fix(node): skip indexing audio files under 50KB, likely-corrupt source

The "P.H. Theme" failure investigated earlier turned out to be a genuinely
corrupt 1256-byte source file with no audio stream at all, just an ID3
tag — a real, if rare, corruption pattern worth guarding against directly
rather than only handling gracefully at playback time. Scoped to audio
only, applied wherever a file actually gets hashed/typed (fresh scan and
the cache-miss rehash path alike) — a tiny file of any other type is still
indexed normally.

1 files changed, 17 insertions, 0 deletions

diff --git a/packages/meshbay-node/src/meshbay_node/indexer/indexer.py b/packages/meshbay-node/src/meshbay_node/indexer/indexer.py
index 3ca34f6..10981c0 100644
--- a/packages/meshbay-node/src/meshbay_node/indexer/indexer.py
+++ b/packages/meshbay-node/src/meshbay_node/indexer/indexer.py
@@ -79,6 +79,19 @@ def _is_indexable(path: Path) -> bool:
     )
 
 
+# Found live: a 1256-byte ".mp3" with no audio stream at all, just an ID3
+# tag — a truncated/corrupted rip, sitting between two good tracks of the
+# same album (docs/musicbay.md). A source this small claiming to be audio
+# is far more likely broken than real, so it is skipped before ever being
+# hashed rather than indexed and left to fail at playback time. Scoped to
+# audio only — a tiny real file of any other type is still worth indexing.
+MIN_AUDIO_SIZE_BYTES = 50 * 1024
+
+
+def _is_indexable_size(path: Path, size: int) -> bool:
+    return not (_detect_type(path) == "audio" and size < MIN_AUDIO_SIZE_BYTES)
+
+
 _HASH_CHUNK = 8 * 1024 * 1024   # 8 MB streaming hash chunks
 
 
@@ -134,6 +147,8 @@ def _scan_file(root: Root, file_path: Path) -> IndexEntry | None:
         return None
     try:
         stat = file_path.stat()
+        if not _is_indexable_size(file_path, stat.st_size):
+            return None
         hasher = blake3.blake3()
         # long_path is a no-op off Windows; there it is what lets a deep media
         # library past MAX_PATH.
@@ -338,6 +353,8 @@ class DirectoryIndexer:
             st = file_path.stat()
         except OSError:
             return None
+        if not _is_indexable_size(file_path, st.st_size):
+            return None
 
         if self._cache is not None:
             cached = await self._cache.lookup(str(file_path), st.st_size, st.st_mtime)