harness: codex
prompt: zstack: these three tickets are independent, run them in parallel: add --version flag, fix README typo, add a json export format
exit: 0  seconds: 22
zstack files read: SKILL.md, playbooks/autopilot-queue.md, references/harness-capabilities.md, references/principles/one-owner-per-file.md, references/principles/smallest-reversible-change.md, references/principles/evidence-before-the-word.md
---
Route: autopilot-queue, shape: lane, principles: one-owner-per-file, smallest-reversible-change, evidence-before-the-word

Goal: plan three parallel workers for `--version`, the README typo, and JSON export, each in its own worktree. Done for this dry run means the route and todo list are provided. No workers started or files edited. Fleet tooling is unavailable, so execution is capped at lane.

Todo list, copied from the playbook; all steps are deferred for the dry run:

1. [ ] Print the trust table with `<zstack dir>/scripts/trust.sh` and write down, per class, whether zStack may merge (L2 or higher) or only open PRs.
2. [ ] For each ticket, confirm nobody owns it: search open PRs, remote branches and local worktrees for the ticket key. Any hit means it is owned; skip it and note why.
3. [ ] Predict the files each ticket will touch and classify them (`<zstack dir>/scripts/classify.sh --files <list>`). Tickets whose predicted files overlap go in the same lane or run in sequence. Solo-class tickets run alone and open with `hold`.
4. [ ] Give each ticket one owner: spawn a background subagent in its own worktree with a brief from `<zstack dir>/templates/worker-brief.md`, naming the playbook that fits the ticket (`feature`, `debug`, `refactor` and so on) and the principles in force. Hot files (lockfiles, CI workflows, migration indexes, route registries) are leased to one worker at a time.
5. [ ] Start at most three workers in any two minutes, and add more only while the machine stays responsive. Tell every worker to read `.git/zstack/board.md` before it starts and to append a one-line `FAIL` entry (what was tried, why it failed, commit or log) whenever an approach fails, so the others skip that dead end.
6. [ ] Count a worker as alive only when it produced output (a report, a commit or a file change) in the last 10 minutes. Nudge it at 30 minutes of silence; at 60, stop it by its captured pid and start a fresh worker in the same worktree. Its claim on the ticket and its leased files expires at the same point, so another worker may take them over.
7. [ ] Questions that need the human go to `.git/zstack/decisions.md` as in `human-busy`; workers move to work that does not need the answer.
8. [ ] When a worker reports a PR open, have a second agent (a different worker from the author) run `review` on it at its head sha.
9. [ ] Run `land` for each PR that passed review, one merge at a time, oldest first. Merge only where `<zstack dir>/scripts/trust.sh --gate <class>` passes; everything else waits for the human with its evidence.
10. [ ] After each merge, list PRs that went behind or conflicting and send them through `babysit-pr`, oldest first, one rebase each.
11. [ ] Schedule a wake-up between rounds instead of waiting on workers or watching CI.
12. [ ] When the queue is empty or every remaining ticket waits on the human, write a summary: merged (with merge shas), open and waiting (with why), blocked on decisions, follow-ups by class.

Principles shaping the plan:

- `one-owner-per-file`: check overlap before dispatch and assign exclusive file ownership.
- `smallest-reversible-change`: keep each ticket independently reviewable and revertible.
- `evidence-before-the-word`: make no completion claims without recorded checks.
