2.3 KiB
Small tasks and execution
Choose the simplest reliable route: direct work, delegation or a pipeline. The manager remains responsible for completion and may take over any role directly.
An item
One item changes one observable behavior. State its goal, relevant files, a few testable acceptance checks and scope boundaries. Avoid long history, invented implementation plans and boilerplate rules already in the project map. Separate independent features even when they share a file; resolve small hunks at integration. Serialize only actual dependency or resource conflicts.
Stage jobs
- Planner: produce a short plan and acceptance checks only when needed.
- Implementer: make the focused change, add tests, run focused checks.
- Reviewer: inspect the whole task diff and independently verify relevant checks.
- UI reviewer: exercise rendered behavior using ready controlled data; retain captures.
- Committer: commit all reviewed task changes, integrate main and resolve conflicts.
Handoff desired behavior and necessary evidence, not another role's restrictions. An implementer's "no device use performed" is not a ban on the UI reviewer. A fresh clean worktree is a successful no-op for preparation, not a failure. Nonvisual changes need no device. A visual change needs actual visual evidence.
Pipeline choice
When using the project's area workflows: Android for android/, TUI for internal/tui/, Server for backend/protocol work, Generic for genuinely cross-area work, Plan and land when design is necessary, UI sweep for a visual survey, Probe for a smoke check. Read area maps for project-specific commands. Keep models and costs as agreed.
Recovery and landing
Inspect pipelines inspect ID --json and actual files after failure. Preserve
partial changes. Prefer resuming the original stage with corrected input or fixing
and merging directly; do not repeat completed work or add a merger pipeline.
For delivery=true, return a clean checked candidate and let the server land it.
For direct recovery, merge safely and verify it. Only then check ancestry.
Record real failures without blocking unrelated progress. Never delete branches.
Use pipelines wait ID as a background wait for active runs; no polling driver.
Record stale docs in a per-item note unless documentation itself is the task.
Keep reports short and separate code, testing, landing and deployment status.