feat: add quality subagents, session checkpoints, and GitHub issue sync docs #470
Conversation
…nc docs Cherry-picked unique content from closed PR #446 (supervisor changes were stale). New subagents: backlink-checker, voice transcription/models, document extraction, terminal optimization, subscription audit, rapidfuzz, x-helper. New scripts: session-checkpoint-helper.sh (compaction resilience), x-helper.sh (X/Twitter posting). Doc additions: GitHub issue sync convention in plans.md, compaction resilience workflow in session-manager.md.
|
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. ✨ Finishing touches🧪 Generate unit tests (beta)
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 significantly enhances the Highlights
Changelog
Activity
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: Sat Feb 7 19:48:37 UTC 2026 Generated by AI DevOps Framework Code Review Monitoring |
|
![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 two new helper scripts, session-checkpoint-helper.sh and x-helper.sh, along with extensive documentation for new subagents and workflows. The new features for session checkpointing and GitHub issue syncing are well-documented.
My review found a critical bug in both new shell scripts related to argument parsing that would prevent them from functioning correctly. I've also suggested a small improvement for error handling in x-helper.sh and a fix for an incomplete code example in one of the new documentation files. Overall, the changes are a great addition once the critical issues are addressed.
| # Main dispatch | ||
| main() { | ||
| local command="${1:-help}" | ||
| shift 2>/dev/null || true |
There was a problem hiding this comment.
The shift 2 command is incorrect and will cause argument parsing to fail for most commands. For example, if you run session-checkpoint-helper.sh save --task 1, shift 2 will consume both save and --task, leaving only 1 to be passed to cmd_save, which will then fail. This should be shift or shift 1 to only consume the command name itself.
| shift 2>/dev/null || true | |
| shift || true |
|
|
||
| main() { | ||
| local command="${1:-help}" | ||
| shift 2>/dev/null || true |
There was a problem hiding this comment.
The shift 2 command is incorrect and will cause argument parsing to fail. It attempts to shift two arguments, but only the command name should be shifted before parsing the remaining options. For example, running x-helper.sh fetch <url> would result in the URL being consumed by the shift, causing the fetch command to fail due to a missing URL. This should be shift or shift 1.
| shift 2>/dev/null || true | |
| shift || true |
| response=$(curl -fsS --max-time 20 --retry 2 --retry-connrefused \ | ||
| "${FXTWITTER_API}/${path}" 2>/dev/null) || { |
There was a problem hiding this comment.
Suppressing curl's stderr with 2>/dev/null prevents important error messages from being displayed, making it harder to debug failures (e.g., network issues, timeouts, DNS errors). The -S option is used with curl, which is intended to show errors even with -s, but 2>/dev/null overrides this. Removing the redirection will improve debuggability while maintaining silent operation on success. This also applies to the curl call in cmd_user.
| response=$(curl -fsS --max-time 20 --retry 2 --retry-connrefused \ | |
| "${FXTWITTER_API}/${path}" 2>/dev/null) || { | |
| response=$(curl -fsS --max-time 20 --retry 2 --retry-connrefused \ | |
| "${FXTWITTER_API}/${path}") || { |
| ### Invoice | ||
|
|
||
| ```python | ||
| class Invoice(BaseModel): |
There was a problem hiding this comment.
The code example for the Invoice schema is incomplete because the LineItem class it references is not defined. This makes the example non-runnable and potentially confusing. A similar issue exists for ReceiptItem in the Receipt schema. To make the examples self-contained, please define these nested Pydantic models before they are used.
| class Invoice(BaseModel): | |
| class LineItem(BaseModel): | |
| description: str | |
| quantity: float | |
| unit_price: float | |
| total: float | |
| class Invoice(BaseModel): |
1 participant
Summary
New Files
Scripts:
session-checkpoint-helper.sh— Persist session state to survive context compaction during long autonomous sessionsx-helper.sh— X/Twitter posting helperSubagent docs:
seo/backlink-checker.md— Backlink analysistools/voice/transcription.md— Voice transcriptiontools/voice/voice-models.md— Voice model selectiontools/document/document-extraction.md— Document extractiontools/terminal/terminal-optimization.md— Terminal optimizationtools/accounts/subscription-audit.md— Subscription auditingtools/context/rapidfuzz.md— Fuzzy matchingDoc Updates
workflows/plans.md— Added "GitHub Issue Sync" convention (t-number prefixes on issues, ref:GH# on tasks)workflows/session-manager.md— Added "Compaction Resilience" section with checkpoint workflowsubagent-index.toon— Added session-checkpoint-helper.sh entry