docs(loops): add README and changelog guidance to loop agents#41
docs(loops): add README and changelog guidance to loop agents#41marcusquinn merged 1 commit intomainfrom
Conversation
- Add 'Documentation Updates' section to ralph-loop.md with README and conventional commit guidance - Add 'Documentation & Changelog' section to full-loop.md with commit prefix table - Update completion criteria to include README updates - Add changelog.md to related workflows - Clarify that changelog is auto-generated from conventional commits
WalkthroughUpdates to full-loop and ralph-loop documentation files add comprehensive guidance for README updates and changelog management using conventional commits. Includes structured documentation patterns, examples for feature implementation completion, and new "Documentation in Loops" section detailing handling within automation workflows. Changes
Estimated code review effort🎯 2 (Simple) | ⏱️ ~12 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 |
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 enhances the existing loop agent workflows by providing explicit guidance on documentation responsibilities. It addresses previous ambiguities by detailing when and how to update 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
|
|
🔍 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: Sun Jan 11 04:53:30 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
There was a problem hiding this comment.
Code Review
This pull request adds valuable documentation regarding README updates and changelog generation using conventional commits. The changes in full-loop.md are clear and comprehensive. I've suggested a couple of improvements for ralph-loop.md to ensure consistency between the two documents, mainly by using the same complete list of conventional commit prefixes.
| **Changelog via commits** - Use conventional commit messages for auto-generated changelogs: | ||
|
|
||
| ```text | ||
| # Good commit messages (auto-included in changelog) | ||
| feat: add user authentication | ||
| fix: resolve memory leak in connection pool | ||
| docs: update API documentation | ||
|
|
||
| # Excluded from changelog | ||
| chore: update dependencies | ||
| ``` |
There was a problem hiding this comment.
For consistency and completeness, it would be better to use the same comprehensive Markdown table for conventional commit prefixes as used in .agent/scripts/commands/full-loop.md. The current list is missing perf and refactor prefixes.
| **Changelog via commits** - Use conventional commit messages for auto-generated changelogs: | |
| ```text | |
| # Good commit messages (auto-included in changelog) | |
| feat: add user authentication | |
| fix: resolve memory leak in connection pool | |
| docs: update API documentation | |
| # Excluded from changelog | |
| chore: update dependencies | |
| ``` | |
| **Changelog via commits** - Use conventional commit messages for auto-generated changelogs: | |
| | Prefix | Changelog Section | Example | | |
| |--------|-------------------|---------| | |
| | `feat:` | Added | `feat: add JWT authentication` | | |
| | `fix:` | Fixed | `fix: resolve memory leak in connection pool` | | |
| | `docs:` | Changed | `docs: update API documentation` | | |
| | `perf:` | Changed | `perf: optimize database queries` | | |
| | `refactor:` | Changed | `refactor: simplify auth middleware` | | |
| | `chore:` | (excluded) | `chore: update dependencies` | | |
| - `feat:` → Added section | ||
| - `fix:` → Fixed section | ||
| - `docs:` → Changed section | ||
| - `chore:` → Excluded from changelog |
There was a problem hiding this comment.
This list of commit prefixes is incomplete compared to the table in .agent/scripts/commands/full-loop.md. For consistency, please add the perf and refactor prefixes. You could group them to keep the list concise.
| - `feat:` → Added section | |
| - `fix:` → Fixed section | |
| - `docs:` → Changed section | |
| - `chore:` → Excluded from changelog | |
| - `feat:` → Added section | |
| - `fix:` → Fixed section | |
| - `docs:`, `perf:`, `refactor:` → Changed section | |
| - `chore:` → Excluded from changelog |
There was a problem hiding this comment.
Actionable comments posted: 0
🧹 Nitpick comments (1)
.agent/workflows/ralph-loop.md (1)
581-591: Consider consolidating or cross-referencing the documentation guidance to reduce maintenance burden.Duplication confirmed: lines 583–591 ("Documentation in Loops") recap the same points from lines 230–260 ("Documentation Updates")—README updates, changelog commit prefixes (feat/fix/docs/chore), and the workflows/changelog.md reference. The workflows/changelog.md file is accessible.
While this summary-style pattern supports quick recaps before deep dives, it creates maintenance overhead if guidance evolves—both sections require updates. Either consolidate into a single section with cross-references or explicitly clarify this repetition is intentional design for reader convenience.
📜 Review details
Configuration used: Path: .coderabbit.yaml
Review profile: CHILL
Plan: Pro
📒 Files selected for processing (2)
.agent/scripts/commands/full-loop.md.agent/workflows/ralph-loop.md
⏰ Context from checks skipped due to timeout of 90000ms. You can increase the timeout in your CodeRabbit configuration to a maximum of 15 minutes (900000ms). (3)
- GitHub Check: Audit Log
- GitHub Check: Security Block Notification
- GitHub Check: Codacy Static Code Analysis
🔇 Additional comments (4)
.agent/scripts/commands/full-loop.md (2)
54-60: Clarify completion criteria for documentation updates.The new criteria at lines 58–59 mix conditional (README) and mandatory (conventional commits) requirements:
- Line 58: "README.md updated (if adding features/APIs)" — unclear when this is required
- Line 59: "Conventional commits used (for auto-changelog)" — reads as mandatory but is it enforced?
The Documentation & Changelog section below (lines 139–169) treats conventional commits as a pattern/best practice, not a hard requirement. Align the language to clarify whether these are:
- Hard requirements that block task completion
- Best practices/strong recommendations
- Conditional on task type
This affects how users interpret the loop's expectations.
139-176: Documentation & Changelog section is solid and accurately referenced.The section provides clear operational guidance for the full-loop workflow:
- README updates subsection offers practical context with concrete examples
- Commit prefix table elegantly maps prefix → changelog section with real-world use cases
chore:exclusion from changelog is valuable clarity- All referenced workflow files (
workflows/changelog.md,workflows/ralph-loop.md,workflows/preflight.md,workflows/pr.md,workflows/postflight.md) exist and are accessibleNo duplication detected—this section appears exactly once in the file. Well-integrated into the overall workflow structure.
.agent/workflows/ralph-loop.md (2)
574-574: Human decision points table update is well-aligned.The addition of "README updates" to the AI autonomous column in the Task Development row (line 574) correctly reflects the new documentation responsibilities. This consistency with the "Documentation Updates" section above strengthens the overall guidance structure.
230-258: Excellent restructuring: documentation elevated to primary guidance.Replacing "Escape Hatches" with "Documentation Updates" as section 4 appropriately signals that README and changelog management are core responsibilities, not edge cases. The structure is clear:
- README updates (lines 234–243): Concrete example with task output showing completed work — helpful for setting expectations
- Changelog via commits (lines 245–257): Clear dichotomy between good commits (
feat:,fix:,docs:) and excluded (chore:) with examplesThe reference to
workflows/changelog.mdprovides a path to deeper details. Section numbering is consistent throughout, and the "Documentation in Loops" section (lines 581–591) appropriately reinforces this guidance at the phase level. The human decision points table update correctly adds "README updates" to the AI Autonomous column, maintaining alignment with the expanded documentation requirements.
🤖 Augment PR SummarySummary: This PR updates the loop-agent documentation to make documentation responsibilities explicit during loop-driven development. Changes:
Technical Notes: Guidance aligns with the repo’s release tooling, where 🤖 Was this summary useful? React with 👍 or 👎 |



Summary
Changes
ralph-loop.md
full-loop.md (scripts/commands/)
Why
Loop agents didn't explicitly mention:
This caused confusion about documentation responsibilities during loop workflows.
Testing
Summary by CodeRabbit
✏️ Tip: You can customize this high-level summary in your review settings.