Pairs with the parallel complete_task commit. claim_task opens an agent_runs row, flips status to in_progress only when it's safe (ready/draft → in_progress, never overwriting a deliberate blocked/done/in_progress), and returns the resolved workflow prompt + source level. Idempotent re-claim by the same actor returns the existing run with reused=true and refreshes notes only — started_at is sacred. Different-actor re-claim errors with ALREADY_CLAIMED naming the existing actor and run id. Tenancy fence: if the backlog item exists but in a different workspace than the resolved handle, we refuse with "doesn't belong to workspace" rather than 404. Prevents cross-tenant existence fishing. All three writes (run insert + status flip + audit insert) happen in one db.transaction() so a partial claim is unreachable. tools/index.ts now registers both claim_task and complete_task. Co-authored-by: Cursor <cursoragent@cursor.com> |
||
|---|---|---|
| .. | ||
| Plan-agent-coordination | ||
| Plan-daily-driver-finish | ||
| Plan-multitenant-cursor-sync | ||
| Plan-multitenant-saas-hardening | ||
| README.md | ||
Plans directory
Human- and agent-oriented backlog. Structure:
plans/
Plan-<plan-slug>/
Plan-<plan-slug>.md
Epic-<epic-slug>/
Epic-<epic-slug>.md
Task-<task-slug>.md
Task-<other-task>.md
- Slug: lowercase, hyphenated, stable across renames of display title when possible.
- Templates: copy from
docs/templates/. - Chunking: keep each Task small enough for one Cursor agent or subagent to own; use Epics for milestones that need several tasks.
See docs/Glossary.md and config/CursorSync.md.
Import to database: from the repo root, with DATABASE_URL and your workspace UUID:
pnpm --filter @tasks/database watch:markdown-backlog
Set MARKDOWN_BACKLOG_WORKSPACE_ID (and optionally MARKDOWN_BACKLOG_REPO_ROOT). This runs an initial sync and watches plans/ for changes.