[agents] Add instructions for reviewing

[joshlf]

---

• [agents] Add instructions for reviewing #2855

Latest Update: v2 — Compare vs v1

📚 Full Patch History

Links show the diff between the row version and the column version.

Version	Base	v1
v2	vs Base	vs v1
v1	vs Base

[gemini-code-assist]

Summary of Changes

Hello @joshlf, 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 code review process for AI agents by introducing a new, detailed set of instructions. The changes aim to standardize how AI agents conduct reviews, ensuring they are thorough, context-aware, and provide actionable feedback across critical areas like security, logic, and code style, ultimately improving the quality and reliability of automated reviews.

Highlights

• New Reviewing Guidelines for AI Agents: Introduces a dedicated document outlining comprehensive protocols and standards for AI agents performing code reviews, ensuring a structured and consistent approach.
• Mandatory "Analyze-First" Protocol: Establishes a rule requiring AI agents to read the full file context using view_file before commenting on any line of code, aiming to prevent hallucinations and ensure context-aware feedback.
• Defined Reviewer Personas: Specifies four distinct personas for AI agents (Security Auditor, Logic Detective, Style Cop, Simplicity Advocate), each with a unique focus and checklist to ensure multi-disciplinary and thorough reviews.
• Operational Protocols for Feedback: Outlines requirements for Chain-of-Thought reasoning, actionable feedback (including severity and exact code snippets for fixes), and a structured approach to handling TODO comments.
• Anti-Patterns for AI Reviewers: Lists explicit actions AI agents must avoid, such as approving PRs with missing safety comments or assuming function behavior without verification, to maintain high review quality.

Ignored Files

• Ignored by pattern: .gemini/** (1)
  • .gemini/styleguide.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 new documentation for AI agents, outlining the standards and protocols for conducting code reviews within the repository. The new agent_docs/reviewing.md file is well-structured and comprehensive. My review focuses on ensuring the new documentation adheres to the project's own style guidelines, specifically the 80-column line limit for markdown files. I've provided suggestions to correct a few lines that exceed this limit and to improve readability in one spot.

[codecov-commenter]

Codecov Report

✅ All modified and coverable lines are covered by tests.
✅ Project coverage is 92.05%. Comparing base (bca589a) to head (7c3c63a).
⚠️ Report is 1 commits behind head on main.

Additional details and impacted files

@@            Coverage Diff             @@
##             main    #2855      +/-   ##
==========================================
- Coverage   92.33%   92.05%   -0.29%     
==========================================
  Files          20       20              
  Lines        5794     5812      +18     
==========================================
  Hits         5350     5350              
- Misses        444      462      +18     

☔ View full report in Codecov by Sentry.
📢 Have feedback on the report? Share it here.

🚀 New features to boost your workflow:

• ❄️ Test Analytics: Detect flaky tests, report on failures, and find test suite problems.