Update Agent Evals to run in a custom home directory

[samedson]

Description

Allows us to use features like Gemini CLI memory, extensions, etc.

Also removes the need to mess with the user's real MCP servers.

[gemini-code-assist]

Summary of Changes

Hello @samedson, 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 significantly enhances the robustness and isolation of the Agent Evals system by introducing a custom home directory for Gemini CLI runs. This strategic change ensures that evaluations can leverage advanced Gemini CLI features like memory and extensions without interfering with a developer's local setup, while also streamlining the setup process by eliminating the need to clear existing MCP servers.

Highlights

• Custom Home Directory for Agent Evals: The Gemini CLI evaluations now run within a dedicated, isolated home directory, preventing conflicts with the user's actual Gemini CLI configuration.
• Enabled Gemini CLI Features: This change allows the agent evaluations to properly utilize Gemini CLI features such as memory and extensions, which rely on user-specific settings.
• Removed MCP Server Cleanup: The previous step of clearing user's MCP servers before evaluations has been removed, as the new isolated environment makes it unnecessary.
• Metric Protection: A fixed installation ID is now written to the custom home directory to prevent evaluation runs from artificially inflating Gemini CLI usage metrics.

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 refactors the agent evaluation tests to run within a custom home directory, which is an excellent improvement for test isolation. By setting the HOME environment variable for the Gemini CLI process, you've effectively sandboxed the tests, preventing interference with the user's global configuration. The introduction of RunDirectories and the new helper methods in GeminiCliRunner make the code cleaner and more modular. I've added a couple of suggestions to further improve type safety and robustness in gemini-cli-runner.ts. Overall, this is a solid change that enhances the reliability of the test suite.

[schnecle]

This is awesome! Thanks Sam!