mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
cea3e56628
* 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>
87 lines
3.0 KiB
Python
87 lines
3.0 KiB
Python
"""QA claim_review evidence carries the conventions validator findings (gated)."""
|
|
|
|
from __future__ import annotations
|
|
|
|
from typing import Any
|
|
from unittest.mock import AsyncMock, MagicMock
|
|
from uuid import uuid4
|
|
|
|
import pytest
|
|
from roboco.config import settings
|
|
from roboco.services.gateway.choreographer import Choreographer, ChoreographerDeps
|
|
from roboco.services.gateway.evidence_builder import build_evidence_for_task
|
|
|
|
|
|
def _make_choreographer(*, check_result: dict[str, Any]) -> Choreographer:
|
|
base: dict[str, Any] = {
|
|
"task": AsyncMock(),
|
|
"work_session": AsyncMock(),
|
|
"git": AsyncMock(),
|
|
"a2a": AsyncMock(),
|
|
"journal": AsyncMock(),
|
|
"audit": AsyncMock(),
|
|
"evidence_repo": AsyncMock(),
|
|
}
|
|
base["git"].conventions_check_for_task.return_value = check_result
|
|
return Choreographer(ChoreographerDeps(**base))
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_findings_surfaced_when_flag_on(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
monkeypatch.setattr(settings, "conventions_enabled", True)
|
|
findings = [{"file": "x.py", "line": 1, "level": "warn", "fix_hint": "h"}]
|
|
c = _make_choreographer(check_result={"findings": findings, "could_not_run": False})
|
|
assert await c._qa_convention_findings(uuid4(), MagicMock()) == findings
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_empty_when_flag_off(monkeypatch: pytest.MonkeyPatch) -> None:
|
|
monkeypatch.setattr(settings, "conventions_enabled", False)
|
|
c = _make_choreographer(
|
|
check_result={"findings": [{"file": "x"}], "could_not_run": False}
|
|
)
|
|
assert await c._qa_convention_findings(uuid4(), MagicMock()) == []
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_could_not_run_surfaced_as_single_entry(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
monkeypatch.setattr(settings, "conventions_enabled", True)
|
|
c = _make_choreographer(
|
|
check_result={"findings": [], "could_not_run": True, "reason": "boom"}
|
|
)
|
|
out = await c._qa_convention_findings(uuid4(), MagicMock())
|
|
assert len(out) == 1
|
|
assert out[0]["could_not_run"] is True
|
|
assert out[0]["reason"] == "boom"
|
|
|
|
|
|
def _stub_task() -> MagicMock:
|
|
task = MagicMock()
|
|
task.pr_number = None
|
|
task.pr_url = None
|
|
task.commits = []
|
|
task.dev_notes = None
|
|
task.acceptance_criteria_status = []
|
|
return task
|
|
|
|
|
|
def test_evidence_payload_includes_convention_findings() -> None:
|
|
findings = [{"file": "x", "line": 1}]
|
|
ev = build_evidence_for_task(
|
|
_stub_task(),
|
|
journal_highlights=[],
|
|
files_changed=[],
|
|
convention_findings=findings,
|
|
)
|
|
assert ev.as_dict()["convention_findings"] == findings
|
|
|
|
|
|
def test_evidence_payload_convention_findings_default_empty() -> None:
|
|
"""An empty findings list is omitted from as_dict() entirely (zero-noise
|
|
posture, matching build_task_handoff) — the attribute itself stays []."""
|
|
ev = build_evidence_for_task(_stub_task(), journal_highlights=[], files_changed=[])
|
|
assert ev.convention_findings == []
|
|
assert "convention_findings" not in ev.as_dict()
|