+Schema v19 adds `task_pull_requests.check_id` (the pre-PR check each opening followed) and `merge_jobs`: one row per job or refused click, with three columns: `id` (the click's action ID, primary key), `plan_key` (the task, indexed by `merge_jobs_plan`) and `data`. `data` is a JSON record holding the rest: the click's review token, the guarded merge's action ID once the job reaches that step, `state`, `step`, `reason`, required-check names and states, the merge result URL, start and update times, and `refused` for a refused click. Lookups by state (the running job, the latest job that was not refused) read these JSON fields. A refused click's row is replayed to that click and never shown as the task's job. Writing it never changes the task's state version, so the readiness preparation recorded stays valid while the job waits. A resend of the same click returns its row; another click while a job runs is refused. While a job runs, `prepare-merge` is refused (the job prepares the merge itself). `publish` is refused too, by publishing's own status rule: it publishes only a running task whose plan items have all run, or a task that needs a person, and a job runs only for a task in review or approved but merge blocked. So no publish can push the pull request's head or begin a refresh of it while the job prepares, waits or merges.
0 commit comments