Files
transcription/tests/services/test_workflows_reliability.py
T
zoltan57andCopilot App 110f40a28b Phase 4: measure only the provider call in duration_ms
Review log [55]. Three historical local_timeout rows recorded 0.4-2.0s more
than the configured budget because the measurement window opened before the
provider call.

The plan named two causes, and both were already gone. Diffed against
f86c0ff~1: at V4.6 the window held resolve_provider_input (async;
normalization + artifact write + DB work) and a session.commit(). Phase 1
deleted both. What remains between the clock and the wait_for is
build_provider_input, now pure field copying because normalization moved to
ingest and file_hash is already stored: 6.2 us per call, zero awaits, so it
cannot yield to the event loop.

A third cause was still there and is not in the plan. The regression test
below measured 890ms where ~200ms was expected. services.sources.provider is
a lazy property that appears as an argument expression to _call_transcriber,
so it is evaluated after the clock starts but before wait_for begins timing.
Constructing OpenRouterTranscriptionProvider costs 475ms on first access and
0.001ms after, so the first attempt of every worker process booked half a
second of HTTP client construction as provider latency. That plausibly
accounts for the low end of the historical overshoot.

workflows.py
  - Re-capture monotonic_started_at immediately before the wait_for, reusing
    the same variable. The pre-loop assignment stays as the fallback: binding
    a new name inside the try would leave the general-exception handler
    referencing an unbound variable when build_provider_input raises. All
    three duration write sites (success, TimeoutError, general failure) then
    measure the correct window with no further change.
  - Hoist the provider property above the per-source loop. It is
    loop-invariant, so this also removes the repeated lookup from the two
    evidence-capture sites.

tests/services/test_workflows_reliability.py
  test_timeout_duration_excludes_pre_call_setup simulates 400ms of blocking
  setup against a 200ms budget and asserts the recorded duration sits near
  the budget and well clear of budget+setup. Confirmed to fail on the pre-fix
  code (assert 625 < 540) and pass after, so it guards behaviour rather than
  restating it. This is the plan's verification criterion as a test.

ui/pages/sources_page.py
  _format_duration renders >=1s as "27.6 s" and below that as "612 ms",
  replacing the raw "27612 ms". No test asserted the old format.

Plan task 3 (record preprocessing as its own value) declined and logged as a
deviation: after Phase 1 there is no preprocessing left to record, and a
preprocessing_ms column to measure 6 us of attribute copying is complexity
without a reader.

Verified: 293 passed, 4 skipped, 0 ruff, 0 ty.

Co-authored-by: Copilot App <[email protected]>
2026-08-18 16:02:58 -05:00

236 lines
9.4 KiB
Python

"""Reliability tests for worker workflow timeout behavior."""
import asyncio
import time
from pathlib import Path
from uuid import uuid4
import pytest
from sqlmodel import col
from sqlmodel import select
from transcription.config import Settings
from transcription.db.models import Document
from transcription.db.models import ExecutionAttempt
from transcription.db.models import Job
from transcription.db.models import JobSource
from transcription.db.models import JobSourceStatus
from transcription.db.models import JobStatus
from transcription.db.models import Source
from transcription.providers.base import TranscriptionResult
from transcription.services import ServiceBundle
from transcription.services import workflows as workflows_module
from transcription.services.workflows import process_queued_job
@pytest.mark.integration
class TestWorkflowReliability:
"""Verify timeout and terminal-state reliability behavior."""
@pytest.mark.asyncio
async def test_process_queued_job_timeout_marks_job_failed(self, default_session_factory, monkeypatch):
"""Provider timeout transitions a queued job to failed with error detail."""
services = ServiceBundle()
object.__setattr__(
services,
"documents",
services.documents.__class__(session_factory=default_session_factory),
)
object.__setattr__(
services,
"jobs",
services.jobs.__class__(session_factory=default_session_factory),
)
object.__setattr__(
services,
"sources",
services.sources.__class__(session_factory=default_session_factory),
)
async with services.jobs._session_scope() as session:
document = Document(id=uuid4(), name="timeout-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="timeout.jpg",
filename="timeout.jpg",
file_path=str(Path("tests/fixtures/images/real/Book Two - page 02.jpg")),
file_hash="c" * 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 _never_returns(
image_path,
*,
prompt_name="transcribe_document.md",
prompt_text=None,
temperature=None,
top_p=None,
settings=None,
provider=None,
):
_ = (image_path, prompt_name, prompt_text, temperature, top_p, settings, provider)
raise TimeoutError("simulated provider timeout")
monkeypatch.setattr("transcription.services.workflows.transcribe_document_image", _never_returns)
timeout_settings = Settings(openrouter_api_key="test-key", worker_provider_timeout_seconds=20.0)
result = await process_queued_job(job=loaded, services=services, settings=timeout_settings)
assert result is not None
assert result.status == JobStatus.FAILED
async with services.jobs._session_scope() as session:
attempts = (
await session.execute(
select(ExecutionAttempt).where(
col(ExecutionAttempt.job_source_id).in_([js.id for js in result.job_sources])
)
)
).scalars().all()
error_detail = next(attempt.error_detail for attempt in attempts if attempt.error_detail is not None)
assert "timed out" in error_detail.lower()
assert "20.0s" in error_detail
@pytest.mark.asyncio
async def test_timeout_duration_excludes_pre_call_setup(self, default_session_factory, monkeypatch):
"""duration_ms covers only the provider call, not the setup preceding it.
Regression guard for review log [55]: three historical ``local_timeout`` rows
recorded 0.4-2.0 s more than the configured budget because the measurement
window opened before payload resolution. Blocking setup is simulated here so
the assertion fails if that window ever reopens.
"""
services = ServiceBundle.from_session_factory(default_session_factory)
async with services.jobs._session_scope() as session:
document = Document(id=uuid4(), name="window-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="window.jpg",
filename="window.jpg",
file_path=str(Path("tests/fixtures/images/real/Book Two - page 02.jpg")),
file_hash="d" * 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)
setup_seconds = 0.40
budget_seconds = 0.20
real_build = workflows_module.build_provider_input
def _slow_build(source_arg):
time.sleep(setup_seconds)
return real_build(source_arg)
async def _never_returns(*args, **kwargs):
_ = (args, kwargs)
await asyncio.sleep(budget_seconds * 20)
monkeypatch.setattr("transcription.services.workflows.build_provider_input", _slow_build)
monkeypatch.setattr("transcription.services.workflows.transcribe_document_image", _never_returns)
result = await process_queued_job(
job=loaded,
services=services,
settings=Settings(openrouter_api_key="test-key", worker_provider_timeout_seconds=budget_seconds),
)
assert result is not None
assert result.status == JobStatus.FAILED
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
duration_ms = attempts[0].duration_ms
# At or just above the budget, and well clear of budget + setup.
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_completed_page_is_committed_before_next_provider_call_finishes(
self,
default_session_factory,
monkeypatch,
):
services = ServiceBundle.from_session_factory(default_session_factory)
async with services.jobs._session_scope() as session:
document = Document(id=uuid4(), name="durability-doc")
session.add(document)
await session.flush()
job = Job(document_id=document.id, status=JobStatus.QUEUED)
session.add(job)
await session.flush()
for page_number in (1, 2):
source = Source(
document_id=document.id,
page_number=page_number,
upload_name=f"page-{page_number}.jpg",
filename=f"page-{page_number}.jpg",
file_path=str(Path("tests/fixtures/images/real/Book Two - page 02.jpg")),
file_hash=str(page_number) * 64,
file_size_bytes=1,
)
session.add(source)
await session.flush()
session.add(JobSource(job_id=job.id, source_id=source.id))
await session.commit()
loaded = await services.jobs.read_job(job_id=job.id, session=session)
second_started = asyncio.Event()
release_second = asyncio.Event()
call_count = 0
async def _transcribe(image_path, **kwargs):
nonlocal call_count
_ = (image_path, kwargs)
call_count += 1
if call_count == 2:
second_started.set()
await release_second.wait()
return TranscriptionResult(text=f"page {call_count}", provider="fixture", model="model")
monkeypatch.setattr("transcription.services.workflows.transcribe_document_image", _transcribe)
task = asyncio.create_task(process_queued_job(job=loaded, services=services))
await asyncio.wait_for(second_started.wait(), timeout=2)
attempts = await services.evidence.list_execution_attempts(job_id=job.id)
assert len(attempts) == 1
assert attempts[0].raw_transcription == "page 1"
release_second.set()
result = await task
assert result is not None
assert result.status == JobStatus.TRANSCRIBED