V9

[cs-util]

This pull request updates the AGENTS.md documentation to clarify and strengthen the development workflow, especially around test-driven development (TDD), dependency management, and documentation practices. The changes emphasize a more disciplined, iterative approach and add guidance to improve maintainability and knowledge sharing.

Development workflow improvements:

• Specify that only one prioritized task should be done per iteration, with a TDD approach where possible, and require running npm test before and after any change.
• Instruct developers to search the codebase before adding functionality to avoid duplication, and to prefer refactoring over re-implementation if similar code exists.
• Require a concise update to docs/implementation-progress.md after each iteration to track decisions and learning across iterations.

Testing practices:

• Add that when adding or updating tests, a brief comment should explain why the test matters, to help future maintainers.
• Clarify the importance of property-based tests and combine the explanation into a single line for clarity.

Dependency management:

• Adjust dependency management instructions to run npm outdated weekly (instead of before and after every task), but still require running npm test before and after any change.

[gemini-code-assist]

Summary of Changes

Hello @cs-util, 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 updates the AGENTS.md documentation to establish clearer and more robust development guidelines. The changes aim to foster a more structured, test-driven, and maintainable development process, improving code quality, reducing duplication, and enhancing knowledge sharing across iterations.

Highlights

• Enhanced Development Workflow: Introduced a more disciplined approach requiring a single prioritized task per iteration, TDD where possible, and running npm test before and after changes.
• Codebase Search & Refactoring: Mandated searching the codebase before adding new functionality to prevent duplication and preferring refactoring existing code.
• Iterative Progress Tracking: Required concise updates to docs/implementation-progress.md after each iteration to document decisions and learnings.
• Improved Testing Practices: Added guidance to include brief comments in tests explaining their purpose and consolidated the explanation for property-based tests.
• Refined Dependency Management: Adjusted the frequency of running npm outdated to weekly, while maintaining the npm test requirement for every change.

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 several beneficial updates to the AGENTS.md documentation, enhancing clarity around the development workflow, testing practices, and dependency management. The changes effectively promote a more disciplined and iterative approach. I've added a couple of minor suggestions to further improve the readability and precision of the new guidelines.

[gemini-code-assist]

The use of "etc." at the end of the sentence is a bit vague. For improved clarity and to ensure the instruction is as precise as possible, it's better to list the expected items explicitly or rephrase to avoid ambiguity.

Suggested change

	- After each iteration add a concise update at the end of docs/implementation-progress.md to use it as the memory between iterations for learnings, decisions, planning etc.
	- After each iteration add a concise update at the end of docs/implementation-progress.md to use it as the memory between iterations for learnings, decisions, and planning.