gpt-5.3 codex review: Phase 4
Quality Gate / gate (push) Failing after 11s

This commit is contained in:
Jim Lancaster
2026-08-19 21:16:36 -05:00
parent 30fcef3892
commit cdd846fe29
16 changed files with 765 additions and 26 deletions
+69 -1
View File
@@ -181,6 +181,74 @@ class TestWorkflowReliability:
assert duration_ms >= int(budget_seconds * 1000 * 0.9)
assert duration_ms < int((budget_seconds + setup_seconds) * 1000 * 0.9)
@pytest.mark.asyncio
async def test_attempt_metadata_persists_provider_and_processing_durations(
self,
default_session_factory,
monkeypatch,
):
"""Execution metadata records both provider-only and end-to-end durations."""
services = ServiceBundle.from_session_factory(default_session_factory)
async with services.jobs._session_scope() as session:
document = Document(id=uuid4(), name="timing-metadata-doc")
session.add(document)
await session.flush()
job = Job(document_id=document.id, status=JobStatus.QUEUED)
session.add(job)
await session.flush()
source = Source(
document_id=document.id,
page_number=1,
upload_name="timing.jpg",
filename="timing.jpg",
file_path=str(Path("tests/fixtures/images/real/Book Two - page 02.jpg")),
file_hash="f" * 64,
file_size_bytes=1,
)
session.add(source)
await session.flush()
session.add(JobSource(job_id=job.id, source_id=source.id, status=JobSourceStatus.PENDING))
await session.commit()
loaded = await services.jobs.read_job(job_id=job.id, session=session)
async def _returns_text(*args, **kwargs):
_ = (args, kwargs)
await asyncio.sleep(0.03)
return TranscriptionResult(text="timed output", provider="fixture", model="fixture-model")
monkeypatch.setattr("transcription.services.workflows.transcribe_document_image", _returns_text)
result = await process_queued_job(
job=loaded,
services=services,
settings=Settings(openrouter_api_key="test-key", worker_provider_timeout_seconds=2.0),
)
assert result is not None
assert result.status == JobStatus.TRANSCRIBED
async with services.jobs._session_scope() as session:
attempts = (
(
await session.exec(
select(ExecutionAttempt).where(
col(ExecutionAttempt.job_source_id).in_([js.id for js in result.job_sources])
)
)
)
.all()
)
assert len(attempts) == 1
attempt = attempts[0]
timing = (attempt.normalized_metadata or {}).get("processing_timing")
assert isinstance(timing, dict)
provider_call_ms = timing.get("provider_call_duration_ms")
processing_ms = timing.get("processing_duration_ms")
assert isinstance(provider_call_ms, int)
assert isinstance(processing_ms, int)
assert provider_call_ms >= 0
assert processing_ms >= provider_call_ms
assert attempt.duration_ms == provider_call_ms
@pytest.mark.asyncio
async def test_error_after_claim_fails_the_job_instead_of_stranding_it(
self,
@@ -239,7 +307,7 @@ class TestWorkflowReliability:
assert final.status == JobStatus.FAILED
@pytest.mark.asyncio
async def test_completed_page_is_committed_before_next_provider_call_finishes(
async def test_transcribed_page_is_committed_before_next_provider_call_finishes(
self,
default_session_factory,
monkeypatch,