- changelog-authoring: a VS Code entry requires the surface to be
mounted from the VS Code entrypoint (consult the surface map in
packages/vscode/src/DOCUMENTATION.md when present); shared-but-unmounted
code earns no entry
- triage-prs: yulia-ivashko is a core maintainer with merge rights —
her review decisions carry maintainer weight in sweeps
Either the manual check guards an irreversible path and the verdict
reads 'MERGE — after you verify X', or the verdict is a plain MERGE
with no checklist: residual cosmetic risk is absorbed by the verdict
(users surface it, a revert costs one commit). Post-merge homework
lists were the reviewer offloading uncertainty onto the maintainer.
- PRs/issues with human thread activity run in pickup mode across all
three skills: the output opens with thread state (asked / answered /
resolved at HEAD / remaining) and continues the conversation instead
of restarting review — the sweep remembers the maintainer's own
comments for them
- every PR/issue reference in maintainer-facing output is a clickable
markdown link, never a bare number
- report entries are calibrated: 2-4 sentences each (what, why this
verdict, main risk), needs-your-hands lives inside the entry rather
than a number-repeating section
A sweep verifies whether an earlier push-back or recorded product
decision was addressed at the current HEAD and reports that explicitly;
it never re-decides or re-asks. The generic rebase-request is never
posted over an existing substantive review comment.
Comments and reviews from patrick-motard and mattv8 are strong human
signals during batch triage: their approval upgrades confidence, their
concerns become findings to verify. They write free-form; sweeps map
their conclusions onto the verdict ladder.
Re-enable the automated PR review (pull_request_target + /oc-review
comments) on zai-coding-plan/glm-5.3-flash via ZHIPU_API_KEY.
Recalibrate the output contract based on an audit of 69 past reviews
(22 PRs, Aug 15-18): 18 of 27 BLOCKED verdicts were template-policing,
3.1 reviews per PR, ~8.4K chars per comment.
- BLOCKED now means code/merge problems only; handoff/template gaps move
to a separate one-line Handoff flag that never changes the verdict
- re-reviews emit deltas (verdict + what changed) instead of full
re-emission; push-triggered re-reviews are throttled to one per 15
minutes (manual /oc-review always runs)
- hard length budgets by change class; the applied-guidance table is
gone (guidance is applied silently, named only when it produced a
finding); empty evidence/security sections are omitted
- evidence demands are single-shot and escapable, never raised for
dependency bumps, string edits, server code, or packaging
- the comment opens with a one-line maintainer verdict (merge / merge
after X / don't merge because Y), enforced by the workflow
- triage-prs skill treats review:* labels as a pre-sort for verdict
reviews
Bohdan Triapitsyn