Use mocha to run Agent Evals

[samedson]

Description

Use mocha for the test harness so that it's familiar to programmers and has automatic support for some features we want (like retryability and failure on throw).

Sample Commands

npm run test:dev

[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 refactors the 'Agent Evals' testing infrastructure by transitioning from a custom test runner to the Mocha framework. This migration aims to enhance the maintainability, scalability, and reliability of the evaluation system by adopting a widely-used and feature-rich testing solution. The changes involve updating project dependencies, restructuring test files, and integrating automated cleanup processes to ensure a consistent and clean testing environment.

Highlights

• Testing Framework Migration: The Agent Evals testing suite has been migrated from a custom tsx-based runner to the Mocha testing framework, leveraging its robust features for test organization and execution.
• Dependency Updates: The package.json and package-lock.json files have been updated to remove vitest and introduce mocha along with its associated type definitions (@types/mocha, @types/node). rxjs was also added as a dev dependency.
• Test Structure Refactor: The old main.ts and tests.ts files, which contained custom test execution logic and test case definitions, have been removed. The new structure adopts standard Mocha test files (.spec.ts) for better organization.
• Automated Test Cleanup: A global cleanup mechanism has been implemented using Mocha's afterEach hook. This ensures that resources, particularly CLI processes, are properly cleaned up after each test run, promoting isolated and reliable tests.
• TypeScript Configuration Update: The tsconfig.json has been modified to align with the new testing setup, including changes to module and moduleResolution to NodeNext, setting an outDir for compiled JavaScript, and updating typeRoots.

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 successfully migrates the agent evaluation tests from a custom runner to the Mocha test framework. This is a great improvement that leverages a standard, feature-rich testing tool. The changes are well-structured, including new Mocha configuration, updated package definitions, and helper files for test setup and cleanup. My review includes suggestions to improve the robustness of the test cleanup process, remove an unused dependency and an unnecessary configuration path, and align with modern JavaScript best practices for variable declarations.