Switch overnight PR reviews to Codex - #203
Merged
Merged
Conversation
Restrict unattended Codex writes to review artifacts, preserve engine-specific failure classification, and cover persisted caps and author filtering.
There was a problem hiding this comment.
🟡 Changes recommended
Claude rate-limit detection is not gated on a failing exit code, which can misclassify successful reviews if output contains matching phrases.
Once you've addressed the issues Copilot identified, you can request another Copilot review.
Pull request overview
This PR updates the dotfiles’ automated PR-review automation to support running unattended overnight reviews via the Codex CLI (while keeping Claude as the default for manual runs), including new safety limits and better classification of engine-level failures.
Changes:
- Add
--engine,--author-team, and--daily-max-prssupport so scheduled runs can use Codex, restrict candidate authors, and cap daily attempts (including failures). - Update the
review-all-prsLaunchAgent/service wrapper to run Codex, review one PR per hourly tick, and limit to two attempts per calendar day. - Add offline test coverage for Codex JSONL extraction, token usage capture, author-team filtering, and daily attempt limits.
File summaries
| File | Description |
|---|---|
| README.md | Documents Codex/Claude engine selection, unattended LaunchAgent behavior, and prerequisites. |
| macos/LaunchAgents/com.haacked.review-all-prs.plist | Switches scheduled job arguments to run Codex with author filtering and safety limits. |
| bin/run-pr-reviews.sh | Implements engine boundary (Claude vs Codex), daily attempt cap, Codex JSONL parsing, and engine auth/quota handling. |
| bin/review-all-prs.sh | Adds --author-team as a strict post-merge filter and refactors team member retrieval. |
| bin/review-all-prs-service.sh | Keeps service wrapper args aligned with LaunchAgent: Codex + filters + caps. |
| bin/lib/test-run-pr-reviews.sh | New offline test suite covering Codex execution sandboxing, artifacts, usage capture, and daily limits. |
| bin/lib/test-review-search-queries.sh | Extends query tests for --author-team behavior and repeatability. |
Review details
- Files reviewed: 2/7 changed files
- Comments generated: 0
- Review effort level: Lite
💡 Add a code-review agent skill or configure MCP servers for context-aware, tailored reviews. Learn more in the docs.
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
team-feature-flagsauthors, start one PR per hourly tick, and allow two attempts per calendar day, including failures.Test plan
bin/lib/test-review-search-queries.sh(29 passed)bin/lib/test-run-pr-reviews.sh(39 passed)