US07-04: Prove Concurrency and Crash Recovery (#86)

photo_pipeline/jobs/worker.py

@@ -16,6 +16,7 @@ from collections.abc import Mapping, Sequence
 from sqlalchemy import select
 from sqlalchemy.orm import sessionmaker
 
+from photo_pipeline.faults import JOB_ITEM_DONE, maybe_fault
 from photo_pipeline.jobs.handlers import REGISTRY, Cancelled, Handler, JobContext
 from photo_pipeline.models import JobItem
 from photo_pipeline.services.jobs import ItemState, JobConflict, JobService, JobState
@@ -86,6 +87,9 @@ class Worker:
                 )
             else:
                 self.service.set_item(job_id, item_key, ItemState.SUCCEEDED, fencing_token=token)
+                # One item is durably done, the job outcome is not: the control point
+                # for a crash mid-batch (US07-04). Recovery must not re-run this item.
+                maybe_fault(JOB_ITEM_DONE)
             self.service.heartbeat(job_id, self.worker_id, lease_seconds=self.lease_seconds)
 
         self._finalize(job_id, token, cancelled=cancelled, any_failed=any_failed)