Introduce limits for search results.

[gundermanc]

Summary

Add limits params so that the agent can limit how many grep results it gets back.

Part of #17112

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 enhances the grep and ripgrep tools by introducing new parameters that allow for precise control over the number of search results. This change aims to improve the efficiency and usability of these tools by preventing an overwhelming volume of matches, thereby making the output more manageable and relevant for agents. The new limits can be applied per file or across the entire search operation, providing flexibility in how search results are constrained.

Highlights

• Introduce Search Result Limits: Two new optional parameters, max_matches_per_file and total_max_matches, have been added to the grep and ripgrep tools. These allow agents to control the volume of search results returned.
• Per-File Match Limiting: The max_matches_per_file parameter enables limiting the number of matches returned from any single file, preventing large files from dominating search results. This is supported by both the native git grep/grep commands and the JavaScript fallback.
• Overall Match Limiting: The total_max_matches parameter sets an overall cap on the total number of matches returned across all files, with a default of 2000 if not specified. This helps manage the overall response size and performance.
• Validation and Testing: Input validation has been added to ensure that both max_matches_per_file and total_max_matches are positive integers. Comprehensive unit tests were also introduced to verify the correct behavior of these new limits in both grep and ripgrep tools, including truncation logic.

Changelog

• packages/core/src/tools/definitions/coreTools.ts
  • Added max_matches_per_file and total_max_matches properties to the GREP_DEFINITION schema, including descriptions, types, and minimum value constraints.
• packages/core/src/tools/grep.test.ts
  • Introduced a new test case to verify that total_max_matches correctly truncates results in the JavaScript fallback implementation.
  • Added a new test case to ensure max_matches_per_file is respected in the JavaScript fallback, limiting matches per file.
• packages/core/src/tools/grep.ts
  • Extended the GrepToolParams interface to include max_matches_per_file and total_max_matches.
  • Implemented logic to use this.params.total_max_matches as the totalMaxMatches value, defaulting to DEFAULT_TOTAL_MAX_MATCHES if not provided.
  • Modified the _searchInDir method to pass max_matches_per_file to the underlying search functions.
  • Updated the _searchWithGitGrep function to conditionally add the --max-count argument when max_matches_per_file is specified.
  • Updated the _searchWithGrep function to conditionally add the --max-count argument when max_matches_per_file is specified.
  • Modified the _searchWithJsFallback function to track matchesInFile and break the loop if max_matches_per_file is reached.
  • Added validation checks in the build method to ensure max_matches_per_file and total_max_matches are at least 1 if provided.
• packages/core/src/tools/ripGrep.test.ts
  • Added a test case to confirm that ripgrep passes --max-count when max_matches_per_file is provided.
  • Introduced a test case to verify that total_max_matches correctly truncates ripgrep results.
• packages/core/src/tools/ripGrep.ts
  • Extended the RipGrepToolParams interface to include max_matches_per_file and total_max_matches.
  • Implemented logic to use this.params.total_max_matches as the totalMaxMatches value, defaulting to DEFAULT_TOTAL_MAX_MATCHES if not provided.
  • Modified the _searchWithRipGrep method to pass max_matches_per_file.
  • Updated the _searchWithRipGrep function to conditionally add the --max-count argument to rgArgs when max_matches_per_file is specified.
  • Added max_matches_per_file and total_max_matches properties to the RIPGREP_DEFINITION schema, including descriptions, types, and minimum value constraints.
  • Added validation checks in the build method to ensure max_matches_per_file and total_max_matches are at least 1 if provided.

Activity

• The pull request was created by gundermanc with the title 'Introduce limits for search results' and a summary indicating the addition of limit parameters for grep results.
• The author provided a 'How to Validate' section (currently empty) and a 'Pre-Merge Checklist' (partially checked).

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 introduces max_matches_per_file and total_max_matches parameters to the grep and ripgrep tools to limit search results. The implementation is sound and includes corresponding tests. However, I've identified a critical inconsistency: the tool's schema documentation specifies a default of 2000 for total_max_matches, but the implementation defaults to 100. This discrepancy could lead to unexpected behavior from the agent. I've provided suggestions to align the documentation with the code's behavior.

[gemini-code-assist]

There's an inconsistency between the documented default for total_max_matches and the implementation. The description states it defaults to 2000, but the code in grep.ts uses DEFAULT_TOTAL_MAX_MATCHES, which is set to 100. This could mislead the agent into expecting more results than it will receive by default.

To fix this, the description should be updated to reflect the actual default value of 100.

Suggested change

	total_max_matches: {
	description:
	'Optional: Maximum number of total matches to return. Use this to limit the overall size of the response. Defaults to 2000 if omitted.',
	type: 'integer',
	minimum: 1,
	},
	total_max_matches: {
	description:
	'Optional: Maximum number of total matches to return. Use this to limit the overall size of the response. Defaults to 100 if omitted.',
	type: 'integer',
	minimum: 1,
	},

[gemini-code-assist]

There's an inconsistency between the documented default for total_max_matches and the implementation. The description states it defaults to 2000, but the code uses DEFAULT_TOTAL_MAX_MATCHES, which is set to 100. This could mislead the agent into expecting more results than it will receive by default.

To ensure the documentation is accurate, the description should be updated to reflect the actual default value of 100.

Suggested change

	total_max_matches: {
	description:
	'Optional: Maximum number of total matches to return. Use this to limit the overall size of the response. Defaults to 2000 if omitted.',
	type: 'integer',
	minimum: 1,
	},
	total_max_matches: {
	description:
	'Optional: Maximum number of total matches to return. Use this to limit the overall size of the response. Defaults to 100 if omitted.',
	type: 'integer',
	minimum: 1,
	},

[github-actions]

Size Change: +2.62 kB (+0.01%)

Total Size: 24.3 MB

Filename	Size	Change
./bundle/gemini.js	24.3 MB	+2.62 kB (+0.01%)

ℹ️ View Unchanged

Filename	Size
./bundle/sandbox-macos-permissive-closed.sb	1.03 kB
./bundle/sandbox-macos-permissive-open.sb	890 B
./bundle/sandbox-macos-permissive-proxied.sb	1.31 kB
./bundle/sandbox-macos-restrictive-closed.sb	3.29 kB
./bundle/sandbox-macos-restrictive-open.sb	3.36 kB
./bundle/sandbox-macos-restrictive-proxied.sb	3.56 kB

_{compressed-size-action}