🤖 docs: bound the PR review loop by scope, not round count - #4208
Conversation
Add early-stop cases for non-converging review loops and a scope classification for review fixes to the PR Workflow section of AGENTS.md. --- _Generated with `xum` • Model: `anthropic:claude-fable-5-1` • Thinking: `high` • Cost: `$940.64`_ <!-- mux-attribution: model=anthropic:claude-fable-5-1 thinking=high costs=940.64 -->
|
Preview deployment for your docs. Learn more about Mintlify Previews.
💡 Tip: Enable Automations to automatically generate PRs for you. |
Codex Review SummaryThis comment shows the latest Codex review activity on this pull request.
ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
Codex reacts with 👀 while any review is running, comments if it has suggestions, and reacts with 👍 once all reviews finish with no findings. |
|
@codex review |
--- _Generated with `xum` • Model: `anthropic:claude-fable-5-1` • Thinking: `high` • Cost: `$940.64`_ <!-- mux-attribution: model=anthropic:claude-fable-5-1 thinking=high costs=940.64 -->
🛡️ Codex Security Review · Automatically triggeredSecurity review completed. No security issues were found in this pull request. Reviewed commit: Only the user who started this review can view the report in Codex. ℹ️ About Codex security reviews in GitHubThis is an experimental Codex feature. Security reviews are triggered when:
Once complete, Codex will leave suggestions, or a comment if no findings are found. |
|
@codex review |
![chatgpt-codex-connector[bot]](https://avatars.githubusercontent.com/in/1144995?s=60&v=4){kind=small}
There was a problem hiding this comment.
💡 Codex Review
Here are some automated review suggestions for this pull request.
Reviewed commit: a60cdd0010
ℹ️ About Codex in GitHub
Your team has set up Codex to review pull requests in this repo. Reviews are triggered when you
- Open a pull request for review
- Mark a draft as ready
- Comment "@codex review".
If Codex has suggestions, it will comment; otherwise it will react with 👍.
Codex can also answer questions or update the PR. Try commenting "@codex address that feedback".
🛡️ Codex Security Review · Automatically triggeredSecurity review completed. No security issues were found in this pull request. Reviewed commit: Only the user who started this review can view the report in Codex. ℹ️ About Codex security reviews in GitHubThis is an experimental Codex feature. Security reviews are triggered when:
Once complete, Codex will leave suggestions, or a comment if no findings are found. |
Split the success prohibition from the stop exception, classify fixes by whether this PR introduced the defect instead of by diff size alone, and base deferral on the defect rather than its trigger condition. --- _Generated with `xum` • Model: `anthropic:claude-fable-5-1` • Thinking: `high` • Cost: `$940.64`_ <!-- mux-attribution: model=anthropic:claude-fable-5-1 thinking=high costs=940.64 -->
|
@codex review |
|
Codex Review: Didn't find any major issues. Already looking forward to the next diff. Reviewed commit: ℹ️ About Codex in GitHubYour team has set up Codex to review pull requests in this repo. Reviews are triggered when you
If Codex has suggestions, it will comment; otherwise it will react with 👍. Codex can also answer questions or update the PR. Try commenting "@codex address that feedback". |
🛡️ Codex Security Review · Automatically triggeredSecurity review completed. No security issues were found in this pull request. Reviewed commit: Only the user who started this review can view the report in Codex. ℹ️ About Codex security reviews in GitHubThis is an experimental Codex feature. Security reviews are triggered when:
Once complete, Codex will leave suggestions, or a comment if no findings are found. |
1 participant
Summary
The PR Workflow section of
AGENTS.mdnow bounds the Codex review loop by scope instead of by "iterate until clean". It adds two early-stop cases (the loop does not converge, or the next fix grows the scope) and a classification for review fixes that keeps a PR recognizable as the change it started as.Background
PR #4139 grew from +447/-64 to +15.8k/-506 over 91 Codex rounds because every finding was fixed in place, including findings that needed new modules, on-disk artifacts, persisted fields, and second-backend races. The existing guidance had one early-stop case (reviewer misunderstands the change) and no scope rule. ThomasK33 asked for guidance that describes the shape of scope growth without hard numeric thresholds, written in plain English (short sentences, condition before command, numbered steps).
Implementation
Doc-only change to
docs/AGENTS.md(the rootAGENTS.mdis a symlink):### Review fixes and scopesubsection: fix in place when small and inside the original change, otherwise reply on the thread, resolve, and deliver as a stacked PR (gh stack) or tracked follow-up. Findings that need corrupted persisted state, narrow crash windows, or a second racing backend are deferrable unless the PR introduced that surface. A reasoned rejection is a valid resolution.Risks
None at runtime. Agent behavior changes: agents will pause and report a split proposal instead of growing a PR under review.
Generated with
xum• Model:anthropic:claude-fable-5-1• Thinking:high• Cost:$940.64