Files
roboco/tests/unit/services/test_review_findings_repository.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

292 lines
9.2 KiB
Python

"""Real-DB tests for ReviewFindingsRepository — the revision-findings ledger.
Follows the ``test_audit_real_query.py`` / ``test_vault_task_queries_real.py``
pattern: real Postgres via the session-scoped test DB (local:
ROBOCO_TEST_DB_PORT=55432 ROBOCO_TEST_DB_USER=renzof). ``Base.metadata.create_all``
builds the schema from live ORM metadata, so ``TaskReviewFindingTable`` needs no
migration replay here.
"""
from __future__ import annotations
from typing import TYPE_CHECKING
from uuid import UUID, uuid4
import pytest
from roboco.db.tables import AgentTable, TaskTable
from roboco.foundation.policy.content import Finding, Severity
from roboco.models.base import AgentRole, AgentStatus, TaskStatus, TaskType, Team
from roboco.services.repositories.review_findings import (
STATUS_ADDRESSED,
STATUS_OPEN,
STATUS_VERIFIED,
STATUS_WAIVED,
ReviewFindingsRepository,
)
if TYPE_CHECKING:
from sqlalchemy.ext.asyncio import AsyncSession
_EXPECTED_TWO = 2
async def _seed_agent(session: AsyncSession) -> UUID:
agent = AgentTable(
id=uuid4(),
name="Ledger Test Agent",
slug=f"ledger-test-{uuid4().hex[:8]}",
role=AgentRole.DEVELOPER,
team=None,
status=AgentStatus.ACTIVE,
model_config={},
system_prompt="ledger test",
capabilities=[],
permissions={},
metrics={},
)
session.add(agent)
await session.flush()
return UUID(str(agent.id))
async def _seed_task(session: AsyncSession, created_by: UUID) -> UUID:
task = TaskTable(
id=uuid4(),
title="ledger seed task",
description="seed",
acceptance_criteria=["seeded"],
status=TaskStatus.NEEDS_REVISION,
priority=2,
task_type=TaskType.CODE,
team=Team.BACKEND,
created_by=created_by,
)
session.add(task)
await session.flush()
return UUID(str(task.id))
def _finding(**overrides: object) -> Finding:
base: dict[str, object] = {
"file": "roboco/services/task.py",
"line": 10,
"severity": Severity.MAJOR,
"expected": "raises on bad input",
"actual": "swallows the error",
}
base.update(overrides)
return Finding.model_validate(base)
@pytest.mark.asyncio
async def test_insert_many_persists_one_row_per_finding(
db_session: AsyncSession,
) -> None:
agent_id = await _seed_agent(db_session)
task_id = await _seed_task(db_session, agent_id)
repo = ReviewFindingsRepository(db_session)
rows = await repo.insert_many(
task_id=task_id,
origin="qa",
round=1,
author_slug="be-qa",
findings=[_finding(), _finding(criterion="AC1")],
)
assert len(rows) == _EXPECTED_TWO
assert all(r.id is not None for r in rows)
assert all(r.status == STATUS_OPEN for r in rows)
assert all(r.round == 1 for r in rows)
assert all(r.origin == "qa" for r in rows)
assert rows[1].criterion == "AC1"
@pytest.mark.asyncio
async def test_list_for_task_orders_newest_round_first(
db_session: AsyncSession,
) -> None:
agent_id = await _seed_agent(db_session)
task_id = await _seed_task(db_session, agent_id)
repo = ReviewFindingsRepository(db_session)
await repo.insert_many(
task_id=task_id,
origin="qa",
round=1,
author_slug="be-qa",
findings=[_finding()],
)
await repo.insert_many(
task_id=task_id,
origin="pr_gate",
round=2,
author_slug="be-pr-reviewer",
findings=[_finding(actual="round 2 issue")],
)
rows = await repo.list_for_task(task_id)
assert [r.round for r in rows] == [2, 1]
@pytest.mark.asyncio
async def test_list_for_task_filters_by_status(db_session: AsyncSession) -> None:
agent_id = await _seed_agent(db_session)
task_id = await _seed_task(db_session, agent_id)
repo = ReviewFindingsRepository(db_session)
rows = await repo.insert_many(
task_id=task_id,
origin="qa",
round=1,
author_slug="be-qa",
findings=[_finding()],
)
await repo.mark_addressed(task_id, str(rows[0].id), commit="abc123", note="fixed")
open_rows = await repo.list_for_task(task_id, status=STATUS_OPEN)
addressed_rows = await repo.list_for_task(task_id, status=STATUS_ADDRESSED)
assert open_rows == []
assert len(addressed_rows) == 1
@pytest.mark.asyncio
async def test_list_for_task_scoped_to_one_task(db_session: AsyncSession) -> None:
agent_id = await _seed_agent(db_session)
task_a = await _seed_task(db_session, agent_id)
task_b = await _seed_task(db_session, agent_id)
repo = ReviewFindingsRepository(db_session)
await repo.insert_many(
task_id=task_a, origin="qa", round=1, author_slug="be-qa", findings=[_finding()]
)
assert len(await repo.list_for_task(task_a)) == 1
assert await repo.list_for_task(task_b) == []
@pytest.mark.asyncio
async def test_mark_addressed_by_full_id(db_session: AsyncSession) -> None:
agent_id = await _seed_agent(db_session)
task_id = await _seed_task(db_session, agent_id)
repo = ReviewFindingsRepository(db_session)
rows = await repo.insert_many(
task_id=task_id,
origin="qa",
round=1,
author_slug="be-qa",
findings=[_finding()],
)
updated = await repo.mark_addressed(
task_id, str(rows[0].id), commit="deadbeef", note="fixed the guard"
)
assert updated is not None
assert updated.status == STATUS_ADDRESSED
assert updated.addressed_by_commit == "deadbeef"
assert updated.resolution_note == "fixed the guard"
@pytest.mark.asyncio
async def test_mark_addressed_by_8_char_prefix(db_session: AsyncSession) -> None:
agent_id = await _seed_agent(db_session)
task_id = await _seed_task(db_session, agent_id)
repo = ReviewFindingsRepository(db_session)
rows = await repo.insert_many(
task_id=task_id,
origin="qa",
round=1,
author_slug="be-qa",
findings=[_finding()],
)
prefix = str(rows[0].id)[:8]
updated = await repo.mark_addressed(task_id, prefix, commit=None, note=None)
assert updated is not None
assert updated.id == rows[0].id
@pytest.mark.asyncio
async def test_mark_addressed_unknown_ref_is_a_noop(db_session: AsyncSession) -> None:
agent_id = await _seed_agent(db_session)
task_id = await _seed_task(db_session, agent_id)
repo = ReviewFindingsRepository(db_session)
await repo.insert_many(
task_id=task_id,
origin="qa",
round=1,
author_slug="be-qa",
findings=[_finding()],
)
result = await repo.mark_addressed(task_id, "ffffffff", commit=None, note=None)
assert result is None
assert len(await repo.list_for_task(task_id, status=STATUS_OPEN)) == 1
@pytest.mark.asyncio
async def test_mark_addressed_wrong_task_is_a_noop(db_session: AsyncSession) -> None:
"""A finding_ref that exists but belongs to a DIFFERENT task must not match —
an agent can never address another task's finding."""
agent_id = await _seed_agent(db_session)
task_a = await _seed_task(db_session, agent_id)
task_b = await _seed_task(db_session, agent_id)
repo = ReviewFindingsRepository(db_session)
rows = await repo.insert_many(
task_id=task_a, origin="qa", round=1, author_slug="be-qa", findings=[_finding()]
)
result = await repo.mark_addressed(task_b, str(rows[0].id), commit=None, note=None)
assert result is None
assert len(await repo.list_for_task(task_a, status=STATUS_OPEN)) == 1
@pytest.mark.asyncio
async def test_mark_verified_bulk_by_id(db_session: AsyncSession) -> None:
agent_id = await _seed_agent(db_session)
task_id = await _seed_task(db_session, agent_id)
repo = ReviewFindingsRepository(db_session)
rows = await repo.insert_many(
task_id=task_id,
origin="qa",
round=1,
author_slug="be-qa",
findings=[_finding(), _finding(actual="second")],
)
ids = [UUID(str(r.id)) for r in rows]
count = await repo.mark_verified(ids)
assert count == _EXPECTED_TWO
verified = await repo.list_for_task(task_id, status=STATUS_VERIFIED)
assert len(verified) == _EXPECTED_TWO
@pytest.mark.asyncio
async def test_mark_verified_empty_list_is_a_noop(db_session: AsyncSession) -> None:
repo = ReviewFindingsRepository(db_session)
assert await repo.mark_verified([]) == 0
@pytest.mark.asyncio
async def test_mark_waived_requires_note(db_session: AsyncSession) -> None:
agent_id = await _seed_agent(db_session)
task_id = await _seed_task(db_session, agent_id)
repo = ReviewFindingsRepository(db_session)
rows = await repo.insert_many(
task_id=task_id,
origin="qa",
round=1,
author_slug="be-qa",
findings=[_finding()],
)
ok = await repo.mark_waived(UUID(str(rows[0].id)), "not a real defect")
assert ok is True
waived = await repo.list_for_task(task_id, status=STATUS_WAIVED)
assert len(waived) == 1
assert waived[0].resolution_note == "not a real defect"
@pytest.mark.asyncio
async def test_mark_waived_unknown_id_returns_false(db_session: AsyncSession) -> None:
repo = ReviewFindingsRepository(db_session)
assert await repo.mark_waived(uuid4(), "note") is False