Files
pipelines/internal/author/skill/references/queue.md
T

1.3 KiB

Queue and integration

Keep one concise list: item, current source/branch, next action and blocker. Track implemented, tested, landed and deployed separately. Preserve run IDs and commit references; the server is authoritative for execution status, Git for source.

Run independent small items concurrently in separate worktrees. A possible small merge conflict is not a dependency. Serialize exclusive device use, real source dependencies and measured machine/provider capacity limits.

The manager can perform direct recovery, testing and merges; a pipeline is not required to finish another failed workflow. Do not start a separate landing pipeline. When a stage has delivery=true, its clean successful candidate is landed by the server after the stage returns. Do not demand ancestry before that happens.

Before a direct merge, inspect the candidate and main, preserve unrelated work, integrate main into the candidate if necessary, resolve conflicts and run relevant checks. Coordinate canonical-main updates; never overwrite concurrent changes. After landing, run git merge-base --is-ancestor BRANCH main.

Do not delete branches. Do not discard dirty work or remove unlanded worktrees. An unlanded item stays referenced in the queue; unrelated items continue. Do not restart shared services over active work. Deliver when authorized and safe.