V4.7 Phase 2: Evidence Model Simplification (part 2)

tests/services/test_job_service.py

@@ -342,7 +342,6 @@ class TestJobService:
                     job_id=job.id,
                     source_id=source_one.id,
                     status=JobSourceStatus.TRANSCRIBED,
-                    raw_transcription="done",
                 )
             )
             session.add(
@@ -360,9 +359,8 @@ class TestJobService:
         refreshed = await job_service.read_job(job_id=job.id)
         statuses = {item.status for item in refreshed.job_sources}
         assert JobSourceStatus.TRANSCRIBED in statuses
-        assert JobSourceStatus.FAILED in statuses
-        pending_entry = next(item for item in refreshed.job_sources if item.status == JobSourceStatus.FAILED)
-        assert pending_entry.error_detail == "Cancelled by user"
+        assert JobSourceStatus.CANCELLED in statuses
+        assert JobSourceStatus.FAILED not in statuses
 
     @pytest.mark.asyncio
     async def test_resubmit_failed_sources_resets_only_failed(
@@ -406,8 +404,6 @@ class TestJobService:
                     job_id=job.id,
                     source_id=source_one.id,
                     status=JobSourceStatus.FAILED,
-                    raw_transcription=None,
-                    error_detail="prior error",
                 )
             )
             session.add(
@@ -415,7 +411,6 @@ class TestJobService:
                     job_id=job.id,
                     source_id=source_two.id,
                     status=JobSourceStatus.TRANSCRIBED,
-                    raw_transcription="done text",
                 )
             )
             await session.commit()
@@ -433,7 +428,6 @@ class TestJobService:
             item for item in refreshed.job_sources if item.source is not None and item.source.page_number == 2
         )
         assert failed_entry.status == JobSourceStatus.PENDING
-        assert failed_entry.error_detail is None
         assert failed_entry.source is not None
         assert failed_entry.source.raw_transcription == "existing text"
         assert transcribed_entry.status == JobSourceStatus.TRANSCRIBED
@@ -486,7 +480,6 @@ class TestJobService:
                     job_id=job.id,
                     source_id=source_two.id,
                     status=JobSourceStatus.TRANSCRIBED,
-                    raw_transcription="done text",
                 )
             )
             await session.commit()
@@ -494,6 +487,46 @@ class TestJobService:
         with pytest.raises(JobResubmitBlockedError):
             await job_service.resubmit_failed_sources(job_id=job.id)
 
+    @pytest.mark.asyncio
+    async def test_resubmit_failed_sources_includes_cancelled(
+        self,
+        job_service: JobService,
+        document_service: DocumentService,
+    ):
+        """Cancel is recoverable: cancelled pages are re-attempted on resubmit."""
+        document = Document(id=uuid4(), name="resubmit-cancelled-doc")
+        await document_service.create_document(document=document)
+
+        job = Job(document_id=document.id, status=JobStatus.FAILED)
+        await job_service.create_job(job=job)
+
+        async with job_service._session_scope() as session:
+            source = Source(
+                document_id=document.id,
+                page_number=1,
+                upload_name="resubmit-cancelled.jpg",
+                filename="stored-resubmit-cancelled.jpg",
+                file_path="/uploads/stored-resubmit-cancelled.jpg",
+                file_hash="3" * 64,
+                file_size_bytes=1,
+            )
+            session.add(source)
+            await session.flush()
+            session.add(
+                JobSource(
+                    job_id=job.id,
+                    source_id=source.id,
+                    status=JobSourceStatus.CANCELLED,
+                )
+            )
+            await session.commit()
+
+        assert await job_service.resubmit_failed_sources(job_id=job.id) == 1
+
+        refreshed = await job_service.read_job(job_id=job.id)
+        assert refreshed.status == JobStatus.QUEUED
+        assert refreshed.job_sources[0].status == JobSourceStatus.PENDING
+
     @pytest.mark.asyncio
     async def test_resubmit_failed_sources_blocks_when_processing(
         self,

tests/services/test_v2_crud.py

@@ -322,6 +322,10 @@ async def test_update_job_source_transcription_persists_provider_json_payloads(d
 
     stored_rows = await transcriptions.list_job_sources(job_id=job.id)
     assert len(stored_rows) == 1
-    assert stored_rows[0].raw_transcription == "provider transcript"
-    assert stored_rows[0].ai_metadata == metadata
-    assert stored_rows[0].raw_api_response == raw_payload
+    assert stored_rows[0].status == JobSourceStatus.TRANSCRIBED
+
+    attempt = await transcriptions.read_latest_execution_attempt(job_source_id=stored_rows[0].id)
+    assert attempt is not None
+    assert attempt.attempt.raw_transcription == "provider transcript"
+    assert attempt.attempt.normalized_metadata == metadata
+    assert attempt.attempt.sdk_response_snapshot == raw_payload

tests/services/test_workflows_reliability.py

@@ -5,9 +5,12 @@ 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
@@ -87,9 +90,18 @@ class TestWorkflowReliability:
 
         assert result is not None
         assert result.status == JobStatus.FAILED
-        assert result.error_detail is not None
-        assert "timed out" in result.error_detail.lower()
-        assert "20.0s" in result.error_detail
+
+        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_completed_page_is_committed_before_next_provider_call_finishes(