fix: serialize tool errors as strings in FunctionResponse

[Omzee15]

Tool errors were previously serialized as error interfaces which marshal to empty JSON objects ({}), making it impossible for LLMs to understand what went wrong. This fix converts errors to strings using err.Error() before including them in the FunctionResponse.

Changes:

• Modified callTool() in base_flow.go to call .Error() on error objects
• Added comprehensive tests for error serialization scenarios
• Covers tool execution errors, before/after callback errors

Fixes issue where LLMs received error: {} instead of meaningful error messages.

[google-cla[bot]]

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[bot]]

Summary of Changes

Hello @Omzee15, I'm Gemini Code Assist[^1]! 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 resolves an issue where Large Language Models (LLMs) received uninformative empty JSON objects when tool calls resulted in errors. By explicitly converting error interfaces to their string representations, the change ensures that LLMs receive meaningful and actionable error messages, significantly improving their ability to understand and respond to tool failures.

Highlights

• Error Serialization: Tool errors are now explicitly serialized as strings using the .Error() method before being included in the FunctionResponse. This prevents errors from being marshaled into empty JSON objects, which were previously uninterpretable by LLMs.
• Affected Error Scenarios: The fix applies to errors originating from BeforeToolCallback failures, actual tool execution failures, and AfterToolCallback failures, ensuring consistent error reporting across all tool-related operations.
• Comprehensive Testing: New tests have been added to validate the correct serialization of various error types (e.g., fmt.Errorf, errors.New, wrapped errors) and to confirm that errors remain properly formatted after JSON marshaling and unmarshaling.

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 :thumbsup: and :thumbsdown: 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.

[^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.