perf(node): sample 9 MB with the size above 9 MB, keep known ids0.19

hash_version 3: size + first 4 MB + last 4 MB + 1 MB at the middle,
5.5x faster cold on a USB disk than the 45 MB sample. The cache now
serves a hit under whatever version it holds, so no existing id moves.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

1 files changed, 6 insertions, 7 deletions

diff --git a/packages/meshbay-node/src/meshbay_node/indexer/cache.py b/packages/meshbay-node/src/meshbay_node/indexer/cache.py
index 5e328ef..afa4f85 100644
--- a/packages/meshbay-node/src/meshbay_node/indexer/cache.py
+++ b/packages/meshbay-node/src/meshbay_node/indexer/cache.py
@@ -112,17 +112,16 @@ class IndexCache:
     async def __aexit__(self, *_):
         await self.close()
 
-    async def lookup(self, path: str, size: int, mtime: float,
-                     hash_version: int = 1) -> CachedEntry | None:
+    async def lookup(self, path: str, size: int, mtime: float) -> CachedEntry | None:
         """
-        A cache hit requires an EXACT match on size, mtime AND hash_version.
-        A v1 cached hash won't serve a v2 lookup for the same path — the file
-        is re-hashed with the new algorithm instead.
+        A cache hit requires an EXACT match on size and mtime, and serves the
+        hash under whatever hash_version it was computed: a scheme change must
+        not change the id of a file the node already knows.
         """
         async with self._db.execute(
                 "SELECT hash, type, added_at, hash_version FROM files "
-                "WHERE path = ? AND size = ? AND mtime = ? AND hash_version = ?",
-                (path, size, mtime, hash_version)) as cur:
+                "WHERE path = ? AND size = ? AND mtime = ?",
+                (path, size, mtime)) as cur:
             row = await cur.fetchone()
         return CachedEntry(hash=row[0], type=row[1], added_at=row[2],
                            hash_version=row[3]) if row else None