Add Agent Eval assertions on files

[samedson]

WIP

chai-fs's assertion api on files is kindof wacky

[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 agent evaluation framework by integrating chai-fs for file system assertions. This allows tests to not only verify tool calls and text output but also to assert the existence, properties, and content of files generated or modified during agent execution, leading to more comprehensive and reliable agent evaluations.

Highlights

• New File Assertion Capabilities: Introduced chai-fs to enable robust file system assertions within agent evaluation tests, allowing verification of file existence, properties, and content.
• expectFs Method: Added an expectFs method to the AgentTestRunner interface and its GeminiCliRunner implementation, providing a convenient way for tests to assert on files within the agent's run directory.
• Dependency Updates: Updated package.json and package-lock.json to include chai, chai-fs, and their TypeScript type definitions, along with several new transitive dependencies required for file system assertions.
• Example Usage: Demonstrated the new file assertion feature in firebase-init.spec.ts by adding a test that verifies the content of a generated .gemini/settings.json file.

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 file system assertion capabilities to the agent evaluation tests by integrating chai-fs. The changes include adding the new dependency, creating a helper for chai configuration, and extending the AgentTestRunner to support file assertions. The implementation is sound, and a new test demonstrates the feature. I've provided a couple of suggestions to improve correctness and code style.

[gemini-code-assist]

The contains assertion on a string (which is what contents provides) expects a string argument, not an array of strings. This will likely fail at runtime or not behave as expected. Please pass the expected substring directly as a string.

Suggested change

	run.expectFs(".gemini/settings.json").to.be.a.file().and.contents.contains(["experimental"]);
	run.expectFs(".gemini/settings.json").to.be.a.file().and.contents.contains("experimental");

[samedson]

TODO: Undo