poll

# Poll PR and Act on Feedback Poll PR #$ARGUMENTS for CI, CodeRabbit, and human review status, then fix what's broken. The script manages its own state in `.claude/poll-state/pr-$ARGUMENTS.json` and loops internally with adaptive backoff (120-600s). It shows a full report on the first run, then delta-only on subsequent polls so only new events surface. ## CRITICAL: always use run_in_background: true Run the script via the Bash tool with `run_in_background: true`. **Never use `&`** to background it in the shell — that detaches the process and makes the exit code invisible. ```bash # Bash tool call — set run_in_background: true bash .claude/scripts/poll-pr.sh $ARGUMENTS ``` The script sleeps and polls on its own. Do not interrupt it. When it exits, you will be notified automatically. ## Exit codes — what to do when notified | Code | Meaning | Action | |------|---------|--------| | 0 | All checks pass | Ready to merge | | 1 | CI failures | Fix code, push, re-run (background again) | | 2 | Checks pending | Should not exit 2 unless --max-polls hit; re-run | | 3 | Inline review comments | Address comments, push, re-run (background again) | | 4 | Awaiting human review | Reviewer team notified; CronCreate to re-poll later | ## Exit 4 — schedule a re-poll cron When the script exits 4, it has already posted a comment and requested reviewers. Use CronCreate to check back automatically: ```text CronCreate: every 2 hours, /poll $ARGUMENTS ``` Delete the cron (CronDelete) once the PR is approved or merged. ## Exit 1 — CI failures Run the relevant test/lint commands per the project's `AGENTS.md` to reproduce and fix failures locally. After fixing: push, then re-run the script via Bash with `run_in_background: true`. ## Exit 3 — inline review comments Run `--once --full` to see comments with reply/resolve commands: ```bash bash .claude/scripts/poll-pr.sh $ARGUMENTS --once --full ``` **Evaluate each comment critically — automated reviewers are often right but not always.** Read the full context, understand what it's flagging, and make a genuine judgment call: - **Valid**: fix the code, then reply explaining what you changed before resolving - **Invalid or inapplicable**: reply with your reasoning, then resolve - **Unclear**: reply asking for clarification (do NOT resolve) Steps: 1. Read all inline comments (reply command + resolve command shown per thread) 2. Evaluate: fix, reply with rationale, or ask a follow-up question 3. Once settled, resolve the thread via GraphQL 4. Push and re-run the script via Bash with `run_in_background: true` ## Push and re-run ```bash git add -A && git commit -m "type(scope): address feedback" git push origin <branch> # then re-run poll via Bash tool with run_in_background: true ``` Repeat until exit 0.