process_job updates

src/transcription/config.py

@@ -75,7 +75,7 @@ LOGGING_CONFIG: dict[str, object] = {
     "disable_existing_loggers": False,
     "formatters": {
         "standard": {
-            "format": "%(asctime)s | %(levelname)-8s | %(name)s | %(message)s",
+            "format": "%(asctime)s %(levelname)-8s | %(message)s",
             "datefmt": "%Y-%m-%d %H:%M:%S",
         }
     },

src/transcription/services/documents.py

@@ -15,7 +15,6 @@ from ..errors import AppError
 from ..errors import ErrorCategory
 from ..models import Document
 from ..models import Job
-from ..models import JobStatus
 from .base import ServiceBase
 from .store import store_file
 
@@ -178,10 +177,7 @@ async def _create_upload_records(
     session.add(document)
     await session.flush()
 
-    job = Job(
-        document_id=document.id,
-        status=JobStatus.QUEUED,
-    )
+    job = Job(document_id=document.id)
     session.add(job)
     await session.commit()
     await session.refresh(document)

src/transcription/worker.py

@@ -70,18 +70,40 @@ async def _get_queue_item(queue: asyncio.Queue[UUID]) -> AsyncGenerator[UUID]:
     queue.task_done()
 
 
-async def process_job(job: Job, services: ServiceBundle) -> None:
+async def process_job(
+    job: Job,
+    services: ServiceBundle,
+    settings: Settings | None = None,
+    session: AsyncSession | None = None,
+) -> Job | None:
     """Process a single job using the service bundle."""
+    settings = settings or get_settings()
     match job.status:
         case JobStatus.QUEUED:
             job.status = JobStatus.PROCESSING
             try:
-                await services.transcriptions.transcribe_image(job.document.file_path)
+                # await services.transcriptions.transcribe_image(job.document.file_path)
                 job.status = JobStatus.TRANSCRIBED
             except TranscriptionError as exc:
                 job.status = JobStatus.FAILED
                 job.error_message = str(exc)
-            await services.jobs.update_job(job)
+                logger.error(
+                    "Job failed operation=worker.process_job job_id=%s document_id=%s error=%s",
+                    job.id,
+                    job.document.id,
+                    exc,
+                )
+        case JobStatus.FAILED:
+            if job.retry_count < settings.worker_max_retries:
+                job.retry_count += 1
+                job.status = JobStatus.QUEUED
+                logger.info(f"Queuing job {job.id} for retry {job.retry_count}/{settings.worker_max_retries}")
+            else:
+                logger.error(f"Job {job.id} has failed and reached max retries.")
+                return
+        case _:
+            return
+    return await services.jobs.update_job(job, session=session)
 
 
 async def run_worker_loop(