generated from john/python-template
V4.2 Updated what ai_raw_response data is being captured. The changes were more extensive than I expected.
This commit is contained in:
Jim Lancaster
@@ -0,0 +1,356 @@
|
||||
"""Focused V4.2 evidence, integrity, and benchmark tests."""
|
||||
|
||||
from __future__ import annotations
|
||||
|
||||
import hashlib
|
||||
import json
|
||||
from datetime import UTC
|
||||
from datetime import datetime
|
||||
from uuid import uuid4
|
||||
|
||||
import httpx
|
||||
import pytest
|
||||
|
||||
from transcription.benchmarking import EditorialAssessment
|
||||
from transcription.benchmarking import score_transcription
|
||||
from transcription.config import Settings
|
||||
from transcription.db.models import Document
|
||||
from transcription.db.models import Job
|
||||
from transcription.db.models import JobSource
|
||||
from transcription.db.models import JobSourceStatus
|
||||
from transcription.db.models import ProcessingArtifact
|
||||
from transcription.db.models import Source
|
||||
from transcription.providers.base import ProviderError
|
||||
from transcription.providers.base import TranscriptionResult
|
||||
from transcription.providers.evidence import SourceEvidenceReference
|
||||
from transcription.providers.openrouter import OpenRouterTranscriptionProvider
|
||||
from transcription.services.documents import DocumentService
|
||||
from transcription.services.jobs import JobDeleteBlockedError
|
||||
from transcription.services.jobs import JobService
|
||||
from transcription.services.sources import SourceDeleteBlockedError
|
||||
from transcription.services.sources import SourceService
|
||||
from transcription.services.sources import TranscriptionError
|
||||
from transcription.services.sources import transcribe_document_image
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_openrouter_captures_exact_transport_and_secret_safe_manifest():
|
||||
response_body = (
|
||||
b'{"id":"gen-1","created":1,"model":"vendor/model","object":"chat.completion",'
|
||||
b'"system_fingerprint":null,"choices":[{"index":0,"finish_reason":"stop",'
|
||||
b'"message":{"role":"assistant","content":"Transcript"}}],'
|
||||
b'"unknown_transport_field":{"retained":true}}'
|
||||
)
|
||||
|
||||
async def handler(request: httpx.Request) -> httpx.Response:
|
||||
assert request.headers["authorization"] == "Bearer test-key"
|
||||
return httpx.Response(
|
||||
200,
|
||||
content=response_body,
|
||||
headers={
|
||||
"Content-Type": "application/json",
|
||||
"X-Request-Id": "req-123",
|
||||
"Set-Cookie": "must-not-persist=1",
|
||||
},
|
||||
request=request,
|
||||
)
|
||||
|
||||
async_client = httpx.AsyncClient(transport=httpx.MockTransport(handler))
|
||||
provider = OpenRouterTranscriptionProvider(
|
||||
settings=Settings(openrouter_api_key="test-key"),
|
||||
async_client=async_client,
|
||||
)
|
||||
result = await provider.transcribe(
|
||||
prompt_text="Literal prompt",
|
||||
image_bytes=b"source-bytes",
|
||||
mime_type="image/png",
|
||||
source_reference=SourceEvidenceReference(
|
||||
source_id=uuid4(),
|
||||
digest_sha256=hashlib.sha256(b"source-bytes").hexdigest(),
|
||||
byte_size=len(b"source-bytes"),
|
||||
media_type="image/png",
|
||||
page_number=1,
|
||||
),
|
||||
)
|
||||
|
||||
assert result.transport_evidence is not None
|
||||
assert result.transport_evidence.body == response_body
|
||||
assert result.transport_evidence.safe_headers == {
|
||||
"content-type": "application/json",
|
||||
"x-request-id": "req-123",
|
||||
}
|
||||
assert b'"unknown_transport_field":{"retained":true}' in result.transport_evidence.body
|
||||
assert result.request_manifest is not None
|
||||
serialized_manifest = json.dumps(result.request_manifest.model_dump(mode="json"))
|
||||
assert "data:image/png;base64" not in serialized_manifest
|
||||
assert "test-key" not in serialized_manifest
|
||||
assert result.request_manifest.omitted_optional_parameters == ("temperature", "top_p")
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_openrouter_failure_retains_safe_response_evidence():
|
||||
async def handler(request: httpx.Request) -> httpx.Response:
|
||||
return httpx.Response(
|
||||
500,
|
||||
content=b'{"error":{"message":"provider unavailable"}}',
|
||||
headers={"Content-Type": "application/json", "Retry-After": "2", "Set-Cookie": "secret=1"},
|
||||
request=request,
|
||||
)
|
||||
|
||||
provider = OpenRouterTranscriptionProvider(
|
||||
settings=Settings(openrouter_api_key="test-key"),
|
||||
async_client=httpx.AsyncClient(transport=httpx.MockTransport(handler)),
|
||||
)
|
||||
with pytest.raises(ProviderError) as failure:
|
||||
await provider.transcribe(
|
||||
prompt_text="Literal prompt",
|
||||
image_bytes=b"source-bytes",
|
||||
mime_type="image/png",
|
||||
)
|
||||
|
||||
evidence = failure.value.transport_evidence
|
||||
assert evidence is not None
|
||||
assert evidence.status_code == 500
|
||||
assert evidence.body == b'{"error":{"message":"provider unavailable"}}'
|
||||
assert evidence.safe_headers == {"content-type": "application/json", "retry-after": "2"}
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_openrouter_does_not_reuse_prior_response_on_connection_failure():
|
||||
call_count = 0
|
||||
|
||||
async def handler(request: httpx.Request) -> httpx.Response:
|
||||
nonlocal call_count
|
||||
call_count += 1
|
||||
if call_count == 1:
|
||||
return httpx.Response(500, content=b'{"error":"first"}', request=request)
|
||||
raise httpx.ConnectError("connection failed", request=request)
|
||||
|
||||
provider = OpenRouterTranscriptionProvider(
|
||||
settings=Settings(openrouter_api_key="test-key"),
|
||||
async_client=httpx.AsyncClient(transport=httpx.MockTransport(handler)),
|
||||
)
|
||||
with pytest.raises(ProviderError) as first_failure:
|
||||
await provider.transcribe(prompt_text="First", image_bytes=b"one", mime_type="image/png")
|
||||
with pytest.raises(ProviderError) as second_failure:
|
||||
await provider.transcribe(prompt_text="Second", image_bytes=b"two", mime_type="image/png")
|
||||
|
||||
assert first_failure.value.transport_evidence is not None
|
||||
assert second_failure.value.transport_evidence is not None
|
||||
assert second_failure.value.transport_evidence.response_received is False
|
||||
assert second_failure.value.transport_evidence.body is None
|
||||
await provider.aclose()
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_attempts_are_append_only_and_exported_with_integrity(default_session_factory):
|
||||
documents = DocumentService(session_factory=default_session_factory)
|
||||
jobs = JobService(session_factory=default_session_factory)
|
||||
sources = SourceService(session_factory=default_session_factory)
|
||||
document = await documents.create_document(Document(name="Evidence"))
|
||||
job = await jobs.create_job(Job(document_id=document.id))
|
||||
source = await sources.create_source(
|
||||
Source(
|
||||
document_id=document.id,
|
||||
page_number=1,
|
||||
upload_name="page.png",
|
||||
filename="page.png",
|
||||
file_path="page.png",
|
||||
file_hash="a" * 64,
|
||||
file_size_bytes=10,
|
||||
)
|
||||
)
|
||||
await sources.create_job_source(JobSource(job_id=job.id, source_id=source.id))
|
||||
now = datetime.now(UTC)
|
||||
|
||||
await sources.update_job_source_transcription(
|
||||
job_id=job.id,
|
||||
source_id=source.id,
|
||||
text=None,
|
||||
error_detail="first failed",
|
||||
error_category="external_provider_error",
|
||||
failure_phase="connection",
|
||||
started_at=now,
|
||||
finished_at=now,
|
||||
)
|
||||
await sources.update_job_source_transcription(
|
||||
job_id=job.id,
|
||||
source_id=source.id,
|
||||
text="second succeeded",
|
||||
provider="openrouter",
|
||||
model="vendor/model",
|
||||
started_at=now,
|
||||
finished_at=now,
|
||||
)
|
||||
|
||||
attempts = await sources.list_execution_attempts(source_id=source.id)
|
||||
assert [attempt.attempt_number for attempt in attempts] == [1, 2]
|
||||
assert attempts[0].status == JobSourceStatus.FAILED
|
||||
assert attempts[0].error_detail == "first failed"
|
||||
assert attempts[1].status == JobSourceStatus.TRANSCRIBED
|
||||
assert attempts[1].raw_transcription == "second succeeded"
|
||||
|
||||
payload = {"words": [{"text": "second", "polygon": [0, 0, 1, 1]}]}
|
||||
payload_bytes = json.dumps(payload, sort_keys=True, separators=(",", ":")).encode()
|
||||
artifact = await sources.create_processing_artifact(
|
||||
ProcessingArtifact(
|
||||
source_id=source.id,
|
||||
execution_attempt_id=attempts[1].id,
|
||||
artifact_type="ocr.words",
|
||||
media_type="application/json",
|
||||
schema_name="example.ocr.words",
|
||||
schema_version="1",
|
||||
producer="fixture",
|
||||
producer_version="1",
|
||||
inline_payload=payload,
|
||||
payload_sha256=hashlib.sha256(payload_bytes).hexdigest(),
|
||||
byte_size=len(payload_bytes),
|
||||
coordinate_metadata={
|
||||
"units": "normalized",
|
||||
"origin": "top-left",
|
||||
"width": 1,
|
||||
"height": 1,
|
||||
"transformations": [],
|
||||
},
|
||||
)
|
||||
)
|
||||
export = await sources.build_evidence_export(source_id=source.id)
|
||||
assert export["source"]["digest_sha256"] == "a" * 64
|
||||
assert [item["attempt_number"] for item in export["attempts"]] == [1, 2]
|
||||
assert export["artifacts"][0]["id"] == str(artifact.id)
|
||||
assert "file_path" not in json.dumps(export)
|
||||
with pytest.raises(JobDeleteBlockedError):
|
||||
await jobs.delete_job_with_guardrails(job_id=job.id)
|
||||
|
||||
detail = await sources.read_source_detail(source.id)
|
||||
latest_job_source = detail.latest_job_source
|
||||
assert latest_job_source is not None
|
||||
assert latest_job_source.execution_attempts == []
|
||||
assert detail.processing_artifacts == []
|
||||
latest_attempt = await sources.read_latest_execution_attempt(job_source_id=latest_job_source.id)
|
||||
assert latest_attempt is not None
|
||||
assert latest_attempt.attempt_number == 2
|
||||
|
||||
|
||||
def test_benchmark_scoring_preserves_literal_differences():
|
||||
score = score_transcription(
|
||||
execution_attempt_id=uuid4(),
|
||||
reference="Farm house",
|
||||
candidate="farm house",
|
||||
assessment=EditorialAssessment(silent_normalizations=1),
|
||||
latency_ms=125,
|
||||
)
|
||||
assert score.character_edits == 1
|
||||
assert score.word_edits == 1
|
||||
assert score.assessment.silent_normalizations == 1
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_large_json_artifact_uses_constrained_atomic_storage(
|
||||
default_session_factory,
|
||||
tmp_path,
|
||||
):
|
||||
settings = Settings(
|
||||
openrouter_api_key="test-key",
|
||||
artifact_dir=tmp_path / "artifacts",
|
||||
artifact_inline_threshold_bytes=10,
|
||||
)
|
||||
documents = DocumentService(session_factory=default_session_factory, settings=settings)
|
||||
sources = SourceService(session_factory=default_session_factory, settings=settings)
|
||||
document = await documents.create_document(Document(name="External Artifact"))
|
||||
source = await sources.create_source(
|
||||
Source(
|
||||
document_id=document.id,
|
||||
page_number=1,
|
||||
upload_name="page.png",
|
||||
filename="page.png",
|
||||
file_path="page.png",
|
||||
file_hash="b" * 64,
|
||||
file_size_bytes=10,
|
||||
)
|
||||
)
|
||||
|
||||
artifact = await sources.create_json_artifact(
|
||||
source_id=source.id,
|
||||
execution_attempt_id=None,
|
||||
artifact_type="ocr.layout",
|
||||
schema_name="example.layout",
|
||||
schema_version="1",
|
||||
producer="fixture",
|
||||
producer_version="1",
|
||||
payload={"blocks": [{"text": "long enough to be external"}]},
|
||||
)
|
||||
|
||||
assert artifact.inline_payload is None
|
||||
assert artifact.external_reference is not None
|
||||
stored_path = settings.artifact_dir / artifact.external_reference
|
||||
assert stored_path.is_file()
|
||||
assert hashlib.sha256(stored_path.read_bytes()).hexdigest() == artifact.payload_sha256
|
||||
with pytest.raises(SourceDeleteBlockedError):
|
||||
await sources.delete_unlinked_source(source_id=source.id)
|
||||
|
||||
stored_path.write_bytes(b'{"tampered":true}')
|
||||
with pytest.raises(TranscriptionError, match="integrity verification"):
|
||||
await sources.build_evidence_export(source_id=source.id)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_rejects_inline_artifact_with_incorrect_integrity(default_session_factory):
|
||||
documents = DocumentService(session_factory=default_session_factory)
|
||||
sources = SourceService(session_factory=default_session_factory)
|
||||
document = await documents.create_document(Document(name="Inline Integrity"))
|
||||
source = await sources.create_source(
|
||||
Source(
|
||||
document_id=document.id,
|
||||
page_number=1,
|
||||
upload_name="page.png",
|
||||
filename="page.png",
|
||||
file_path="page.png",
|
||||
file_hash="d" * 64,
|
||||
file_size_bytes=10,
|
||||
)
|
||||
)
|
||||
|
||||
with pytest.raises(TranscriptionError, match="integrity verification"):
|
||||
await sources.create_processing_artifact(
|
||||
ProcessingArtifact(
|
||||
source_id=source.id,
|
||||
artifact_type="ocr.words",
|
||||
media_type="application/json",
|
||||
schema_name="example.words",
|
||||
schema_version="1",
|
||||
producer="fixture",
|
||||
producer_version="1",
|
||||
inline_payload={"words": []},
|
||||
payload_sha256="0" * 64,
|
||||
byte_size=1,
|
||||
)
|
||||
)
|
||||
|
||||
|
||||
@pytest.mark.asyncio
|
||||
async def test_standalone_transcription_closes_locally_created_provider(tmp_path, monkeypatch):
|
||||
image_path = tmp_path / "page.png"
|
||||
image_path.write_bytes(b"image")
|
||||
|
||||
class _Provider:
|
||||
closed = False
|
||||
|
||||
async def transcribe(self, **kwargs):
|
||||
_ = kwargs
|
||||
return TranscriptionResult(text="result", provider="fixture", model="model")
|
||||
|
||||
async def aclose(self):
|
||||
self.closed = True
|
||||
|
||||
provider = _Provider()
|
||||
monkeypatch.setattr("transcription.services.sources.get_transcription_provider", lambda **_kwargs: provider)
|
||||
|
||||
result = await transcribe_document_image(
|
||||
image_path,
|
||||
prompt_text="Prompt",
|
||||
settings=Settings(openrouter_api_key="test-key"),
|
||||
)
|
||||
|
||||
assert result.text == "result"
|
||||
assert provider.closed is True
|
||||
Reference in New Issue
Block a user