fix: implement deletion grace period and vector sync status tool

This commit addresses issues with vector database synchronization that
were causing test failures:

1. **Deletion Grace Period** (scanner.py)
   - Fixed premature deletion of documents due to pagination cursor
     inconsistencies in Notes API
   - Implemented 2-scan verification with 1.5x scan interval grace period
     (15 seconds default)
   - Documents must be missing for 2 consecutive scans before deletion
   - Documents that reappear are removed from deletion tracking
   - Prevents false deletions during concurrent note creation/indexing

2. **Vector Sync Status Tool** (server/notes.py, models/notes.py)
   - Added nc_notes_get_vector_sync_status MCP tool
   - Returns indexed_count, pending_count, status, and enabled fields
   - Enables tests and clients to wait for vector sync completion
   - Uses lifespan context to access document queue and Qdrant client

3. **Test Improvements** (test_sampling.py, conftest.py)
   - Added temporary_note_factory fixture for creating multiple test notes
   - Updated all sampling tests to wait for vector sync completion
   - Adjusted score_threshold to 0.0 for SimpleEmbeddingProvider
     (feature hashing produces low-quality embeddings)
   - Fixed CallToolResult extraction (removed ["result"] key access)
   - Removed invalid @pytest.mark.asyncio markers (anyio mode)

All integration tests now pass successfully.

🤖 Generated with [Claude Code](https://claude.com/claude-code)

Co-Authored-By: Claude <noreply@anthropic.com>
This commit is contained in:
Chris Coutinho
2025-11-09 03:11:39 +01:00
parent bb5d4f464f
commit a854656d3c
5 changed files with 367 additions and 55 deletions
+83
View File
@@ -25,6 +25,7 @@ from nextcloud_mcp_server.models.notes import (
SemanticSearchNotesResponse,
SemanticSearchResult,
UpdateNoteResponse,
VectorSyncStatusResponse,
)
logger = logging.getLogger(__name__)
@@ -726,3 +727,85 @@ def configure_notes_tools(mcp: FastMCP):
message=f"Failed to delete note {note_id}: server error ({e.response.status_code})",
)
)
@mcp.tool()
async def nc_notes_get_vector_sync_status(ctx: Context) -> VectorSyncStatusResponse:
"""Get the current vector sync status.
Returns information about the vector sync process, including:
- Number of documents indexed in the vector database
- Number of documents pending processing
- Current sync status (idle, syncing, or disabled)
This is useful for determining when vector indexing is complete
after creating or updating notes.
"""
import os
# Check if vector sync is enabled
vector_sync_enabled = (
os.getenv("VECTOR_SYNC_ENABLED", "false").lower() == "true"
)
if not vector_sync_enabled:
return VectorSyncStatusResponse(
indexed_count=0,
pending_count=0,
status="disabled",
enabled=False,
)
try:
# Get document queue from lifespan context
lifespan_ctx = ctx.request_context.lifespan_context
document_queue = getattr(lifespan_ctx, "document_queue", None)
if document_queue is None:
logger.debug("document_queue not available in lifespan context")
return VectorSyncStatusResponse(
indexed_count=0,
pending_count=0,
status="unknown",
enabled=True,
)
# Get pending count from queue
pending_count = document_queue.qsize()
# Get Qdrant client and query indexed count
indexed_count = 0
try:
from nextcloud_mcp_server.config import get_settings
from nextcloud_mcp_server.vector.qdrant_client import get_qdrant_client
settings = get_settings()
qdrant_client = await get_qdrant_client()
# Count documents in collection
count_result = await qdrant_client.count(
collection_name=settings.qdrant_collection
)
indexed_count = count_result.count
except Exception as e:
logger.warning(f"Failed to query Qdrant for indexed count: {e}")
# Continue with indexed_count = 0
# Determine status
status = "syncing" if pending_count > 0 else "idle"
return VectorSyncStatusResponse(
indexed_count=indexed_count,
pending_count=pending_count,
status=status,
enabled=True,
)
except Exception as e:
logger.error(f"Error getting vector sync status: {e}")
raise McpError(
ErrorData(
code=-1,
message=f"Failed to retrieve vector sync status: {str(e)}",
)
)