feat(search): add file_path metadata and chunk offsets to search results

Changes:
- Add file_path to metadata in semantic and BM25 hybrid search algorithms
  for PDF viewer integration (search/semantic.py:161-163, search/bm25_hybrid.py:230-232)
- Include chunk_start_offset, chunk_end_offset, page_number, and page_count
  in search results for rich chunk display (api/management.py:981-1004)
- Add point_id field to SearchResult for batch retrieval (models/semantic.py)
- Fix type narrowing for chunk context API parameters (api/management.py:1102-1111)
- Fix None-safety in doc_types discovery (search/algorithms.py:114)

This enables the Astroglobe UI to display PDF pages at the correct
location for matched chunks.

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

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

nextcloud_mcp_server/search/algorithms.py

@@ -111,7 +111,7 @@ async def get_indexed_doc_types(user_id: str) -> set[str]:
         doc_types: set[str] = {
             str(point.payload.get("doc_type"))
             for point in scroll_results
-            if point.payload.get("doc_type")
+            if point.payload and point.payload.get("doc_type")
         }
 
         logger.debug(f"Found indexed document types for user {user_id}: {doc_types}")
@@ -138,6 +138,7 @@ class SearchResult:
         chunk_start_offset: Character position where chunk starts (None if not available)
         chunk_end_offset: Character position where chunk ends (None if not available)
         page_number: Page number for PDF documents (None for other doc types)
+        page_count: Total number of pages in PDF document (None for other doc types)
         chunk_index: Zero-based index of this chunk in the document
         total_chunks: Total number of chunks in the document
         point_id: Qdrant point ID for batch vector retrieval (None if not from Qdrant)
@@ -152,6 +153,7 @@ class SearchResult:
     chunk_start_offset: int | None = None
     chunk_end_offset: int | None = None
     page_number: int | None = None
+    page_count: int | None = None
     chunk_index: int = 0
     total_chunks: int = 1
     point_id: str | None = None

nextcloud_mcp_server/search/bm25_hybrid.py

@@ -226,6 +226,10 @@ class BM25HybridSearchAlgorithm(SearchAlgorithm):
                     "search_method": f"bm25_hybrid_{self.fusion_name}",
                 }
 
+                # Add file-specific metadata for PDF viewer
+                if doc_type == "file" and (path := result.payload.get("file_path")):
+                    metadata["path"] = path
+
                 # Add deck_card-specific metadata for frontend URL construction
                 if doc_type == "deck_card":
                     if board_id := result.payload.get("board_id"):
@@ -243,6 +247,7 @@ class BM25HybridSearchAlgorithm(SearchAlgorithm):
                         chunk_start_offset=result.payload.get("chunk_start_offset"),
                         chunk_end_offset=result.payload.get("chunk_end_offset"),
                         page_number=result.payload.get("page_number"),
+                        page_count=result.payload.get("page_count"),
                         chunk_index=result.payload.get("chunk_index", 0),
                         total_chunks=result.payload.get("total_chunks", 1),
                         point_id=str(result.id),  # Qdrant point ID for batch retrieval

nextcloud_mcp_server/search/semantic.py

@@ -157,6 +157,10 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
                 "total_chunks": result.payload.get("total_chunks"),
             }
 
+            # Add file-specific metadata for PDF viewer
+            if doc_type == "file" and (path := result.payload.get("file_path")):
+                metadata["path"] = path
+
             # Add deck_card-specific metadata for frontend URL construction
             if doc_type == "deck_card":
                 if board_id := result.payload.get("board_id"):
@@ -174,6 +178,7 @@ class SemanticSearchAlgorithm(SearchAlgorithm):
                     chunk_start_offset=result.payload.get("chunk_start_offset"),
                     chunk_end_offset=result.payload.get("chunk_end_offset"),
                     page_number=result.payload.get("page_number"),
+                    page_count=result.payload.get("page_count"),
                     chunk_index=result.payload.get("chunk_index", 0),
                     total_chunks=result.payload.get("total_chunks", 1),
                     point_id=str(result.id),  # Qdrant point ID for batch retrieval