Keep an eye on this PR. Review and resolve pull request comments and fix build failures autonomously. Use when asked to review PR feedback, address reviewer comments, fix CI failures, resolve PR threads, or handle PR maintenance tasks like "review PR comments", "fix the build", "address PR feedback", "clean up PR", or "resolve comments". Handles comment triage (resolve false positives, fix trivial issues, flag complex ones), build/lint/type errors, and e2e snapshot updates.
Autonomously review PR comments and build status, resolving what can be done with high confidence (>=80%) and flagging the rest for human review.
Note: this repository requires that you be using node 24. Use nvm to switch to node 24 before running any commands:
nvm use 24
# Get PR number for current branch
gh pr view --json number,headRefName,url
# Get review threads with resolution status
gh api graphql -f query='
query($owner: String!, $repo: String!, $number: Int!) {
repository(owner: $owner, name: $repo) {
pullRequest(number: $number) {
reviewThreads(first: 100) {
nodes {
id
isResolved
comments(first: 50) {
nodes {
body
path
line
author { login }
createdAt
databaseId
}
}
}
}
}
}
}
'
Filter to unresolved threads only.
Read the referenced code and investigate. Classify into:
A. False positive / already resolved — The issue no longer exists in current code.
B. Trivial fix (>=80% confidence) — Obvious, mechanical fix. No design decisions or matters of opinion. Examples: typos, missing null checks, wrong variable names, off-by-one, missing imports.
C. Needs human input (<80% confidence) — Design question, significant refactor, or ambiguous fix.
Reply to a comment:
gh api repos/{owner}/{repo}/pulls/{number}/comments/{comment_id}/replies \
-f body="<your reply>"
Resolve a thread:
gh api graphql -f query='
mutation($threadId: ID!) {
resolveReviewThread(input: {threadId: $threadId}) {
thread { isResolved }
}
}
' -f threadId="$THREAD_ID"
Always push fixes, then reply, then resolve related threads (in that order).
gh pr checks --json name,status,conclusion
Investigate failures by category:
Lint errors — Run yarn lint-current. Fix if mechanical (formatting, import order, unused vars). Flag if the lint rule itself is questionable.
Type errors — Run yarn typecheck from repo root. Fix straightforward type mismatches. Flag if fix requires architectural decisions.
Unit test failures — Run yarn test run in relevant workspace. Fix if test expectation is clearly outdated due to intentional code changes. Flag if failure reveals actual bug or design concern.
E2E snapshot failures — Determine whether the PR's code changes should cause visual differences:
update-snapshots label to trigger the automated update workflow:
gh pr edit --add-label "update-snapshots"
Mysterious/unexpected failures — Do not attempt to fix. Flag for human review with error output.
git add <specific files>
git commit -m "Address PR review feedback
- <summary of changes>"
git push
Stage specific files only. Never force push. Never use git add -A.
Always end with:
## PR review summary
### Resolved
- <thread>: <what was done>
### Fixed
- <description of fix>
### Needs your input
- <thread>: <why it needs human judgment>
### Build status
- <status of each check, any actions taken>
Omit empty sections.
yarn typecheck) or lint (yarn lint-current).