-
Notifications
You must be signed in to change notification settings - Fork 2.1k
fix: Support list[BaseModel] annotation about FunctionTool args #3186
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
fix: Support list[BaseModel] annotation about FunctionTool args #3186
Conversation
Thanks for your pull request! It looks like this may be your first contribution to a Google open source project. Before we can look at your pull request, you'll need to sign a Contributor License Agreement (CLA).
View this failed invocation of the CLA check for more information.
For the most up to date status, view the checks section at the bottom of the pull request.
Summary of ChangesHello @t-miyak, I'm Gemini Code Assist1 ! I'm currently reviewing this pull request and will post my feedback shortly. In the meantime, here's a summary to help you and other reviewers quickly get up to speed! This pull request significantly improves the Highlights
Using Gemini Code AssistThe full guide for Gemini Code Assist can be found on our documentation page, here are some quick tips. Invoking Gemini You can request assistance from Gemini at any point by creating a comment using either
Customization To customize Gemini Code Assist for GitHub experience, repository maintainers can create a configuration file and/or provide a custom code review style guide (such as PEP-8 for Python) by creating and adding files to a Limitations & Feedback Gemini Code Assist may make mistakes. Please leave feedback on any instances where its feedback is incorrect or counter productive. You can react with 👍 and 👎 on @gemini-code-assist comments. If you're interested in giving your feedback about your experience with Gemini Code Assist for Github and other Google products, sign up here. You can also get AI-powered code generation, chat, as well as code reviews directly in the IDE at no cost with the Gemini Code Assist IDE Extension. Footnotes
|
Response from ADK Triaging Agent
Hello @t-miyak, thank you for your contribution!
Before we can review this PR, could you please address the following points from our contribution guidelines:
- Sign the Contributor License Agreement (CLA): It looks like the CLA check has failed. Please sign the CLA to proceed. You can find more information at https://cla.developers.google.com/.
- Associate an issue: For a new feature like this, please create a GitHub issue that describes the problem and the proposed solution, and then link it to this PR.
- Add a testing plan: Please add a "Testing plan" section to your PR description, explaining how you've tested these changes.
You can find our full contribution guidelines here: https://github.com/google/adk-python/blob/main/CONTRIBUTING.md
Thank you!
@gemini-code-assist
gemini-code-assist
bot
left a comment
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
Code Review
This pull request adds support for list[pydantic.BaseModel] as a type annotation for function tool arguments, which is a great enhancement. The implementation correctly identifies and processes lists of Pydantic models, converting dictionaries from the LLM response into model instances. The added unit tests are thorough and cover various scenarios, including optional lists and invalid data handling. I have one suggestion to make the exception handling more specific, which will improve code robustness and clarity.
There was a problem hiding this comment.
Choose a reason for hiding this comment
The reason will be displayed to describe this comment to others. Learn more.
While using except Exception is robust, it's generally better practice to catch more specific exceptions. This prevents accidentally catching and silencing unrelated errors (like KeyboardInterrupt or SystemExit) and makes the code's intent clearer. In this case, pydantic.ValidationError is the most expected exception during model validation.
76fa997 to
985e948
Compare
I've tested locally and confirmed it works.
➜ uv run pytest tests/unittests/tools/test_function_tool_pydantic.py
================================================================ test session starts ================================================================
platform darwin -- Python 3.11.4, pytest-8.4.2, pluggy-1.6.0
configfile: pyproject.toml
plugins: mock-3.15.1, asyncio-1.2.0, anyio-4.11.0, xdist-3.8.0, langsmith-0.4.35
asyncio: mode=Mode.AUTO, debug=False, asyncio_default_fixture_loop_scope=function, asyncio_default_test_loop_scope=function
collected 14 items
tests/unittests/tools/test_function_tool_pydantic.py .............. [100%]
================================================================ 14 passed in 6.55s =================================================================
Thanks for adding list support! One concern though if any item failsmodel_validate, we skip it and still overwrite the argument with the (now shorter) converted list. That is a behavior change from the singlevalue path, it kept the original value on failure. Can you fix so we would it will not silently drop data?
Summary
Add support for
list[pydantic.BaseModel]type arguments in FunctionTool, enabling automatic conversion of JSON arrays from LLM tool call responses to lists of Pydantic model instances.Problem
Currently, when a function tool is defined with
list[PydanticModel]type annotation, the LLM tool call response provideslist[dict], requiring manual conversion in each tool function. This leads to repetitive boilerplate code and makes tool definitions less clean.