Cap Thinking Budget to prevent runaway thought loops

[abhipatel12]

Summary

Caps the thinking budget to prevent run-away thought loops.

Related Issues

Fixes # 976

Pre-Merge Checklist

• Updated relevant documentation and README (if needed)
• Added/updated tests (if needed)
• Noted breaking changes (if any)
• Validated on required platforms/methods:
  • MacOS
    • npm run
    • npx
    • Docker
    • Podman
    • Seatbelt

[gemini-code-assist]

Summary of Changes

Hello @abhipatel12, 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 introduces a crucial change to prevent potential runaway thought loops within the Codebase Investigator agent. It achieves this by setting a default maximum 'thinking budget' to 8192. This ensures that the agent operates within defined computational boundaries, leading to more stable and predictable performance, and mitigating scenarios where it might otherwise consume excessive resources or get stuck in infinite processing.

Highlights

• Thinking Budget Default: The default value for the 'Thinking Budget' setting in the CLI configuration has been updated from -1 to 8192.
• Core Thinking Mode Constant: The DEFAULT_THINKING_MODE constant in the core models has been changed from -1 to 8192, explicitly capping the thinking budget.
• Preventing Runaway Loops: These changes collectively aim to prevent runaway thought loops in the Codebase Investigator agent by establishing a clear upper limit for its thinking budget.

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 aims to cap the thinking budget for the CodebaseInvestigatorAgent to prevent runaway thought loops by changing the default value from -1 (unlimited) to 8192. While the changes in the settings schema and the new constant are correct, the agent's definition itself still uses a hardcoded value of -1 for its thinking budget. This makes the change ineffective. My review includes a critical comment pointing this out with a suggestion on how to fix it.

[github-actions]

Size Change: +2 B (0%)

Total Size: 20.3 MB

ℹ️ View Unchanged

Filename	Size	Change
./bundle/gemini.js	20.3 MB	+2 B (0%)
./bundle/sandbox-macos-permissive-closed.sb	1.03 kB	0 B
./bundle/sandbox-macos-permissive-open.sb	890 B	0 B
./bundle/sandbox-macos-permissive-proxied.sb	1.31 kB	0 B
./bundle/sandbox-macos-restrictive-closed.sb	3.29 kB	0 B
./bundle/sandbox-macos-restrictive-open.sb	3.36 kB	0 B
./bundle/sandbox-macos-restrictive-proxied.sb	3.56 kB	0 B

_{compressed-size-action}

[abhipatel12]

/patch preview

[github-actions]

✅ Patch workflow(s) dispatched successfully!

📋 Details:

• Channels: preview
• Commit: 59e0b10e6cf4d7cf3af652d95035be9ef9fb181a
• Workflows Created: 1

🔗 Track Progress:

• View patch workflows
• This workflow run

[github-actions]

🚀 Patch PR Created!

📋 Patch Details:

• Channel: preview → will publish to npm tag preview
• Commit: 59e0b10e6cf4d7cf3af652d95035be9ef9fb181a
• Hotfix Branch: hotfix/v0.12.0-preview.9/0.12.0-preview.10/preview/cherry-pick-59e0b10/pr-12416
• Hotfix PR: #12492
• ⚠️ Status: Cherry-pick conflicts detected - manual resolution required

📝 Next Steps:

1. ⚠️ Resolve conflicts in the hotfix PR first: #12492
2. Test your changes after resolving conflicts
3. Once merged, the patch release will automatically trigger
4. You'll receive updates here when the release completes

🔗 Track Progress:

• View hotfix PR #12492