mirror of
https://github.com/rennf93/roboco.git
synced 2026-08-03 07:23:24 +02:00
Renn F
ce4d02b3c2
Evidence-assembly git legs (diff, changed-files, branch fetch, advisory conventions run) ran unbounded inside claim_review / claim_doc_task / claim_gate_review / evidence() / i_am_done's envelope build, so a slow clone turned the whole verb into a silent 120s FlowVerbTimeout 504. Each leg now runs through run_bounded_leg under a shared LegBudget (evidence_assembly_timeout_seconds, 45s total): a timed-out leg — both asyncio TimeoutError and git's own GitTimeoutError — degrades into an evidence_gaps note on the envelope instead of hanging the verb, while non-timeout git errors still propagate. The advisory conventions run gets an inner-only timeout (conventions_validator_advisory_timeout_ seconds, 30s) threaded down to the subprocess so it is never orphaned by an outer cancel; the fail-closed i_am_done/pr_pass conventions gates keep their hardcoded 120s. _ensure_pm_decision now reports a PmDecisionOutcome: a transient DB failure recording the PM's decision journal (e.g. lock timeout under load) no longer launders into a journal:decision gate rejection that escalates and BLOCKS the task — the verb's own rationale satisfies the gate with a structured warning, across all seven PM verbs. Also: repo-wide ruff realignment to the lockfile-pinned ruff (8 format-only diffs, 14 UP038 isinstance conversions) that a transiently newer venv ruff had masked. Gate: 15474 passed, 459 skipped; ruff/mypy/xenon/vulture/bandit/ pip-audit/deptry/import-linter/foundation-check all green.
103 lines
3.5 KiB
Python
103 lines
3.5 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})
|
|
gaps: list[str] = []
|
|
assert (
|
|
await c._qa_convention_findings(uuid4(), MagicMock(), timeout=30.0, gaps=gaps)
|
|
== findings
|
|
)
|
|
assert gaps == []
|
|
|
|
|
|
@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}
|
|
)
|
|
gaps: list[str] = []
|
|
assert (
|
|
await c._qa_convention_findings(uuid4(), MagicMock(), timeout=30.0, gaps=gaps)
|
|
== []
|
|
)
|
|
assert gaps == []
|
|
|
|
|
|
@pytest.mark.asyncio
|
|
async def test_could_not_run_surfaced_as_single_entry(
|
|
monkeypatch: pytest.MonkeyPatch,
|
|
) -> None:
|
|
"""A non-timeout could_not_run reason ("boom") stays fail-open in
|
|
convention_findings but must NOT also spam evidence_gaps — only a
|
|
detected timeout does (see test_claim_review_conventions_timeout_
|
|
degrades_with_gap in test_evidence_assembly_bounded_legs.py)."""
|
|
monkeypatch.setattr(settings, "conventions_enabled", True)
|
|
c = _make_choreographer(
|
|
check_result={"findings": [], "could_not_run": True, "reason": "boom"}
|
|
)
|
|
gaps: list[str] = []
|
|
out = await c._qa_convention_findings(uuid4(), MagicMock(), timeout=30.0, gaps=gaps)
|
|
assert len(out) == 1
|
|
assert out[0]["could_not_run"] is True
|
|
assert out[0]["reason"] == "boom"
|
|
assert gaps == []
|
|
|
|
|
|
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()
|