Skip to content

chore: silence bot reviewers (Claude high-signal, CodeRabbit disabled) - #168

Merged
thomasluizon merged 1 commit into
mainfrom
chore/silence-bot-reviewers
May 19, 2026
Merged

chore: silence bot reviewers (Claude high-signal, CodeRabbit disabled)#168
thomasluizon merged 1 commit into
mainfrom
chore/silence-bot-reviewers

Conversation

@thomasluizon

@thomasluizon thomasluizon commented May 19, 2026

Copy link
Copy Markdown
Owner

Summary

The chat-clarification PR (#167) generated 14 rounds of bot reviews and 101 resolved threads. Each push produced fresh findings — eventually all just style / wording / hypothetical-future-proofing. The loop never converges because bots are optimized to surface findings, not to approve.

This PR rewrites .github/workflows/claude-review.yml to enforce a strict high-signal-only bar (correctness, security, contract break, missing-test on mutating state, AGENTS.md hard rules) and requires Claude to pick one of three formal review states: APPROVE (default), REQUEST_CHANGES, or COMMENT. Manufacturing nits to avoid approving is explicitly called out as a bug.

CodeRabbit and ChatGPT Codex auto-reviews are disabled at the integration level (their respective dashboards / app uninstalls), not via repo files.

Why now

Real correctness/security findings landed in rounds 1-6 of the chat-clarification review. Rounds 7-14 were all polish: EventId ordering, comment wording, optional-chaining-vs-typeof flip-flops, .nullable().optional() modifier purity. None blocked merging.

Test plan

Follow-ups (manual, not in this PR)

🤖 Generated with Claude Code

Bot reviewers were generating infinite nit-cycle reviews — each push
triggered a fresh full-PR rescan that surfaced increasingly small
style / wording / hypothetical-future-proofing findings, never
converging on approval.

This rewrites the Claude review workflow prompt to enforce a strict
high-signal-only bar (correctness, security, contract, missing-test on
mutating state, AGENTS.md hard rules) and require an explicit APPROVE /
REQUEST_CHANGES / COMMENT outcome via `gh pr review`. Default is APPROVE
— manufacturing nits to avoid approving is now explicitly called out as
a bug. Added Bash(gh pr review:*) to the allowed tools.

CodeRabbit and ChatGPT Codex auto-reviews are disabled at the
integration level (CodeRabbit and ChatGPT settings respectively); no
repo files needed.

Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
@thomasluizon
thomasluizon force-pushed the chore/silence-bot-reviewers branch from 37f0743 to 6c01477 Compare May 19, 2026 20:06
@coderabbitai

coderabbitai Bot commented May 19, 2026

Copy link
Copy Markdown

Note

Currently processing new changes in this PR. This may take a few minutes, please wait...

⚙️ Run configuration

Configuration used: defaults

Review profile: CHILL

Plan: Pro Plus

Run ID: a47b259b-f633-4a00-ab83-d48ac695124a

📥 Commits

Reviewing files that changed from the base of the PR and between 8c6a816 and 6c01477.

📒 Files selected for processing (1)
  • .github/workflows/claude-review.yml
 ___________________________________________________________________________________________________________________
< Work with a user to think like a user. It's the best way to gain insight into how the system will really be used. >
 -------------------------------------------------------------------------------------------------------------------
  \
   \   \
        \ /\
        ( )
      .( o ).
✨ Finishing Touches
🧪 Generate unit tests (beta)
  • Create PR with unit tests
  • Commit unit tests in branch chore/silence-bot-reviewers

Comment @coderabbitai help to get the list of available commands and usage tips.

@thomasluizon
thomasluizon merged commit 26cf9cb into main May 19, 2026
1 of 3 checks passed
@thomasluizon
thomasluizon deleted the chore/silence-bot-reviewers branch May 19, 2026 20:07
Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment

Labels

None yet

Projects

None yet

Development

Successfully merging this pull request may close these issues.

1 participant