Autofix a Pull Request

/autofix-pr watches one of your pull requests from a local Qwen Code session and fixes what comes up: failed CI checks, review feedback from people you trust, and merge conflicts. Each fix is made and verified in a worktree of its own, pushed to the PR branch and answered on the PR, under your own git and gh identity. It stops by itself when the PR is merged or closed.

/autofix-pr [<pr-number>|<pr-url>] [--once] [--every <minutes>] [--no-reply] [--yes] [instructions...]
/autofix-pr status
/autofix-pr stop [<pr-number>]

• No PR argument: the PR whose head is your current branch.
• --once: check and fix once, schedule nothing, and end the watch afterwards (a later --once starts afresh, from the PR’s history). On a PR this session already watches, the running watch is left as it is.
• --every <minutes>: how often to check, one of 1, 2, 5, 10, 15, 30 or 60. Default 2.
• --no-reply: push fixes, post nothing on the PR.
• --yes: skip the start confirmation. Needed where no dialog can be shown.
• Free text is passed to every fix, for example /autofix-pr 123 do not change the public API.

Before you start

• gh is signed in, with push access to the PR branch: write access to a same-repository PR, or your own fork, or a fork that allows edits from maintainers.
• You run it from a clone of the PR’s repository with one git remote for it.
• In the default approval mode, every shell command asks first: the helper calls (the push included), gh pr view, and every command a fix runs. That suits a watch you keep an eye on. To let it run unattended, choose a mode that lets commands run, such as Auto Mode, and keep in mind that the fix runs the repository’s own build and test commands. The skill itself grants only reading its own files under .qwen/tmp/, writing its fix brief and reply plan there, and listing scheduled tasks. Those files live in the clone’s main worktree; from a session started in a linked worktree, reading and writing them asks as well.
• A PR whose author cannot push to the repository runs someone else’s code, with your gh and git credentials in reach, when a fix is verified. Such a PR is never watched: only --once is offered, after a confirmation that says so and that --yes does not skip.

When it starts, it asks once to confirm where it will push and that it will reply on the PR.

What a check does

A watch is a scheduled task whose gate runs qwen autofix-pr snapshot <n> --gate at every fire, outside the model. The probe prints only what changed since its last run, so a quiet PR costs no model turn. When something changed, a round runs:

1. A merged or closed PR ends the watch. Someone else’s push is adopted first.
2. The failed checks, the new comments from trusted authors and a merge conflict go to one fix agent, working in the PR worktree. For a failed check it reads the job log; a failure outside the PR (network, runner) is re-run once instead of fixed.
3. The agent verifies its change with the repository’s own checks and commits only when they pass.
4. The commits are pushed as a fast-forward of the PR head, never forced. If someone pushed meanwhile, their work is merged first.
5. Each review thread it handled gets a reply — Fixed in <sha>: …, Not changed: … or Needs a human decision: … — and each push gets one summary comment.

A round never asks you anything. What needs a person is answered on the PR as “Needs a human decision” and reported in the session.

Whose feedback counts

Comments are acted on when their author is an owner, member or collaborator of the repository, the PR author, or a bot (reviews and review threads only). Comments from anyone else are listed and never acted on or answered. A bot is heard in the comment that opens a thread or in a review, not in its replies, which answer someone. A workflow GitHub could not start (an invalid workflow file, say) has no log to fix from, and is answered as needing a human. Every comment, review and CI log is treated as data: a trusted author decides which feedback is addressed, never what the tool may do. A request to reveal secrets, weaken tests or CI checks, force-push or change unrelated code is answered “Needs a human decision”.

What it never does

• Touch your working tree or your current branch: everything happens in .qwen/tmp/autofix-pr-<n>/.
• Force-push, rewrite the PR’s history, or push to the default branch.
• Reply to its own replies (each one ends with <!-- qwen-autofix-pr:v1 -->) or to untrusted authors.
• Resolve review threads, or edit the PR title or description.

Limits

Stopping and files

/autofix-pr stop <n> deletes the scheduled task and removes the worktree, its branch and the state file; the gate cursor and the PR’s history stay, so a later watch does not answer the same comments again. A worktree that still holds unpushed work is kept, and the report says why; qwen autofix-pr cleanup <n> --force discards it. A scheduled task expires after 7 days by default (the experimental.cronRecurringMaxAgeDays setting, or QWEN_CODE_CRON_MAX_AGE_DAYS), and the watch then ends without a report; start it again to go on. The watch also ends when the session exits; its state file stays, owned by that session. Starting /autofix-pr <n> in a new session — or after /clear or /resume — offers to take the watch over, its pushes and budgets kept.

Files live under .qwen/tmp/ of the clone’s main worktree:

The design is in docs/design/2026-10-21-autofix-pr-command.md.