chat/app.py

@@ -16,6 +16,7 @@ from chat.db.migrate import apply_migrations
 from chat.eventlog.log import read_events
 from chat.eventlog.projector import apply_event
 from chat.services.background import BackgroundWorker
+from chat.services.embedding_worker import EmbeddingWorker
 from chat.services.snapshot import latest_snapshot_path, restore_from_snapshot
 
 # Trigger handler registration:
@@ -85,9 +86,23 @@ async def lifespan(app: FastAPI):
     await worker.start()
     app.state.background_worker = worker
 
+    # T97: separate worker for the async embedding pass. Each
+    # ``memory_written`` enqueues an EmbeddingJob; the worker drains the
+    # queue, calls ``generate_embedding``, and emits ``embedding_indexed``.
+    # Phase 4's pseudo-embedding path is local so the worker doesn't need
+    # an LLM client; we still pass one so the Phase 4.5 swap to a real
+    # model is a one-line change.
+    embedding_worker = EmbeddingWorker(
+        conn_factory=lambda: open_db(settings.db_path),
+        client=_factory(),
+    )
+    await embedding_worker.start()
+    app.state.embedding_worker = embedding_worker
+
     try:
         yield
     finally:
+        await embedding_worker.stop()
         await worker.stop()