Conversation
The review job has exited `success` on eight PRs without ever posting; #82 recorded two permission denials and an empty inline comment buffer, and the SDK output is suppressed by default so the denied tools cannot be identified. Turn on `show_full_output` to capture them, and fetch full history so the review has a base commit to diff the head against. Both changes are diagnostic and meant to be reverted or narrowed once the cause is known. Signed-off-by: Alejandro Mery <amery@apptly.co>
|
Warning Review limit reached
Next review available in: 80 minutes You've used all free OSS reviews for now. Wait for the free limit to reset to keep reviewing this public repository. How can I continue?After more reviews become available, a review can be triggered using the To avoid repeated limits, reduce automatic review volume by pausing incremental auto-reviews earlier, using label-based review opt-in, excluding WIP or generated PR titles, or requesting reviews manually when the PR is ready. If your team needs uninterrupted high-volume reviews, an organization admin can enable usage-based reviews. How do review limits work?CodeRabbit enforces per-developer PR review limits for each organization. Most developers receive the normal plan review availability. For paid Pro and Pro+ PR reviews, CodeRabbit uses adaptive limits for sustained high-volume activity. When a developer's recent PR review activity reaches the 95th percentile or higher among CodeRabbit users, additional reviews become available more gradually as earlier reviews age out of the rolling window. Please refer docs for additional details. Review details⚙️ Run configurationConfiguration used: defaults Review profile: CHILL Plan: Pro Plus Run ID: 📒 Files selected for processing (1)
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 |
Diagnostic, not a fix. Opened so the Claude review job runs against
a real PR with its output visible.
Why
The job has exited
successon eight non-renovate PRs without everposting a comment —
pr-amery-plugin(×3),pr-amery-eslint-config,pr-amery-workflows,pr-amery-chores,pr-amery-deps-eslint-configandpr-amery-scripts. Everythingsince 2026-04-07 has been renovate-authored and correctly skipped by
the actor filter, which masked the problem.
The one run whose log survives, on #82, ended:
{"type":"result","subtype":"success","is_error":false, "num_turns":8,"total_cost_usd":1.0125425, "permission_denials_count":2}and its final step reported
No buffered inline comments. So theagent ran for eight turns, had two tool calls denied, and buffered
nothing for the action to post.
The denials are not GitHub token scopes — the job grants
pull-requests: writeandissues: write, and the runner confirmsboth. They are Claude Code's own tool gate, which has no allowlist to
work from:
git ls-files .claudeis empty, so nothing repo-sidereaches the runner even though the action reads
projectsettings.What this changes
show_full_output: true— the SDK output is suppressed bydefault, which is why the two denied tools cannot be named.
fetch-depth: 0— a depth-1 checkout gives the review no basecommit to diff the head against.
Next
Read the denial lines from this PR's run, then either commit a
.claude/settings.jsongranting the tools involved or pass them viaclaude_args, and revert or narrow both changes here.