Files
transcription/tests/services/test_v45_candidates.py
T

131 lines
5.1 KiB
Python

"""V4.5 retranscription candidate and promotion tests."""
from uuid import uuid4
import pytest
from transcription.config import Settings
from transcription.db.models import Document
from transcription.db.models import Job
from transcription.db.models import JobPurpose
from transcription.db.models import JobSource
from transcription.db.models import Source
from transcription.services import ServiceBundle
from transcription.services.documents import DocumentService
from transcription.services.jobs import JobService
from transcription.services.sources import CandidatePromotionError
from transcription.services.sources import SourceService
from transcription.services.workflows import create_source_retranscription_job
def _services(default_session_factory, settings: Settings) -> ServiceBundle:
return ServiceBundle(
documents=DocumentService(session_factory=default_session_factory, settings=settings),
jobs=JobService(session_factory=default_session_factory, settings=settings),
sources=SourceService(session_factory=default_session_factory, settings=settings),
)
async def _seed_source(services: ServiceBundle) -> Source:
document = await services.documents.create_document(Document(name="V4.5 source"))
source = Source(
document_id=document.id,
page_number=1,
upload_name="page.jpg",
filename="page.jpg",
file_path="page.jpg",
file_hash="a" * 64,
file_size_bytes=1,
revised_text="human revision",
)
return await services.sources.create_source(source)
@pytest.mark.integration
@pytest.mark.asyncio
async def test_first_success_is_preferred_and_later_success_remains_candidate(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="first result",
provider="fixture",
model="model-a",
)
selected = await services.sources.read_source(source.id)
first_attempt_id = selected.preferred_execution_attempt_id
await services.sources.update_job_source_transcription(
job_id=second_job.id,
source_id=source.id,
text="candidate result",
provider="fixture",
model="model-b",
)
unchanged = await services.sources.read_source(source.id)
attempts = await services.sources.list_execution_attempts(source_id=source.id)
assert unchanged.raw_transcription == "first result"
assert unchanged.preferred_execution_attempt_id == first_attempt_id
assert {attempt.raw_transcription for attempt in attempts} == {"first result", "candidate result"}
candidate = next(attempt for attempt in attempts if attempt.raw_transcription == "candidate result")
promoted = await services.sources.promote_machine_attempt(
source_id=source.id,
execution_attempt_id=candidate.id,
)
assert promoted.raw_transcription == "candidate result"
assert promoted.preferred_execution_attempt_id == candidate.id
assert promoted.revised_text == "human revision"
@pytest.mark.integration
@pytest.mark.asyncio
async def test_promotion_rejects_unrelated_attempt(default_session_factory):
settings = Settings(openrouter_api_key="test-key", provider_models=None)
services = _services(default_session_factory, settings)
source = await _seed_source(services)
with pytest.raises(CandidatePromotionError):
await services.sources.promote_machine_attempt(
source_id=source.id,
execution_attempt_id=uuid4(),
)
@pytest.mark.integration
@pytest.mark.asyncio
async def test_retranscription_job_locks_source_and_frozen_model(default_session_factory, tmp_path):
settings = Settings(
openrouter_api_key="test-key",
prompt_dir=tmp_path,
provider_model="vendor/default",
provider_models=["vendor/alternate"],
)
(tmp_path / settings.default_prompt_name).write_text("Transcribe verbatim.", encoding="utf-8")
services = _services(default_session_factory, settings)
source = await _seed_source(services)
job = await create_source_retranscription_job(
source_id=source.id,
model="vendor/alternate",
services=services,
settings=settings,
)
loaded = await services.jobs.read_job(job.id)
assert loaded.purpose == JobPurpose.RETRANSCRIPTION
assert loaded.document_id == source.document_id
assert loaded.provider == "openrouter"
assert loaded.model == "vendor/alternate"
assert loaded.user_prompt == "Transcribe verbatim."
assert [link.source_id for link in loaded.job_sources] == [source.id]