fix: Reconstruct full content for notes to match indexed offsets

Notes are indexed as "{title}\n\n{content}" in processor.py but were
being retrieved as just content during chunk expansion, causing
chunk_start_offset and chunk_end_offset to be misaligned.

This fix reconstructs the full content structure when fetching notes
for chunk expansion, ensuring the displayed chunks match the excerpts
shown in search results.

Fixes chunk/excerpt mismatch reported in vector visualization.

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

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

nextcloud_mcp_server/search/context.py

@@ -153,7 +153,11 @@ async def _fetch_document_text(
         if doc_type == "note":
             # Fetch note by ID
             note = await nc_client.notes.get_note(note_id=int(doc_id))
-            return note.get("content", "")
+            # Reconstruct full content as indexed: title + "\n\n" + content
+            # This ensures chunk offsets align with indexed content structure
+            title = note.get("title", "")
+            content = note.get("content", "")
+            return f"{title}\n\n{content}"
         elif doc_type == "file":
             # Fetch file content via WebDAV
             try: