ci: add Codex PR auto-review (homelab fleet rollout)#7
Merged
Conversation
Adds the Codex review workflow + generic homelab rubric + output schema, matching openclaw-homelab. Requires the OPENAI_CODEX_REVIEW_KEY repo secret to activate (soft-fails until then). Co-Authored-By: Claude <noreply@anthropic.com> Claude-Session: https://claude.ai/code/session_01A2mPyA6bLEBRQCA4aYZY9k
🤖 Codex Review — failedCodex did not produce a review for commit Failure of this optional review is non-blocking and does not gate merging. |
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
1 participant
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Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be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.
Summary
Adds Codex PR auto-review to this repo as part of the homelab fleet rollout — the same mechanism already running on
openclaw-homelab. On each PR a GitHub Action runs OpenAI Codex (read-only sandbox) against a Claude-Code-optimized rubric and posts a structured review comment (verdict +file:linefindings + severity + confidence + embedded JSON). Non-blocking by design.Files added:
.github/workflows/codex-review.yml— review workflow (pinned action + CLI + modelgpt-5.5,effort: xhigh)..github/codex/rubric.md— homelab-generic rubric (Claude-Code-consumer optimized; secret-hygiene + operational-safety first)..github/codex/rubric.schema.json— strict output schema.Required follow-up (review is inert until then)
Needs the repo Actions secret
OPENAI_CODEX_REVIEW_KEY(dedicated OpenAI key). Until set, the codex step soft-fails (continue-on-error) and posts a non-blocking "did not produce a review" comment.Generated with Claude Code
https://claude.ai/code/session_01A2mPyA6bLEBRQCA4aYZY9k