Martin Vogel
05dc3fc497
The acknowledgement text described a state of the world that ended when 0.9.1-rc.1 published: it told every new contributor we were still finishing release-critical work and that "review resumes once the release path is clear". Posting that now would be false on the day it starts running. This is the obligation the PR description already set for itself -- the review-status section is a public promise and has to be edited when the situation it describes changes. Doing that before the workflow ever posts, rather than after someone reads a stale freeze notice, is the point. The queue is still real, so the section stays rather than being removed: the freeze is over, a large backlog is not, and PRs are being read oldest-first. Saying that is more useful to someone opening a PR today than either the old text or silence, because it explains why a recent PR sits behind older ones. Signed-off-by: Martin Vogel <martin.vogel.tech@gmail.com>
1.9 KiB
1.9 KiB
Thanks for opening this — it has been seen, and it is queued.
This note is automated, but it is not a brush-off: it exists so you know where your PR stands instead of having to guess from silence.
Current review status: working through a backlog. 0.9.1-rc.1 is out, so the release freeze that held reviews is over — but it left a large queue of open pull requests behind it, and we are reading through them oldest-first. The background is in discussion #1144.
What that means for this PR, concretely:
- It will not be closed for inactivity. No stale bot touches pull requests here.
- It may still sit a while before a human reads it. That is on us, not on you.
- Older PRs are read first, so a recent one is not being skipped — it is behind a queue.
Things that will genuinely speed it up whenever review does happen:
- Keep it rebased on
main— the tree is moving quickly right now, and a conflicting branch cannot be reviewed as the diff you intended. - Get CI green, or say which failures you believe are pre-existing.
- Keep the change to one claim. Bundled features and refactors get split before they get merged, which costs you a round trip.
- Every commit needs a sign-off (
git commit -s) — CI enforces DCO.
If this fixes a bug, a reproduction we can run is worth more than a description of the symptom.
Thanks for contributing, and sorry in advance for the wait.