Fix tool result processing in Claude model

[stevearmstrong-dev]

Fixes #566

Problem

Tool results were only processed if they contained a 'result' key, causing other valid Map structures to be ignored.

Solution

Changed the Claude model to serialize the entire response Map to JSON instead of extracting only the 'result' key.

Changes

• Modified Claude.java:171-182 to use ObjectMapper.writeValueAsString()
• Added proper error handling with try-catch
• Falls back to .toString() if JSON serialization fails

Testing

• ✅ All FunctionTool tests pass (36/36)
• ✅ Code compiles successfully
• ✅ Verified with the reproduction case from the issue

[gemini-code-assist]

Summary of Changes

Hello @stevearmstrong-dev, 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 resolves a critical bug in the Claude model's tool result processing. Previously, only tool responses containing a specific 'result' key were processed, leading to valid tool outputs being ignored. The change ensures that all tool response Map structures are correctly serialized to JSON, significantly improving the reliability and flexibility of tool integrations within the system.

Highlights

• Tool Result Processing Fix: Addressed an issue where the Claude model's tool result processing was overly restrictive, only recognizing results containing a specific 'result' key and ignoring other valid Map structures.
• Enhanced Serialization: Modified the Claude model to serialize the entire tool response Map to JSON using ObjectMapper.writeValueAsString() for comprehensive data handling.
• Robust Error Handling: Implemented proper error handling with a try-catch block during JSON serialization, including a fallback to .toString() if serialization fails.

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. ↩

[gemini-code-assist]

Code Review

This pull request correctly fixes an issue where tool results were not being processed correctly by serializing the entire response map to JSON. The change is well-contained and includes appropriate error handling with a fallback mechanism.

My review includes a suggestion to improve performance, robustness, and readability by reusing the ObjectMapper instance, catching a more specific exception, and reducing redundant code. While the provided code suggestion only addresses one of these points directly to fit within the diff, I highly recommend applying all the suggested improvements.

[stevearmstrong-dev]

@mazas-google @Poggecci Could you please review this PR?