feat(gateway): substantive-plan gate — approach >=150 + real sub_task descriptions (#171)

Plans were vague because the gate accepted the bare minimum: PM
approach >=20 chars and title-only sub_tasks. minimax wrote exactly
the minimum.

- IWillPlanRequest.approach min_length 20 -> 150 (kept in sync with
  _PM_APPROACH_MIN_LEN; the gate enforces it at the choreographer
  layer too so direct/MCP callers can't bypass the HTTP boundary).
- New _thin_subtask_hint: every PM sub_task must have a title and a
  description >= _PM_SUBTASK_DESC_MIN_LEN (60) saying what the step
  does — each sub_task is both a delegate target AND a
  progress-checklist item, so a title alone is not a plan.
- cell_pm/main_pm role prompts: explicit "the gate REJECTS thin plans"
  framing + concrete sub_task example + the new minimums.
- Updated all affected test fixtures across the suite to use
  substantive approaches/descriptions; added thin-sub_task rejection
  coverage.

Commit 1 of 3 for the plan/progress quality work (#171/#172/#173).
This commit is contained in:
Renn F
2026-05-16 10:14:45 +02:00
parent e94159dce8
commit ed828a719b
14 changed files with 415 additions and 82 deletions
+12 -3
View File
@@ -237,11 +237,20 @@ async def test_i_will_plan_dispatches_to_choreographer() -> None:
"task_id": _TASK_ID,
"plan": "break into 3 subtasks for backend",
"approach": (
"Decompose into backend API slice, QA verification pass, "
"and documentation update."
"Decompose into a backend API slice that be-dev-1 owns end "
"to end; QA reviews after the PR opens, documentation follows, "
"then be-pm completes and submits up. Single-cell — no "
"frontend or ux work; strict sequencing with no cross-cell "
"dependencies for this planning task."
),
"sub_tasks": [
{"title": "Backend API slice", "description": "Implement endpoint"}
{
"title": "Backend API slice",
"description": (
"be-dev-1 implements the endpoint with tests, commits "
"with the task-id prefix, opens the leaf PR for QA."
),
}
],
},
headers=_HEADERS,