Merge pull request #765 from AnishSarkar22/fix/documents

feat: Add document ownership & deletion of documents

surfsense_backend/app/routes/circleback_webhook_route.py

@@ -9,8 +9,12 @@ import logging
 from datetime import datetime
 from typing import Any
 
-from fastapi import APIRouter, HTTPException
+from fastapi import APIRouter, Depends, HTTPException
 from pydantic import BaseModel, Field
+from sqlalchemy import select
+from sqlalchemy.ext.asyncio import AsyncSession
+
+from app.db import SearchSourceConnector, SearchSourceConnectorType, get_async_session
 
 logger = logging.getLogger(__name__)
 
@@ -212,6 +216,7 @@ def format_circleback_meeting_to_markdown(payload: CirclebackWebhookPayload) ->
 async def receive_circleback_webhook(
     search_space_id: int,
     payload: CirclebackWebhookPayload,
+    session: AsyncSession = Depends(get_async_session),
 ):
     """
     Receive and process a Circleback webhook.
@@ -223,6 +228,7 @@ async def receive_circleback_webhook(
     Args:
         search_space_id: The ID of the search space to save the document to
         payload: The Circleback webhook payload containing meeting data
+        session: Database session for looking up the connector
 
     Returns:
         Success message with document details
@@ -236,6 +242,26 @@ async def receive_circleback_webhook(
             f"Received Circleback webhook for meeting {payload.id} in search space {search_space_id}"
         )
 
+        # Look up the Circleback connector for this search space
+        connector_result = await session.execute(
+            select(SearchSourceConnector.id).where(
+                SearchSourceConnector.search_space_id == search_space_id,
+                SearchSourceConnector.connector_type
+                == SearchSourceConnectorType.CIRCLEBACK_CONNECTOR,
+            )
+        )
+        connector_id = connector_result.scalar_one_or_none()
+
+        if connector_id:
+            logger.info(
+                f"Found Circleback connector {connector_id} for search space {search_space_id}"
+            )
+        else:
+            logger.warning(
+                f"No Circleback connector found for search space {search_space_id}. "
+                "Document will be created without connector_id."
+            )
+
         # Convert to markdown
         markdown_content = format_circleback_meeting_to_markdown(payload)
 
@@ -264,6 +290,7 @@ async def receive_circleback_webhook(
             markdown_content=markdown_content,
             metadata=meeting_metadata,
             search_space_id=search_space_id,
+            connector_id=connector_id,
         )
 
         logger.info(

surfsense_backend/app/routes/composio_routes.py

@@ -20,6 +20,7 @@ from pydantic import ValidationError
 from sqlalchemy.exc import IntegrityError
 from sqlalchemy.ext.asyncio import AsyncSession
 from sqlalchemy.future import select
+from sqlalchemy.orm.attributes import flag_modified
 
 from app.config import config
 from app.db import (
@@ -330,10 +331,19 @@ async def composio_callback(
                     )
 
             # Update existing connector with new connected_account_id
+            # IMPORTANT: Merge new credentials with existing config to preserve
+            # user settings like selected_folders, selected_files, indexing_options,
+            # drive_page_token, etc. that would otherwise be wiped on reconnection.
             logger.info(
                 f"Updating existing Composio connector {existing_connector.id} with new connected_account_id {final_connected_account_id}"
             )
-            existing_connector.config = connector_config
+            existing_config = (
+                existing_connector.config.copy() if existing_connector.config else {}
+            )
+            existing_config.update(connector_config)
+            existing_connector.config = existing_config
+
+            flag_modified(existing_connector, "config")
             await session.commit()
             await session.refresh(existing_connector)
 

surfsense_backend/app/routes/notes_routes.py

@@ -76,6 +76,7 @@ async def create_note(
         document_metadata={"NOTE": True},
         embedding=None,  # Will be generated on first reindex
         updated_at=datetime.now(UTC),
+        created_by_id=user.id,  # Track who created this note
     )
 
     session.add(document)
@@ -93,6 +94,7 @@ async def create_note(
         search_space_id=document.search_space_id,
         created_at=document.created_at,
         updated_at=document.updated_at,
+        created_by_id=document.created_by_id,
     )
 
 

surfsense_backend/app/routes/search_source_connectors_routes.py

@@ -527,9 +527,17 @@ async def delete_search_source_connector(
     user: User = Depends(current_active_user),
 ):
     """
-    Delete a search source connector.
+    Delete a search source connector and all its associated documents.
+
+    The deletion runs in background via Celery task. User is notified
+    via the notification system when complete (no polling required).
+
     Requires CONNECTORS_DELETE permission.
     """
+    from app.tasks.celery_tasks.connector_deletion_task import (
+        delete_connector_with_documents_task,
+    )
+
     try:
         # Get the connector first
         result = await session.execute(
@@ -551,7 +559,12 @@ async def delete_search_source_connector(
             "You don't have permission to delete this connector",
         )
 
-        # Delete any periodic schedule associated with this connector
+        # Store connector info before we queue the deletion task
+        connector_name = db_connector.name
+        connector_type = db_connector.connector_type.value
+        search_space_id = db_connector.search_space_id
+
+        # Delete any periodic schedule associated with this connector (lightweight, sync)
         if db_connector.periodic_indexing_enabled:
             success = delete_periodic_schedule(connector_id)
             if not success:
@@ -559,7 +572,7 @@ async def delete_search_source_connector(
                     f"Failed to delete periodic schedule for connector {connector_id}"
                 )
 
-        # For Composio connectors, also delete the connected account in Composio
+        # For Composio connectors, delete the connected account in Composio (lightweight API call, sync)
         composio_connector_types = [
             SearchSourceConnectorType.COMPOSIO_GOOGLE_DRIVE_CONNECTOR,
             SearchSourceConnectorType.COMPOSIO_GMAIL_CONNECTOR,
@@ -591,16 +604,33 @@ async def delete_search_source_connector(
                         f"Error deleting Composio connected account {composio_connected_account_id}: {composio_error!s}"
                     )
 
-        await session.delete(db_connector)
-        await session.commit()
-        return {"message": "Search source connector deleted successfully"}
+        # Queue background task to delete documents and connector
+        # This handles potentially large document counts without blocking the API
+        delete_connector_with_documents_task.delay(
+            connector_id=connector_id,
+            user_id=str(user.id),
+            search_space_id=search_space_id,
+            connector_name=connector_name,
+            connector_type=connector_type,
+        )
+
+        logger.info(
+            f"Queued deletion task for connector {connector_id} ({connector_name})"
+        )
+
+        return {
+            "message": "Connector deletion started. You will be notified when complete.",
+            "status": "queued",
+            "connector_id": connector_id,
+            "connector_name": connector_name,
+        }
     except HTTPException:
         raise
     except Exception as e:
         await session.rollback()
         raise HTTPException(
             status_code=500,
-            detail=f"Failed to delete search source connector: {e!s}",
+            detail=f"Failed to start connector deletion: {e!s}",
         ) from e