docs: add AGENTS.md with AI coding guidelines

[nvzhihanj]

Summary

• Restructure CLAUDE.md to contain only @AGENTS.md include directive
• Create AGENTS.md with comprehensive, tool-agnostic repo guidelines for AI coding agents
• Add policy requiring AGENTS.md updates alongside significant refactors (with reviewer checklist)
• Add catalog of common AI coding pitfalls specific to this codebase (serialization, multi-process boundary, async patterns, testing conventions, etc.)

Test plan

• Verify CLAUDE.md contains only @AGENTS.md
• Verify AGENTS.md code organization tree matches actual repo structure
• Verify pre-commit passes (pre-commit run --all-files)

🤖 Generated with Claude Code

[github-actions]

MLCommons CLA bot All contributors have signed the MLCommons CLA ✍️ ✅

[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 significantly enhances the repository's documentation for AI coding agents by introducing a dedicated and comprehensive AGENTS.md file. This new guide centralizes project information, architectural details, development standards, and a crucial list of common AI coding pitfalls, ensuring that AI-assisted development aligns with the codebase's specific conventions and performance requirements. The change also includes a mechanism to keep this documentation up-to-date with future refactors.

Highlights

• Documentation Restructuring: CLAUDE.md was restructured to solely include the new AGENTS.md directive, centralizing AI coding guidelines.
• New AI Coding Guidelines: A new AGENTS.md file was created, providing comprehensive, tool-agnostic guidelines for AI coding agents working within the repository.
• Guideline Maintenance Policy: A policy was introduced requiring AGENTS.md to be updated concurrently with significant refactors, supported by a reviewer checklist.
• AI Coding Pitfalls Catalog: A catalog of common AI coding pitfalls specific to this codebase was added, covering areas like serialization, multi-process boundaries, async patterns, and testing conventions.

🧠 New Feature in Public Preview: You can now enable Memory to help Gemini Code Assist learn from your team's feedback. This makes future code reviews more consistent and personalized to your project's style. Click here to enable Memory in your admin console.

Changelog

• AGENTS.md
  • Added a new file containing comprehensive guidelines for AI coding agents.
  • Included sections on project overview, architecture, code organization, development standards, and common pitfalls.
  • Established a policy for keeping the document updated with significant refactors.
• CLAUDE.md
  • Updated to include a single directive referencing AGENTS.md.

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 a comprehensive AGENTS.md file to guide AI coding agents, which is a great initiative for improving AI-assisted development in this repository. The document is well-structured and covers many important aspects of the codebase. I've found a couple of minor inconsistencies in the documentation that could be improved for clarity and accuracy.