feat(node): indexing v2 — partial-read hashing for files above 40 MB

Files above 40 MB are no longer read in full. Instead, blake3 hashes
45 MB of samples (first 20 MB + last 20 MB + 5 MB at 50% offset).
Files at or below 40 MB are unchanged (full read, hash_version 1).

A new `hash_version` field on IndexEntry (default 1) travels on the
wire and through the cache so both versions coexist without breaking
existing nodes or clients.

The IndexCache auto-migrates its schema on open (ALTER TABLE), so no
manual step is required on upgrade. A standalone migration script is
available in QE/migration/ for operators who want to preview or force
a full re-hash.

Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>

1 files changed, 77 insertions, 0 deletions

diff --git a/packages/meshbay-node/tests/test_index_cache.py b/packages/meshbay-node/tests/test_index_cache.py
index 24e2f76..036b4d7 100644
--- a/packages/meshbay-node/tests/test_index_cache.py
+++ b/packages/meshbay-node/tests/test_index_cache.py
@@ -122,3 +122,80 @@ async def test_cache_survives_reopen(tmp_path):
 
     assert hit is not None
     assert hit.hash == "abc123"
+
+
+# ── hash_version support (indexing v2) ─────────────────────────────────────────
+
+
+@pytest.mark.asyncio
+async def test_put_v2_then_lookup_hits(cache):
+    await cache.put("/lib/big.mkv", size=50_000_000, mtime=111.0,
+                     hash="partial_abc", type="video", added_at=42,
+                     hash_version=2)
+
+    hit = await cache.lookup("/lib/big.mkv", size=50_000_000, mtime=111.0,
+                              hash_version=2)
+    assert hit is not None
+    assert hit.hash == "partial_abc"
+    assert hit.hash_version == 2
+
+
+@pytest.mark.asyncio
+async def test_lookup_misses_on_wrong_hash_version(cache):
+    await cache.put("/lib/big.mkv", size=50_000_000, mtime=111.0,
+                     hash="full_hash", type="video", added_at=42,
+                     hash_version=1)
+
+    assert await cache.lookup("/lib/big.mkv", size=50_000_000, mtime=111.0,
+                               hash_version=2) is None
+
+
+@pytest.mark.asyncio
+async def test_put_v2_overwrites_v1_for_same_path(cache):
+    await cache.put("/lib/big.mkv", size=50_000_000, mtime=111.0,
+                     hash="full_hash", type="video", added_at=42,
+                     hash_version=1)
+    await cache.put("/lib/big.mkv", size=50_000_000, mtime=111.0,
+                     hash="partial_hash", type="video", added_at=42,
+                     hash_version=2)
+
+    assert await cache.lookup("/lib/big.mkv", size=50_000_000, mtime=111.0,
+                               hash_version=1) is None
+    hit = await cache.lookup("/lib/big.mkv", size=50_000_000, mtime=111.0,
+                              hash_version=2)
+    assert hit is not None
+    assert hit.hash == "partial_hash"
+
+
+@pytest.mark.asyncio
+async def test_v1_schema_auto_migrates(tmp_path):
+    """An index_cache.db created by old code (no hash_version column) gains
+    the column on the next open(), and existing rows default to hash_version=1."""
+    import aiosqlite
+    db_path = tmp_path / "old_cache.db"
+    async with aiosqlite.connect(str(db_path)) as db:
+        await db.executescript("""
+            CREATE TABLE files (
+                path      TEXT PRIMARY KEY,
+                mtime     REAL NOT NULL,
+                size      INTEGER NOT NULL,
+                hash      TEXT NOT NULL,
+                type      TEXT NOT NULL,
+                added_at  INTEGER NOT NULL
+            );
+        """)
+        await db.execute(
+            "INSERT INTO files (path, mtime, size, hash, type, added_at) "
+            "VALUES (?, ?, ?, ?, ?, ?)",
+            ("/lib/old.mkv", 111.0, 1000, "oldhash", "video", 42))
+        await db.commit()
+
+    cache = IndexCache(db_path=db_path)
+    await cache.open()
+    hit = await cache.lookup("/lib/old.mkv", size=1000, mtime=111.0,
+                              hash_version=1)
+    await cache.close()
+
+    assert hit is not None
+    assert hit.hash == "oldhash"
+    assert hit.hash_version == 1