) Failing after 32s
Test llama stack list-deps / list-deps (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 39s
Test Llama Stack Build / build (push) Failing after 33s
UI Tests / ui-tests (22) (push) Successful in 1m25s
Pre-commit / pre-commit (push) Successful in 3m49s
# What does this PR do? To match https://github.com/llamastack/llama-stack/pull/3847 We must not update the lock manually, but always reflect the update in the pyproject.toml. The lock is a state at build time. Signed-off-by: Sébastien Han <seb@redhat.com> |
||
|
Ashwin Bharambe
|
4e6c769cc4
|
fix(context): prevent provider data leak between streaming requests (#3924)
## Summary - `preserve_contexts_async_generator` left `PROVIDER_DATA_VAR` (and other context vars) populated after a streaming generator completed on HEAD~1, so the asyncio context for request N+1 started with request N's provider payload. - FastAPI dependencies and middleware execute before `request_provider_data_context` rebinds the header data, meaning auth/logging hooks could observe a prior tenant's credentials or treat them as authenticated. Traces and any background work that inspects the context outside the `with` block leak as well—this is a real security regression, not just a CLI artifact. - The wrapper now restores each tracked `ContextVar` to the value it held before the iteration (falling back to clearing when necessary) after every yield and when the generator terminates, so provider data is wiped while callers that set their own defaults keep them. ## Test Plan - `uv run pytest tests/unit/core/test_provider_data_context.py -q` - `uv run pytest tests/unit/distribution/test_context.py -q` Both suites fail on HEAD~1 and pass with this change. |
||
|
ehhuang
|
c077d01ddf
|
chore(telemetry): more cleanup: remove apis.telemetry (#3919)
# What does this PR do? ## Test Plan CI |
||
|
ehhuang
|
1c9a31d8bd
|
chore(telemetry): add grafana dashboards (#3921)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Installer CI / lint (push) Failing after 3s
Installer CI / smoke-test-on-dev (push) Failing after 4s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Test Llama Stack Build / generate-matrix (push) Successful in 3s
Python Package Build Test / build (3.12) (push) Failing after 1s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 4s
Test llama stack list-deps / generate-matrix (push) Successful in 2s
Python Package Build Test / build (3.13) (push) Failing after 2s
Vector IO Integration Tests / test-matrix (push) Failing after 7s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 5s
Test llama stack list-deps / show-single-provider (push) Failing after 5s
Test External API and Providers / test-external (venv) (push) Failing after 5s
Unit Tests / unit-tests (3.13) (push) Failing after 5s
Test llama stack list-deps / list-deps (push) Failing after 8s
Unit Tests / unit-tests (3.12) (push) Failing after 10s
API Conformance Tests / check-schema-compatibility (push) Successful in 47s
Test Llama Stack Build / build (push) Failing after 41s
Test Llama Stack Build / build-single-provider (push) Failing after 48s
Test llama stack list-deps / list-deps-from-config (push) Failing after 45s
UI Tests / ui-tests (22) (push) Successful in 1m18s
Pre-commit / pre-commit (push) Successful in 1m48s
# What does this PR do? - add a dashboard in grafana (vibe-coded) ## Test Plan <img width="2416" height="1114" alt="image" src="https://github.com/user-attachments/assets/8927aad2-cc14-4a1d-847e-350522cac02f" /> |
||
|
ehhuang
|
b7dd3f5c56
|
chore!: BREAKING CHANGE: vector_db_id -> vector_store_id (#3923)
# What does this PR do? ## Test Plan CI vector_io tests will fail until next client sync passed with https://github.com/llamastack/llama-stack-client-python/pull/286 checked out locally |
||
|
Nathan Weinberg
|
b6954c9882
|
fix: add missing shutdown methods to PromptServiceImpl and ConversationServiceImpl (#3925)
Change is visible in server shutdown logs, changes `WARNING` loglines to `INFO` Signed-off-by: Nathan Weinberg <nweinber@redhat.com> |
||
Matthew Farrellee
|
a9b00db421
|
feat: add provider data keys for Cerebras, Databricks, NVIDIA, and RunPod (#3734)
# What does this PR do? add provider-data key passing support to Cerebras, Databricks, NVIDIA and RunPod also, added missing tests for Fireworks, Anthropic, Gemini, SambaNova, and vLLM addresses #3517 ## Test Plan ci w/ new tests --------- Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com> |
||
|
Ashwin Bharambe
|
471b1b248b
|
chore(package): migrate to src/ layout (#3920)
Migrates package structure to src/ layout following Python packaging best practices. All code moved from `llama_stack/` to `src/llama_stack/`. Public API unchanged - imports remain `import llama_stack.*`. Updated build configs, pre-commit hooks, scripts, and GitHub workflows accordingly. All hooks pass, package builds cleanly. **Developer note**: Reinstall after pulling: `pip install -e .` |
||
|
IAN MILLER
|
98a5047f9d
|
feat(prompts): attach prompts to storage stores in run configs (#3893)
# What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> This PR is responsible for attaching prompts to storage stores in run configs. It allows to specify prompts as stores in different distributions. The need of this functionality was initiated in #3514 > Note, #3514 is divided on three separate PRs. Current PR is the first of three. <!-- 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.* --> Manual testing and updated CI unit tests Prerequisites: 1. `uv run --with llama-stack llama stack list-deps starter | xargs -L1 uv pip install` 2. `llama stack run starter ` ``` INFO 2025-10-23 15:36:17,387 llama_stack.cli.stack.run:100 cli: Using run configuration: /Users/ianmiller/llama-stack/llama_stack/distributions/starter/run.yaml INFO 2025-10-23 15:36:17,423 llama_stack.cli.stack.run:157 cli: HTTPS enabled with certificates: Key: None Cert: None INFO 2025-10-23 15:36:17,424 llama_stack.cli.stack.run:159 cli: Listening on ['::', '0.0.0.0']:8321 INFO 2025-10-23 15:36:17,749 llama_stack.core.server.server:521 core::server: Run configuration: INFO 2025-10-23 15:36:17,756 llama_stack.core.server.server:524 core::server: apis: - agents - batches - datasetio - eval - files - inference - post_training - safety - scoring - tool_runtime - vector_io image_name: starter providers: agents: - config: persistence: agent_state: backend: kv_default namespace: agents responses: backend: sql_default max_write_queue_size: 10000 num_writers: 4 table_name: responses provider_id: meta-reference provider_type: inline::meta-reference batches: - config: kvstore: backend: kv_default namespace: batches provider_id: reference provider_type: inline::reference datasetio: - config: kvstore: backend: kv_default namespace: datasetio::huggingface provider_id: huggingface provider_type: remote::huggingface - config: kvstore: backend: kv_default namespace: datasetio::localfs provider_id: localfs provider_type: inline::localfs eval: - config: kvstore: backend: kv_default namespace: eval provider_id: meta-reference provider_type: inline::meta-reference files: - config: metadata_store: backend: sql_default table_name: files_metadata storage_dir: /Users/ianmiller/.llama/distributions/starter/files provider_id: meta-reference-files provider_type: inline::localfs inference: - config: api_key: '********' url: https://api.fireworks.ai/inference/v1 provider_id: fireworks provider_type: remote::fireworks - config: api_key: '********' url: https://api.together.xyz/v1 provider_id: together provider_type: remote::together - config: {} provider_id: bedrock provider_type: remote::bedrock - config: api_key: '********' base_url: https://api.openai.com/v1 provider_id: openai provider_type: remote::openai - config: api_key: '********' provider_id: anthropic provider_type: remote::anthropic - config: api_key: '********' provider_id: gemini provider_type: remote::gemini - config: api_key: '********' url: https://api.groq.com provider_id: groq provider_type: remote::groq - config: api_key: '********' url: https://api.sambanova.ai/v1 provider_id: sambanova provider_type: remote::sambanova - config: {} provider_id: sentence-transformers provider_type: inline::sentence-transformers post_training: - config: checkpoint_format: meta provider_id: torchtune-cpu provider_type: inline::torchtune-cpu safety: - config: excluded_categories: [] provider_id: llama-guard provider_type: inline::llama-guard - config: {} provider_id: code-scanner provider_type: inline::code-scanner scoring: - config: {} provider_id: basic provider_type: inline::basic - config: {} provider_id: llm-as-judge provider_type: inline::llm-as-judge - config: openai_api_key: '********' provider_id: braintrust provider_type: inline::braintrust tool_runtime: - config: api_key: '********' max_results: 3 provider_id: brave-search provider_type: remote::brave-search - config: api_key: '********' max_results: 3 provider_id: tavily-search provider_type: remote::tavily-search - config: {} provider_id: rag-runtime provider_type: inline::rag-runtime - config: {} provider_id: model-context-protocol provider_type: remote::model-context-protocol vector_io: - config: persistence: backend: kv_default namespace: vector_io::faiss provider_id: faiss provider_type: inline::faiss - config: db_path: /Users/ianmiller/.llama/distributions/starter/sqlite_vec.db persistence: backend: kv_default namespace: vector_io::sqlite_vec provider_id: sqlite-vec provider_type: inline::sqlite-vec registered_resources: benchmarks: [] datasets: [] models: [] scoring_fns: [] shields: [] tool_groups: - provider_id: tavily-search toolgroup_id: builtin::websearch - provider_id: rag-runtime toolgroup_id: builtin::rag vector_stores: [] server: port: 8321 storage: backends: kv_default: db_path: /Users/ianmiller/.llama/distributions/starter/kvstore.db type: kv_sqlite sql_default: db_path: /Users/ianmiller/.llama/distributions/starter/sql_store.db type: sql_sqlite stores: conversations: backend: sql_default table_name: openai_conversations inference: backend: sql_default max_write_queue_size: 10000 num_writers: 4 table_name: inference_store metadata: backend: kv_default namespace: registry prompts: backend: kv_default namespace: prompts telemetry: enabled: true vector_stores: default_embedding_model: model_id: nomic-ai/nomic-embed-text-v1.5 provider_id: sentence-transformers default_provider_id: faiss version: 2 INFO 2025-10-23 15:36:20,032 llama_stack.providers.utils.inference.inference_store:74 inference: Write queue disabled for SQLite to avoid concurrency issues WARNING 2025-10-23 15:36:20,422 llama_stack.providers.inline.telemetry.meta_reference.telemetry:84 telemetry: OTEL_EXPORTER_OTLP_ENDPOINT is not set, skipping telemetry INFO 2025-10-23 15:36:22,379 llama_stack.providers.utils.inference.openai_mixin:436 providers::utils: OpenAIInferenceAdapter.list_provider_model_ids() returned 105 models INFO 2025-10-23 15:36:22,703 uvicorn.error:84 uncategorized: Started server process [17328] INFO 2025-10-23 15:36:22,704 uvicorn.error:48 uncategorized: Waiting for application startup. INFO 2025-10-23 15:36:22,706 llama_stack.core.server.server:179 core::server: Starting up Llama Stack server (version: 0.3.0) INFO 2025-10-23 15:36:22,707 llama_stack.core.stack:470 core: starting registry refresh task INFO 2025-10-23 15:36:22,708 uvicorn.error:62 uncategorized: Application startup complete. INFO 2025-10-23 15:36:22,708 uvicorn.error:216 uncategorized: Uvicorn running on http://['::', '0.0.0.0']:8321 (Press CTRL+C to quit) ``` As you can see, prompts are attached to stores in config Testing: 1. Create prompt: ``` curl -X POST http://localhost:8321/v1/prompts \ -H "Content-Type: application/json" \ -d '{ "prompt": "Hello {{name}}! You are working at {{company}}. Your role is {{role}} at {{company}}. Remember, {{name}}, to be {{tone}}.", "variables": ["name", "company", "role", "tone"] }' ``` `{"prompt":"Hello {{name}}! You are working at {{company}}. Your role is {{role}} at {{company}}. Remember, {{name}}, to be {{tone}}.","version":1,"prompt_id":"pmpt_a90e09e67acfe23776f2778c603eb6c17e139dab5f6e163f","variables":["name","company","role","tone"],"is_default":false}% ` 2. Get prompt: `curl -X GET http://localhost:8321/v1/prompts/pmpt_a90e09e67acfe23776f2778c603eb6c17e139dab5f6e163f` `{"prompt":"Hello {{name}}! You are working at {{company}}. Your role is {{role}} at {{company}}. Remember, {{name}}, to be {{tone}}.","version":1,"prompt_id":"pmpt_a90e09e67acfe23776f2778c603eb6c17e139dab5f6e163f","variables":["name","company","role","tone"],"is_default":false}% ` 3. Query sqlite KV storage to check created prompt: ``` sqlite> .mode column sqlite> .headers on sqlite> SELECT * FROM kvstore WHERE key LIKE 'prompts:v1:%'; key value expiration ------------------------------------------------------------ ------------------------------------------------------------ ---------- prompts:v1:pmpt_a90e09e67acfe23776f2778c603eb6c17e139dab5f6e {"prompt_id": "pmpt_a90e09e67acfe23776f2778c603eb6c17e139dab 163f:1 5f6e163f", "prompt": "Hello {{name}}! You are working at {{c ompany}}. Your role is {{role}} at {{company}}. Remember, {{ name}}, to be {{tone}}.", "version": 1, "variables": ["name" , "company", "role", "tone"], "is_default": false} prompts:v1:pmpt_a90e09e67acfe23776f2778c603eb6c17e139dab5f6e 1 163f:default sqlite> ``` |
||
Luis Tomas Bolivar
|
63422e5b36
|
fix!: Enhance response API support to not fail with tool calling (#3385)
Some checks failed
Python Package Build Test / build (3.12) (push) Failing after 8s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 5s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 6s
Python Package Build Test / build (3.13) (push) Failing after 6s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 10s
Unit Tests / unit-tests (3.13) (push) Failing after 14s
Unit Tests / unit-tests (3.12) (push) Failing after 19s
Test External API and Providers / test-external (venv) (push) Failing after 1m3s
Vector IO Integration Tests / test-matrix (push) Failing after 1m6s
API Conformance Tests / check-schema-compatibility (push) Successful in 1m17s
UI Tests / ui-tests (22) (push) Successful in 1m18s
Pre-commit / pre-commit (push) Successful in 3m5s
# What does this PR do? Introduces two main fixes to enhance the stability of Responses API when dealing with tool calling responses and structured outputs. ### Changes Made 1. It added OpenAIResponseOutputMessageMCPCall and ListTools to OpenAIResponseInput but https://github.com/llamastack/llama-stack/pull/3810 got merge that did the same in a different way. Still this PR does it in a way that keep the sync between OpenAIResponsesOutput and the allowed objects in OpenAIResponseInput. 2. Add protection in case self.ctx.response_format does not have type attribute BREAKING CHANGE: OpenAIResponseInput now uses OpenAIResponseOutput union type. This is semantically equivalent - all previously accepted types are still supported via the OpenAIResponseOutput union. This improves type consistency and maintainability. |
||
|
Luis Tomas Bolivar
|
f18b5eb537
|
fix: Avoid BadRequestError due to invalid max_tokens (#3667)
This patch ensures if max tokens is not defined, then is set to None instead of 0 when calling openai_chat_completion. This way some providers (like gemini) that cannot handle the `max_tokens = 0` will not fail Issue: #3666 |
||
|
Derek Higgins
|
00d8414597
|
fix(tests): limit vector store providers for record mode in CI tests (#3898)
The vector_provider_wrapper was only limiting providers to faiss/sqlite-vec for replay mode, but CI tests also run in record mode with the same limited set of providers. This caused test failures when trying to test against milvus, chromadb, pgvector, weaviate, and qdrant which aren't configured in the record job. |
||
|
Sébastien Han
|
7c0e43424d
|
chore: remove duplicate provider definition (#3917)
# What does this PR do? Files was present twice. Signed-off-by: Sébastien Han <seb@redhat.com> |
||
dependabot[bot]
|
9c223d8593
|
chore(github-deps): bump actions/upload-artifact from 4.6.2 to 5.0.0 (#3905)
Bumps [actions/upload-artifact](https://github.com/actions/upload-artifact) from 4.6.2 to 5.0.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/actions/upload-artifact/releases">actions/upload-artifact's releases</a>.</em></p> <blockquote> <h2>v5.0.0</h2> <h2>What's Changed</h2> <p><strong>BREAKING CHANGE:</strong> this update supports Node <code>v24.x</code>. This is not a breaking change per-se but we're treating it as such.</p> <ul> <li>Update README.md by <a href="https://github.com/GhadimiR"><code>@GhadimiR</code></a> in <a href="https://redirect.github.com/actions/upload-artifact/pull/681">actions/upload-artifact#681</a></li> <li>Update README.md by <a href="https://github.com/nebuk89"><code>@nebuk89</code></a> in <a href="https://redirect.github.com/actions/upload-artifact/pull/712">actions/upload-artifact#712</a></li> <li>Readme: spell out the first use of GHES by <a href="https://github.com/danwkennedy"><code>@danwkennedy</code></a> in <a href="https://redirect.github.com/actions/upload-artifact/pull/727">actions/upload-artifact#727</a></li> <li>Update GHES guidance to include reference to Node 20 version by <a href="https://github.com/patrikpolyak"><code>@patrikpolyak</code></a> in <a href="https://redirect.github.com/actions/upload-artifact/pull/725">actions/upload-artifact#725</a></li> <li>Bump <code>@actions/artifact</code> to <code>v4.0.0</code></li> <li>Prepare <code>v5.0.0</code> by <a href="https://github.com/danwkennedy"><code>@danwkennedy</code></a> in <a href="https://redirect.github.com/actions/upload-artifact/pull/734">actions/upload-artifact#734</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/GhadimiR"><code>@GhadimiR</code></a> made their first contribution in <a href="https://redirect.github.com/actions/upload-artifact/pull/681">actions/upload-artifact#681</a></li> <li><a href="https://github.com/nebuk89"><code>@nebuk89</code></a> made their first contribution in <a href="https://redirect.github.com/actions/upload-artifact/pull/712">actions/upload-artifact#712</a></li> <li><a href="https://github.com/danwkennedy"><code>@danwkennedy</code></a> made their first contribution in <a href="https://redirect.github.com/actions/upload-artifact/pull/727">actions/upload-artifact#727</a></li> <li><a href="https://github.com/patrikpolyak"><code>@patrikpolyak</code></a> made their first contribution in <a href="https://redirect.github.com/actions/upload-artifact/pull/725">actions/upload-artifact#725</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/upload-artifact/compare/v4...v5.0.0">https://github.com/actions/upload-artifact/compare/v4...v5.0.0</a></p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
8ad9dd7d60
|
chore(github-deps): bump astral-sh/setup-uv from 7.1.0 to 7.1.1 (#3906)
Bumps [astral-sh/setup-uv](https://github.com/astral-sh/setup-uv) from 7.1.0 to 7.1.1. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/astral-sh/setup-uv/releases">astral-sh/setup-uv's releases</a>.</em></p> <blockquote> <h2>v7.1.1 🌈 Fix empty workdir detection and lowest resolution strategy</h2> <h2>Changes</h2> <p>This release fixes a bug where the <code>working-directory</code> input was not used to detect an empty work dir. It also fixes the <code>lowest</code> resolution strategy resolving to latest when only a lower bound was specified.</p> <p>Special thanks to <a href="https://github.com/tpgillam"><code>@tpgillam</code></a> for the first contribution!</p> <h2>🐛 Bug fixes</h2> <ul> <li>Fix "lowest" resolution strategy with lower-bound only <a href="https://github.com/tpgillam"><code>@tpgillam</code></a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/649">#649</a>)</li> <li>Use working-directory to detect empty workdir <a href="https://github.com/eifinger"><code>@eifinger</code></a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/645">#645</a>)</li> </ul> <h2>🧰 Maintenance</h2> <ul> <li>chore: update known checksums for 0.9.4 @<a href="https://github.com/apps/github-actions">github-actions[bot]</a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/651">#651</a>)</li> <li>chore: update known checksums for 0.9.3 @<a href="https://github.com/apps/github-actions">github-actions[bot]</a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/644">#644</a>)</li> </ul> <h2>📚 Documentation</h2> <ul> <li>Change version in docs to v7 <a href="https://github.com/eifinger"><code>@eifinger</code></a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/647">#647</a>)</li> </ul> <h2>⬆️ Dependency updates</h2> <ul> <li>Bump github/codeql-action from 4.30.7 to 4.30.8 @<a href="https://github.com/apps/dependabot">dependabot[bot]</a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/639">#639</a>)</li> <li>Bump actions/setup-node from 5.0.0 to 6.0.0 @<a href="https://github.com/apps/dependabot">dependabot[bot]</a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/641">#641</a>)</li> <li>Bump eifinger/actionlint-action from 1.9.1 to 1.9.2 @<a href="https://github.com/apps/dependabot">dependabot[bot]</a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/634">#634</a>)</li> <li>Update lockfile with latest npm <a href="https://github.com/eifinger"><code>@eifinger</code></a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/636">#636</a>)</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
9d6e589120
|
chore(ui-deps): bump @types/node from 24.8.1 to 24.9.1 in /llama_stack/ui (#3912)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Python Package Build Test / build (3.13) (push) Failing after 2s
Python Package Build Test / build (3.12) (push) Failing after 4s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 6s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 6s
Vector IO Integration Tests / test-matrix (push) Failing after 7s
Test External API and Providers / test-external (venv) (push) Failing after 5s
Unit Tests / unit-tests (3.13) (push) Failing after 5s
Unit Tests / unit-tests (3.12) (push) Failing after 6s
API Conformance Tests / check-schema-compatibility (push) Successful in 13s
UI Tests / ui-tests (22) (push) Successful in 47s
Pre-commit / pre-commit (push) Successful in 1m43s
Bumps [@types/node](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/node) from 24.8.1 to 24.9.1. <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/node">compare view</a></li> </ul> </details> <br /> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
dependabot[bot]
|
948951cc5c
|
chore(ui-deps): bump @tailwindcss/postcss from 4.1.14 to 4.1.16 in /llama_stack/ui (#3913)
Bumps [@tailwindcss/postcss](https://github.com/tailwindlabs/tailwindcss/tree/HEAD/packages/@tailwindcss-postcss) from 4.1.14 to 4.1.16. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/tailwindlabs/tailwindcss/releases"><code>@tailwindcss/postcss</code>'s releases</a>.</em></p> <blockquote> <h2>v4.1.16</h2> <h3>Fixed</h3> <ul> <li>Discard candidates with an empty data type (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19172">#19172</a>)</li> <li>Fix canonicalization of arbitrary variants with attribute selectors (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19176">#19176</a>)</li> <li>Fix invalid colors due to nested <code>&</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19184">#19184</a>)</li> <li>Improve canonicalization for <code>& > :pseudo</code> and <code>& :pseudo</code> arbitrary variants (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19178">#19178</a>)</li> </ul> <h2>v4.1.15</h2> <h3>Fixed</h3> <ul> <li>Fix Safari devtools rendering issue due to <code>color-mix</code> fallback (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19069">#19069</a>)</li> <li>Suppress Lightning CSS warnings about <code>:deep</code>, <code>:slotted</code>, and <code>:global</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19094">#19094</a>)</li> <li>Fix resolving theme keys when starting with the name of another theme key in JS configs and plugins (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19097">#19097</a>)</li> <li>Allow named groups in combination with <code>not-*</code>, <code>has-*</code>, and <code>in-*</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19100">#19100</a>)</li> <li>Prevent important utilities from affecting other utilities (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19110">#19110</a>)</li> <li>Don’t index into strings with the <code>theme(…)</code> function (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19111">#19111</a>)</li> <li>Fix parsing issue when <code>\t</code> is used in at-rules (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19130">#19130</a>)</li> <li>Upgrade: Canonicalize utilities containing <code>0</code> values (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19095">#19095</a>)</li> <li>Upgrade: Migrate deprecated <code>break-words</code> to <code>wrap-break-word</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19157">#19157</a>)</li> </ul> <h3>Changed</h3> <ul> <li>Remove the <code>postinstall</code> script from oxide (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19149">#19149</a>)</li> </ul> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/tailwindlabs/tailwindcss/blob/main/CHANGELOG.md"><code>@tailwindcss/postcss</code>'s changelog</a>.</em></p> <blockquote> <h2>[4.1.16] - 2025-10-23</h2> <h3>Fixed</h3> <ul> <li>Discard candidates with an empty data type (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19172">#19172</a>)</li> <li>Fix canonicalization of arbitrary variants with attribute selectors (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19176">#19176</a>)</li> <li>Fix invalid colors due to nested <code>&</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19184">#19184</a>)</li> <li>Improve canonicalization for <code>& > :pseudo</code> and <code>& :pseudo</code> arbitrary variants (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19178">#19178</a>)</li> </ul> <h2>[4.1.15] - 2025-10-20</h2> <h3>Fixed</h3> <ul> <li>Fix Safari devtools rendering issue due to <code>color-mix</code> fallback (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19069">#19069</a>)</li> <li>Suppress Lightning CSS warnings about <code>:deep</code>, <code>:slotted</code>, and <code>:global</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19094">#19094</a>)</li> <li>Fix resolving theme keys when starting with the name of another theme key in JS configs and plugins (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19097">#19097</a>)</li> <li>Allow named groups in combination with <code>not-*</code>, <code>has-*</code>, and <code>in-*</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19100">#19100</a>)</li> <li>Prevent important utilities from affecting other utilities (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19110">#19110</a>)</li> <li>Don’t index into strings with the <code>theme(…)</code> function (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19111">#19111</a>)</li> <li>Fix parsing issue when <code>\t</code> is used in at-rules (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19130">#19130</a>)</li> <li>Upgrade: Canonicalize utilities containing <code>0</code> values (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19095">#19095</a>)</li> <li>Upgrade: Migrate deprecated <code>break-words</code> to <code>wrap-break-word</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19157">#19157</a>)</li> </ul> <h3>Changed</h3> <ul> <li>Remove the <code>postinstall</code> script from oxide (<a href="https://github.com/tailwindlabs/tailwindcss/tree/HEAD/packages/@tailwindcss-postcss/issues/19149">#19149</a>)(<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19149">tailwindlabs/tailwindcss#19149</a>)</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
00bfda4eff
|
chore(ui-deps): bump @types/react-dom from 19.2.1 to 19.2.2 in /llama_stack/ui (#3915)
Bumps [@types/react-dom](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/react-dom) from 19.2.1 to 19.2.2. <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/DefinitelyTyped/DefinitelyTyped/commits/HEAD/types/react-dom">compare view</a></li> </ul> </details> <br /> [](https://docs.github.com/en/github/managing-security-vulnerabilities/about-dependabot-security-updates#about-compatibility-scores) Dependabot will resolve any conflicts with this PR as long as you don't alter it yourself. You can also trigger a rebase manually by commenting `@dependabot rebase`. [//]: # (dependabot-automerge-start) [//]: # (dependabot-automerge-end) --- <details> <summary>Dependabot commands and options</summary> <br /> You can trigger Dependabot actions by commenting on this PR: - `@dependabot rebase` will rebase this PR - `@dependabot recreate` will recreate this PR, overwriting any edits that have been made to it - `@dependabot merge` will merge this PR after your CI passes on it - `@dependabot squash and merge` will squash and merge this PR after your CI passes on it - `@dependabot cancel merge` will cancel a previously requested merge and block automerging - `@dependabot reopen` will reopen this PR if it is closed - `@dependabot close` will close this PR and stop Dependabot recreating it. You can achieve the same result by closing it manually - `@dependabot show <dependency name> ignore conditions` will show all of the ignore conditions of the specified dependency - `@dependabot ignore this major version` will close this PR and stop Dependabot creating any more for this major version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this minor version` will close this PR and stop Dependabot creating any more for this minor version (unless you reopen the PR or upgrade to it yourself) - `@dependabot ignore this dependency` will close this PR and stop Dependabot creating any more for this dependency (unless you reopen the PR or upgrade to it yourself) </details> Signed-off-by: dependabot[bot] <support@github.com> Co-authored-by: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com> |
||
|
dependabot[bot]
|
68e5a66ca9
|
chore(ui-deps): bump @testing-library/jest-dom from 6.8.0 to 6.9.1 in /llama_stack/ui (#3914)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.12) (push) Failing after 1s
Python Package Build Test / build (3.13) (push) Failing after 1s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Vector IO Integration Tests / test-matrix (push) Failing after 4s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Unit Tests / unit-tests (3.12) (push) Failing after 3s
Unit Tests / unit-tests (3.13) (push) Failing after 3s
API Conformance Tests / check-schema-compatibility (push) Successful in 12s
UI Tests / ui-tests (22) (push) Successful in 40s
Pre-commit / pre-commit (push) Successful in 1m33s
Bumps [@testing-library/jest-dom](https://github.com/testing-library/jest-dom) from 6.8.0 to 6.9.1. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/testing-library/jest-dom/releases"><code>@testing-library/jest-dom</code>'s releases</a>.</em></p> <blockquote> <h2>v6.9.1</h2> <h2><a href="https://github.com/testing-library/jest-dom/compare/v6.9.0...v6.9.1">6.9.1</a> (2025-10-01)</h2> <h3>Bug Fixes</h3> <ul> <li>Fix undefined <code>Node</code> error (nodejs) (<a href="https://redirect.github.com/testing-library/jest-dom/issues/707">#707</a>) (<a href=" |
||
|
ehhuang
|
509676641a
|
chore: update run configs (#3902)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Python Package Build Test / build (3.12) (push) Failing after 0s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Python Package Build Test / build (3.13) (push) Failing after 1s
Test External API and Providers / test-external (venv) (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 12s
UI Tests / ui-tests (22) (push) Successful in 39s
Pre-commit / pre-commit (push) Successful in 1m34s
Vector IO Integration Tests / test-matrix (push) Failing after 5s
Unit Tests / unit-tests (3.12) (push) Failing after 3s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
# What does this PR do? telemetry was deprecated ## Test Plan |
||
|
ehhuang
|
2a1a813308
|
chore: update docs for telemetry api removal (#3900)
# What does this PR do? Telemetry is no longer an API/provider. ## Test Plan |
||
Francisco Arceo
|
4566eebe05
|
feat: Add static file import system for docs (#3882)
# What does this PR do? Add static file import system for docs - Use `remark-code-import` plugin to embed code at build time - Support importing Python code with syntax highlighting using `raw-loader` + `ReactMarkdown` One caveat is that currently when embedding markdown with code used the syntax highlighting isn't behaving but I'll investigate that in a follow up. ## Test Plan Python Example: <img width="1372" height="995" alt="Screenshot 2025-10-23 at 9 22 18 PM" src="https://github.com/user-attachments/assets/656d2c78-4d9b-45a4-bd5e-3f8490352b85" /> Markdown example: <img width="1496" height="1070" alt="Screenshot 2025-10-23 at 9 22 38 PM" src="https://github.com/user-attachments/assets/6c0a07ec-ff7c-45aa-b05f-8c46acd4445c" /> --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> |
||
|
ehhuang
|
8265d4efc8
|
chore(telemetry): code cleanup (#3897)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Python Package Build Test / build (3.12) (push) Failing after 2s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 4s
Python Package Build Test / build (3.13) (push) Failing after 3s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (push) Failing after 6s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 14s
UI Tests / ui-tests (22) (push) Successful in 43s
Pre-commit / pre-commit (push) Successful in 1m35s
# What does this PR do? Clean up telemetry code since the telemetry API has been remove. - moved telemetry files out of providers to core - removed from Api ## Test Plan ❯ OTEL_SERVICE_NAME=llama_stack OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 uv run llama stack run starter ❯ curl http://localhost:8321/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "openai/gpt-4o-mini", "messages": [ { "role": "user", "content": "Hello!" } ] }' -> verify traces in Grafana CI |
||
|
ehhuang
|
9916cb3b17
|
chore: support default model in moderations API (#3890)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Vector IO Integration Tests / test-matrix (push) Failing after 5s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 5s
Python Package Build Test / build (3.12) (push) Failing after 1s
Python Package Build Test / build (3.13) (push) Failing after 2s
Test Llama Stack Build / build-single-provider (push) Failing after 3s
Test Llama Stack Build / generate-matrix (push) Successful in 5s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 4s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 7s
Test External API and Providers / test-external (venv) (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 12s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Test Llama Stack Build / build (push) Failing after 3s
Unit Tests / unit-tests (3.12) (push) Failing after 5s
UI Tests / ui-tests (22) (push) Successful in 41s
Pre-commit / pre-commit (push) Successful in 1m33s
# What does this PR do? https://platform.openai.com/docs/api-reference/moderations supports optional model parameter. This PR adds support for using moderations API with model=None if a default shield id is provided via safety config. ## Test Plan added tests manual test: ``` > SAFETY_MODEL='together/meta-llama/Llama-Guard-4-12B' uv run llama stack run starter > curl http://localhost:8321/v1/moderations \ -H "Content-Type: application/json" \ -d '{ "input": [ "hello" ] }' ``` |
||
|
ehhuang
|
d12e5f0999
|
chore(telemetry): add an arguement to select conatiner runtime explicitly (#3896)
# What does this PR do? ## Test Plan ❯ ./scripts/telemetry/setup_telemetry.sh --container docker |
||
|
Ashwin Bharambe
|
658fb2c777 |
refactor(k8s): update run configs to v2 storage and registered_resources structure
Some checks failed
Python Package Build Test / build (3.13) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 1s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
Test Llama Stack Build / generate-matrix (push) Successful in 3s
Test Llama Stack Build / build-single-provider (push) Failing after 3s
Python Package Build Test / build (3.12) (push) Failing after 3s
Vector IO Integration Tests / test-matrix (push) Failing after 5s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 4s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 4s
Test Llama Stack Build / build (push) Failing after 3s
Unit Tests / unit-tests (3.13) (push) Failing after 3s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Unit Tests / unit-tests (3.12) (push) Failing after 5s
API Conformance Tests / check-schema-compatibility (push) Successful in 12s
UI Tests / ui-tests (22) (push) Successful in 42s
Pre-commit / pre-commit (push) Successful in 1m30s
Migrates k8s run configs to match the updated run configs - Replace storage.references with storage.stores - Wrap resources under registered_resources section - Update provider configs to use persistence with namespace/backend - Add telemetry and vector_stores top-level sections - Simplify agent/files metadata store configuration |
||
|
Ashwin Bharambe
|
0e57233a0a
|
chore(misc): update datasets, benchmarks to use alpha, beta prefixes (#3891)
This will be landed together with https://github.com/llamastack/llama-stack-client-python/pull/282 (hence CI will be red on this one.) I have verified locally that tests pass with the updated version of the client-sdk. |
||
|
Ashwin Bharambe
|
7918188f1e
|
fix(ci): enable responses tests in CI; suppress expected MCP auth error logs (#3889)
Let us enable responses suite in CI now. Also a minor fix: MCP tool tests intentionally trigger authentication failures to verify error handling, but the resulting error logs clutter test output. |
||
|
Ashwin Bharambe
|
7b90e0e9c8
|
test: suppress expected error logs in SSE test (#3886)
Our unit test outputs are filled with all kinds of obscene logs. This makes it really hard to spot real issues quickly. The problem is that these logs are necessary to output at the given logging level when the server is operating normally. It's just that we don't want to see some of them (especially the noisy ones) during tests. This PR begins the cleanup. We pytest's caplog fixture to for suppression. |
||
|
ehhuang
|
f8eaa40580
|
chore: better error messages for moderations API (#3887)
# What does this PR do? ## Test Plan ``` ~/projects/lst3 remotes/origin/HEAD* .venv ❯ curl http://localhost:8321/v1/moderations \ -H "Content-Type: application/json" \ -d '{ "model": "gpt-4o-mini", "input": [ "hello" ] }' {"detail":"Invalid value: No shield associated with provider_resource id gpt-4o-mini: choose from ['together/meta-llama/Llama-Guard-4-12B']"} ``` |
||
|
Ashwin Bharambe
|
30ba8c8655
|
fix(responses): sync conversation before yielding terminal events in streaming (#3888)
Move conversation sync logic before yield to ensure it executes even when streaming consumers break early after receiving response.completed event. ## Test Plan ``` OLLAMA_URL=http://localhost:11434 \ pytest -sv tests/integration/responses/ \ --stack-config server:ci-tests \ --text-model ollama/llama3.2:3b-instruct-fp16 \ --inference-mode live \ -k conversation_multi ``` This test now passes. |
||
|
Ashwin Bharambe
|
cb2185b936
|
fix(logging): ensure logs go to stderr, loggers obey levels (#3885)
Important fix to the logging system |