gitea-admin/gh-christianlouis-docuelevate
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

Fix file_id propagation through task chain

Browse Source 
- Pass file_id as parameter through all task chains
- Update process_document, extract_metadata_with_gpt, embed_metadata_into_pdf, finalize_document_storage, send_to_all_destinations, rotate_pdf_pages, and process_with_azure_document_intelligence
- Remove unreliable LIKE queries, use explicit file_id passing instead

Co-authored-by: christianlouis <361235+christianlouis@users.noreply.github.com>
This commit is contained in:
copilot-swe-agent[bot]
2026-02-06 22:34:01 +00:00
parent 1903dc5bcd
commit 74680c8849
7 changed files with 61 additions and 54 deletions
Download Patch File Download Diff File Expand all files Collapse all files
app/tasks/finalize_document_storage.py
+12 -12
View File
@@ -17,29 +17,29 @@ logger = logging.getLogger(__name__)
@celery.task(base=BaseTaskWithRetry, bind=True)
def finalize_document_storage(self, original_file: str, processed_file: str, metadata: dict):
def finalize_document_storage(self, original_file: str, processed_file: str, metadata: dict, file_id: int = None):
"""
Final storage step after embedding metadata.
We will now call 'send_to_all_destinations' to push the final PDF to Dropbox/Nextcloud/Paperless.
"""
task_id = self.request.id
logger.info(f"[{task_id}] Finalizing document storage for {processed_file}")
log_task_progress(task_id, "finalize_document_storage", "in_progress", f"Finalizing: {os.path.basename(processed_file)}")
log_task_progress(task_id, "finalize_document_storage", "in_progress", f"Finalizing: {os.path.basename(processed_file)}", file_id=file_id)
# Get file_id from database
file_id = None
with SessionLocal() as db:
# Try to find by the processed file path first
file_record = db.query(FileRecord).filter(
FileRecord.local_filename.like(f"%{os.path.basename(original_file)}%")
).first()
if file_record:
file_id = file_record.id
# Get file_id from database if not provided
if file_id is None:
with SessionLocal() as db:
# Try to find by the original file path
file_record = db.query(FileRecord).filter(
FileRecord.local_filename.like(f"%{os.path.basename(original_file)}%")
).first()
if file_record:
file_id = file_record.id
# 2) Enqueue uploads to all destinations (Dropbox, Nextcloud, Paperless)
logger.info(f"[{task_id}] Queueing uploads to all destinations")
log_task_progress(task_id, "finalize_document_storage", "success", "Queuing uploads to destinations", file_id=file_id)
send_to_all_destinations.delay(processed_file)
send_to_all_destinations.delay(processed_file, True, file_id)
return {
"status": "Completed",