Add fallback parser for markdown files with invalid YAML frontmatter to prevent indexing failures

backend/indexer.py

@@ -1,6 +1,7 @@
 import os
 import asyncio
 import logging
+import re
 from pathlib import Path
 from datetime import datetime, timezone
 from typing import Dict, List, Optional, Any
@@ -62,6 +63,20 @@ def _extract_title(post: frontmatter.Post, filepath: Path) -> str:
     return str(title)
 
 
+def parse_markdown_file(raw: str) -> frontmatter.Post:
+    """Parse markdown frontmatter, falling back to plain content if YAML is invalid."""
+    try:
+        return frontmatter.loads(raw)
+    except Exception as exc:
+        logger.warning(f"Invalid frontmatter detected, falling back to plain markdown parsing: {exc}")
+        content = raw
+        if raw.startswith("---"):
+            match = re.match(r"^---\s*\r?\n.*?\r?\n---\s*\r?\n?", raw, flags=re.DOTALL)
+            if match:
+                content = raw[match.end():]
+        return frontmatter.Post(content, **{})
+
+
 def _scan_vault(vault_name: str, vault_path: str) -> Dict[str, Any]:
     """Synchronously scan a single vault directory."""
     vault_root = Path(vault_path)
@@ -96,7 +111,7 @@ def _scan_vault(vault_name: str, vault_path: str) -> Dict[str, Any]:
             content_preview = raw[:200].strip()
 
             if ext == ".md":
-                post = frontmatter.loads(raw)
+                post = parse_markdown_file(raw)
                 tags = _extract_tags(post)
                 title = _extract_title(post, fpath)
                 content_preview = post.content[:200].strip()

backend/main.py

@@ -16,6 +16,7 @@ from backend.indexer import (
     index,
     get_vault_data,
     find_file_in_index,
+    parse_markdown_file,
     SUPPORTED_EXTENSIONS,
 )
 from backend.search import search, get_all_tags
@@ -211,7 +212,7 @@ async def api_file(vault_name: str, path: str = Query(..., description="Relative
     ext = file_path.suffix.lower()
 
     if ext == ".md":
-        post = frontmatter.loads(raw)
+        post = parse_markdown_file(raw)
 
         # Extract metadata
         tags = post.metadata.get("tags", [])