mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-10-04 12:07:34 +00:00
2785 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Francisco Arceo
|
a6b1588dc6
|
revert: Fireworks chat completion broken due to telemetry (#3402)
Reverts llamastack/llama-stack#3392 |
||
ehhuang
|
f6bf36343d
|
chore: logging perf improvments (#3393)
# What does this PR do? - Use BackgroundLogger when logging metric events. - Reuse event loop in BackgroundLogger ## Test Plan ``` cd /docs/source/distributions/k8s-benchmark # start mock server python openai-mock-server.py --port 8000 # start stack server LLAMA_STACK_LOGGING="all=WARNING" uv run --with llama-stack python -m llama_stack.core.server.server docs/source/distributions/k8s-benchmark/stack_run_config.yaml # run benchmark script uv run python3 benchmark.py --duration 120 --concurrent 50 --base-url=http://localhost:8321/v1/openai/v1 --model=vllm-inference/meta-llama/Llama-3.2-3B-Instruct ``` ### RPS from 57 -> 62 |
||
slekkala1
|
935b8e28de
|
fix: Fireworks chat completion broken due to telemetry (#3392)
# What does this PR do? Fix fireworks chat completion broken due to telemetry expecting response.usage Closes https://github.com/llamastack/llama-stack/issues/3391 ## Test Plan 1. `uv run --with llama-stack llama stack build --distro starter --image-type venv --run` Try ``` curl -X POST http://0.0.0.0:8321/v1/openai/v1/chat/completions \ -H "Content-Type: application/json" \ -d '{ "model": "fireworks/accounts/fireworks/models/llama-v3p1-8b-instruct", "messages": [{"role": "user", "content": "Hello!"}] }' ``` ``` {"id":"chatcmpl-ee922a08-0df0-4974-b0d3-b322113e8bc0","choices":[{"message":{"role":"assistant","content":"Hello! How can I assist you today?","name":null,"tool_calls":null},"finish_reason":"stop","index":0,"logprobs":null}],"object":"chat.completion","created":1757456375,"model":"fireworks/accounts/fireworks/models/llama-v3p1-8b-instruct"}% ``` Without fix fails as mentioned in https://github.com/llamastack/llama-stack/issues/3391 Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com> |
||
Sébastien Han
|
c86e45496e
|
ci: Re-enable pre-commit to fail (#3399)
Some checks failed
Python Package Build Test / build (3.12) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 1s
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 1s
Vector IO Integration Tests / test-matrix (push) Failing after 5s
API Conformance Tests / check-schema-compatibility (push) Successful in 9s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 5s
UI Tests / ui-tests (22) (push) Successful in 58s
Pre-commit / pre-commit (push) Successful in 1m14s
If pre-commit fails, the workflow must fail. --------- Signed-off-by: Sébastien Han <seb@redhat.com> |
||
Matthew Farrellee
|
0e27016cf2
|
chore: update the vertexai inference impl to use openai-python for openai-compat functions (#3377)
# What does this PR do? update VertexAI inference provider to use openai-python for openai-compat functions ## Test Plan ``` $ VERTEX_AI_PROJECT=... uv run llama stack build --image-type venv --providers inference=remote::vertexai --run ... $ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model vertexai/vertex_ai/gemini-2.5-flash tests/integration/inference/test_openai_completion.py ... ``` i don't have an account to test this. `get_api_key` may also need to be updated per https://cloud.google.com/vertex-ai/generative-ai/docs/start/openai --------- Signed-off-by: Sébastien Han <seb@redhat.com> Co-authored-by: Sébastien Han <seb@redhat.com> |
||
Akram Ben Aissi
|
c836fa29e3
|
fix: pre-commit issues: non executable shebang file and removal of @pytest.mark.asyncio decorator (#3397)
# What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> Fix pre-commit issues: non executable shebang file, @pytest.mark.asyncio decorator <!-- 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.* --> |
||
|
Akram Ben Aissi
|
1671431310
|
fix: Add missing files_api parameter to MemoryToolRuntimeImpl test (#3394)
# What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> The test_query_adds_vector_db_id_to_chunk_metadata test was failing because MemoryToolRuntimeImpl.__init__() now requires a files_api parameter. Fixes failing unit tests for Python 3.12 and 3.13. <!-- 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.* --> |
||
Cesare Pompeiano
|
1c23aeb937
|
feat: Add vector_db_id to chunk metadata (#3304)
# What does this PR do?
When running RAG in a multi vector DB setting, it can be difficult to
trace where retrieved chunks originate from. This PR adds the
`vector_db_id` into each chunk’s metadata, making it easier to
understand which database a given chunk came from. This is helpful for
debugging and for analyzing retrieval behavior of multiple DBs.
Relevant code:
```python
for vector_db_id, result in zip(vector_db_ids, results):
for chunk, score in zip(result.chunks, result.scores):
if not hasattr(chunk, "metadata") or chunk.metadata is None:
chunk.metadata = {}
chunk.metadata["vector_db_id"] = vector_db_id
chunks.append(chunk)
scores.append(score)
```
## Test Plan
* Ran Llama Stack in debug mode.
* Verified that `vector_db_id` was added to each chunk’s metadata.
* Confirmed that the metadata was printed in the console when using the
RAG tool.
---------
Co-authored-by: are-ces <cpompeia@redhat.com>
Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com>
|
||
Ashwin Bharambe
|
81ad240faa |
fix(k8s): unwedge run.yaml to add files
Some checks failed
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 1s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 3s
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
Vector IO Integration Tests / test-matrix (push) Failing after 4s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 5s
API Conformance Tests / check-schema-compatibility (push) Successful in 7s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Test External API and Providers / test-external (venv) (push) Failing after 5s
Update ReadTheDocs / update-readthedocs (push) Failing after 5s
Unit Tests / unit-tests (3.13) (push) Failing after 6s
UI Tests / ui-tests (22) (push) Successful in 38s
Pre-commit / pre-commit (push) Successful in 1m28s
|
||
|
Matthew Farrellee
|
dd1f946b3e
|
feat: include a default inference store during llama stack build (#3373)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 1s
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
Python Package Build Test / build (3.12) (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 (3.13) (push) Failing after 1s
API Conformance Tests / check-schema-compatibility (push) Successful in 7s
Vector IO Integration Tests / test-matrix (push) Failing after 5s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 3s
Test Llama Stack Build / build-single-provider (push) Failing after 4s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 4s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 3s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Test Llama Stack Build / build (push) Failing after 5s
UI Tests / ui-tests (22) (push) Successful in 43s
Pre-commit / pre-commit (push) Successful in 1m14s
# What does this PR do?
enables completions storage when using `llama stack build --providers` -
- GET /v1/chat/completions
- GET /v1/chat/completions/{id}
todo: llama stack build and distro codegen should use the same code
paths
## Test Plan
ci
|
||
|
ehhuang
|
9d3a234bf3
|
chore: remove unused variable (#3389)
# What does this PR do? ## Test Plan |
||
|
Ashwin Bharambe
|
a8aa815b6a
|
feat(tests): migrate to global "setups" system for test configuration (#3390)
This PR refactors the integration test system to use global "setups"
which provides better separation of concerns:
**suites = what to test, setups = how to configure.**
NOTE: if you naming suggestions, please provide feedback
Changes:
- New `tests/integration/setups.py` with global, reusable configurations
(ollama, vllm, gpt, claude)
- Modified `scripts/integration-tests.sh` options to match with the
underlying pytest options
- Updated documentation to reflect the new global setup system
The main benefit is that setups can be reused across multiple suites
(e.g., use "gpt" with any suite) even though sometimes they could
specifically tailored for a suite (vision <> ollama-vision). It is now
easier to add new configurations without modifying existing suites.
Usage examples:
- `pytest tests/integration --suite=responses --setup=gpt`
- `pytest tests/integration --suite=vision` # auto-selects
"ollama-vision" setup
- `pytest tests/integration --suite=base --setup=vllm`
|
||
github-actions[bot]
|
28696c3f30 |
build: Bump version to 0.2.21
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 3s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4s
Test Llama Stack Build / generate-matrix (push) Successful in 4s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 7s
API Conformance Tests / check-schema-compatibility (push) Successful in 8s
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
Python Package Build Test / build (3.13) (push) Failing after 2s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 8s
Test Llama Stack Build / build-single-provider (push) Failing after 5s
Vector IO Integration Tests / test-matrix (push) Failing after 7s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 6s
Unit Tests / unit-tests (3.12) (push) Failing after 3s
Update ReadTheDocs / update-readthedocs (push) Failing after 2s
Unit Tests / unit-tests (3.13) (push) Failing after 3s
Test Llama Stack Build / build (push) Failing after 4s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 41s
UI Tests / ui-tests (22) (push) Successful in 37s
Test External API and Providers / test-external (venv) (push) Failing after 41s
Pre-commit / pre-commit (push) Successful in 2m0s
|
||
|
Ashwin Bharambe
|
30468d0c43
|
fix(deps): bump datasets versions for all providers (#3382)
Not doing so results in errors of the kind you see in:
|
||
|
slekkala1
|
c9268a7a8c
|
fix: pre-commit failing (#3381)
# What does this PR do? Fix failing pre-commit, https://github.com/llamastack/llama-stack/actions/workflows/pre-commit.yml ## Test Plan CI |
||
|
Swapna Lekkala
|
09141361fb | fix: use dataset version 4.0.0 or above | ||
Derek Higgins
|
ef02b9ea10
|
fix: environment variable typo in inference recorder error message (#3374)
The error message was referencing LLAMA_STACK_INFERENCE_MODE instead of the correct LLAMA_STACK_TEST_INFERENCE_MODE environment variable. |
||
|
Francisco Arceo
|
ad6ea7fb91
|
feat: Adding OpenAI Prompts API (#3319)
# What does this PR do? This PR adds support for OpenAI Prompts API. Note, OpenAI does not explicitly expose the Prompts API but instead makes it available in the Responses API and in the [Prompts Dashboard](https://platform.openai.com/docs/guides/prompting#create-a-prompt). I have added the following APIs: - CREATE - GET - LIST - UPDATE - Set Default Version The Set Default Version API is made available only in the Prompts Dashboard and configures which prompt version is returned in the GET (the latest version is the default). Overall, the expected functionality in Responses will look like this: ```python from openai import OpenAI client = OpenAI() response = client.responses.create( prompt={ "id": "pmpt_68b0c29740048196bd3a6e6ac3c4d0e20ed9a13f0d15bf5e", "version": "2", "variables": { "city": "San Francisco", "age": 30, } } ) ``` ### Resolves https://github.com/llamastack/llama-stack/issues/3276 ## Test Plan Unit tests added. Integration tests can be added after client generation. ## Next Steps 1. Update Responses API to support Prompt API 2. I'll enhance the UI to implement the Prompt Dashboard. 3. Add cache for lower latency --------- Signed-off-by: Francisco Javier Arceo <farceo@redhat.com> |
||
Mohammad Daoud Farooqi
|
9618adba89
|
docs: add MongoDB to external provider list (#3369)
Some checks failed
Python Package Build Test / build (3.12) (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 1s
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
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Python Package Build Test / build (3.13) (push) Failing after 2s
Vector IO Integration Tests / test-matrix (push) Failing after 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 8s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Unit Tests / unit-tests (3.13) (push) Failing after 5s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 10s
Update ReadTheDocs / update-readthedocs (push) Failing after 36s
Test External API and Providers / test-external (venv) (push) Failing after 41s
UI Tests / ui-tests (22) (push) Successful in 1m3s
Pre-commit / pre-commit (push) Successful in 2m10s
The MongoDB integration - Vector search, Full-Text search and Hybrid search have now been added as an external provider offering for Llama Stack: https://github.com/mongodb-partners/mongodb-llama-stack |
||
|
Akram Ben Aissi
|
072dca0609
|
feat: Add Kubernetes auth provider to use SelfSubjectReview and kubernetes api server (#2559)
# What does this PR do? Add Kubernetes authentication provider support - Add KubernetesAuthProvider class for token validation using Kubernetes SelfSubjectReview API - Add KubernetesAuthProviderConfig with configurable API server URL, TLS settings, and claims mapping - Implement authentication via POST requests to /apis/authentication.k8s.io/v1/selfsubjectreviews endpoint - Add support for parsing Kubernetes SelfSubjectReview response format to extract user information - Add KUBERNETES provider type to AuthProviderType enum - Update create_auth_provider factory function to handle 'kubernetes' provider type - Add comprehensive unit tests for KubernetesAuthProvider functionality - Add documentation with configuration examples and usage instructions The provider validates tokens by sending SelfSubjectReview requests to the Kubernetes API server and extracts user information from the userInfo structure in the response. <!-- 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.* --> What This Verifies: Authentication header validation Token validation with Kubernetes SelfSubjectReview and kubernetes server API endpoint Error handling for invalid tokens and HTTP errors Request payload structure and headers ``` python -m pytest tests/unit/server/test_auth.py -k "kubernetes" -v ``` Signed-off-by: Akram Ben Aissi <akram.benaissi@gmail.com> |
||
dependabot[bot]
|
44e1a40595
|
chore(github-deps): bump actions/checkout from 4.1.7 to 5.0.0 (#3357)
[//]: # (dependabot-start) ⚠️ **Dependabot is rebasing this PR** ⚠️ Rebasing might not happen immediately, so don't worry if this takes some time. Note: if you make any changes to this PR yourself, they will take precedence over the rebase. --- [//]: # (dependabot-end) Bumps [actions/checkout](https://github.com/actions/checkout) from 4.1.7 to 5.0.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/actions/checkout/releases">actions/checkout's releases</a>.</em></p> <blockquote> <h2>v5.0.0</h2> <h2>What's Changed</h2> <ul> <li>Update actions checkout to use node 24 by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/2226">actions/checkout#2226</a></li> <li>Prepare v5.0.0 release by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/2238">actions/checkout#2238</a></li> </ul> <h2>⚠️ Minimum Compatible Runner Version</h2> <p><strong>v2.327.1</strong><br /> <a href="https://github.com/actions/runner/releases/tag/v2.327.1">Release Notes</a></p> <p>Make sure your runner is updated to this version or newer to use this release.</p> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/checkout/compare/v4...v5.0.0">https://github.com/actions/checkout/compare/v4...v5.0.0</a></p> <h2>v4.3.0</h2> <h2>What's Changed</h2> <ul> <li>docs: update README.md by <a href="https://github.com/motss"><code>@motss</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1971">actions/checkout#1971</a></li> <li>Add internal repos for checking out multiple repositories by <a href="https://github.com/mouismail"><code>@mouismail</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1977">actions/checkout#1977</a></li> <li>Documentation update - add recommended permissions to Readme by <a href="https://github.com/benwells"><code>@benwells</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/2043">actions/checkout#2043</a></li> <li>Adjust positioning of user email note and permissions heading by <a href="https://github.com/joshmgross"><code>@joshmgross</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/2044">actions/checkout#2044</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/checkout/pull/2194">actions/checkout#2194</a></li> <li>Update CODEOWNERS for actions by <a href="https://github.com/TingluoHuang"><code>@TingluoHuang</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/2224">actions/checkout#2224</a></li> <li>Update package dependencies by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/2236">actions/checkout#2236</a></li> <li>Prepare release v4.3.0 by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/2237">actions/checkout#2237</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/motss"><code>@motss</code></a> made their first contribution in <a href="https://redirect.github.com/actions/checkout/pull/1971">actions/checkout#1971</a></li> <li><a href="https://github.com/mouismail"><code>@mouismail</code></a> made their first contribution in <a href="https://redirect.github.com/actions/checkout/pull/1977">actions/checkout#1977</a></li> <li><a href="https://github.com/benwells"><code>@benwells</code></a> made their first contribution in <a href="https://redirect.github.com/actions/checkout/pull/2043">actions/checkout#2043</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/checkout/pull/2194">actions/checkout#2194</a></li> <li><a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> made their first contribution in <a href="https://redirect.github.com/actions/checkout/pull/2236">actions/checkout#2236</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/checkout/compare/v4...v4.3.0">https://github.com/actions/checkout/compare/v4...v4.3.0</a></p> <h2>v4.2.2</h2> <h2>What's Changed</h2> <ul> <li><code>url-helper.ts</code> now leverages well-known environment variables by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1941">actions/checkout#1941</a></li> <li>Expand unit test coverage for <code>isGhes</code> by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1946">actions/checkout#1946</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/checkout/compare/v4.2.1...v4.2.2">https://github.com/actions/checkout/compare/v4.2.1...v4.2.2</a></p> <h2>v4.2.1</h2> <h2>What's Changed</h2> <ul> <li>Check out other refs/* by commit if provided, fall back to ref by <a href="https://github.com/orhantoy"><code>@orhantoy</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1924">actions/checkout#1924</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/Jcambass"><code>@Jcambass</code></a> made their first contribution in <a href="https://redirect.github.com/actions/checkout/pull/1919">actions/checkout#1919</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/checkout/compare/v4.2.0...v4.2.1">https://github.com/actions/checkout/compare/v4.2.0...v4.2.1</a></p> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/actions/checkout/blob/main/CHANGELOG.md">actions/checkout's changelog</a>.</em></p> <blockquote> <h1>Changelog</h1> <h2>V5.0.0</h2> <ul> <li>Update actions checkout to use node 24 by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/2226">actions/checkout#2226</a></li> </ul> <h2>V4.3.0</h2> <ul> <li>docs: update README.md by <a href="https://github.com/motss"><code>@motss</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1971">actions/checkout#1971</a></li> <li>Add internal repos for checking out multiple repositories by <a href="https://github.com/mouismail"><code>@mouismail</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1977">actions/checkout#1977</a></li> <li>Documentation update - add recommended permissions to Readme by <a href="https://github.com/benwells"><code>@benwells</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/2043">actions/checkout#2043</a></li> <li>Adjust positioning of user email note and permissions heading by <a href="https://github.com/joshmgross"><code>@joshmgross</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/2044">actions/checkout#2044</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/checkout/pull/2194">actions/checkout#2194</a></li> <li>Update CODEOWNERS for actions by <a href="https://github.com/TingluoHuang"><code>@TingluoHuang</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/2224">actions/checkout#2224</a></li> <li>Update package dependencies by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/2236">actions/checkout#2236</a></li> </ul> <h2>v4.2.2</h2> <ul> <li><code>url-helper.ts</code> now leverages well-known environment variables by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1941">actions/checkout#1941</a></li> <li>Expand unit test coverage for <code>isGhes</code> by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1946">actions/checkout#1946</a></li> </ul> <h2>v4.2.1</h2> <ul> <li>Check out other refs/* by commit if provided, fall back to ref by <a href="https://github.com/orhantoy"><code>@orhantoy</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1924">actions/checkout#1924</a></li> </ul> <h2>v4.2.0</h2> <ul> <li>Add Ref and Commit outputs by <a href="https://github.com/lucacome"><code>@lucacome</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1180">actions/checkout#1180</a></li> <li>Dependency updates by <a href="https://github.com/dependabot"><code>@dependabot</code></a>- <a href="https://redirect.github.com/actions/checkout/pull/1777">actions/checkout#1777</a>, <a href="https://redirect.github.com/actions/checkout/pull/1872">actions/checkout#1872</a></li> </ul> <h2>v4.1.7</h2> <ul> <li>Bump the minor-npm-dependencies group across 1 directory with 4 updates by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1739">actions/checkout#1739</a></li> <li>Bump actions/checkout from 3 to 4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1697">actions/checkout#1697</a></li> <li>Check out other refs/* by commit by <a href="https://github.com/orhantoy"><code>@orhantoy</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1774">actions/checkout#1774</a></li> <li>Pin actions/checkout's own workflows to a known, good, stable version. by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1776">actions/checkout#1776</a></li> </ul> <h2>v4.1.6</h2> <ul> <li>Check platform to set archive extension appropriately by <a href="https://github.com/cory-miller"><code>@cory-miller</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1732">actions/checkout#1732</a></li> </ul> <h2>v4.1.5</h2> <ul> <li>Update NPM dependencies by <a href="https://github.com/cory-miller"><code>@cory-miller</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1703">actions/checkout#1703</a></li> <li>Bump github/codeql-action from 2 to 3 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1694">actions/checkout#1694</a></li> <li>Bump actions/setup-node from 1 to 4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1696">actions/checkout#1696</a></li> <li>Bump actions/upload-artifact from 2 to 4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1695">actions/checkout#1695</a></li> <li>README: Suggest <code>user.email</code> to be <code>41898282+github-actions[bot]@users.noreply.github.com</code> by <a href="https://github.com/cory-miller"><code>@cory-miller</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1707">actions/checkout#1707</a></li> </ul> <h2>v4.1.4</h2> <ul> <li>Disable <code>extensions.worktreeConfig</code> when disabling <code>sparse-checkout</code> by <a href="https://github.com/jww3"><code>@jww3</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1692">actions/checkout#1692</a></li> <li>Add dependabot config by <a href="https://github.com/cory-miller"><code>@cory-miller</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1688">actions/checkout#1688</a></li> <li>Bump the minor-actions-dependencies group with 2 updates by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1693">actions/checkout#1693</a></li> <li>Bump word-wrap from 1.2.3 to 1.2.5 by <a href="https://github.com/dependabot"><code>@dependabot</code></a> in <a href="https://redirect.github.com/actions/checkout/pull/1643">actions/checkout#1643</a></li> </ul> <h2>v4.1.3</h2> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
d458817af5
|
chore(github-deps): bump actions/setup-python from 5.6.0 to 6.0.0 (#3354)
Bumps [actions/setup-python](https://github.com/actions/setup-python) from 5.6.0 to 6.0.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/actions/setup-python/releases">actions/setup-python's releases</a>.</em></p> <blockquote> <h2>v6.0.0</h2> <h2>What's Changed</h2> <h3>Breaking Changes</h3> <ul> <li>Upgrade to node 24 by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/1164">actions/setup-python#1164</a></li> </ul> <p>Make sure your runner is on version v2.327.1 or later to ensure compatibility with this release. <a href="https://github.com/actions/runner/releases/tag/v2.327.1">See Release Notes</a></p> <h3>Enhancements:</h3> <ul> <li>Add support for <code>pip-version</code> by <a href="https://github.com/priyagupta108"><code>@priyagupta108</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/1129">actions/setup-python#1129</a></li> <li>Enhance reading from .python-version by <a href="https://github.com/krystof-k"><code>@krystof-k</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/787">actions/setup-python#787</a></li> <li>Add version parsing from Pipfile by <a href="https://github.com/aradkdj"><code>@aradkdj</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/1067">actions/setup-python#1067</a></li> </ul> <h3>Bug fixes:</h3> <ul> <li>Clarify pythonLocation behaviour for PyPy and GraalPy in environment variables by <a href="https://github.com/aparnajyothi-y"><code>@aparnajyothi-y</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/1183">actions/setup-python#1183</a></li> <li>Change missing cache directory error to warning by <a href="https://github.com/aparnajyothi-y"><code>@aparnajyothi-y</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/1182">actions/setup-python#1182</a></li> <li>Add Architecture-Specific PATH Management for Python with --user Flag on Windows by <a href="https://github.com/aparnajyothi-y"><code>@aparnajyothi-y</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/1122">actions/setup-python#1122</a></li> <li>Include python version in PyPy python-version output by <a href="https://github.com/cdce8p"><code>@cdce8p</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/1110">actions/setup-python#1110</a></li> <li>Update docs: clarification on pip authentication with setup-python by <a href="https://github.com/priya-kinthali"><code>@priya-kinthali</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/1156">actions/setup-python#1156</a></li> </ul> <h3>Dependency updates:</h3> <ul> <li>Upgrade idna from 2.9 to 3.7 in /<strong>tests</strong>/data by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/actions/setup-python/pull/843">actions/setup-python#843</a></li> <li>Upgrade form-data to fix critical vulnerabilities <a href="https://redirect.github.com/actions/setup-python/issues/182">#182</a> & <a href="https://redirect.github.com/actions/setup-python/issues/183">#183</a> by <a href="https://github.com/aparnajyothi-y"><code>@aparnajyothi-y</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/1163">actions/setup-python#1163</a></li> <li>Upgrade setuptools to 78.1.1 to fix path traversal vulnerability in PackageIndex.download by <a href="https://github.com/aparnajyothi-y"><code>@aparnajyothi-y</code></a> in <a href="https://redirect.github.com/actions/setup-python/pull/1165">actions/setup-python#1165</a></li> <li>Upgrade actions/checkout from 4 to 5 by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/actions/setup-python/pull/1181">actions/setup-python#1181</a></li> <li>Upgrade <code>@actions/tool-cache</code> from 2.0.1 to 2.0.2 by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/actions/setup-python/pull/1095">actions/setup-python#1095</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/krystof-k"><code>@krystof-k</code></a> made their first contribution in <a href="https://redirect.github.com/actions/setup-python/pull/787">actions/setup-python#787</a></li> <li><a href="https://github.com/cdce8p"><code>@cdce8p</code></a> made their first contribution in <a href="https://redirect.github.com/actions/setup-python/pull/1110">actions/setup-python#1110</a></li> <li><a href="https://github.com/aradkdj"><code>@aradkdj</code></a> made their first contribution in <a href="https://redirect.github.com/actions/setup-python/pull/1067">actions/setup-python#1067</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/setup-python/compare/v5...v6.0.0">https://github.com/actions/setup-python/compare/v5...v6.0.0</a></p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
dfa13d68f1
|
chore(github-deps): bump actions/setup-node from 4.4.0 to 5.0.0 (#3353)
Bumps [actions/setup-node](https://github.com/actions/setup-node) from 4.4.0 to 5.0.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/actions/setup-node/releases">actions/setup-node's releases</a>.</em></p> <blockquote> <h2>v5.0.0</h2> <h2>What's Changed</h2> <h3>Breaking Changes</h3> <ul> <li>Enhance caching in setup-node with automatic package manager detection by <a href="https://github.com/priya-kinthali"><code>@priya-kinthali</code></a> in <a href="https://redirect.github.com/actions/setup-node/pull/1348">actions/setup-node#1348</a></li> </ul> <p>This update, introduces automatic caching when a valid <code>packageManager</code> field is present in your <code>package.json</code>. This aims to improve workflow performance and make dependency management more seamless. To disable this automatic caching, set <code>package-manager-cache: false</code></p> <pre lang="yaml"><code>steps: - uses: actions/checkout@v5 - uses: actions/setup-node@v5 with: package-manager-cache: false </code></pre> <ul> <li>Upgrade action to use node24 by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://redirect.github.com/actions/setup-node/pull/1325">actions/setup-node#1325</a></li> </ul> <p>Make sure your runner is on version v2.327.1 or later to ensure compatibility with this release. <a href="https://github.com/actions/runner/releases/tag/v2.327.1">See Release Notes</a></p> <h3>Dependency Upgrades</h3> <ul> <li>Upgrade <code>@octokit/request-error</code> and <code>@actions/github</code> by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/actions/setup-node/pull/1227">actions/setup-node#1227</a></li> <li>Upgrade uuid from 9.0.1 to 11.1.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/actions/setup-node/pull/1273">actions/setup-node#1273</a></li> <li>Upgrade undici from 5.28.5 to 5.29.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/actions/setup-node/pull/1295">actions/setup-node#1295</a></li> <li>Upgrade form-data to bring in fix for critical vulnerability by <a href="https://github.com/gowridurgad"><code>@gowridurgad</code></a> in <a href="https://redirect.github.com/actions/setup-node/pull/1332">actions/setup-node#1332</a></li> <li>Upgrade actions/checkout from 4 to 5 by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/actions/setup-node/pull/1345">actions/setup-node#1345</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/priya-kinthali"><code>@priya-kinthali</code></a> made their first contribution in <a href="https://redirect.github.com/actions/setup-node/pull/1348">actions/setup-node#1348</a></li> <li><a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> made their first contribution in <a href="https://redirect.github.com/actions/setup-node/pull/1325">actions/setup-node#1325</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/setup-node/compare/v4...v5.0.0">https://github.com/actions/setup-node/compare/v4...v5.0.0</a></p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
58c61d85c8
|
chore(github-deps): bump actions/stale from 9.1.0 to 10.0.0 (#3352)
Bumps [actions/stale](https://github.com/actions/stale) from 9.1.0 to 10.0.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/actions/stale/releases">actions/stale's releases</a>.</em></p> <blockquote> <h2>v10.0.0</h2> <h2>What's Changed</h2> <h3>Breaking Changes</h3> <ul> <li>Upgrade to node 24 by <a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> in <a href="https://redirect.github.com/actions/stale/pull/1279">actions/stale#1279</a> Make sure your runner is on version v2.327.1 or later to ensure compatibility with this release. <a href="https://github.com/actions/runner/releases/tag/v2.327.1">Release Notes</a></li> </ul> <h3>Enhancement</h3> <ul> <li>Introducing sort-by option by <a href="https://github.com/suyashgaonkar"><code>@suyashgaonkar</code></a> in <a href="https://redirect.github.com/actions/stale/pull/1254">actions/stale#1254</a></li> </ul> <h3>Dependency Upgrades</h3> <ul> <li>Upgrade actions/publish-immutable-action from 0.0.3 to 0.0.4 by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/actions/stale/pull/1186">actions/stale#1186</a></li> <li>Upgrade undici from 5.28.4 to 5.28.5 by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/actions/stale/pull/1201">actions/stale#1201</a></li> <li>Upgrade <code>@action/cache</code> from 4.0.0 to 4.0.2 by <a href="https://github.com/aparnajyothi-y"><code>@aparnajyothi-y</code></a> in <a href="https://redirect.github.com/actions/stale/pull/1226">actions/stale#1226</a></li> <li>Upgrade <code>@action/cache</code> from 4.0.2 to 4.0.3 by <a href="https://github.com/suyashgaonkar"><code>@suyashgaonkar</code></a> in <a href="https://redirect.github.com/actions/stale/pull/1233">actions/stale#1233</a></li> <li>Upgrade undici from 5.28.5 to 5.29.0 by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/actions/stale/pull/1251">actions/stale#1251</a></li> <li>Upgrade form-data to bring in fix for critical vulnerability by <a href="https://github.com/gowridurgad"><code>@gowridurgad</code></a> in <a href="https://redirect.github.com/actions/stale/pull/1277">actions/stale#1277</a></li> </ul> <h3>Documentation changes</h3> <ul> <li>Changelog update for recent releases by <a href="https://github.com/suyashgaonkar"><code>@suyashgaonkar</code></a> in <a href="https://redirect.github.com/actions/stale/pull/1224">actions/stale#1224</a></li> <li>Permissions update in Readme by <a href="https://github.com/ghadimir"><code>@ghadimir</code></a> in <a href="https://redirect.github.com/actions/stale/pull/1248">actions/stale#1248</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/suyashgaonkar"><code>@suyashgaonkar</code></a> made their first contribution in <a href="https://redirect.github.com/actions/stale/pull/1224">actions/stale#1224</a></li> <li><a href="https://github.com/GhadimiR"><code>@GhadimiR</code></a> made their first contribution in <a href="https://redirect.github.com/actions/stale/pull/1248">actions/stale#1248</a></li> <li><a href="https://github.com/gowridurgad"><code>@gowridurgad</code></a> made their first contribution in <a href="https://redirect.github.com/actions/stale/pull/1277">actions/stale#1277</a></li> <li><a href="https://github.com/salmanmkc"><code>@salmanmkc</code></a> made their first contribution in <a href="https://redirect.github.com/actions/stale/pull/1279">actions/stale#1279</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/actions/stale/compare/v9...v10.0.0">https://github.com/actions/stale/compare/v9...v10.0.0</a></p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
Yuan Tang
|
2f91344c1f
|
docs: Update changelog (#3343)
This updates the changelog doc to include the latest updates. Signed-off-by: Yuan Tang <terrytangyuan@gmail.com> |
||
|
dependabot[bot]
|
51012a82a3
|
chore(github-deps): bump astral-sh/setup-uv from 6.6.0 to 6.6.1 (#3355)
Bumps [astral-sh/setup-uv](https://github.com/astral-sh/setup-uv) from 6.6.0 to 6.6.1. <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>v6.6.1 🌈 Fix exclusions in cache-dependency-glob</h2> <h2>Changes</h2> <p>Exclusions with a leading <code>!</code> in the <a href="https://github.com/astral-sh/setup-uv?tab=readme-ov-file#cache-dependency-glob">cache-dependency-glob</a> did not work and got fixed with this release. Thank you <a href="https://github.com/KnisterPeter"><code>@KnisterPeter</code></a> for raising this!</p> <h2>🐛 Bug fixes</h2> <ul> <li>Fix exclusions in cache-dependency-glob <a href="https://github.com/eifinger"><code>@eifinger</code></a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/546">#546</a>)</li> </ul> <h2>🧰 Maintenance</h2> <ul> <li>Bump dependencies <a href="https://github.com/eifinger"><code>@eifinger</code></a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/547">#547</a>)</li> <li>chore: update known versions for 0.8.14 @<a href="https://github.com/apps/github-actions">github-actions[bot]</a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/543">#543</a>)</li> <li>chore: update known versions for 0.8.13 @<a href="https://github.com/apps/github-actions">github-actions[bot]</a> (<a href="https://redirect.github.com/astral-sh/setup-uv/issues/536">#536</a>)</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
e1b81ce1fc
|
chore(ui-deps): bump @radix-ui/react-dropdown-menu from 2.1.14 to 2.1.16 in /llama_stack/ui (#3361)
Bumps [@radix-ui/react-dropdown-menu](https://github.com/radix-ui/primitives) from 2.1.14 to 2.1.16. <details> <summary>Commits</summary> <ul> <li>See full diff in <a href="https://github.com/radix-ui/primitives/commits">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]
|
e508aef320
|
chore(ui-deps): bump lucide-react from 0.510.0 to 0.542.0 in /llama_stack/ui (#3363)
Bumps [lucide-react](https://github.com/lucide-icons/lucide/tree/HEAD/packages/lucide-react) from 0.510.0 to 0.542.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/lucide-icons/lucide/releases">lucide-react's releases</a>.</em></p> <blockquote> <h2>Version 0.542.0</h2> <h2>What's Changed</h2> <ul> <li>feat(docs): add MDN Web Docs & Nuxt to showcase by <a href="https://github.com/karsa-mistmere"><code>@karsa-mistmere</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3590">lucide-icons/lucide#3590</a></li> <li>feat(icons): added <code>list-chevrons-down-up</code> icon by <a href="https://github.com/juliankellydesign"><code>@juliankellydesign</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3492">lucide-icons/lucide#3492</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/juliankellydesign"><code>@juliankellydesign</code></a> made their first contribution in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3492">lucide-icons/lucide#3492</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/lucide-icons/lucide/compare/0.541.0...0.542.0">https://github.com/lucide-icons/lucide/compare/0.541.0...0.542.0</a></p> <h2>Version 0.541.0</h2> <h2>What's Changed</h2> <ul> <li>feat(packages/lucide): added support for providing a custom root element by <a href="https://github.com/karsa-mistmere"><code>@karsa-mistmere</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3543">lucide-icons/lucide#3543</a></li> <li>fix(icons): optimized <code>chrome</code> icon & renamed to <code>chromium</code> by <a href="https://github.com/jguddas"><code>@jguddas</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3572">lucide-icons/lucide#3572</a></li> <li>fix(icons): changed <code>wallpaper</code> icon by <a href="https://github.com/jguddas"><code>@jguddas</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3566">lucide-icons/lucide#3566</a></li> <li>fix(icons): optimized <code>cog</code> icon by <a href="https://github.com/jguddas"><code>@jguddas</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3548">lucide-icons/lucide#3548</a></li> <li>fix(icons): changed <code>building</code> icon by <a href="https://github.com/karsa-mistmere"><code>@karsa-mistmere</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3510">lucide-icons/lucide#3510</a></li> <li>feat(dpi-preview): add previous version for easier comparison by <a href="https://github.com/jguddas"><code>@jguddas</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3532">lucide-icons/lucide#3532</a></li> <li>feat(icons): added 'panel-dashed' variants + update tags on existing icons by <a href="https://github.com/irvineacosta"><code>@irvineacosta</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3500">lucide-icons/lucide#3500</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/lucide-icons/lucide/compare/0.540.0...0.541.0">https://github.com/lucide-icons/lucide/compare/0.540.0...0.541.0</a></p> <h2>Version 0.540.0</h2> <h2>What's Changed</h2> <ul> <li>fix(license): add full text of Feather license by <a href="https://github.com/jguddas"><code>@jguddas</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3530">lucide-icons/lucide#3530</a></li> <li>fix(icons): changed <code>umbrella</code> icon by <a href="https://github.com/karsa-mistmere"><code>@karsa-mistmere</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3490">lucide-icons/lucide#3490</a></li> <li>docs(site): added official statement on brand logos in Lucide by <a href="https://github.com/karsa-mistmere"><code>@karsa-mistmere</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3541">lucide-icons/lucide#3541</a></li> <li>fix(icons): changed <code>camera</code> icon by <a href="https://github.com/karsa-mistmere"><code>@karsa-mistmere</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3539">lucide-icons/lucide#3539</a></li> <li>feat(icons): added <code>rose</code> icon by <a href="https://github.com/jguddas"><code>@jguddas</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/1972">lucide-icons/lucide#1972</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/lucide-icons/lucide/compare/0.539.0...0.540.0">https://github.com/lucide-icons/lucide/compare/0.539.0...0.540.0</a></p> <h2>Version 0.539.0</h2> <h2>What's Changed</h2> <ul> <li>feat(icons): added <code>brick-wall-shield</code> icon by <a href="https://github.com/karsa-mistmere"><code>@karsa-mistmere</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3476">lucide-icons/lucide#3476</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/lucide-icons/lucide/compare/0.538.0...0.539.0">https://github.com/lucide-icons/lucide/compare/0.538.0...0.539.0</a></p> <h2>Version 0.538.0</h2> <h2>What's Changed</h2> <ul> <li>fix(icons): changed <code>apple</code> icon by <a href="https://github.com/karsa-mistmere"><code>@karsa-mistmere</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3505">lucide-icons/lucide#3505</a></li> <li>fix(icons): changed <code>store</code> icon by <a href="https://github.com/karsa-mistmere"><code>@karsa-mistmere</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3501">lucide-icons/lucide#3501</a></li> <li>fix(icons): changed <code>mic-off</code> icon by <a href="https://github.com/lieonlion"><code>@lieonlion</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/2823">lucide-icons/lucide#2823</a></li> <li>chore(deps): bump astro from 5.5.2 to 5.12.8 by <a href="https://github.com/dependabot"><code>@dependabot</code></a>[bot] in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3523">lucide-icons/lucide#3523</a></li> <li>fix(icons): deprecate rail-symbol by <a href="https://github.com/jguddas"><code>@jguddas</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/2862">lucide-icons/lucide#2862</a></li> <li>feat(icons): added <code>kayak</code> icon by <a href="https://github.com/jpjacobpadilla"><code>@jpjacobpadilla</code></a> in <a href="https://redirect.github.com/lucide-icons/lucide/pull/3054">lucide-icons/lucide#3054</a></li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
91c7c4570e
|
chore(ui-deps): bump sonner from 2.0.6 to 2.0.7 in /llama_stack/ui (#3364)
Bumps [sonner](https://github.com/emilkowalski/sonner) from 2.0.6 to 2.0.7. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/emilkowalski/sonner/releases">sonner's releases</a>.</em></p> <blockquote> <h2>v2.0.7</h2> <p>Sonner now supports multiple <code><Toaster /></code> components, see more <a href="https://sonner.emilkowal.ski/toaster#multiple-toasters">here</a>.</p> <h2>What's Changed</h2> <ul> <li>feat: add testId prop for individual toast components by <a href="https://github.com/b-like-bahar"><code>@b-like-bahar</code></a> in <a href="https://redirect.github.com/emilkowalski/sonner/pull/660">emilkowalski/sonner#660</a></li> <li>feat(toaster): add support for multiple toasters with unique identifiers by <a href="https://github.com/taroj1205"><code>@taroj1205</code></a> in <a href="https://redirect.github.com/emilkowalski/sonner/pull/665">emilkowalski/sonner#665</a></li> <li>fix: tests by <a href="https://github.com/emilkowalski"><code>@emilkowalski</code></a> in <a href="https://redirect.github.com/emilkowalski/sonner/pull/677">emilkowalski/sonner#677</a></li> </ul> <h2>New Contributors</h2> <ul> <li><a href="https://github.com/b-like-bahar"><code>@b-like-bahar</code></a> made their first contribution in <a href="https://redirect.github.com/emilkowalski/sonner/pull/660">emilkowalski/sonner#660</a></li> <li><a href="https://github.com/taroj1205"><code>@taroj1205</code></a> made their first contribution in <a href="https://redirect.github.com/emilkowalski/sonner/pull/665">emilkowalski/sonner#665</a></li> </ul> <p><strong>Full Changelog</strong>: <a href="https://github.com/emilkowalski/sonner/compare/v2.0.6...v2.0.7">https://github.com/emilkowalski/sonner/compare/v2.0.6...v2.0.7</a></p> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
fe134d90e5
|
chore(ui-deps): bump react-dom and @types/react-dom in /llama_stack/ui (#3360)
Bumps [react-dom](https://github.com/facebook/react/tree/HEAD/packages/react-dom) and [@types/react-dom](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/react-dom). These dependencies needed to be updated together. Updates `react-dom` from 19.1.0 to 19.1.1 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/facebook/react/releases">react-dom's releases</a>.</em></p> <blockquote> <h2>19.1.1 (July 28, 2025)</h2> <h3>React</h3> <ul> <li>Fixed Owner Stacks to work with ES2015 function.name semantics (<a href="https://redirect.github.com/facebook/react/pull/33680">#33680</a> by <a href="https://github.com/hoxyq"><code>@hoxyq</code></a>)</li> </ul> </blockquote> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/facebook/react/blob/main/CHANGELOG.md">react-dom's changelog</a>.</em></p> <blockquote> <h2>19.1.1 (July 28, 2025)</h2> <h3>React</h3> <ul> <li>Fixed Owner Stacks to work with ES2015 function.name semantics (<a href="https://redirect.github.com/facebook/react/pull/33680">#33680</a> by <a href="https://github.com/hoxyq"><code>@hoxyq</code></a>)</li> </ul> </blockquote> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
Matthew Farrellee
|
6a35bd7bb6
|
chore: update the anthropic inference impl to use openai-python for openai-compat functions (#3366)
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
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
API Conformance Tests / check-schema-compatibility (push) Successful in 6s
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 4s
UI Tests / ui-tests (22) (push) Successful in 38s
Pre-commit / pre-commit (push) Successful in 1m13s
# What does this PR do? update the Anthropic inference provider to use openai-python for the openai-compat endpoints ## Test Plan ci Co-authored-by: raghotham <rsm@meta.com> |
||
|
Matthew Farrellee
|
78cab5331a
|
chore(groq test): skip completions tests for groq, api is not supported server-side (#3347)
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
Python Package Build Test / build (3.13) (push) Failing after 3s
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 4s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 6s
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 4s
API Conformance Tests / check-schema-compatibility (push) Successful in 12s
UI Tests / ui-tests (22) (push) Successful in 37s
Pre-commit / pre-commit (push) Successful in 1m16s
# What does this PR do? skip /v1/completions tests on groq, endpoint is not supported Co-authored-by: raghotham <rsm@meta.com> |
||
|
Matthew Farrellee
|
d23607483f
|
chore: update the groq inference impl to use openai-python for openai-compat functions (#3348)
# What does this PR do? update Groq inference provider to use OpenAIMixin for openai-compat endpoints changes on api.groq.com - - json_schema is now supported for specific models, see https://console.groq.com/docs/structured-outputs#supported-models - response_format with streaming is now supported for models that support response_format - groq no longer returns a 400 error if tools are provided and tool_choice is not "required" ## Test Plan ``` $ GROQ_API_KEY=... uv run llama stack build --image-type venv --providers inference=remote::groq --run ... $ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model groq/llama-3.3-70b-versatile tests/integration/inference/test_openai_completion.py -k 'not store' ... SKIPPED [3] tests/integration/inference/test_openai_completion.py:44: Model groq/llama-3.3-70b-versatile hosted by remote::groq doesn't support OpenAI completions. SKIPPED [3] tests/integration/inference/test_openai_completion.py:94: Model groq/llama-3.3-70b-versatile hosted by remote::groq doesn't support vllm extra_body parameters. SKIPPED [4] tests/integration/inference/test_openai_completion.py:73: Model groq/llama-3.3-70b-versatile hosted by remote::groq doesn't support n param. SKIPPED [1] tests/integration/inference/test_openai_completion.py💯 Model groq/llama-3.3-70b-versatile hosted by remote::groq doesn't support chat completion calls with base64 encoded files. ======================= 8 passed, 11 skipped, 8 deselected, 2 warnings in 5.13s ======================== ``` --------- Co-authored-by: raghotham <rsm@meta.com> |
||
Charlie Doern
|
ecd9d8dc1a
|
test: introduce api conformance test (#3257)
Some checks failed
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 0s
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
Vector IO Integration Tests / test-matrix (push) Failing after 4s
Python Package Build Test / build (3.13) (push) Failing after 3s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 7s
Test External API and Providers / test-external (venv) (push) Failing after 4s
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 12s
UI Tests / ui-tests (22) (push) Successful in 40s
Pre-commit / pre-commit (push) Successful in 1m48s
# What does this PR do? this test runs on each PR and uses a new conformance workflow to compare the base (main) branch openapi spec to the one on this PR if one of our "stable" APIs change, the test will fail. this workflow uses `oasdiff` to identify breaking changes for paths we want to ensure comptability for. specifically this is using `oasdiff breaking` with `--match-path` which only checks breaking changes for the specified paths. As a follow up to this, we can add an optional way to make it so that it is OK to make these change if properly documented or in a changelog or something. or by using a label on the PR to override the failing test. related to #3237 ## Test Plan conformance test should pass given there are no changes Signed-off-by: Charlie Doern <cdoern@redhat.com> |
||
|
Matthew Farrellee
|
9252d9fc01
|
chore(groq test): skip with_n tests for groq, it is not supported server-side (#3346)
# What does this PR do? skip the with_n test for groq, because it isn't supported by the provider's service see https://console.groq.com/docs/openai#currently-unsupported-openai-features Co-authored-by: raghotham <rsm@meta.com> |
||
|
Matthew Farrellee
|
bf02cd846f
|
chore: update the sambanova inference impl to use openai-python for openai-compat functions (#3345)
# What does this PR do? update SambaNova inference provider to use OpenAIMixin for openai-compat endpoints ## Test Plan ``` $ SAMBANOVA_API_KEY=... uv run llama stack build --image-type venv --providers inference=remote::sambanova --run ... $ LLAMA_STACK_CONFIG=http://localhost:8321 uv run --group test pytest -v -ra --text-model sambanova/Meta-Llama-3.3-70B-Instruct tests/integration/inference -k 'not store' ... FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=sambanova/Meta-Llama-3.3-70B-Instruct-inference:chat_completion:tool_calling_tools_absent-True] - AttributeError: 'NoneType' object has no attribute 'delta' FAILED tests/integration/inference/test_text_inference.py::test_text_chat_completion_tool_calling_tools_not_in_request[txt=sambanova/Meta-Llama-3.3-70B-Instruct-inference:chat_completion:tool_calling_tools_absent-False] - llama_stack_client.InternalServerError: Error code: 500 - {'detail': 'Internal server error: An une... =========== 2 failed, 16 passed, 68 skipped, 8 deselected, 3 xfailed, 13 warnings in 15.85s ============ ``` the two failures also exist before this change. they are part of the deprecated inference.chat_completion tests that flow through litellm. they can be resolved later. |
||
|
Matthew Farrellee
|
4c28544c04
|
chore(gemini, tests): add skips for n and completions, gemini api does not support them (#3350)
# What does this PR do? the gemini api endpoints do not support the n param or completions ## Test Plan ci |
||
|
Matthew Farrellee
|
d6c3b36390
|
chore: update the gemini inference impl to use openai-python for openai-compat functions (#3351)
# What does this PR do? update the Gemini inference provider to use openai-python for the openai-compat endpoints partially addresses #3349, does not address /inference/completion or /inference/chat-completion ## Test Plan ci |
||
|
Francisco Arceo
|
7cd1c2c238
|
feat: Updating Rag Tool to use Files API and Vector Stores API (#3344)
Some checks failed
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 1s
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
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 18s
Update ReadTheDocs / update-readthedocs (push) Failing after 15s
Python Package Build Test / build (3.13) (push) Failing after 19s
Test External API and Providers / test-external (venv) (push) Failing after 17s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 23s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 22s
Unit Tests / unit-tests (3.12) (push) Failing after 19s
Unit Tests / unit-tests (3.13) (push) Failing after 19s
Vector IO Integration Tests / test-matrix (push) Failing after 23s
UI Tests / ui-tests (22) (push) Successful in 44s
Pre-commit / pre-commit (push) Successful in 1m32s
|
||
|
Ashwin Bharambe
|
47b640370e
|
feat(tests): introduce a test "suite" concept to encompass dirs, options (#3339)
Some checks failed
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 (3.13) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 4s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4s
Vector IO Integration Tests / test-matrix (push) Failing after 4s
Python Package Build Test / build (3.12) (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 4s
Unit Tests / unit-tests (3.13) (push) Failing after 3s
UI Tests / ui-tests (22) (push) Successful in 33s
Pre-commit / pre-commit (push) Successful in 1m15s
Our integration tests need to be 'grouped' because each group often needs a specific set of models it works with. We separated vision tests due to this, and we have a separate set of tests which test "Responses" API. This PR makes this system a bit more official so it is very easy to target these groups and apply all testing infrastructure towards all the groups (for example, record-replay) uniformly. There are three suites declared: - base - vision - responses Note that our CI currently runs the "base" and "vision" suites. You can use the `--suite` option when running pytest (or any of the testing scripts or workflows.) For example: ``` OLLAMA_URL=http://localhost:11434 \ pytest -s -v tests/integration/ --stack-config starter --suite vision ``` |
||
|
Matthew Farrellee
|
0c2757a05b
|
chore(sambanova test): skip with_n tests for sambanova, it is not implemented server-side (#3342)
# What does this PR do? skip a test that cannot pass for sambanova see https://docs-legacy.sambanova.ai/sambastudio/latest/open-ai-api.html\#_example_requests_using_openai_client ## Test Plan ci |
||
|
Matthew Farrellee
|
df1526991f
|
feat(batches, completions): add /v1/completions support to /v1/batches (#3309)
# What does this PR do? add support for /v1/completions to the /v1/batches api ## Test Plan ci |
||
|
Francisco Arceo
|
e2fe39aee1
|
feat!: Migrate Vector DB IDs to Vector Store IDs (breaking change) (#3253)
Some checks failed
Test External Providers Installed via Module / test-external-providers-from-module (venv) (push) Has been skipped
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 1s
Integration Tests (Replay) / Integration Tests (, , , client=, vision=) (push) Failing after 3s
Vector IO Integration Tests / test-matrix (push) Failing after 4s
Test Llama Stack Build / generate-matrix (push) Successful in 3s
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 / build-custom-container-distribution (push) Failing after 3s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 3s
Python Package Build Test / build (3.12) (push) Failing after 2s
Test External API and Providers / test-external (venv) (push) Failing after 3s
Unit Tests / unit-tests (3.13) (push) Failing after 3s
Update ReadTheDocs / update-readthedocs (push) Failing after 3s
Test Llama Stack Build / build (push) Failing after 3s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
UI Tests / ui-tests (22) (push) Successful in 35s
Pre-commit / pre-commit (push) Successful in 1m15s
# What does this PR do?
This change migrates the VectorDB id generation to Vector Stores.
This is a breaking change for **_some users_** that may have application
code using the `vector_db_id` parameter in the request of the VectorDB
protocol instead of the `VectorDB.identifier` in the response.
By default we will now create a Vector Store every time we register a
VectorDB. The caveat with this approach is that this maps the
`vector_db_id` → `vector_store.name`. This is a reasonable tradeoff to
transition users towards OpenAI Vector Stores.
As an added benefit, registering VectorDBs will result in them appearing
in the VectorStores admin UI.
### Why?
This PR makes the `POST` API call to `/v1/vector-dbs` swap the
`vector_db_id` parameter in the **request body** into the VectorStore's
name field and sets the `vector_db_id` to the generated vector store id
(e.g., `vs_038247dd-4bbb-4dbb-a6be-d5ecfd46cfdb`).
That means that users would have to do something like follows in their
application code:
```python
res = client.vector_dbs.register(
vector_db_id='my-vector-db-id',
embedding_model='ollama/all-minilm:l6-v2',
embedding_dimension=384,
)
vector_db_id = res.identifier
```
And then the rest of their code would behave, including `VectorIO`'s
insert protocol using `vector_db_id` in the request.
An alternative implementation would be to just delete the `vector_db_id`
parameter in `VectorDB` but the end result would still require users
having to write `vector_db_id = res.identifier` since
`VectorStores.create()` generates the ID for you.
So this approach felt the easiest way to migrate users towards
VectorStores (subsequent PRs will be added to trigger `files.create()`
and `vector_stores.files.create()`).
## Test Plan
Unit tests and integration tests have been added.
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
|
||
|
Derek Higgins
|
64b2977162
|
fix: Fix locations of distrubution runtime directories (#3336)
The defaults were mixed up Signed-off-by: Derek Higgins <derekh@redhat.com> |
||
Sumanth Kamenani
|
0b00c68d59
|
fix: use lambda pattern for bedrock config env vars (#3307)
# What does this PR do? Improved bedrock provider config to read from environment variables like AWS_ACCESS_KEY_ID. Updated all fields to use default_factory with lambda patterns like the nvidia provider does. Now the environment variables work as documented. Closes #3305 ## Test Plan Ran the new bedrock config tests: ```bash python -m pytest tests/unit/providers/inference/bedrock/test_config.py -v Verified existing provider tests still work: python -m pytest tests/unit/providers/test_configs.py -v |
||
|
ehhuang
|
3a7ac4227d
|
chore: unbreak inference store test (#3340)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 1s
SqlStore Integration Tests / test-postgres (3.13) (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
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=, vision=) (push) Failing after 2s
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 4s
Unit Tests / unit-tests (3.13) (push) Failing after 5s
UI Tests / ui-tests (22) (push) Successful in 1m21s
Pre-commit / pre-commit (push) Successful in 2m27s
# What does this PR do? The inference store writes were moved to asyncio.create_task and not await anymore ## Test Plan ❯ OLLAMA_URL=http://localhost:11434 LLAMA_STACK_CONFIG=server:starter uv run --with pytest-repeat pytest tests/integration/inference --text-model="ollama/llama3.2:3b-instruct-fp16" -vvs -k "test_inference_store_tool_calls and 3b-instruct-fp16-True" --count=10 Uninstalled 2 packages in 102ms Installed 2 packages in 138ms INFO 2025-09-04 14:10:17,775 tests.integration.conftest:66 tests: Setting DISABLE_CODE_SANDBOX=1 for macOS ========================================================================================================== test session starts =========================================================================================================== platform darwin -- Python 3.12.3, pytest-8.4.1, pluggy-1.6.0 -- /Users/erichuang/.cache/uv/builds-v0/.tmpSGMlgt/bin/python cachedir: .pytest_cache metadata: {'Python': '3.12.3', 'Platform': 'macOS-15.6.1-arm64-arm-64bit', 'Packages': {'pytest': '8.4.1', 'pluggy': '1.6.0'}, 'Plugins': {'repeat': '0.9.4', '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-git configfile: pyproject.toml plugins: repeat-0.9.4, 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 970 items / 950 deselected / 20 selected tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-1-10] 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) Waiting for server at http://localhost:8321... (15.2s elapsed) Waiting for server at http://localhost:8321... (15.7s elapsed) Server is ready at http://localhost:8321 llama_stack_client instantiated in 20.583s PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-2-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-3-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-4-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-5-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-6-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-7-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-8-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-9-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[openai_client-txt=ollama/llama3.2:3b-instruct-fp16-True-10-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-1-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-2-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-3-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-4-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-5-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-6-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-7-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-8-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-9-10] PASSED tests/integration/inference/test_openai_completion.py::test_inference_store_tool_calls[client_with_models-txt=ollama/llama3.2:3b-instruct-fp16-True-10-10] PASSEDTerminating llama stack server process... Terminating process 53307 and its group... Server process and children terminated gracefully |
||
|
Sumanth Kamenani
|
55a8c5f439
|
fix: show descriptive MCP server connection errors instead of generic 500s (#3256)
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 1s
Python Package Build Test / build (3.12) (push) Failing after 1s
Python Package Build Test / build (3.13) (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=, vision=) (push) Failing after 3s
Vector IO Integration Tests / test-matrix (push) Failing after 5s
Unit Tests / unit-tests (3.12) (push) Failing after 3s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Update ReadTheDocs / update-readthedocs (push) Failing after 3s
Unit Tests / unit-tests (3.13) (push) Failing after 3s
UI Tests / ui-tests (22) (push) Successful in 1m20s
Pre-commit / pre-commit (push) Successful in 2m37s
What does this PR do? Fixes error handling when MCP server connections fail. Instead of returning generic 500 errors, now provides descriptive error messages with proper HTTP status codes. Closes #3107 Test Plan Before fix: curl -X GET "http://localhost:8321/v1/tool-runtime/list-tools?tool_group_id=bad-mcp-server" Returns: {"detail": "Internal server error: An unexpected error occurred."} (500) After fix: curl -X GET "http://localhost:8321/v1/tool-runtime/list-tools?tool_group_id=bad-mcp-server" Returns: {"error": {"detail": "Failed to connect to MCP server at http://localhost:9999/sse: Connection refused"}} (502) Tests: - Added unit test for ConnectionError → 502 translation - Manually tested with unreachable MCP servers (connection refused) |
||
|
slekkala1
|
561d2fc6b8
|
fix: Move to older version for docker container failure [fireworks-ai] (#3338)
# What does this PR do?
Noticed the test
https://github.com/llamastack/llama-stack-ops/actions/workflows/test-maybe-cut.yaml
are still failing randomly.
Earlier fixed this with 0.18.0 of fireworks here
https://github.com/llamastack/llama-stack/pull/3267, the local testing
may have inadvertently picked a lower version with `<=` which I assumed
picks latest version.
Now tested with `==` to find the version where it broke and pinning to
version(`<=`) where it was passing.
## Test Plan
Tested locally with the following commands to start a container
Build container
`llama stack build --distro starter --image-type container`
start container `docker run -d -p 8321:8321 --name llama-stack-test
distribution-starter:0.2.20`
check health `http://localhost:8321/v1/health`
Above steps fails without the fix
Tested with `==` to ensure the same version is picked in local testing
instead of anything lower.
Following here for the fix from `fireworks-ai`
|
||
|
ehhuang
|
bcc7f2c7d0
|
chore: async inference store write (#3318)
# What does this PR do? ## Test Plan ``` cd /docs/source/distributions/k8s-benchmark # start mock server python openai-mock-server.py --port 8000 # start stack server uv run --with llama-stack python -m llama_stack.core.server.server docs/source/distributions/k8s-benchmark/stack_run_config.yaml # run benchmark script uv run python3 benchmark.py --duration 30 --concurrent 50 --base-url=http://localhost:8321/v1/openai/v1 --model=vllm-inference/meta-llama/Llama-3.2-3B-Instruct ``` Before: ============================================================ BENCHMARK RESULTS ============================================================ Total time: 30.00s Concurrent users: 50 Total requests: 1267 Successful requests: 1267 Failed requests: 0 Success rate: 100.0% Requests per second: 42.23 After: ============================================================ BENCHMARK RESULTS ============================================================ Total time: 30.00s Concurrent users: 50 Total requests: 1449 Successful requests: 1449 Failed requests: 0 Success rate: 100.0% Requests per second: 48.30 |
||
|
Derek Higgins
|
5bbca56cfc
|
fix: Make SentenceTransformer embedding operations non-blocking (#3335)
- Wrap model loading with asyncio.to_thread() to prevent blocking during model download/initialization - Wrap encoding operations with asyncio.to_thread() to run in background thread - Convert _load_sentence_transformer_model() to async method This ensures the async event loop remains responsive during embedding operations. Closes: #3332 Signed-off-by: Derek Higgins <derekh@redhat.com> Co-authored-by: Francisco Arceo <arceofrancisco@gmail.com> |