feat: add /pr-loop slash command for iterative PR monitoring #251
Conversation
Summary of ChangesHello @marcusquinn, 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 introduces the Highlights
Using Gemini Code AssistThe 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
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 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
|
|
Warning Rate limit exceeded
⌛ How to resolve this issue?After the wait time has elapsed, a review can be triggered using the We recommend that you space out your commits to avoid hitting the rate limit. 🚦 How do rate limits work?CodeRabbit enforces hourly rate limits for each developer per organization. Our paid plans have higher rate limits than the trial, open-source and free plans. In all cases, we re-allow further reviews after a brief timeout. Please see our FAQ for further information. WalkthroughIntroduces comprehensive documentation for the PR loop agent command. The new file defines usage syntax, command options, workflow steps, completion outcomes, CI polling strategies, example invocations, state file management, timeout recovery procedures, and references to related commands. Changes
Estimated code review effort🎯 1 (Trivial) | ⏱️ ~3 minutes Possibly related PRs
Poem
🚥 Pre-merge checks | ✅ 3✅ Passed checks (3 passed)
✏️ Tip: You can configure your own custom pre-merge checks in the settings. Thanks for using CodeRabbit! It's free for OSS, and your support helps us grow. If you like it, consider giving us a shout-out. Comment |
![gemini-code-assist[bot]](https://avatars.githubusercontent.com/in/956858?s=60&v=4){kind=small}
There was a problem hiding this comment.
Code Review
This pull request introduces documentation for the new /pr-loop slash command. The documentation is thorough and well-organized, covering usage, options, workflow, and recovery steps. I've added a couple of minor suggestions to enhance the consistency and clarity of the documentation, particularly regarding placeholder conventions and the 'Completion Promises' table.
| ## Usage | ||
|
|
||
| ```bash | ||
| /pr-loop [--pr N] [--wait-for-ci] [--max-iterations N] [--no-auto-trigger] |
There was a problem hiding this comment.
For consistency with the 'Options' table below, it would be clearer to use <n> as a placeholder for numbers instead of N. This ensures a uniform convention throughout the documentation.
| /pr-loop [--pr N] [--wait-for-ci] [--max-iterations N] [--no-auto-trigger] | |
| /pr-loop [--pr <n>] [--wait-for-ci] [--max-iterations <n>] [--no-auto-trigger] |
| |---------|---------| | ||
| | PR approved | `<promise>PR_APPROVED</promise>` | | ||
| | PR merged | `<promise>PR_MERGED</promise>` | | ||
| | Max iterations reached | Exit with status report | |
There was a problem hiding this comment.
The 'Promise' column for 'Max iterations reached' is inconsistent with the other entries. While other outcomes map to a <promise> tag, this one describes an action ('Exit with status report'). For clarity and consistency, consider either providing a corresponding promise tag (e.g., <promise>MAX_ITERATIONS_REACHED</promise>) or explicitly stating that no promise is returned in this case (e.g., 'N/A').
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Thu Jan 29 01:02:49 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
🤖 Augment PR SummarySummary: Adds documentation for a new Changes:
Technical Notes: This command is designed to integrate with the existing quality-loop infrastructure and GitHub CLI-based PR status signals. 🤖 Was this summary useful? React with 👍 or 👎 |
![augmentcode[bot]](https://avatars.githubusercontent.com/in/1027498?s=60&v=4){kind=small}
|
|
||
| ## State Tracking | ||
|
|
||
| Progress is tracked in `.agent/loop-state/quality-loop.local.state`: |
There was a problem hiding this comment.
The state file referenced here (.agent/loop-state/quality-loop.local.state) is written by quality-loop-helper.sh as YAML frontmatter (e.g., type, iteration, status, options, checks_passed/failed), so the Markdown checklist example below doesn’t match what users will actually see.
🤖 Was this useful? React with 👍 or 👎
![coderabbitai[bot]](https://avatars.githubusercontent.com/in/347564?s=60&v=4){kind=small}
There was a problem hiding this comment.
Actionable comments posted: 1
🤖 Fix all issues with AI agents
In @.agent/scripts/commands/pr-loop.md:
- Around line 103-117: The example state block under "PR Review Loop State" uses
a fixed timestamp for the "Last Check:" field; update that markdown snippet so
it uses a placeholder like "<iso8601>" or an explicit label such as "EXAMPLE:
2025-01-29T14:30:00Z" instead of a stale concrete date; change the "Last Check:"
line in the example state (the markdown code block showing Check Results and
Last Check) to use the placeholder or example marker to avoid presenting stale
timestamps.
🧹 Nitpick comments (2)
.agent/scripts/commands/pr-loop.md (2)
11-158: Reduce inline detail; move guidance to AGENTS.md / subagent docs.This reads like a full runbook. For .agent docs, please keep a concise overview and point to subagent/AGENTS.md for deep workflow, timing, state, and recovery steps to preserve progressive disclosure and the single-source-of-truth policy. Based on learnings: “All instructions, documentation, and operational guidance should be maintained in AGENTS.md as the single source of truth.”
13-15: Replace inline command blocks with authoritative file:line references.Inline examples should only appear when they’re authoritative; otherwise, point to the actual implementation via file:line references. This keeps the doc aligned with the automation source of truth. As per coding guidelines: “Include code examples only when authoritative; use
file:linereferences to point to actual implementation instead of inline code snippets.”✅ Suggested doc edit (replace inline code blocks)
-```bash -/pr-loop [--pr N] [--wait-for-ci] [--max-iterations N] [--no-auto-trigger] -``` +See implementation: file:line (authoritative source for invocation syntax)Also applies to: 40-42, 79-99, 131-148
|
🔍 Code Quality Report�[0;35m[MONITOR]�[0m Code Review Monitoring Report �[0;34m[INFO]�[0m Latest Quality Status: �[0;34m[INFO]�[0m Recent monitoring activity: 📈 Current Quality Metrics
Generated on: Thu Jan 29 01:08:56 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
1 participant
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.