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
@@ -325,8 +325,22 @@ async def test_i_will_plan_pm_with_already_active_task_rejects() -> None:
task_id,
plan="x" * 30,
rich_plan={
"approach": "Decompose planning task into backend and frontend subtasks.",
"sub_tasks": [{"title": "Slice A", "description": "backend API work"}],
"approach": (
"Decompose the planning task into backend and frontend "
"developer-claimable subtasks. Backend lands first, QA "
"reviews each PR after it opens, documentation follows, then "
"complete and submit up. Strict sequencing with no cross-cell "
"dependencies beyond the stated ordering."
),
"sub_tasks": [
{
"title": "Slice A",
"description": (
"be-dev-1 implements the backend API change with "
"tests and opens the leaf PR for QA review."
),
}
],
},
)
body = env.as_dict()
@@ -427,8 +441,22 @@ async def test_i_will_plan_pending_claim_fails() -> None:
task_id,
plan="my plan that is long enough",
rich_plan={
"approach": "Decompose planning task into backend and frontend subtasks.",
"sub_tasks": [{"title": "Slice A", "description": "backend API work"}],
"approach": (
"Decompose the planning task into backend and frontend "
"developer-claimable subtasks. Backend lands first, QA "
"reviews each PR after it opens, documentation follows, then "
"complete and submit up. Strict sequencing with no cross-cell "
"dependencies beyond the stated ordering."
),
"sub_tasks": [
{
"title": "Slice A",
"description": (
"be-dev-1 implements the backend API change with "
"tests and opens the leaf PR for QA review."
),
}
],
},
)
body = env.as_dict()
@@ -1047,8 +1075,22 @@ async def test_i_will_plan_pending_claim_returns_none_emit_rejection() -> None:
task_id,
plan="my plan that is long enough",
rich_plan={
"approach": "Decompose planning task into backend and frontend subtasks.",
"sub_tasks": [{"title": "Slice A", "description": "backend API work"}],
"approach": (
"Decompose the planning task into backend and frontend "
"developer-claimable subtasks. Backend lands first, QA "
"reviews each PR after it opens, documentation follows, then "
"complete and submit up. Strict sequencing with no cross-cell "
"dependencies beyond the stated ordering."
),
"sub_tasks": [
{
"title": "Slice A",
"description": (
"be-dev-1 implements the backend API change with "
"tests and opens the leaf PR for QA review."
),
}
],
},
)
body = env.as_dict()