perf: persist model-isolated sqlite-vec indexes and index new notes incrementally

backend/tests/test_routed_retrieval.py

@@ -66,6 +66,52 @@ async def seed():
     return apple, banana
 
 
+def test_native_spaces_isolate_dimensions_and_reuse_without_json_scan(runtime, monkeypatch):
+    from app.retrieval import space_index
+    async def scenario():
+        apple, banana = await seed()
+        ids = [b.block_id for note in (apple, banana) for b in note.blocks]
+        conn = connect()
+        try:
+            with transaction(conn):
+                routed_vectors.store_remote(conn, ids, routed_vectors.RemoteEmbeddings('space-a', 4, [[1., 0., 0., 0.]] * len(ids)))
+            assert conn.execute('SELECT COUNT(DISTINCT dimensions) FROM routed_block_vectors').fetchone()[0] == 2
+        finally:
+            conn.close()
+        # A new connection uses the persistent native index, without reading vector JSON.
+        def forbidden(*args, **kwargs):
+            raise AssertionError('query decoded stored JSON')
+        monkeypatch.setattr(space_index.json, 'loads', forbidden)
+        hits = await routed_vectors.search_remote('apple orchard', top_k=2, strict=True)
+        assert len(hits) == 2
+        assert hits[0].id == apple.blocks[0].block_id
+    asyncio.run(scenario())
+
+
+def test_legacy_vectors_migrate_without_document_embedding(runtime):
+    from app.retrieval import space_index
+    async def scenario():
+        apple, banana = await seed()
+        conn = connect()
+        table = space_index.table_name('space-a', 3)
+        try:
+            with transaction(conn):
+                conn.execute(f'DROP TRIGGER {table}_delete')
+                conn.execute(f'DROP TRIGGER {table}_update')
+                conn.execute(f'DROP TABLE {table}')
+                conn.execute('ALTER TABLE routed_block_vectors RENAME TO saved_vectors')
+                conn.execute('CREATE TABLE routed_block_vectors(space_id TEXT,block_id TEXT REFERENCES blocks(block_id) ON DELETE CASCADE,dimensions INTEGER,vector TEXT,PRIMARY KEY(space_id,block_id))')
+                conn.execute('INSERT INTO routed_block_vectors SELECT * FROM saved_vectors')
+                conn.execute('DROP TABLE saved_vectors')
+        finally:
+            conn.close()
+        runtime.calls.clear()
+        hits = await routed_vectors.search_remote('apple orchard', top_k=2, strict=True)
+        assert len(hits) == 2
+        assert runtime.calls == [['apple orchard']]
+    asyncio.run(scenario())
+
+
 @pytest.mark.parametrize("outcome", ["api", "api_failure", "missing_space"])
 def test_benchmark_reports_actual_embedding_and_fallback(runtime, outcome):
     from app.benchmarks import service

backend/tests/test_workspace_background.py

@@ -5,6 +5,33 @@ from app.config import get_settings
 from app.services import index_service, workspace_service
 
 
+def test_external_new_note_does_not_rebuild_existing_notes(monkeypatch):
+    from app.services import note_service
+    async def scenario():
+        await note_service.create_note(title='Existing', markdown='Keep existing vectors', folder=None, tags=[])
+        calls = []
+        original = index_service.prepare_note_index
+        async def record(parsed, **kwargs):
+            calls.append(parsed.file_path)
+            return await original(parsed, **kwargs)
+        async def forbidden(*args, **kwargs):
+            raise AssertionError('full rebuild should not run')
+        monkeypatch.setattr(index_service, 'prepare_note_index', record)
+        monkeypatch.setattr(index_service, 'rebuild', forbidden)
+        path = get_settings().vault_path / 'external.md'
+        path.write_text('# External\n\nNew content', encoding='utf-8')
+        try:
+            await workspace_service.refresh_workspace_tree()
+            await index_service._background_task
+            assert calls == ['external.md']
+            assert not index_service.get_status().vector_refresh_required
+            await workspace_service.open_workspace(None)
+            assert calls == ['external.md']
+        finally:
+            await index_service.shutdown()
+    asyncio.run(scenario())
+
+
 def test_open_returns_before_vectors_and_deduplicates_background(monkeypatch):
     async def scenario():
         started, release = asyncio.Event(), asyncio.Event()