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
+102
View File
@@ -121,3 +121,105 @@ async def test_retranscription_job_locks_source_and_frozen_model(default_session
assert loaded.model == "vendor/alternate"
assert loaded.user_prompt == "Transcribe verbatim."
assert [link.source_id for link in loaded.job_sources] == [source.id]
@pytest.mark.integration
@pytest.mark.asyncio
async def test_promoting_candidate_does_not_mutate_execution_attempt_history(default_session_factory):
settings = Settings(openrouter_api_key="test-key", provider_models=None)
services = _services(default_session_factory, settings)
source = await _seed_source(services)
first_job = await services.jobs.create_job(Job(document_id=source.document_id))
second_job = await services.jobs.create_job(Job(document_id=source.document_id))
await services.sources.create_job_source(JobSource(job_id=first_job.id, source_id=source.id))
await services.sources.create_job_source(JobSource(job_id=second_job.id, source_id=source.id))
await services.sources.update_job_source_transcription(
job_id=first_job.id,
source_id=source.id,
text="baseline",
provider="fixture",
model="model-a",
)
await services.sources.update_job_source_transcription(
job_id=second_job.id,
source_id=source.id,
text="candidate",
provider="fixture",
model="model-b",
)
before = [
(
attempt.id,
attempt.job_id,
attempt.source_id,
attempt.attempt_number,
attempt.status.value,
attempt.raw_transcription,
attempt.error_category,
attempt.error_detail,
attempt.failure_phase,
)
for attempt in await services.evidence.list_execution_attempts(source_id=source.id)
]
candidate = next(
attempt
for attempt in await services.evidence.list_execution_attempts(source_id=source.id)
if attempt.raw_transcription == "candidate"
)
await services.evidence.promote_machine_attempt(source_id=source.id, execution_attempt_id=candidate.id)
after = [
(
attempt.id,
attempt.job_id,
attempt.source_id,
attempt.attempt_number,
attempt.status.value,
attempt.raw_transcription,
attempt.error_category,
attempt.error_detail,
attempt.failure_phase,
)
for attempt in await services.evidence.list_execution_attempts(source_id=source.id)
]
assert after == before
@pytest.mark.integration
@pytest.mark.asyncio
async def test_retry_appends_new_attempt_instead_of_rewriting_history(default_session_factory):
settings = Settings(openrouter_api_key="test-key", provider_models=None)
services = _services(default_session_factory, settings)
source = await _seed_source(services)
job = await services.jobs.create_job(Job(document_id=source.document_id))
await services.sources.create_job_source(JobSource(job_id=job.id, source_id=source.id))
await services.sources.update_job_source_transcription(
job_id=job.id,
source_id=source.id,
text=None,
error_detail="timeout",
error_category="timeout",
provider="fixture",
model="model-a",
failure_phase="provider_call",
)
await services.sources.update_job_source_transcription(
job_id=job.id,
source_id=source.id,
text="retry-success",
provider="fixture",
model="model-a",
)
attempts = list(await services.evidence.list_execution_attempts(source_id=source.id))
assert len(attempts) == 2
assert [attempt.attempt_number for attempt in attempts] == [1, 2]
assert attempts[0].raw_transcription is None
assert attempts[1].raw_transcription == "retry-success"