b2aff2045b
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>
54 lines
1.9 KiB
Markdown
54 lines
1.9 KiB
Markdown
---
|
|
kind: epic
|
|
slug: mcp-claim-complete
|
|
title: MCP claim_task and complete_task — atomic lifecycle for agents
|
|
plan_slug: agent-coordination
|
|
status: ready
|
|
priority: P2
|
|
tenant_id: global
|
|
cursor_epic_id: null
|
|
updated_at: "2026-06-01"
|
|
---
|
|
|
|
# Epic objective
|
|
|
|
Add two MCP tools that give a coding agent a shaped lifecycle for a task: `claim_task` (status flip + open `agent_runs` row + return effective workflow prompt) and `complete_task` (status flip + close `agent_runs` row with outcome + tokens).
|
|
|
|
These replace the current freeform composition where an agent has to call `update_object` repeatedly and pray.
|
|
|
|
## In scope / out of scope
|
|
|
|
**In scope**
|
|
|
|
- New MCP tools `claim_task` and `complete_task` with zod schemas.
|
|
- Idempotency rules (don't double-claim).
|
|
- Integration with the `agent_runs` table from the previous epic.
|
|
|
|
**Out of scope**
|
|
|
|
- A long-running orchestrator (deferred epic).
|
|
- A `pause_task` / `resume_task` tool. Resist; you can model that with two `complete_task` calls (`cancelled` + a new claim) until evidence demands it.
|
|
|
|
## Related tasks
|
|
|
|
| Task | Link |
|
|
|------|------|
|
|
| MCP claim_task tool | `./Task-mcp-claim-task-tool.md` |
|
|
| MCP complete_task tool | `./Task-mcp-complete-task-tool.md` |
|
|
|
|
## Dependencies
|
|
|
|
- Depends on: `Epic-task-as-runnable-unit` (needs `workflow_prompt` and `agent_runs`).
|
|
|
|
## Acceptance criteria
|
|
|
|
- [x] An agent can call `claim_task({ workspace, backlogItemId })` and receive the effective workflow prompt + a `runId`.
|
|
- [x] An agent can call `complete_task({ runId, outcome, tokens, notes })` to finalize.
|
|
- [x] Double-claim of the same task by the same actor returns the existing open run; by a different actor returns an explicit `ALREADY_CLAIMED` error naming the existing actor and run id.
|
|
|
|
## Proposed timeline
|
|
|
|
| Phase | Window | Notes |
|
|
|-------|--------|-------|
|
|
| claim_task | Day 1 | Tool + idempotency. |
|
|
| complete_task | Day 2 | Tool + run finalization. |
|