Feat/tool registry discovery

[ved015]

Summary

Adds a small tool registry for eval reporting, plus AST extraction for the tool names used inside eval assertions.

Details

• Builds a registry from ALL_BUILTIN_TOOL_NAMES and TOOL_LEGACY_ALIASES in @google/gemini-cli-core.
• Groups built-in tools into categories like file system, shell, web, planning, tracker, agent, and MCP.
• Adds a typed category map so newly added core tools have to be categorized.
• Extends eval analysis to collect tool references per eval case and per file.
• Adds tests for registry creation, alias resolution, category grouping, deduping, sorting, imported constants, and common eval assertion patterns.

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, 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 structured tool registry to manage built-in tools and their categories, while simultaneously enhancing the eval analysis framework to track tool usage. By statically extracting tool references from eval assertions, the system can now better validate tool names and improve reporting accuracy during evaluation runs.

Highlights

• Tool Registry Implementation: Introduced a new tool registry utility that categorizes built-in tools and manages legacy alias resolution.
• Eval Analysis Enhancement: Extended the eval analysis engine to statically extract and validate tool references used within eval assertions.
• Test Coverage: Added comprehensive unit tests for the tool registry and verified tool reference extraction across various code patterns.

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 the 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 counterproductive. 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.

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. ↩

[github-actions]

📊 PR Size: size/L

• Lines changed: 752
• Additions: +752
• Deletions: -0
• Files changed: 4

[gemini-code-assist]

Code Review

This pull request introduces a tool registry utility (tool-registry.ts) and updates the eval analysis script (eval-analysis.ts) to statically extract and resolve tool references from eval assertions, accompanied by comprehensive unit tests. The feedback correctly identifies that validating tool names solely against the built-in tool registry will cause false-positive warnings for valid Model Context Protocol (MCP) or dynamically discovered tools. To resolve this, the reviewer suggests importing and utilizing isValidToolName from @google/gemini-cli-core to properly handle non-built-in tool name patterns.