fix: update Paperless webhook payload to match include_document format

- Change model field from document_id to id (Paperless sends id)
- Add content, created, modified, added, original_file_name, owner fields
- Add extra="ignore" config to handle additional Paperless fields
- Update sync service to use content from webhook payload
- Skip Paperless API call when content already provided

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

Co-Authored-By: Claude Opus 4.5 <noreply@anthropic.com>

src/services/document_sync_service.py

@@ -86,6 +86,8 @@ class DocumentSyncService:
         self,
         document_id: int,
         user: str,
+        content: Optional[str] = None,
+        title: Optional[str] = None,
     ) -> IndexResult:
         """
         Index a single document from Paperless into vectors and graph.
@@ -93,6 +95,8 @@ class DocumentSyncService:
         Args:
             document_id: Paperless document ID
             user: User identifier for multi-tenancy
+            content: Optional document content (if provided, skip Paperless API call)
+            title: Optional document title (if provided, skip Paperless API call)
 
         Returns:
             IndexResult with success status and details
@@ -100,24 +104,36 @@ class DocumentSyncService:
         logger.info(f"Indexing document {document_id} for user {user}")
 
         try:
-            # Fetch document from Paperless
-            doc = await self.paperless.get_document(document_id)
-            if not doc:
-                return IndexResult(
-                    success=False,
-                    document_id=document_id,
-                    error="Document not found in Paperless"
-                )
+            # If content and title provided (from webhook), skip API call
+            if content is not None and title is not None:
+                doc_title = title
+                doc_content = content
+                original_filename = None
+                correspondent = None
+                document_type = None
+                tags = []
+            else:
+                # Fetch document from Paperless
+                doc = await self.paperless.get_document(document_id)
+                if not doc:
+                    return IndexResult(
+                        success=False,
+                        document_id=document_id,
+                        error="Document not found in Paperless"
+                    )
+                doc_title = doc.title
+                doc_content = doc.content or ""
+                original_filename = doc.original_file_name
+                correspondent = doc.correspondent
+                document_type = doc.document_type
+                tags = doc.tags
 
-            title = doc.title
-            content = doc.content or ""
-
-            if not content.strip():
+            if not doc_content.strip():
                 logger.warning(f"Document {document_id} has no text content")
                 return IndexResult(
                     success=True,
                     document_id=document_id,
-                    title=title,
+                    title=doc_title,
                     chunks_created=0,
                     error="No text content (possibly image/video only)"
                 )
@@ -125,23 +141,23 @@ class DocumentSyncService:
             # Index vectors
             chunks_created = await self._index_vectors(
                 document_id=document_id,
-                title=title,
-                content=content,
+                title=doc_title,
+                content=doc_content,
                 user=user,
                 metadata={
                     "paperless_id": document_id,
-                    "original_filename": doc.original_file_name,
-                    "correspondent": doc.correspondent,
-                    "document_type": doc.document_type,
-                    "tags": doc.tags,
+                    "original_filename": original_filename,
+                    "correspondent": correspondent,
+                    "document_type": document_type,
+                    "tags": tags,
                 }
             )
 
             # Index graph node
             await self._index_graph(
                 document_id=document_id,
-                title=title,
-                content=content,
+                title=doc_title,
+                content=doc_content,
                 user=user,
             )
 
@@ -156,7 +172,7 @@ class DocumentSyncService:
             return IndexResult(
                 success=True,
                 document_id=document_id,
-                title=title,
+                title=doc_title,
                 chunks_created=chunks_created
             )