Files
roboco/tests/unit/gateway/test_choreographer_request_changes.py
T
cea3e56628 feat(lifecycle): revision findings ledger — structured failure feedback, persisted and delivered down the chain (#486)
* feat(lifecycle): revision findings ledger — structured QA/PR/PM/CEO failure feedback, persisted and delivered down the chain

Every bounce used to survive only as flattened prose: rounds overwrote each
other in notes_structured, request_changes persisted nothing, two raw
dev_notes appends were silently destroyed by the next handoff note, and the
dev prompt pointed at fields (qa_notes via evidence(), pm_notes) the API
never delivered. Agents re-interpreted and re-discovered every failure
before they could start fixing it.

- task_review_findings (migration 071, append-only): file/line/severity/
  criterion(AC-id-validated)/expected/actual/fix/evidence per finding, with
  origin (qa|pr_gate|pm|ceo), round, and an open->addressed->verified
  lifecycle (waived reserved); new tasks.pm_notes + PmReviewContent give
  request_changes a structured home
- producers: fail_review/pr_fail/request_changes take findings=[...] (prose
  issues shimmed+merged for one release, deprecation-logged); ceo_reject
  validates its reason (no 500), lands an origin=ceo finding, and bumps
  round+audit on branchless coordination roots; guardrails at the verb
  chokepoint (nudge >5, hard reject >10, field caps, traversal-safe file);
  the dev_notes data-loss appends are removed; new task.request_changes +
  task.ceo_reject audit events close rework attribution
- delivery: qa_notes/pr_reviewer_notes/pm_notes carry the deterministic
  [F-id8] rendering; claim briefings, evidence(), the REVISION_REQUIRED
  spawn prompt, PM triage bounced-blocks, and A2A bodies deliver open
  findings; round-N+1 QA and gate reviewers get the full prior ledger;
  panel Findings tab + bounced-xN chip; metrics pm_rejects/ceo_rejects +
  findings counts; vault task notes render a Findings section (fail-open)
- resolution closes for every origin: i_am_done and submit_up/submit_root
  take resolved_findings gated by FINDINGS_ADDRESSED (owner-gated so a
  stale non-owner PM can never mutate the ledger); pass_review/pr_pass/
  complete verify-stamp same-transaction; ceo_approve stamps best-effort
- 24 real-DB integration tests drive the full loop through the real
  choreographer; full suite 12856 green

* docs: revision findings ledger sweep — CLAUDE.md, map, RAG corpus

- CLAUDE.md: new ledger section + corrected request_changes row
- docs/map/review-findings.md (new subsystem map) + surgical updates to
  task-service/pr-gate-review/metrics-observability/vault/panel maps
- docs/rag: producers' findings contract across qa/pr-reviewer/developer/
  cell-pm/main-pm/ceo role docs (the PM docs were missing request_changes
  entirely), verb references, and a new architecture/review-findings.md
  disambiguating ledger findings from convention findings

* test(e2e): resubmit resolves the pr_fail finding per the ledger contract

The scripted pr_fail revision loop resubmitted submit_up without
resolved_findings — correctly rejected now that FINDINGS_ADDRESSED gates
the PM resubmit verbs (green locally, red only in CI since the e2e suite
skips without ROBOCO_E2E_SMOKE=1). The scripted PM now reads the open
ledger row pr_fail persisted (new open_finding_ids arc helper) and
resolves it on resubmit, asserting the open set drains — exercising the
coordinator half of the new contract end to end.

---------

Co-authored-by: Renn F <rennf93@users.noreply.github.com>
2026-07-11 22:54:42 +02:00

157 lines
4.9 KiB
Python

"""Choreographer.request_changes — the PM merge-level reject (S6 gap B4).
At awaiting_pm_review the PM previously had only complete/escalate, so an AC
violation caught at merge review looped i_am_blocked→escalate. request_changes
routes it to needs_revision with concrete issues and a2a-delivers the reason.
"""
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
def _make_deps(**overrides: Any) -> ChoreographerDeps:
base = {
"task": AsyncMock(),
"work_session": AsyncMock(),
"git": AsyncMock(),
"a2a": AsyncMock(),
"journal": AsyncMock(),
"audit": AsyncMock(),
"evidence_repo": AsyncMock(),
}
base.update(overrides)
repo = base["evidence_repo"]
for method 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, method).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 _pm_review_task(task_id: Any, assigned_to: Any) -> MagicMock:
return MagicMock(
id=task_id,
status="awaiting_pm_review",
assigned_to=assigned_to,
team="frontend",
task_type="code",
pr_number=176,
branch_name="feature/frontend/abc--def--ghi",
orchestration_markers=None,
)
def _pm_agent_mock(pm_id: Any, role: str = "cell_pm") -> MagicMock:
agent = MagicMock(id=pm_id, team="frontend", slug="fe-pm")
agent.role = role
return agent
@pytest.mark.asyncio
async def test_request_changes_succeeds_and_notifies_new_owner() -> None:
pm_id = uuid4()
task_id = uuid4()
dev_id = uuid4()
t = _pm_review_task(task_id, pm_id)
after = MagicMock(
id=task_id,
status="needs_revision",
assigned_to=dev_id,
team="frontend",
)
task_svc = AsyncMock()
task_svc.get.return_value = t
task_svc.agent_for.return_value = _pm_agent_mock(pm_id)
task_svc.request_changes.return_value = after
task_svc.session = MagicMock()
task_svc.session.add = MagicMock()
task_svc.session.flush = AsyncMock()
task_svc.session.begin_nested = MagicMock(
return_value=MagicMock(
__aenter__=AsyncMock(return_value=None),
__aexit__=AsyncMock(return_value=False),
)
)
a2a_svc = AsyncMock()
deps = _make_deps(task=task_svc, a2a=a2a_svc)
c = Choreographer(deps)
issues = [
"frontend/CLAUDE.md modified out of scope — revert the doc commit hunk",
]
env = await c.request_changes(pm_id, task_id, issues)
assert env.error is None
assert env.status == "needs_revision"
task_svc.request_changes.assert_awaited_once()
a2a_svc.send.assert_awaited_once()
# The ledger insert ran (findings=[the shimmed issue]) before the transition.
task_svc.session.add.assert_called_once()
@pytest.mark.asyncio
async def test_request_changes_requires_at_least_one_issue() -> None:
pm_id = uuid4()
task_id = uuid4()
t = _pm_review_task(task_id, pm_id)
task_svc = AsyncMock()
task_svc.get.return_value = t
task_svc.agent_for.return_value = _pm_agent_mock(pm_id)
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.request_changes(pm_id, task_id, issues=[])
body = env.as_dict()
assert body["error"] == "invalid_state"
assert "finding" in body["message"].lower()
@pytest.mark.asyncio
async def test_request_changes_rejected_outside_pm_review() -> None:
pm_id = uuid4()
task_id = uuid4()
t = _pm_review_task(task_id, pm_id)
t.status = "in_progress"
task_svc = AsyncMock()
task_svc.get.return_value = t
task_svc.agent_for.return_value = _pm_agent_mock(pm_id)
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.request_changes(pm_id, task_id, issues=["real issue here"])
body = env.as_dict()
assert body["error"] is not None
task_svc.request_changes.assert_not_awaited()
@pytest.mark.asyncio
async def test_request_changes_rejected_for_non_pm_role() -> None:
dev_id = uuid4()
task_id = uuid4()
t = _pm_review_task(task_id, dev_id)
task_svc = AsyncMock()
task_svc.get.return_value = t
task_svc.agent_for.return_value = _pm_agent_mock(dev_id, role="developer")
deps = _make_deps(task=task_svc)
c = Choreographer(deps)
env = await c.request_changes(dev_id, task_id, issues=["real issue here"])
body = env.as_dict()
assert body["error"] is not None
task_svc.request_changes.assert_not_awaited()