Implement Rec - Phase 3 complete

tests/services/test_workflows_reliability.py

@@ -86,6 +86,7 @@ class TestWorkflowReliability:
             provider=None,
             source_reference=None,
             requested_model=None,
+            evidence_capture=None,
         ):
             _ = (
                 image_path,
@@ -97,6 +98,7 @@ class TestWorkflowReliability:
                 provider,
                 source_reference,
                 requested_model,
+                evidence_capture,
             )
             raise TimeoutError("simulated provider timeout")
 
@@ -370,6 +372,64 @@ class TestWorkflowReliability:
         assert result is not None
         assert result.status == JobStatus.TRANSCRIBED
 
+    @pytest.mark.asyncio
+    async def test_intermediate_page_commit_advances_job_liveness_timestamp(
+        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="heartbeat-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, 3):
+                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)
+
+        third_started = asyncio.Event()
+        release_third = asyncio.Event()
+        call_count = 0
+
+        async def _transcribe(image_path, **kwargs):
+            nonlocal call_count
+            _ = (image_path, kwargs)
+            call_count += 1
+            if call_count == 3:
+                third_started.set()
+                await release_third.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(third_started.wait(), timeout=2)
+
+        async with services.jobs._session_scope() as session:
+            current_job = await session.get(Job, loaded.id)
+            assert current_job is not None
+            attempts = await services.evidence.list_execution_attempts(job_id=loaded.id, session=session)
+
+        assert len(attempts) == 2
+        assert current_job.date_updated >= attempts[1].finished_at
+
+        release_third.set()
+        await task
+
     @pytest.mark.asyncio
     async def test_failed_job_with_validation_category_is_not_requeued(self, default_session_factory):
         services = ServiceBundle.from_session_factory(default_session_factory)