mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
* 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>
117 lines
3.7 KiB
Python
117 lines
3.7 KiB
Python
"""assemble_task_note_data threads the revision-findings ledger.
|
|
|
|
Fetched via ``task_service.session`` rather than a new threaded parameter —
|
|
see ``roboco/services/vault_assembly.py`` ``_resolve_findings`` for why (every
|
|
real caller already carries a real session; only some unit-test stubs don't,
|
|
and those must degrade to empty rather than crash).
|
|
"""
|
|
|
|
from __future__ import annotations
|
|
|
|
from types import SimpleNamespace
|
|
from typing import Any
|
|
from unittest.mock import AsyncMock, MagicMock, patch
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
from roboco.services.vault_assembly import assemble_task_note_data
|
|
from roboco.services.vault_writer import VaultWriter
|
|
|
|
|
|
def _task(**overrides: Any) -> SimpleNamespace:
|
|
base: dict[str, Any] = {
|
|
"id": uuid4(),
|
|
"title": "t",
|
|
"description": "d",
|
|
"status": "in_progress",
|
|
"team": "backend",
|
|
"priority": 2,
|
|
"task_type": "code",
|
|
"acceptance_criteria": [],
|
|
"pr_number": None,
|
|
"pr_url": None,
|
|
"project_id": None,
|
|
"parent_task_id": None,
|
|
"dependency_ids": [],
|
|
"batch_id": None,
|
|
}
|
|
base.update(overrides)
|
|
return SimpleNamespace(**base)
|
|
|
|
|
|
def _finding_row(**overrides: Any) -> SimpleNamespace:
|
|
base: dict[str, Any] = {
|
|
"id": uuid4(),
|
|
"severity": "major",
|
|
"file": "roboco/services/task.py",
|
|
"line": 42,
|
|
"expected": "x",
|
|
"actual": "y",
|
|
"fix": "do z",
|
|
"status": "open",
|
|
"round": 1,
|
|
}
|
|
base.update(overrides)
|
|
return SimpleNamespace(**base)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_assemble_threads_findings_via_task_service_session() -> None:
|
|
task_service = MagicMock()
|
|
task_service.session = MagicMock()
|
|
task_service.get_subtasks = AsyncMock(return_value=[])
|
|
project_service = MagicMock()
|
|
|
|
repo = MagicMock()
|
|
repo.list_for_task = AsyncMock(return_value=[_finding_row()])
|
|
with patch(
|
|
"roboco.services.vault_assembly.ReviewFindingsRepository",
|
|
return_value=repo,
|
|
):
|
|
data = await assemble_task_note_data(task_service, project_service, _task())
|
|
|
|
assert len(data.findings) == 1
|
|
row = data.findings[0]
|
|
assert (row.severity, row.file, row.fix, row.status, row.round) == (
|
|
"major",
|
|
"roboco/services/task.py",
|
|
"do z",
|
|
"open",
|
|
1,
|
|
)
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_assemble_findings_empty_when_task_service_has_no_session() -> None:
|
|
"""A duck-typed stub without ``.session`` (e.g. the vault-janitor unit
|
|
tests' ``_TaskSvcStub``) yields no findings rather than crashing."""
|
|
task_service = SimpleNamespace(get_subtasks=AsyncMock(return_value=[]))
|
|
project_service = MagicMock()
|
|
|
|
data = await assemble_task_note_data(task_service, project_service, _task())
|
|
assert data.findings == ()
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_assemble_fails_open_when_findings_fetch_raises(tmp_path: Any) -> None:
|
|
"""A raising repository degrades to an empty findings tuple — the note is
|
|
still assembled and materializes. The best-effort vault seams swallow
|
|
exceptions, so a raise here would silently kill write_task entirely."""
|
|
task_service = MagicMock()
|
|
task_service.session = MagicMock()
|
|
task_service.get_subtasks = AsyncMock(return_value=[])
|
|
project_service = MagicMock()
|
|
|
|
repo = MagicMock()
|
|
repo.list_for_task = AsyncMock(side_effect=RuntimeError("db down"))
|
|
with patch(
|
|
"roboco.services.vault_assembly.ReviewFindingsRepository",
|
|
return_value=repo,
|
|
):
|
|
data = await assemble_task_note_data(task_service, project_service, _task())
|
|
|
|
assert data.findings == ()
|
|
note = VaultWriter(tmp_path).write_task(data)
|
|
assert note.exists()
|
|
assert "## Findings" not in note.read_text(encoding="utf-8")
|