More grep prompt tweaks

[gundermanc]

Summary

Adds another case to the grep prompt.

Details

Related Issues

How to Validate

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
  • Windows
    • npm run
    • npx
    • Docker
  • Linux
    • npm run
    • npx
    • Docker

[gemini-code-assist]

Summary of Changes

Hello @gundermanc, 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 new evaluations and updates core prompt instructions to enhance the agent's efficiency when using search tools. The goal is to ensure the agent minimizes context window usage by applying stricter limits on search results, thereby improving performance and reducing unnecessary data retrieval.

Highlights

• Enhanced Search Efficiency Evaluations: New evaluation tests were added to frugalSearch.eval.ts to verify that the agent uses total_max_matches and max_matches_per_file parameters effectively, ensuring search tools are used frugally.
• Improved Prompt Instructions for Context Efficiency: The core prompt snippets in snippets.ts were updated to provide clearer guidance on scoping and limiting search queries, including recommendations for names_only=true or max_matches_per_file=1 for broad discovery.

Changelog

• evals/frugalSearch.eval.ts
  • Added a JSDoc comment explaining the purpose of the frugal search evaluations.
  • Modified the expect assertions to specifically check for total_max_matches and max_matches_per_file limits in search calls.
• packages/core/src/prompts/snippets.ts
  • Updated the "Context Efficiency" section to provide more detailed guidance on limiting search results.
  • Added a new instruction recommending names_only=true or max_matches_per_file=1 for broad discovery.

Activity

• No human activity has been recorded on this pull request yet.

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 enhances the agent's search efficiency by refining the system prompt to encourage frugal use of search tools and adds corresponding evaluation tests. The prompt changes are clear and provide better guidance. I've suggested an improvement to the new evaluation test to make its validation logic more robust by ensuring a single search call is frugal in all expected ways, rather than checking for different aspects of frugality across multiple calls.

[gemini-code-assist]

The current test logic checks for total_max_matches and max_matches_per_file limits in separate some() calls. This means the test can pass if one grep call has a total_max_matches limit and a different call has a max_matches_per_file limit.

To ensure that the agent is making truly frugal calls, we should verify that at least one call includes both limits simultaneously. This can be done with a single some() and expect() call that combines both conditions.

      const hasFrugalCall = grepParams.some(
        (p) =>
          (p.total_max_matches !== undefined && p.total_max_matches <= 100) &&
          (p.max_matches_per_file !== undefined && p.max_matches_per_file <= 5),
      );
      expect(
        hasFrugalCall,
        `Expected agent to use a small total_max_matches (<= 100) AND max_matches_per_file (<= 5) in at least one call. Actual params: ${JSON.stringify(
          grepParams,
        )}`,
      ).toBe(true);

[github-actions]

Size Change: +208 B (0%)

Total Size: 24.3 MB

ℹ️ View Unchanged

Filename	Size	Change
./bundle/gemini.js	24.3 MB	+208 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}