Files
roboco/tests/unit/gateway/test_delegate_project_routing.py
T
e9ca7d4036 Delegation detail-fidelity + PM-loop hardening (#541)
* feat(gateway): delegation detail-fidelity — details survive hand-off, both directions

Details thinned out at every delegation hop: a PM child task mapped to no
parent criterion was legal (coverage only surfaced at submit_up, after the
whole wave ran — a 12-subtask docs tree grew through 8 review rounds that
way, one child titled 'docs page and route wrapper' shipping only the
page), and QA could pass work on a gestalt read (a 4-scene video brief
shipped 3 scenes past every gate because the features existed only in
prose). Three chokepoint gates:

- delegate (down): every child must declare covers_parent_criteria
  resolving against the parent's real acceptance criteria — no mapping or
  an unresolvable ref rejects naming every offending child and the valid
  criteria; the success envelope carries parent_ac_coverage
  {covered, uncovered} so a wave-planning PM sees remaining gaps in the
  same turn. Full coverage stays enforced at submit_up (waves stay legal).
- pass_review (up): mandatory criteria_verified — one {criterion,
  evidence} entry per task AC, matched by the findings ledger's
  id-or-exact-text matcher, evidence soup-checked and capped; rejects
  naming the unverified criteria; entries render deterministically into
  qa_notes as '[AC] <criterion> — verified: <evidence>' lines. The old
  count-only ac_verdicts gate is superseded (arg kept for back-compat).
- video briefs (structured detail at origination): an enumerable feature
  list (release highlights, or input_props.highlights carried onto a
  reject re-author) becomes its own scene acceptance criterion, bounded to
  the AC caps; a re-author without highlights carries the
  feedback-addressed criterion instead.

Extracted findings.py's criterion matcher into shared unmatched_criteria /
uncovered_acceptance_criteria instead of duplicating it; criteria_verified
joins the WAF free-text exclusion set like findings/issues.

* fix(gateway): break the block/unblock wedge — four hardening fixes from the live PM loop

A cell task looped fe-pm/main-pm block/unblock for hours (10 cycles, 43
spawns): a transient GitHub API error resolving CI became an unwaivable
blocker finding whose own fix text said no code change was required, the
submit freshness guard then demanded a commit no finding called for,
escalate_up auto-blocked, and main-pm's correct recovery plan 422'd on
the approach length cap, degrading it to a bare unblock. Four fixes:

- pr_pass CI-unresolvable refusal is now explicitly transient-worded:
  retry pr_pass shortly, do NOT pr_fail over a CI-status lookup error —
  a platform blip is not a code finding
- submit freshness guard grants ONE unchanged-head resubmission per
  head sha when the findings ledger has zero open rows (all addressed
  without code changes) — stamped via the resubmit_unchanged_head
  marker so the same head can never loop a second time
- unblock carries a flip breaker: block_flip_count marker, and at the
  third flip a one-shot CEO notification flags the task as structurally
  wedged (unblock itself still succeeds — the breaker signals, it does
  not wedge recovery)
- i_will_plan's approach cap truncates at 800 chars instead of
  rejecting — an over-detailed plan must never cost the PM its turn

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
2026-07-17 01:52:33 +02:00

132 lines
4.5 KiB
Python

from __future__ import annotations
from datetime import UTC, datetime
from typing import Any
from unittest.mock import AsyncMock, MagicMock
from uuid import uuid4
import pytest
from roboco.services.gateway.choreographer import (
Choreographer,
ChoreographerDeps,
DelegateInputs,
)
def _make_deps(**overrides: Any) -> ChoreographerDeps:
base: dict[str, Any] = {
"task": AsyncMock(),
"work_session": AsyncMock(),
"git": AsyncMock(),
"a2a": AsyncMock(),
"journal": AsyncMock(),
"audit": AsyncMock(),
"evidence_repo": AsyncMock(),
}
base.update(overrides)
repo = base["evidence_repo"]
for m in (
"list_unread_a2a",
"list_unread_mentions",
"list_pending_notifications",
"task_metadata_gaps",
"recent_team_activity",
"blockers_in_lane",
"journal_highlights_for_task",
):
getattr(repo, m).return_value = []
_ldef = base["journal"].latest_decision_at.return_value
if type(_ldef).__name__ in ("MagicMock", "AsyncMock"):
base["journal"].latest_decision_at.return_value = datetime.now(UTC)
return ChoreographerDeps(**base)
def _parent(pm_id: Any, product_id: Any = None, project_id: Any = None) -> MagicMock:
return MagicMock(
id=uuid4(),
project_id=project_id or uuid4(),
product_id=product_id,
status="in_progress",
assigned_to=pm_id,
team="backend",
# delegate obligates the PM's quick_context resumption section.
quick_context="Decomposition planned; cells implement their slice next.",
# These tests are about project routing, not AC coverage.
acceptance_criteria=[],
)
def _inputs(**kw: Any) -> DelegateInputs:
base: dict[str, Any] = {
"title": "Implement endpoint",
"description": "Add /v1/foo endpoint with tests",
"assigned_to": "be-dev-1",
"team": "backend",
"task_type": "code",
"nature": "technical",
"acceptance_criteria": ["GET /v1/foo returns 200 with body"],
"intends_to_touch": ["backend/api/routers/foo.py"],
}
base.update(kw)
return DelegateInputs(**base)
async def _run(parent: Any, inputs: DelegateInputs, product: Any = None) -> Any:
pm_id = parent.assigned_to
task_svc = AsyncMock()
task_svc.get.return_value = parent
task_svc.agent_for.return_value = MagicMock(role="cell_pm", team="backend")
task_svc.get_subtasks.return_value = []
task_svc.create_subtask.return_value = MagicMock(id=uuid4())
deps = _make_deps(task=task_svc, **({"product": product} if product else {}))
c = Choreographer(deps)
env = await c.delegate(pm_id, parent.id, inputs)
return env, task_svc
@pytest.mark.asyncio
async def test_explicit_project_id_overrides_everything() -> None:
override = uuid4()
parent = _parent(uuid4(), product_id=uuid4())
env, task_svc = await _run(parent, _inputs(project_id=override))
assert env.error is None, env.as_dict()
req = task_svc.create_subtask.call_args.args[0]
assert req.project_id == override
@pytest.mark.asyncio
async def test_product_map_resolves_project_when_no_override() -> None:
mapped = uuid4()
product_id = uuid4()
parent = _parent(uuid4(), product_id=product_id)
product = AsyncMock()
product.project_for.return_value = mapped
env, task_svc = await _run(parent, _inputs(), product=product)
assert env.error is None, env.as_dict()
req = task_svc.create_subtask.call_args.args[0]
assert req.project_id == mapped
assert req.product_id == product_id # inherited onto the subtask
product.project_for.assert_awaited_once()
@pytest.mark.asyncio
async def test_falls_back_to_parent_project_when_no_product() -> None:
parent = _parent(uuid4(), product_id=None)
env, task_svc = await _run(parent, _inputs())
assert env.error is None, env.as_dict()
req = task_svc.create_subtask.call_args.args[0]
assert req.project_id == parent.project_id
@pytest.mark.asyncio
async def test_partial_product_map_degrades_to_parent_project() -> None:
product_id = uuid4()
parent = _parent(uuid4(), product_id=product_id)
product = AsyncMock()
product.project_for.return_value = None # no mapping for this cell
env, task_svc = await _run(parent, _inputs(), product=product)
assert env.error is None, env.as_dict()
req = task_svc.create_subtask.call_args.args[0]
assert req.project_id == parent.project_id
assert req.product_id == product_id