LCORE-2309: Added Pydantic AI Bridge#1817
Conversation
WalkthroughA new module ChangesPydantic AI Llama Stack Integration Utilities
Estimated code review effort🎯 3 (Moderate) | ⏱️ ~25 minutes Possibly related PRs
Suggested reviewers
🚥 Pre-merge checks | ✅ 5✅ Passed checks (5 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. ✨ Finishing Touches🧪 Generate unit tests (beta)
✨ Simplify code
Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![github-advanced-security[bot]](https://avatars.githubusercontent.com/in/57789?s=60&v=4){kind=small}
jrobertboos
force-pushed
the
lcore-2309
branch
2 times, most recently
from
402b0f2 to
53e1b86
Compare
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 3
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/pydantic_ai_lightspeed/llamastack/_transport.py`:
- Around line 89-94: The header presence check treats names case-sensitively and
only checks two spellings, so normalize header names before deciding to inject
provider data: in the block that references self._client.provider_data and the
headers dict, compute a lowercase-key view (e.g., {k.lower(): v for k, v in
headers.items()} or use any(k.lower() == "x-llamastack-provider-data" for k in
headers)) and check for "x-llamastack-provider-data" in that normalized view;
only if absent, add the provider data using the canonical header
"X-LlamaStack-Provider-Data" to headers. Ensure you reference headers and
self._client.provider_data when applying the change.
- Around line 22-40: The _AsyncByteStream currently yields from the wrapped
async generator but doesn't forward closure; implement an async aclose(self) on
class _AsyncByteStream that calls and awaits self._gen.aclose() if the wrapped
generator has an aclose attribute to ensure httpx.Response.aclose() triggers
generator cleanup. In LlamaStackLibraryTransport.handle_async_request change the
provider-data header existence check to be case-insensitive (e.g., inspect
request.headers keys lowercased or use any(k.lower() ==
"x-llamastack-provider-data" for k in request.headers)) before injecting
"X-LlamaStack-Provider-Data" so you don't add a duplicate header when callers
use different casing.
In `@src/utils/pydantic_ai.py`:
- Around line 41-45: The helper _llama_stack_provider_from_client currently
reaches into AsyncLlamaStackClient._client (protected) when building a
LlamaStackProvider; change it to rely on the public HTTP-injection path instead:
update _llama_stack_provider_from_client to accept a public http_client
parameter (or obtain the client's configured http_client via its public API),
and pass that http_client into LlamaStackProvider(base_url=..., api_key=...,
http_client=...) rather than using client._client; ensure callers of
_llama_stack_provider_from_client are updated to provide the public http_client
argument.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: 2d1bdbfc-90ec-412a-b14c-474e9f95a843
⛔ Files ignored due to path filters (1)
uv.lockis excluded by!**/*.lock
📒 Files selected for processing (11)
pyproject.tomlsrc/pydantic_ai_lightspeed/__init__.pysrc/pydantic_ai_lightspeed/llamastack/__init__.pysrc/pydantic_ai_lightspeed/llamastack/_provider.pysrc/pydantic_ai_lightspeed/llamastack/_transport.pysrc/utils/pydantic_ai.pytests/unit/pydantic_ai_lightspeed/__init__.pytests/unit/pydantic_ai_lightspeed/llamastack/__init__.pytests/unit/pydantic_ai_lightspeed/llamastack/test_provider.pytests/unit/pydantic_ai_lightspeed/llamastack/test_transport.pytests/unit/utils/test_pydantic_ai.py
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (12)
- GitHub Check: Konflux kflux-prd-rh02 / lightspeed-stack-on-pull-request
- GitHub Check: unit_tests (3.13)
- GitHub Check: E2E Tests for Lightspeed Evaluation job
- GitHub Check: build-pr
- GitHub Check: list_outdated_dependencies
- GitHub Check: spectral
- GitHub Check: E2E: server mode / ci / group 2
- GitHub Check: E2E: library mode / ci / group 1
- GitHub Check: E2E: server mode / ci / group 3
- GitHub Check: E2E: server mode / ci / group 1
- GitHub Check: E2E: library mode / ci / group 2
- GitHub Check: E2E: library mode / ci / group 3
🧰 Additional context used
📓 Path-based instructions (3)
src/**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
src/**/*.py: Use absolute imports for internal modules:from authentication import get_auth_dependency
Llama Stack imports: Usefrom llama_stack_client import AsyncLlamaStackClient
Checkconstants.pyfor shared constants before defining new ones
All modules must start with descriptive docstrings explaining purpose
Uselogger = get_logger(__name__)fromlog.pyfor module logging
All functions must have complete type annotations for parameters and return types, use modern syntax (str | int), and include descriptive docstrings
Use snake_case with descriptive, action-oriented names for functions (get_, validate_, check_)
Avoid in-place parameter modification anti-patterns; return new data structures instead of modifying function parameters
Useasync deffor I/O operations and external API calls
Use standard log levels with clear purposes:debug()for diagnostic info,info()for program execution,warning()for unexpected events,error()for serious problems
All classes must have descriptive docstrings explaining purpose and use PascalCase with standard suffixes:Configuration,Error/Exception,Resolver,Interface
Abstract classes must use ABC with@abstractmethoddecorators
Follow Google Python docstring conventions with required sections: Parameters, Returns, Raises, and Attributes for classes
Files:
src/pydantic_ai_lightspeed/llamastack/__init__.pysrc/pydantic_ai_lightspeed/__init__.pysrc/utils/pydantic_ai.pysrc/pydantic_ai_lightspeed/llamastack/_provider.pysrc/pydantic_ai_lightspeed/llamastack/_transport.py
src/**/__init__.py
📄 CodeRabbit inference engine (AGENTS.md)
Package
__init__.pyfiles must contain brief package descriptions
Files:
src/pydantic_ai_lightspeed/llamastack/__init__.pysrc/pydantic_ai_lightspeed/__init__.py
tests/**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
tests/**/*.py: Use pytest for all unit and integration tests; do not use unittest
Usepytest.mark.asynciomarker for async tests
Files:
tests/unit/pydantic_ai_lightspeed/llamastack/__init__.pytests/unit/pydantic_ai_lightspeed/__init__.pytests/unit/pydantic_ai_lightspeed/llamastack/test_provider.pytests/unit/pydantic_ai_lightspeed/llamastack/test_transport.pytests/unit/utils/test_pydantic_ai.py
🔇 Additional comments (5)
pyproject.toml (1)
82-83: LGTM!src/pydantic_ai_lightspeed/__init__.py (1)
1-1: LGTM!src/pydantic_ai_lightspeed/llamastack/__init__.py (1)
1-6: LGTM!tests/unit/pydantic_ai_lightspeed/__init__.py (1)
1-1: LGTM!tests/unit/pydantic_ai_lightspeed/llamastack/__init__.py (1)
1-1: LGTM!
| lib_http_client = httpx.AsyncClient( | ||
| transport=transport, |
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Prompt for all review comments with AI agents
Verify each finding against current code. Fix only still-valid issues, skip the
rest with a brief reason, keep changes minimal, and validate.
Inline comments:
In `@src/utils/pydantic_ai.py`:
- Line 35: The single-line docstrings for _llama_stack_provider_from_client and
_model_settings_from_responses_params must be expanded to follow Google Python
docstring conventions: update each function to include Parameters (documenting
args such as client, responses_params, etc. with types and purpose), Returns
(describe the return type and what it represents), and Raises (list any
exceptions the function may raise); ensure the wording matches existing
parameter names and types used in those functions and keep the descriptions
concise and accurate so the new docstrings fully replace the current one-line
descriptions.
🪄 Autofix (Beta)
Fix all unresolved CodeRabbit comments on this PR:
- Push a commit to this branch (recommended)
- Create a new PR with the fixes
ℹ️ Review info
⚙️ Run configuration
Configuration used: Path: .coderabbit.yaml
Review profile: ASSERTIVE
Plan: Pro
Run ID: 31a18f2c-2ccf-4a87-951f-c7039dd5df7d
📒 Files selected for processing (2)
src/utils/pydantic_ai.pytests/unit/utils/test_pydantic_ai.py
📜 Review details
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (11)
- GitHub Check: shellcheck
- GitHub Check: unit_tests (3.13)
- GitHub Check: mypy
- GitHub Check: ruff
- GitHub Check: Pylinter
- GitHub Check: integration_tests (3.12)
- GitHub Check: E2E: server mode / ci / group 1
- GitHub Check: E2E: library mode / ci / group 2
- GitHub Check: E2E: library mode / ci / group 3
- GitHub Check: E2E Tests for Lightspeed Evaluation job
- GitHub Check: Konflux kflux-prd-rh02 / lightspeed-stack-on-pull-request
🧰 Additional context used
📓 Path-based instructions (2)
src/**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
src/**/*.py: Use absolute imports for internal modules:from authentication import get_auth_dependency
Llama Stack imports: Usefrom llama_stack_client import AsyncLlamaStackClient
Checkconstants.pyfor shared constants before defining new ones
All modules must start with descriptive docstrings explaining purpose
Uselogger = get_logger(__name__)fromlog.pyfor module logging
All functions must have complete type annotations for parameters and return types, use modern syntax (str | int), and include descriptive docstrings
Use snake_case with descriptive, action-oriented names for functions (get_, validate_, check_)
Avoid in-place parameter modification anti-patterns; return new data structures instead of modifying function parameters
Useasync deffor I/O operations and external API calls
Use standard log levels with clear purposes:debug()for diagnostic info,info()for program execution,warning()for unexpected events,error()for serious problems
All classes must have descriptive docstrings explaining purpose and use PascalCase with standard suffixes:Configuration,Error/Exception,Resolver,Interface
Abstract classes must use ABC with@abstractmethoddecorators
Follow Google Python docstring conventions with required sections: Parameters, Returns, Raises, and Attributes for classes
Files:
src/utils/pydantic_ai.py
tests/**/*.py
📄 CodeRabbit inference engine (AGENTS.md)
tests/**/*.py: Use pytest for all unit and integration tests; do not use unittest
Usepytest.mark.asynciomarker for async tests
Files:
tests/unit/utils/test_pydantic_ai.py
🧠 Learnings (4)
📓 Common learnings
Learnt from: CR
Repo: lightspeed-core/lightspeed-stack PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-05-06T06:57:52.173Z
Learning: Applies to src/**/*.py : Llama Stack imports: Use `from llama_stack_client import AsyncLlamaStackClient`
📚 Learning: 2026-05-06T06:57:52.173Z
Learnt from: CR
Repo: lightspeed-core/lightspeed-stack PR: 0
File: AGENTS.md:0-0
Timestamp: 2026-05-06T06:57:52.173Z
Learning: Applies to src/**/*.py : Llama Stack imports: Use `from llama_stack_client import AsyncLlamaStackClient`
Applied to files:
src/utils/pydantic_ai.py
📚 Learning: 2026-02-25T07:46:39.608Z
Learnt from: asimurka
Repo: lightspeed-core/lightspeed-stack PR: 1211
File: src/models/responses.py:8-16
Timestamp: 2026-02-25T07:46:39.608Z
Learning: In the lightspeed-stack codebase, src/models/requests.py uses OpenAIResponseInputTool as Tool while src/models/responses.py uses OpenAIResponseTool as Tool. This type difference is intentional - input tools and output/response tools have different schemas in llama-stack-api.
Applied to files:
src/utils/pydantic_ai.py
📚 Learning: 2026-05-20T08:09:43.391Z
Learnt from: max-svistunov
Repo: lightspeed-core/lightspeed-stack PR: 1580
File: src/llama_stack_configuration.py:651-683
Timestamp: 2026-05-20T08:09:43.391Z
Learning: In `src/llama_stack_configuration.py`, the `apply_high_level_inference` function currently emits `provider_id: p_type` (underscore form, e.g. `sentence_transformers`) directly from the high-level type key, which collides with Llama Stack's hyphenated provider IDs (e.g. `sentence-transformers`). This is a known PoC divergence documented in the spike doc ("Findings discovered during PoC") and tracked in the implementation JIRA "Unified llama_stack.config schema + synthesizer". Decision S5 mandates that each backend-specific synthesizer translates LCORE's canonical type Literal vocabulary to the target backend's expected shape (hyphenated provider_id for Llama Stack; model-string prefixes for Pydantic AI). The PoC code will be removed before merge; the fix belongs in the implementation ticket.
Applied to files:
src/utils/pydantic_ai.py
🔇 Additional comments (7)
src/utils/pydantic_ai.py (4)
41-45: 🏗️ Heavy liftAvoid depending on the protected
AsyncLlamaStackClient._client; use the publichttp_clientinjection path.Reaching into
client._clientis an unstable dependency on a private/internal attribute that can break at runtime even while mocked tests stay green. Prefer constructing/passing the HTTP client via the public injection API.
1-29: LGTM!
48-70: LGTM!
73-104: LGTM!tests/unit/utils/test_pydantic_ai.py (3)
1-64: LGTM!
66-196: LGTM!
199-270: LGTM!
|
/retest |
| if isinstance(client, AsyncLlamaStackAsLibraryClient): | ||
| return LlamaStackProvider(library_client=client) | ||
| api_key = client.api_key or "not-needed" | ||
| base = str(client.base_url).rstrip("/") |
There was a problem hiding this comment.
it's ok, but IIRC there's some utility function to do it (correctly ;)
4 participants
Description
Type of change
Tools used to create PR
Identify any AI code assistants used in this PR (for transparency and review context)
Related Tickets & Documents
Checklist before requesting a review
Testing
Summary by CodeRabbit