mirror of
https://github.com/meta-llama/llama-stack.git
synced 2025-12-03 09:53:45 +00:00
1813 commits
| Author | SHA1 | Message | Date | |
|---|---|---|---|---|
Enrico Zimuel
|
6f39c8994d
|
Draft for Elasticsearch as vector db | ||
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
|
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" ] }' ``` |
||
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. |
||
|
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 |
||
|
dependabot[bot]
|
8885cea8d7
|
fix(conversations)!: update Conversations API definitions (was: bump openai from 1.107.0 to 2.5.0) (#3847)
Bumps [openai](https://github.com/openai/openai-python) from 1.107.0 to 2.5.0. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/openai/openai-python/releases">openai's releases</a>.</em></p> <blockquote> <h2>v2.5.0</h2> <h2>2.5.0 (2025-10-17)</h2> <p>Full Changelog: <a href="https://github.com/openai/openai-python/compare/v2.4.0...v2.5.0">v2.4.0...v2.5.0</a></p> <h3>Features</h3> <ul> <li><strong>api:</strong> api update (<a href=" |
||
Jiayi Ni
|
bb1ebb3c6b
|
feat: Add rerank models and rerank API change (#3831)
# What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> - Extend the model type to include rerank models. - Implement `rerank()` method in inference router. - Add `rerank_model_list` to `OpenAIMixin` to enable providers to register and identify rerank models - Update documentation. <!-- 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.* --> ``` pytest tests/unit/providers/utils/inference/test_openai_mixin.py ``` |
||
github-actions[bot]
|
bf2d16997d |
build: Bump version to 0.3.0
Some checks failed
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 2s
Test Llama Stack Build / generate-matrix (push) Successful in 3s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 4s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 7s
Python Package Build Test / build (3.13) (push) Failing after 0s
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
Vector IO Integration Tests / test-matrix (push) Failing after 6s
Test llama stack list-deps / generate-matrix (push) Successful in 4s
Test llama stack list-deps / show-single-provider (push) Failing after 4s
Test llama stack list-deps / list-deps-from-config (push) Failing after 4s
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 (3.12) (push) Failing after 3s
Test Llama Stack Build / build (push) Failing after 5s
Unit Tests / unit-tests (3.13) (push) Failing after 6s
Python Package Build Test / build (3.12) (push) Failing after 25s
Test llama stack list-deps / list-deps (push) Failing after 24s
UI Tests / ui-tests (22) (push) Successful in 52s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 30s
Pre-commit / pre-commit (push) Successful in 1m59s
|
||
|
Ashwin Bharambe
|
557b1b8c2d | fix(logs): restore uvicorn and llama_stack logger settings | ||
slekkala1
|
eb2b240594
|
fix: remove consistency checks (#3881)
# What does this PR do?
metadata is conflicting with the default embedding model set on server
side via extra body, removing the check and just letting metadata take
precedence over extra body
`ValueError: Embedding model inconsistent between metadata
('text-embedding-3-small') and extra_body
('sentence-transformers/nomic-ai/nomic-embed-text-v1.5')`
## Test Plan
CI
|
||
|
slekkala1
|
cb6a5e2687
|
fix: fix segfault in load model (#3879)
# What does this PR do? Fix segfault with load model The cc-vec integration failed with segfault when used with default embedding model on macOS `model_id: nomic-ai/nomic-embed-text-v1.5` and `provider_id: sentence-transformers` Checked crash report and see this is due to torch OPENMP settings. Constrainting to 1 thread works without crashes. ## Test Plan Tested with cc-vec integration 1. start server llama stack run starter 2. Do the setup in https://github.com/raghotham/cc-vec to set env variables and try `uv run cc-vec index --url-patterns "%.github.io" --vector-store-name "ml-research" --limit 50 --chunk-size 800 --overlap 400` |
||
|
Ashwin Bharambe
|
bd3c473208
|
revert: "chore(cleanup)!: remove tool_runtime.rag_tool" (#3877)
Reverts llamastack/llama-stack#3871 This PR broke RAG (even from Responses -- there _is_ a dependency) |
||
|
Ashwin Bharambe
|
71ead88bce
|
fix(logging): move module-level initialization to explicit setup calls (#3874)
- Moved environment variable parsing and `setup_logging()` call from module level to proper initialization points - Added explicit `setup_logging()` calls in `server.py::create_app()` and `library_client.py::AsyncLlamaStackAsLibraryClient.__init__()` Module-level side effects are bad practice and can cause issues with import order, testing, and circular dependencies. The previous implementation ran logging setup on every import of the log module, which is unpredictable and difficult to control. --------- Co-authored-by: Claude <noreply@anthropic.com> |
||
|
Ashwin Bharambe
|
0e96279bee
|
chore(cleanup)!: remove tool_runtime.rag_tool (#3871)
Kill the `builtin::rag` tool group completely since it is no longer targeted. We use the Responses implementation for knowledge_search which uses the `openai_vector_stores` pathway. --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> |
||
|
Ashwin Bharambe
|
122de785c4
|
chore(cleanup)!: kill vector_db references as far as possible (#3864)
There should not be "vector db" anywhere. |
||
|
ehhuang
|
444f6c88f3
|
chore: remove build.py (#3869)
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
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 6s
Vector IO Integration Tests / test-matrix (push) Failing after 4s
Python Package Build Test / build (3.13) (push) Failing after 1s
Test Llama Stack Build / generate-matrix (push) Successful in 5s
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 3s
Test Llama Stack Build / build-custom-container-distribution (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
Test llama stack list-deps / list-deps-from-config (push) Failing after 3s
API Conformance Tests / check-schema-compatibility (push) Successful in 11s
Test External API and Providers / test-external (venv) (push) Failing after 4s
Unit Tests / unit-tests (3.12) (push) Failing after 4s
Test Llama Stack Build / build (push) Failing after 3s
Unit Tests / unit-tests (3.13) (push) Failing after 4s
Python Package Build Test / build (3.12) (push) Failing after 20s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 23s
Test llama stack list-deps / list-deps (push) Failing after 18s
UI Tests / ui-tests (22) (push) Successful in 57s
Pre-commit / pre-commit (push) Successful in 1m52s
# What does this PR do? ## Test Plan CI |
||
|
ehhuang
|
ffeb86385c
|
chore: fix main (#3868)
# What does this PR do? dup entry was added for some reason ## Test Plan |
||
|
ehhuang
|
b215eb5944
|
chore: skip shutdown if otel_endpoint is not set (#3865)
# What does this PR do? rid following error when ctrl+c'd server │ /Users/erichuang/projects/lst3/llama_stack/providers/inline/telemetry/meta_reference/telemetry.py:92 in │ │ shutdown │ │ │ │ 89 │ │ pass │ │ 90 │ │ │ 91 │ async def shutdown(self) -> None: │ │ ❱ 92 │ │ trace.get_tracer_provider().force_flush() │ │ 93 │ │ │ 94 │ async def log_event(self, event: Event, ttl_seconds: int = 604800) -> None: │ │ 95 │ │ if isinstance(event, UnstructuredLogEvent): │ ╰─────────────────────────────────────────────────────────────────────────────────────────────────────────────╯ AttributeError: 'ProxyTracerProvider' object has no attribute 'force_flush' ## Test Plan |
||
|
dependabot[bot]
|
d9274d199e
|
chore(ui-deps): bump @types/node from 24.3.0 to 24.8.1 in /llama_stack/ui (#3851)
Bumps [@types/node](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/node) from 24.3.0 to 24.8.1. <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]
|
ec364499f5
|
chore(ui-deps): bump @tailwindcss/postcss from 4.1.6 to 4.1.14 in /llama_stack/ui (#3850)
Bumps [@tailwindcss/postcss](https://github.com/tailwindlabs/tailwindcss/tree/HEAD/packages/@tailwindcss-postcss) from 4.1.6 to 4.1.14. <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>v4.1.14</h2> <h3>Fixed</h3> <ul> <li>Handle <code>'</code> syntax in ClojureScript when extracting classes (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18888">#18888</a>)</li> <li>Handle <code>@variant</code> inside <code>@custom-variant</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18885">#18885</a>)</li> <li>Merge suggestions when using <code>@utility</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18900">#18900</a>)</li> <li>Ensure that file system watchers created when using the CLI are always cleaned up (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18905">#18905</a>)</li> <li>Do not generate <code>grid-column</code> utilities when configuring <code>grid-column-start</code> or <code>grid-column-end</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18907">#18907</a>)</li> <li>Do not generate <code>grid-row</code> utilities when configuring <code>grid-row-start</code> or <code>grid-row-end</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18907">#18907</a>)</li> <li>Prevent duplicate CSS when overwriting a static utility with a theme key (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18056">#18056</a>)</li> <li>Show Lightning CSS warnings (if any) when optimizing/minifying (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18918">#18918</a>)</li> <li>Use <code>default</code> export condition for <code>@tailwindcss/vite</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18948">#18948</a>)</li> <li>Re-throw errors from PostCSS nodes (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18373">#18373</a>)</li> <li>Detect classes in markdown inline directives (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18967">#18967</a>)</li> <li>Ensure files with only <code>@theme</code> produce no output when built (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18979">#18979</a>)</li> <li>Support Maud templates when extracting classes (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18988">#18988</a>)</li> <li>Upgrade: Do not migrate <code>variant = 'outline'</code> during upgrades (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18922">#18922</a>)</li> <li>Upgrade: Show version mismatch (if any) when running upgrade tool (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19028">#19028</a>)</li> <li>Upgrade: Ensure first class inside <code>className</code> is migrated (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19031">#19031</a>)</li> <li>Upgrade: Migrate classes inside <code>*ClassName</code> and <code>*Class</code> attributes (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19031">#19031</a>)</li> </ul> <h2>v4.1.13</h2> <h3>Changed</h3> <ul> <li>Drop warning from browser build (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/issues/18731">#18731</a>)</li> <li>Drop exact duplicate declarations when emitting CSS (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/issues/18809">#18809</a>)</li> </ul> <h3>Fixed</h3> <ul> <li>Don't transition <code>visibility</code> when using <code>transition</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18795">#18795</a>)</li> <li>Discard matched variants with unknown named values (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18799">#18799</a>)</li> <li>Discard matched variants with non-string values (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18799">#18799</a>)</li> <li>Show suggestions for known <code>matchVariant</code> values (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18798">#18798</a>)</li> <li>Replace deprecated <code>clip</code> with <code>clip-path</code> in <code>sr-only</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18769">#18769</a>)</li> <li>Hide internal fields from completions in <code>matchUtilities</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18820">#18820</a>)</li> <li>Ignore <code>.vercel</code> folders by default (can be overridden by <code>@source …</code> rules) (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18855">#18855</a>)</li> <li>Consider variants starting with <code>@-</code> to be invalid (e.g. <code>@-2xl:flex</code>) (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18869">#18869</a>)</li> <li>Do not allow custom variants to start or end with a <code>-</code> or <code>_</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18867">#18867</a>, <a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18872">#18872</a>)</li> <li>Upgrade: Migrate <code>aria</code> theme keys to <code>@custom-variant</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18815">#18815</a>)</li> <li>Upgrade: Migrate <code>data</code> theme keys to <code>@custom-variant</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18816">#18816</a>)</li> <li>Upgrade: Migrate <code>supports</code> theme keys to <code>@custom-variant</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18817">#18817</a>)</li> </ul> <h2>v4.1.12</h2> <h3>Fixed</h3> <ul> <li>Don't consider the global important state in <code>@apply</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18404">#18404</a>)</li> <li>Add missing suggestions for <code>flex-<number></code> utilities (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18642">#18642</a>)</li> <li>Fix trailing <code>)</code> from interfering with extraction in Clojure keywords (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18345">#18345</a>)</li> <li>Detect classes inside Elixir charlist, word list, and string sigils (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18432">#18432</a>)</li> <li>Track source locations through <code>@plugin</code> and <code>@config</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18345">#18345</a>)</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </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>[4.1.14] - 2025-10-01</h2> <h3>Fixed</h3> <ul> <li>Handle <code>'</code> syntax in ClojureScript when extracting classes (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18888">#18888</a>)</li> <li>Handle <code>@variant</code> inside <code>@custom-variant</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18885">#18885</a>)</li> <li>Merge suggestions when using <code>@utility</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18900">#18900</a>)</li> <li>Ensure that file system watchers created when using the CLI are always cleaned up (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18905">#18905</a>)</li> <li>Do not generate <code>grid-column</code> utilities when configuring <code>grid-column-start</code> or <code>grid-column-end</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18907">#18907</a>)</li> <li>Do not generate <code>grid-row</code> utilities when configuring <code>grid-row-start</code> or <code>grid-row-end</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18907">#18907</a>)</li> <li>Prevent duplicate CSS when overwriting a static utility with a theme key (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18056">#18056</a>)</li> <li>Show Lightning CSS warnings (if any) when optimizing/minifying (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18918">#18918</a>)</li> <li>Use <code>default</code> export condition for <code>@tailwindcss/vite</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18948">#18948</a>)</li> <li>Re-throw errors from PostCSS nodes (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18373">#18373</a>)</li> <li>Detect classes in markdown inline directives (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18967">#18967</a>)</li> <li>Ensure files with only <code>@theme</code> produce no output when built (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18979">#18979</a>)</li> <li>Support Maud templates when extracting classes (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18988">#18988</a>)</li> <li>Upgrade: Do not migrate <code>variant = 'outline'</code> during upgrades (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18922">#18922</a>)</li> <li>Upgrade: Show version mismatch (if any) when running upgrade tool (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19028">#19028</a>)</li> <li>Upgrade: Ensure first class inside <code>className</code> is migrated (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19031">#19031</a>)</li> <li>Upgrade: Migrate classes inside <code>*ClassName</code> and <code>*Class</code> attributes (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/19031">#19031</a>)</li> </ul> <h2>[4.1.13] - 2025-09-03</h2> <h3>Changed</h3> <ul> <li>Drop warning from browser build (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/issues/18731">#18731</a>)</li> <li>Drop exact duplicate declarations when emitting CSS (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/issues/18809">#18809</a>)</li> </ul> <h3>Fixed</h3> <ul> <li>Don't transition <code>visibility</code> when using <code>transition</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18795">#18795</a>)</li> <li>Discard matched variants with unknown named values (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18799">#18799</a>)</li> <li>Discard matched variants with non-string values (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18799">#18799</a>)</li> <li>Show suggestions for known <code>matchVariant</code> values (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18798">#18798</a>)</li> <li>Replace deprecated <code>clip</code> with <code>clip-path</code> in <code>sr-only</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18769">#18769</a>)</li> <li>Hide internal fields from completions in <code>matchUtilities</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18820">#18820</a>)</li> <li>Ignore <code>.vercel</code> folders by default (can be overridden by <code>@source …</code> rules) (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18855">#18855</a>)</li> <li>Consider variants starting with <code>@-</code> to be invalid (e.g. <code>@-2xl:flex</code>) (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18869">#18869</a>)</li> <li>Do not allow custom variants to start or end with a <code>-</code> or <code>_</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18867">#18867</a>, <a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18872">#18872</a>)</li> <li>Upgrade: Migrate <code>aria</code> theme keys to <code>@custom-variant</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18815">#18815</a>)</li> <li>Upgrade: Migrate <code>data</code> theme keys to <code>@custom-variant</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18816">#18816</a>)</li> <li>Upgrade: Migrate <code>supports</code> theme keys to <code>@custom-variant</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18817">#18817</a>)</li> </ul> <h2>[4.1.12] - 2025-08-13</h2> <h3>Fixed</h3> <ul> <li>Don't consider the global important state in <code>@apply</code> (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18404">#18404</a>)</li> <li>Add missing suggestions for <code>flex-<number></code> utilities (<a href="https://redirect.github.com/tailwindlabs/tailwindcss/pull/18642">#18642</a>)</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
ehhuang
|
5678c25b9d
|
chore: remove dead code (#3863)
# What does this PR do? ## Test Plan |
||
|
Ashwin Bharambe
|
94faec7bc5
|
chore(yaml)!: move registered resources to a sub-key (#3861)
**NOTE: this is a backwards incompatible change to the run-configs.** A small QOL update, but this will prove useful when I do a rename for "vector_dbs" to "vector_stores" next. Moves all the `models, shields, ...` keys in run-config under a `registered_resources` sub-key. |
||
Francisco Arceo
|
48581bf651
|
chore: Updating how default embedding model is set in stack (#3818)
# What does this PR do?
Refactor setting default vector store provider and embedding model to
use an optional `vector_stores` config in the `StackRunConfig` and clean
up code to do so (had to add back in some pieces of VectorDB). Also
added remote Qdrant and Weaviate to starter distro (based on other PR
where inference providers were added for UX).
New config is simply (default for Starter distro):
```yaml
vector_stores:
default_provider_id: faiss
default_embedding_model:
provider_id: sentence-transformers
model_id: nomic-ai/nomic-embed-text-v1.5
```
## Test Plan
CI and Unit tests.
---------
Signed-off-by: Francisco Javier Arceo <farceo@redhat.com>
Co-authored-by: Ashwin Bharambe <ashwin.bharambe@gmail.com>
|
||
|
Ashwin Bharambe
|
2c43285e22
|
feat(stores)!: use backend storage references instead of configs (#3697)
**This PR changes configurations in a backward incompatible way.**
Run configs today repeat full SQLite/Postgres snippets everywhere a
store is needed, which means duplicated credentials, extra connection
pools, and lots of drift between files. This PR introduces named storage
backends so the stack and providers can share a single catalog and
reference those backends by name.
## Key Changes
- Add `storage.backends` to `StackRunConfig`, register each KV/SQL
backend once at startup, and validate that references point to the right
family.
- Move server stores under `storage.stores` with lightweight references
(backend + namespace/table) instead of full configs.
- Update every provider/config/doc to use the new reference style;
docs/codegen now surface the simplified YAML.
## Migration
Before:
```yaml
metadata_store:
type: sqlite
db_path: ~/.llama/distributions/foo/registry.db
inference_store:
type: postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
conversations_store:
type: postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
```
After:
```yaml
storage:
backends:
kv_default:
type: kv_sqlite
db_path: ~/.llama/distributions/foo/kvstore.db
sql_default:
type: sql_postgres
host: ${env.POSTGRES_HOST}
port: ${env.POSTGRES_PORT}
db: ${env.POSTGRES_DB}
user: ${env.POSTGRES_USER}
password: ${env.POSTGRES_PASSWORD}
stores:
metadata:
backend: kv_default
namespace: registry
inference:
backend: sql_default
table_name: inference_store
max_write_queue_size: 10000
num_writers: 4
conversations:
backend: sql_default
table_name: openai_conversations
```
Provider configs follow the same pattern—for example, a Chroma vector
adapter switches from:
```yaml
providers:
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL}
kvstore:
type: sqlite
db_path: ~/.llama/distributions/foo/chroma.db
```
to:
```yaml
providers:
vector_io:
- provider_id: chromadb
provider_type: remote::chromadb
config:
url: ${env.CHROMADB_URL}
persistence:
backend: kv_default
namespace: vector_io::chroma_remote
```
Once the backends are declared, everything else just points at them, so
rotating credentials or swapping to Postgres happens in one place and
the stack reuses a single connection pool.
|
||
Shabana Baig
|
add64e8e2a
|
feat: Add instructions parameter in response object (#3741)
# Problem The current inline provider appends the user provided instructions to messages as a system prompt, but the returned response object does not contain the instructions field (as specified in the OpenAI responses spec). # What does this PR do? This pull request adds the instruction field to the response object definition and updates the inline provider. It also ensures that instructions from previous response is not carried over to the next response (as specified in the openAI spec). Closes #[3566](https://github.com/llamastack/llama-stack/issues/3566) ## Test Plan - Tested manually for change in model response w.r.t supplied instructions field. - Added unit test to check that the instructions from previous response is not carried over to the next response. - Added integration tests to check instructions parameter in the returned response object. - Added new recordings for the integration tests. --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> |
||
Derek Higgins
|
1f38359d95
|
fix: nested claims mapping in OAuth2 token validation (#3814)
fix: nested claims mapping in OAuth2 token validation
The get_attributes_from_claims function was only checking for top-level
claim keys, causing token validation to fail when using nested claims
like "resource_access.llamastack.roles" (common in Keycloak JWT tokens).
Updated the function to support dot notation for traversing nested claim
structures. Give precedence to dot notation over literal keys with dots
in claims mapping.
Added test coverage.
Closes: #3812
Signed-off-by: Derek Higgins <derekh@redhat.com>
|
||
|
ehhuang
|
9936f33f7e
|
chore: disable telemetry if otel endpoint isn't set (#3859)
# What does this PR do?
removes error:
ConnectionError: HTTPConnectionPool(host='localhost', port=4318): Max
retries exceeded with url: /v1/traces
(Caused by NewConnectionError('<urllib3.connection.HTTPConnection object
at 0x10fd98e60>: Failed to establish a
new connection: [Errno 61] Connection refused'))
## Test Plan
uv run llama stack run starter
curl http://localhost:8321/v1/models
observe no error in server logs
|
||
|
ehhuang
|
359df3a37c
|
chore: update doc (#3857)
# What does this PR do? follows https://github.com/llamastack/llama-stack/pull/3839 ## Test Plan |
||
|
Jiayi Ni
|
165b8b07f4
|
docs: Documentation update for NVIDIA Inference Provider (#3840)
# What does this PR do? <!-- Provide a short summary of what this PR does and why. Link to relevant issues if applicable. --> <!-- If resolving an issue, uncomment and update the line below --> <!-- Closes #[issue-number] --> - Fix examples in the NVIDIA inference documentation to align with current API requirements. ## 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.* --> N/A |
||
|
dependabot[bot]
|
f675fdda0f
|
chore(ui-deps): bump jest and @types/jest in /llama_stack/ui (#3853)
Some checks failed
SqlStore Integration Tests / test-postgres (3.12) (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 2s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 7s
Python Package Build Test / build (3.12) (push) Failing after 8s
Unit Tests / unit-tests (3.13) (push) Failing after 7s
Unit Tests / unit-tests (3.12) (push) Failing after 9s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 32s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 33s
Test External API and Providers / test-external (venv) (push) Failing after 45s
Vector IO Integration Tests / test-matrix (push) Failing after 47s
API Conformance Tests / check-schema-compatibility (push) Successful in 55s
UI Tests / ui-tests (22) (push) Successful in 2m14s
Pre-commit / pre-commit (push) Successful in 3m28s
Bumps [jest](https://github.com/jestjs/jest/tree/HEAD/packages/jest) and [@types/jest](https://github.com/DefinitelyTyped/DefinitelyTyped/tree/HEAD/types/jest). These dependencies needed to be updated together. Updates `jest` from 29.7.0 to 30.2.0 <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/jestjs/jest/releases">jest's releases</a>.</em></p> <blockquote> <h2>30.2.0</h2> <h3>Chore & Maintenance</h3> <ul> <li><code>[*]</code> Update example repo for testing React Native projects (<a href="https://redirect.github.com/jestjs/jest/pull/15832">#15832</a>)</li> <li><code>[*]</code> Update <code>jest-watch-typeahead</code> to v3 (<a href="https://redirect.github.com/jestjs/jest/pull/15830">#15830</a>)</li> </ul> <h2>Features</h2> <ul> <li><code>[jest-environment-jsdom-abstract]</code> Add support for JSDOM v27 (<a href="https://redirect.github.com/jestjs/jest/pull/15834">#15834</a>)</li> </ul> <h3>Fixes</h3> <ul> <li><code>[babel-jest]</code> Export the <code>TransformerConfig</code> interface (<a href="https://redirect.github.com/jestjs/jest/pull/15820">#15820</a>)</li> <li><code>[jest-config]</code> Fix <code>jest.config.ts</code> with TS loader specified in docblock pragma (<a href="https://redirect.github.com/jestjs/jest/pull/15839">#15839</a>)</li> </ul> <h2>30.1.3</h2> <h3>Fixes</h3> <ul> <li>Fix <code>unstable_mockModule</code> with <code>node:</code> prefixed core modules.</li> </ul> <h2>30.1.2</h2> <h3>Fixes</h3> <ul> <li><code>[jest-snapshot-utils]</code> Correct snapshot header regexp to work with newline across OSes (<a href="https://redirect.github.com/jestjs/jest/pull/15803">#15803</a>)</li> </ul> <h2>30.1.1</h2> <h3>Fixes</h3> <ul> <li><code>[jest-snapshot-utils]</code> Fix deprecated goo.gl snapshot warning not handling Windows end-of-line sequences (<a href="https://redirect.github.com/jestjs/jest/pull/15800">#15800</a>)</li> </ul> <h2>30.1.0</h2> <h2>Features</h2> <ul> <li><code>[jest-leak-detector]</code> Configurable GC aggressiveness regarding to V8 heap snapshot generation (<a href="https://redirect.github.com/jestjs/jest/pull/15793/">#15793</a>)</li> <li><code>[jest-runtime]</code> Reduce redundant ReferenceError messages</li> <li><code>[jest-core]</code> Include test modules that failed to load when --onlyFailures is active</li> </ul> <h3>Fixes</h3> <ul> <li>`[jest-snapshot-utils] Fix deprecated goo.gl snapshot guide link not getting replaced with fully canonical URL (<a href="https://redirect.github.com/jestjs/jest/pull/15787">#15787</a>)</li> <li><code>[jest-circus]</code> Fix <code>it.concurrent</code> not working with <code>describe.skip</code> (<a href="https://redirect.github.com/jestjs/jest/pull/15765">#15765</a>)</li> <li><code>[jest-snapshot]</code> Fix mangled inline snapshot updates when used with Prettier 3 and CRLF line endings</li> <li><code>[jest-runtime]</code> Importing from <code>@jest/globals</code> in more than one file no longer breaks relative paths (<a href="https://redirect.github.com/jestjs/jest/issues/15772">#15772</a>)</li> </ul> <h1>Chore</h1> <ul> <li><code>[expect]</code> Update docblock for <code>toContain()</code> to display info on substring check (<a href="https://redirect.github.com/jestjs/jest/pull/15789">#15789</a>)</li> </ul> <h2>30.0.2</h2> <h2>What's Changed</h2> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Changelog</summary> <p><em>Sourced from <a href="https://github.com/jestjs/jest/blob/main/CHANGELOG.md">jest's changelog</a>.</em></p> <blockquote> <h2>30.2.0</h2> <h3>Chore & Maintenance</h3> <ul> <li><code>[*]</code> Update example repo for testing React Native projects (<a href="https://redirect.github.com/jestjs/jest/pull/15832">#15832</a>)</li> <li><code>[*]</code> Update <code>jest-watch-typeahead</code> to v3 (<a href="https://redirect.github.com/jestjs/jest/pull/15830">#15830</a>)</li> </ul> <h2>Features</h2> <ul> <li><code>[jest-environment-jsdom-abstract]</code> Add support for JSDOM v27 (<a href="https://redirect.github.com/jestjs/jest/pull/15834">#15834</a>)</li> </ul> <h3>Fixes</h3> <ul> <li><code>[jest-matcher-utils]</code> Fix infinite recursion with self-referential getters in <code>deepCyclicCopyReplaceable</code> (<a href="https://redirect.github.com/jestjs/jest/pull/15831">#15831</a>)</li> <li><code>[babel-jest]</code> Export the <code>TransformerConfig</code> interface (<a href="https://redirect.github.com/jestjs/jest/pull/15820">#15820</a>)</li> <li><code>[jest-config]</code> Fix <code>jest.config.ts</code> with TS loader specified in docblock pragma (<a href="https://redirect.github.com/jestjs/jest/pull/15839">#15839</a>)</li> </ul> <h2>30.1.3</h2> <h3>Fixes</h3> <ul> <li>Fix <code>unstable_mockModule</code> with <code>node:</code> prefixed core modules.</li> </ul> <h2>30.1.2</h2> <h3>Fixes</h3> <ul> <li><code>[jest-snapshot-utils]</code> Correct snapshot header regexp to work with newline across OSes (<a href="https://redirect.github.com/jestjs/jest/pull/15803">#15803</a>)</li> </ul> <h2>30.1.1</h2> <h3>Fixes</h3> <ul> <li><code>[jest-snapshot-utils]</code> Fix deprecated goo.gl snapshot warning not handling Windows end-of-line sequences (<a href="https://redirect.github.com/jestjs/jest/pull/15800">#15800</a>)</li> <li><code>[jest-snapshot-utils]</code> Improve messaging about goo.gl snapshot link change (<a href="https://redirect.github.com/jestjs/jest/pull/15821">#15821</a>)</li> </ul> <h2>30.1.0</h2> <h2>Features</h2> <ul> <li><code>[jest-leak-detector]</code> Configurable GC aggressiveness regarding to V8 heap snapshot generation (<a href="https://redirect.github.com/jestjs/jest/pull/15793/">#15793</a>)</li> <li><code>[jest-runtime]</code> Reduce redundant ReferenceError messages</li> <li><code>[jest-core]</code> Include test modules that failed to load when --onlyFailures is active</li> </ul> <h3>Fixes</h3> <ul> <li><code>[jest-snapshot-utils]</code> Fix deprecated goo.gl snapshot guide link not getting replaced with fully canonical URL (<a href="https://redirect.github.com/jestjs/jest/pull/15787">#15787</a>)</li> <li><code>[jest-circus]</code> Fix <code>it.concurrent</code> not working with <code>describe.skip</code> (<a href="https://redirect.github.com/jestjs/jest/pull/15765">#15765</a>)</li> <li><code>[jest-snapshot]</code> Fix mangled inline snapshot updates when used with Prettier 3 and CRLF line endings</li> <li><code>[jest-runtime]</code> Importing from <code>@jest/globals</code> in more than one file no longer breaks relative paths (<a href="https://redirect.github.com/jestjs/jest/issues/15772">#15772</a>)</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
|
dependabot[bot]
|
7a256895aa
|
chore(ui-deps): bump jest-environment-jsdom from 30.1.2 to 30.2.0 in /llama_stack/ui (#3852)
Bumps
[jest-environment-jsdom](https://github.com/jestjs/jest/tree/HEAD/packages/jest-environment-jsdom)
from 30.1.2 to 30.2.0.
<details>
<summary>Release notes</summary>
<p><em>Sourced from <a
href="https://github.com/jestjs/jest/releases">jest-environment-jsdom's
releases</a>.</em></p>
<blockquote>
<h2>30.2.0</h2>
<h3>Chore & Maintenance</h3>
<ul>
<li><code>[*]</code> Update example repo for testing React Native
projects (<a
href="https://redirect.github.com/jestjs/jest/pull/15832">#15832</a>)</li>
<li><code>[*]</code> Update <code>jest-watch-typeahead</code> to v3 (<a
href="https://redirect.github.com/jestjs/jest/pull/15830">#15830</a>)</li>
</ul>
<h2>Features</h2>
<ul>
<li><code>[jest-environment-jsdom-abstract]</code> Add support for JSDOM
v27 (<a
href="https://redirect.github.com/jestjs/jest/pull/15834">#15834</a>)</li>
</ul>
<h3>Fixes</h3>
<ul>
<li><code>[babel-jest]</code> Export the <code>TransformerConfig</code>
interface (<a
href="https://redirect.github.com/jestjs/jest/pull/15820">#15820</a>)</li>
<li><code>[jest-config]</code> Fix <code>jest.config.ts</code> with TS
loader specified in docblock pragma (<a
href="https://redirect.github.com/jestjs/jest/pull/15839">#15839</a>)</li>
</ul>
<h2>30.1.3</h2>
<h3>Fixes</h3>
<ul>
<li>Fix <code>unstable_mockModule</code> with <code>node:</code>
prefixed core modules.</li>
</ul>
</blockquote>
</details>
<details>
<summary>Changelog</summary>
<p><em>Sourced from <a
href="https://github.com/jestjs/jest/blob/main/CHANGELOG.md">jest-environment-jsdom's
changelog</a>.</em></p>
<blockquote>
<h2>30.2.0</h2>
<h3>Chore & Maintenance</h3>
<ul>
<li><code>[*]</code> Update example repo for testing React Native
projects (<a
href="https://redirect.github.com/jestjs/jest/pull/15832">#15832</a>)</li>
<li><code>[*]</code> Update <code>jest-watch-typeahead</code> to v3 (<a
href="https://redirect.github.com/jestjs/jest/pull/15830">#15830</a>)</li>
</ul>
<h2>Features</h2>
<ul>
<li><code>[jest-environment-jsdom-abstract]</code> Add support for JSDOM
v27 (<a
href="https://redirect.github.com/jestjs/jest/pull/15834">#15834</a>)</li>
</ul>
<h3>Fixes</h3>
<ul>
<li><code>[jest-matcher-utils]</code> Fix infinite recursion with
self-referential getters in <code>deepCyclicCopyReplaceable</code> (<a
href="https://redirect.github.com/jestjs/jest/pull/15831">#15831</a>)</li>
<li><code>[babel-jest]</code> Export the <code>TransformerConfig</code>
interface (<a
href="https://redirect.github.com/jestjs/jest/pull/15820">#15820</a>)</li>
<li><code>[jest-config]</code> Fix <code>jest.config.ts</code> with TS
loader specified in docblock pragma (<a
href="https://redirect.github.com/jestjs/jest/pull/15839">#15839</a>)</li>
</ul>
<h2>30.1.3</h2>
<h3>Fixes</h3>
<ul>
<li>Fix <code>unstable_mockModule</code> with <code>node:</code>
prefixed core modules.</li>
</ul>
</blockquote>
</details>
<details>
<summary>Commits</summary>
<ul>
<li><a
href="
|
||
|
dependabot[bot]
|
83d2193077
|
chore(ui-deps): bump eslint-config-next from 15.5.2 to 15.5.6 in /llama_stack/ui (#3849)
Bumps [eslint-config-next](https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next) from 15.5.2 to 15.5.6. <details> <summary>Release notes</summary> <p><em>Sourced from <a href="https://github.com/vercel/next.js/releases">eslint-config-next's releases</a>.</em></p> <blockquote> <h2>v15.5.6</h2> <blockquote> <p>[!NOTE]<br /> This release is backporting bug fixes. It does <strong>not</strong> include all pending features/changes on canary.</p> </blockquote> <h3>Core Changes</h3> <ul> <li>Turbopack: don't define process.cwd() in node_modules <a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/83452">#83452</a></li> </ul> <h3>Credits</h3> <p>Huge thanks to <a href="https://github.com/mischnic"><code>@mischnic</code></a> for helping!</p> <h2>v15.5.5</h2> <blockquote> <p>[!NOTE]<br /> This release is backporting bug fixes. It does <strong>not</strong> include all pending features/changes on canary.</p> </blockquote> <h3>Core Changes</h3> <ul> <li>Split code-frame into separate compiled package (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/84238">#84238</a>)</li> <li>Add deprecation warning to Runtime config (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/84650">#84650</a>)</li> <li>fix: unstable_cache should perform blocking revalidation during ISR revalidation (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/84716">#84716</a>)</li> <li>feat: <code>experimental.middlewareClientMaxBodySize</code> body cloning limit (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/84722">#84722</a>)</li> <li>fix: missing next/link types with typedRoutes (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/84779">#84779</a>)</li> </ul> <h3>Misc Changes</h3> <ul> <li>docs: early October improvements and fixes (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/84334">#84334</a>)</li> </ul> <h3>Credits</h3> <p>Huge thanks to <a href="https://github.com/devjiwonchoi"><code>@devjiwonchoi</code></a>, <a href="https://github.com/ztanner"><code>@ztanner</code></a>, and <a href="https://github.com/icyJoseph"><code>@icyJoseph</code></a> for helping!</p> <h2>v15.5.4</h2> <blockquote> <p>[!NOTE]<br /> This release is backporting bug fixes. It does <strong>not</strong> include all pending features/changes on canary.</p> </blockquote> <h3>Core Changes</h3> <ul> <li>fix: ensure onRequestError is invoked when otel enabled (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/83343">#83343</a>)</li> <li>fix: devtools initial position should be from next config (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/83571">#83571</a>)</li> <li>[devtool] fix overlay styles are missing (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/83721">#83721</a>)</li> <li>Turbopack: don't match dynamic pattern for node_modules packages (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/83176">#83176</a>)</li> <li>Turbopack: don't treat metadata routes as RSC (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/82911">#82911</a>)</li> <li>[turbopack] Improve handling of symlink resolution errors in track_glob and read_glob (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/83357">#83357</a>)</li> <li>Turbopack: throw large static metadata error earlier (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/82939">#82939</a>)</li> <li>fix: error overlay not closing when backdrop clicked (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/83981">#83981</a>)</li> <li>Turbopack: flush Node.js worker IPC on error (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/84077">#84077</a>)</li> </ul> <h3>Misc Changes</h3> <ul> <li>[CNA] use linter preference (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/83194">#83194</a>)</li> <li>CI: use KV for test timing data (<a href="https://github.com/vercel/next.js/tree/HEAD/packages/eslint-config-next/issues/83745">#83745</a>)</li> </ul> <!-- raw HTML omitted --> </blockquote> <p>... (truncated)</p> </details> <details> <summary>Commits</summary> <ul> <li><a href=" |
||
Charlie Doern
|
b11bcfde11
|
refactor(build): rework CLI commands and build process (1/2) (#2974)
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 Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
Test Llama Stack Build / generate-matrix (push) Successful in 22s
Test llama stack list-deps / show-single-provider (push) Failing after 53s
Test Llama Stack Build / build-single-provider (push) Failing after 3s
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 18s
Python Package Build Test / build (3.13) (push) Failing after 24s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 26s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 27s
Unit Tests / unit-tests (3.12) (push) Failing after 26s
Vector IO Integration Tests / test-matrix (push) Failing after 44s
API Conformance Tests / check-schema-compatibility (push) Successful in 52s
Test llama stack list-deps / generate-matrix (push) Successful in 52s
Test Llama Stack Build / build (push) Failing after 29s
Test External API and Providers / test-external (venv) (push) Failing after 53s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 1m2s
Unit Tests / unit-tests (3.13) (push) Failing after 1m30s
Test llama stack list-deps / list-deps-from-config (push) Failing after 1m59s
Test llama stack list-deps / list-deps (push) Failing after 1m10s
UI Tests / ui-tests (22) (push) Successful in 2m26s
Pre-commit / pre-commit (push) Successful in 3m8s
# What does this PR do? This PR does a few things outlined in #2878 namely: 1. adds `llama stack list-deps` a command which simply takes the build logic and instead of executing one of the `build_...` scripts, it displays all of the providers' dependencies using the `module` and `uv`. 2. deprecated `llama stack build` in favor of `llama stack list-deps` 3. updates all tests to use `list-deps` alongside `build`. PR 2/2 will migrate `llama stack run`'s default behavior to be `llama stack build --run` and use the new `list-deps` command under the hood before running the server. examples of `llama stack list-deps starter` ``` llama stack list-deps starter --format json { "name": "starter", "description": "Quick start template for running Llama Stack with several popular providers. This distribution is intended for CPU-only environments.", "apis": [ { "api": "inference", "provider": "remote::cerebras" }, { "api": "inference", "provider": "remote::ollama" }, { "api": "inference", "provider": "remote::vllm" }, { "api": "inference", "provider": "remote::tgi" }, { "api": "inference", "provider": "remote::fireworks" }, { "api": "inference", "provider": "remote::together" }, { "api": "inference", "provider": "remote::bedrock" }, { "api": "inference", "provider": "remote::nvidia" }, { "api": "inference", "provider": "remote::openai" }, { "api": "inference", "provider": "remote::anthropic" }, { "api": "inference", "provider": "remote::gemini" }, { "api": "inference", "provider": "remote::vertexai" }, { "api": "inference", "provider": "remote::groq" }, { "api": "inference", "provider": "remote::sambanova" }, { "api": "inference", "provider": "remote::azure" }, { "api": "inference", "provider": "inline::sentence-transformers" }, { "api": "vector_io", "provider": "inline::faiss" }, { "api": "vector_io", "provider": "inline::sqlite-vec" }, { "api": "vector_io", "provider": "inline::milvus" }, { "api": "vector_io", "provider": "remote::chromadb" }, { "api": "vector_io", "provider": "remote::pgvector" }, { "api": "files", "provider": "inline::localfs" }, { "api": "safety", "provider": "inline::llama-guard" }, { "api": "safety", "provider": "inline::code-scanner" }, { "api": "agents", "provider": "inline::meta-reference" }, { "api": "telemetry", "provider": "inline::meta-reference" }, { "api": "post_training", "provider": "inline::torchtune-cpu" }, { "api": "eval", "provider": "inline::meta-reference" }, { "api": "datasetio", "provider": "remote::huggingface" }, { "api": "datasetio", "provider": "inline::localfs" }, { "api": "scoring", "provider": "inline::basic" }, { "api": "scoring", "provider": "inline::llm-as-judge" }, { "api": "scoring", "provider": "inline::braintrust" }, { "api": "tool_runtime", "provider": "remote::brave-search" }, { "api": "tool_runtime", "provider": "remote::tavily-search" }, { "api": "tool_runtime", "provider": "inline::rag-runtime" }, { "api": "tool_runtime", "provider": "remote::model-context-protocol" }, { "api": "batches", "provider": "inline::reference" } ], "pip_dependencies": [ "pandas", "opentelemetry-exporter-otlp-proto-http", "matplotlib", "opentelemetry-sdk", "sentence-transformers", "datasets", "pymilvus[milvus-lite]>=2.4.10", "codeshield", "scipy", "torchvision", "tree_sitter", "h11>=0.16.0", "aiohttp", "pymongo", "tqdm", "pythainlp", "pillow", "torch", "emoji", "grpcio>=1.67.1,<1.71.0", "fireworks-ai", "langdetect", "psycopg2-binary", "asyncpg", "redis", "together", "torchao>=0.12.0", "openai", "sentencepiece", "aiosqlite", "google-cloud-aiplatform", "faiss-cpu", "numpy", "sqlite-vec", "nltk", "scikit-learn", "mcp>=1.8.1", "transformers", "boto3", "huggingface_hub", "ollama", "autoevals", "sqlalchemy[asyncio]", "torchtune>=0.5.0", "chromadb-client", "pypdf", "requests", "anthropic", "chardet", "aiosqlite", "fastapi", "fire", "httpx", "uvicorn", "opentelemetry-sdk", "opentelemetry-exporter-otlp-proto-http" ] } ``` <img width="1500" height="420" alt="Screenshot 2025-10-16 at 5 53 03 PM" src="https://github.com/user-attachments/assets/765929fb-93e2-44d7-9c3d-8918b70fc721" /> --------- Signed-off-by: Charlie Doern <cdoern@redhat.com> |
||
Emilio Garcia
|
943558af36
|
test(telemetry): Telemetry Tests (#3805)
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
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 10s
Python Package Build Test / build (3.13) (push) Failing after 10s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 14s
Unit Tests / unit-tests (3.13) (push) Failing after 11s
Integration Auth Tests / test-matrix (oauth2_token) (push) Failing after 20s
Unit Tests / unit-tests (3.12) (push) Failing after 16s
Test External API and Providers / test-external (venv) (push) Failing after 28s
Vector IO Integration Tests / test-matrix (push) Failing after 30s
API Conformance Tests / check-schema-compatibility (push) Successful in 38s
UI Tests / ui-tests (22) (push) Successful in 1m32s
Pre-commit / pre-commit (push) Successful in 3m16s
# What does this PR do? Adds a test and a standardized way to build future tests out for telemetry in llama stack. Contributes to https://github.com/llamastack/llama-stack/issues/3806 ## Test Plan This is the test plan 😎 |
||
Alexey Rybak
|
224c99560c
|
docs: update docstrings for better formatting (#3838)
# What does this PR do? Updates docstrings for Conversations and Eval APIs to render better in the docs nav sidebar. Before: <img width="363" height="233" alt="Screenshot 2025-10-17 at 9 52 17 AM" src="https://github.com/user-attachments/assets/3a77f9e3-3b03-43ae-8584-a21d1f44d54d" /> After: <img width="410" height="206" alt="Screenshot 2025-10-17 at 9 52 11 AM" src="https://github.com/user-attachments/assets/fa5d428d-2bde-4453-84fd-9aceebe712e8" /> ## Test Plan * Manual testing |
||
|
Ashwin Bharambe
|
cd152f4240
|
feat(ci): add support for docker:distro in tests (#3832)
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
SqlStore Integration Tests / test-postgres (3.12) (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 2s
Test Llama Stack Build / generate-matrix (push) Successful in 6s
Unit Tests / unit-tests (3.12) (push) Failing after 5s
Test Llama Stack Build / build-single-provider (push) Failing after 9s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 10s
Vector IO Integration Tests / test-matrix (push) Failing after 14s
Unit Tests / unit-tests (3.13) (push) Failing after 7s
Test External API and Providers / test-external (venv) (push) Failing after 12s
API Conformance Tests / check-schema-compatibility (push) Successful in 19s
Test Llama Stack Build / build (push) Failing after 7s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 26s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 25s
Python Package Build Test / build (3.12) (push) Failing after 33s
UI Tests / ui-tests (22) (push) Successful in 1m26s
Pre-commit / pre-commit (push) Successful in 2m18s
Also a critical bug fix so test recordings can be found inside docker |
||
|
ehhuang
|
b3099d40e2
|
fix(telemetry): remove dependency on old telemetry config (#3830)
Some checks failed
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.12) (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
Test Llama Stack Build / generate-matrix (push) Successful in 8s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 10s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 12s
Test Llama Stack Build / build-single-provider (push) Failing after 11s
Python Package Build Test / build (3.12) (push) Failing after 10s
Test External API and Providers / test-external (venv) (push) Failing after 11s
Python Package Build Test / build (3.13) (push) Failing after 13s
Unit Tests / unit-tests (3.13) (push) Failing after 14s
Test Llama Stack Build / build (push) Failing after 12s
Unit Tests / unit-tests (3.12) (push) Failing after 21s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 57s
Vector IO Integration Tests / test-matrix (push) Failing after 1m13s
API Conformance Tests / check-schema-compatibility (push) Successful in 1m22s
UI Tests / ui-tests (22) (push) Successful in 1m33s
Pre-commit / pre-commit (push) Successful in 1m55s
# What does this PR do? old telemetry config was removed in #3815 ## Test Plan ❯ OTEL_SERVICE_NAME=aloha OTEL_EXPORTER_OTLP_ENDPOINT=http://localhost:4318 uv run llama stack run starter <img width="1888" height="605" alt="image" src="https://github.com/user-attachments/assets/dd5cc9f0-213a-4dc6-9385-f61a3a13b4c3" /> |
||
|
ehhuang
|
07ff15d917
|
chore: distrogen enables telemetry by default (#3828)
# What does this PR do? leftover from #3815 ## Test Plan CI --- [//]: # (BEGIN SAPLING FOOTER) Stack created with [Sapling](https://sapling-scm.com). Best reviewed with [ReviewStack](https://reviewstack.dev/llamastack/llama-stack/pull/3828). * #3830 * __->__ #3828 |
||
|
Charlie Doern
|
f22aaef42f
|
chore!: remove telemetry API usage (#3815)
# What does this PR do? remove telemetry as a providable API from the codebase. This includes removing it from generated distributions but also the provider registry, the router, etc since `setup_logger` is tied pretty strictly to `Api.telemetry` being in impls we still need an "instantiated provider" in our implementations. However it should not be auto-routed or provided. So in validate_and_prepare_providers (called from resolve_impls) I made it so that if run_config.telemetry.enabled, we set up the meta-reference "provider" internally to be used so that log_event will work when called. This is the neatest way I think we can remove telemetry from the provider configs but also not need to rip apart the whole "telemetry is a provider" logic just yet, but we can do it internally later without disrupting users. so telemetry is removed from the registry such that if a user puts `telemetry:` as an API in their build/run config it will err out, but can still be used by us internally as we go through this transition. relates to #3806 Signed-off-by: Charlie Doern <cdoern@redhat.com> |
||
|
Ashwin Bharambe
|
185de61d8e
|
fix(openai_mixin): no yelling for model listing if API keys are not provided (#3826)
As indicated in the title. Our `starter` distribution enables all remote providers _very intentionally_ because we believe it creates an easier, more welcoming experience to new folks using the software. If we do that, and then slam the logs with errors making them question their life choices, it is not so good :) Note that this fix is limited in scope. If you ever try to actually instantiate the OpenAI client from a code path without an API key being present, you deserve to fail hard. ## Test Plan Run `llama stack run starter` with `OPENAI_API_KEY` set. No more wall of text, just one message saying "listed 96 models". |
||
|
Ashwin Bharambe
|
07fc8013eb
|
fix(tests): reduce some test noise (#3825)
a bunch of logger.info()s are good for server code to help debug in production, but we don't want them killing our unit test output :) --------- Co-authored-by: github-actions[bot] <github-actions[bot]@users.noreply.github.com> |
||
|
Ashwin Bharambe
|
f70aa99c97
|
fix(models)!: always prefix models with provider_id when registering (#3822)
**!!BREAKING CHANGE!!** The lookup is also straightforward -- we always look for this identifier and don't try to find a match for something without the provider_id prefix. Note that, this ideally means we need to update the `register_model()` API also (we should kill "identifier" from there) but I am not doing that as part of this PR. ## Test Plan Existing unit tests |
||
|
Ashwin Bharambe
|
f205ab6f6c
|
fix(responses): fixes, re-record tests (#3820)
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
Python Package Build Test / build (3.12) (push) Failing after 2s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 5s
Python Package Build Test / build (3.13) (push) Failing after 3s
SqlStore Integration Tests / test-postgres (3.12) (push) Failing after 8s
Vector IO Integration Tests / test-matrix (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 6s
Unit Tests / unit-tests (3.13) (push) Failing after 5s
API Conformance Tests / check-schema-compatibility (push) Successful in 17s
UI Tests / ui-tests (22) (push) Successful in 55s
Pre-commit / pre-commit (push) Successful in 1m43s
Wanted to re-enable Responses CI but it seems to hang for some reason due to some interactions with conversations_store or responses_store. ## Test Plan ``` # library client ./scripts/integration-tests.sh --stack-config ci-tests --suite responses # server ./scripts/integration-tests.sh --stack-config server:ci-tests --suite responses ``` |
||
|
slekkala1
|
99141c29b1
|
feat: Add responses and safety impl extra_body (#3781)
Some checks failed
SqlStore Integration Tests / test-postgres (3.13) (push) Failing after 0s
SqlStore Integration Tests / test-postgres (3.12) (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 (3.13) (push) Failing after 1s
Test Llama Stack Build / generate-matrix (push) Successful in 3s
Integration Tests (Replay) / Integration Tests (, , , client=, ) (push) Failing after 6s
Test Llama Stack Build / build-custom-container-distribution (push) Failing after 3s
Test Llama Stack Build / build-single-provider (push) Failing after 4s
Python Package Build Test / build (3.12) (push) Failing after 6s
Vector IO Integration Tests / test-matrix (push) Failing after 9s
Unit Tests / unit-tests (3.13) (push) Failing after 6s
Test Llama Stack Build / build-ubi9-container-distribution (push) Failing after 9s
Test External API and Providers / test-external (venv) (push) Failing after 8s
Test Llama Stack Build / build (push) Failing after 7s
Unit Tests / unit-tests (3.12) (push) Failing after 9s
API Conformance Tests / check-schema-compatibility (push) Successful in 19s
UI Tests / ui-tests (22) (push) Successful in 37s
Pre-commit / pre-commit (push) Successful in 1m33s
# What does this PR do? Have closed the previous PR due to merge conflicts with multiple PRs Addressed all comments from https://github.com/llamastack/llama-stack/pull/3768 (sorry for carrying over to this one) ## Test Plan Added UTs and integration tests |