admin/mcp-nextcloud
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

fix: Add placeholder staleness check to prevent duplicate processing

Browse Source 
- Only requeue documents if placeholder is older than 2x scan interval (120s default)
- Prevents scanner from immediately requeuing in-flight documents
- Fixes issue where PDFs were being reprocessed every 60 seconds
- Staleness check applied to both notes and files scanning logic
This commit is contained in:
Chris Coutinho
2025-11-20 15:30:10 +01:00
parent 233de3508f
commit 47f0b3db9a
1 changed files with 32 additions and 10 deletions
Download Patch File Download Diff File Expand all files Collapse all files
nextcloud_mcp_server/vector/scanner.py
+32 -10
View File
@@ -265,11 +265,22 @@ async def scan_user_documents(
# Document modified since last indexing # Document modified since last indexing
needs_indexing = True needs_indexing = True
elif existing_metadata.get("is_placeholder", False): elif existing_metadata.get("is_placeholder", False):
# Placeholder exists but processing may have failed - requeue # Placeholder exists - check if it's stale (processing may have failed)
logger.debug( # Only requeue if placeholder is older than 2x scan interval
f"Found existing placeholder for note {doc_id}, requeuing" queued_at = existing_metadata.get("queued_at", 0)
) placeholder_age = time.time() - queued_at
needs_indexing = True stale_threshold = get_settings().vector_sync_scan_interval * 2
if placeholder_age > stale_threshold:
logger.debug(
f"Found stale placeholder for note {doc_id} "
f"(age={placeholder_age:.1f}s), requeuing"
)
needs_indexing = True
else:
logger.debug(
f"Skipping note {doc_id} with recent placeholder "
f"(age={placeholder_age:.1f}s < {stale_threshold:.1f}s)"
)
if needs_indexing: if needs_indexing:
# Write placeholder before queuing # Write placeholder before queuing
@@ -448,11 +459,22 @@ async def scan_user_documents(
# File modified since last indexing # File modified since last indexing
needs_indexing = True needs_indexing = True
elif existing_metadata.get("is_placeholder", False): elif existing_metadata.get("is_placeholder", False):
# Placeholder exists but processing may have failed - requeue # Placeholder exists - check if it's stale (processing may have failed)
logger.debug( # Only requeue if placeholder is older than 2x scan interval
f"Found existing placeholder for file {file_path} (ID: {file_id}), requeuing" queued_at = existing_metadata.get("queued_at", 0)
) placeholder_age = time.time() - queued_at
needs_indexing = True stale_threshold = get_settings().vector_sync_scan_interval * 2
if placeholder_age > stale_threshold:
logger.debug(
f"Found stale placeholder for file {file_path} (ID: {file_id}) "
f"(age={placeholder_age:.1f}s), requeuing"
)
needs_indexing = True
else:
logger.debug(
f"Skipping file {file_path} (ID: {file_id}) with recent placeholder "
f"(age={placeholder_age:.1f}s < {stale_threshold:.1f}s)"
)
if needs_indexing: if needs_indexing:
# Write placeholder before queuing # Write placeholder before queuing