fix: Support list[BaseModel] annotation about FunctionTool args

[t-miyak]

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 provides list[dict], requiring manual conversion in each tool function. This leads to repetitive boilerplate code and makes tool definitions less clean.

[google-cla]

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.

[gemini-code-assist]

Summary of Changes

Hello @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 FunctionTool's ability to handle complex data structures by introducing automatic conversion for arguments typed as list[pydantic.BaseModel]. Previously, developers had to manually parse JSON arrays into Pydantic model lists, which added repetitive code. This change streamlines the integration of LLM tool calls with Pydantic-defined data, making tool definitions more intuitive and reducing development overhead.

Highlights

• Automatic Pydantic List Conversion: The FunctionTool now automatically converts JSON arrays from LLM tool call responses into list[pydantic.BaseModel] instances when the function argument is type-hinted as such.
• Reduced Boilerplate: This enhancement eliminates the need for manual conversion of list[dict] to list[PydanticModel] within tool functions, leading to cleaner and more concise code.
• Robust Error Handling: The conversion process includes error handling, logging warnings and skipping individual items within a list that fail Pydantic model validation, ensuring the overall process doesn't halt due to malformed data.

Using Gemini Code Assist

The 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 /gemini <command> or @gemini-code-assist <command>. Below is a summary of the supported commands on the current page.

Feature	Command	Description
Code Review	/gemini review	Performs a code review for the current pull request in its current state.
Pull Request Summary	/gemini summary	Provides a summary of the current pull request in its current state.
Comment	@gemini-code-assist	Responds in comments when explicitly tagged, both in pull request comments and review comments.
Help	/gemini help	Displays a list of available commands.

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 .gemini/ folder in the base of the repository. Detailed instructions can be found here.

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

1. Review the Privacy Notices, Generative AI Prohibited Use Policy, Terms of Service, and learn how to configure Gemini Code Assist in GitHub here. Gemini can make mistakes, so double check it and use code with caution. ↩

[adk-bot]

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]

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.

[gemini-code-assist]

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.

Suggested change

	except Exception as e:
	# Skip items that fail validation
	logger.warning(
	f"Skipping item in '{param_name}': "
	f'Failed to convert to {element_type.__name__}: {e}'
	)
	except pydantic.ValidationError as e:
	# Skip items that fail validation
	logger.warning(
	f"Skipping item in '{param_name}': "
	f'Failed to convert to {element_type.__name__}: {e}'
	)

[t-miyak]

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 =================================================================

[t-miyak]

@GWeale

I fixed the CI errors.

Thank you!