perf: cache Timmy agent at startup instead of per-request (#471)

src/timmy_serve/app.py

@@ -75,6 +75,8 @@ def create_timmy_serve_app() -> FastAPI:
     @asynccontextmanager
     async def lifespan(app: FastAPI):
         logger.info("Timmy Serve starting")
+        app.state.timmy = create_timmy()
+        logger.info("Timmy agent cached in app state")
         yield
         logger.info("Timmy Serve shutting down")
 
@@ -101,7 +103,7 @@ def create_timmy_serve_app() -> FastAPI:
     async def serve_chat(request: Request, body: ChatRequest):
         """Process a chat request."""
         try:
-            timmy = create_timmy()
+            timmy = request.app.state.timmy
             result = timmy.run(body.message, stream=False)
             response_text = result.content if hasattr(result, "content") else str(result)
 

tests/timmy/test_timmy_serve_app.py

@@ -8,11 +8,14 @@ from fastapi.testclient import TestClient
 
 @pytest.fixture
 def serve_client():
-    """Create a TestClient for the timmy-serve app."""
-    from timmy_serve.app import create_timmy_serve_app
+    """Create a TestClient for the timmy-serve app with mocked Timmy agent."""
+    with patch("timmy_serve.app.create_timmy") as mock_create:
+        mock_create.return_value = MagicMock()
+        from timmy_serve.app import create_timmy_serve_app
 
-    app = create_timmy_serve_app()
-    return TestClient(app)
+        app = create_timmy_serve_app()
+        with TestClient(app) as client:
+            yield client
 
 
 class TestHealthEndpoint:
@@ -34,18 +37,40 @@ class TestServeStatus:
 
 class TestServeChatEndpoint:
     @patch("timmy_serve.app.create_timmy")
-    def test_chat_returns_response(self, mock_create, serve_client):
+    def test_chat_returns_response(self, mock_create):
         mock_agent = MagicMock()
         mock_result = MagicMock()
         mock_result.content = "I am Timmy."
         mock_agent.run.return_value = mock_result
         mock_create.return_value = mock_agent
 
-        resp = serve_client.post(
-            "/serve/chat",
-            json={"message": "Who are you?"},
-        )
+        from timmy_serve.app import create_timmy_serve_app
+
+        app = create_timmy_serve_app()
+        with TestClient(app) as client:
+            resp = client.post(
+                "/serve/chat",
+                json={"message": "Who are you?"},
+            )
         assert resp.status_code == 200
         data = resp.json()
         assert data["response"] == "I am Timmy."
         mock_agent.run.assert_called_once_with("Who are you?", stream=False)
+
+    @patch("timmy_serve.app.create_timmy")
+    def test_agent_cached_at_startup(self, mock_create):
+        """Verify create_timmy is called once at startup, not per request."""
+        mock_agent = MagicMock()
+        mock_result = MagicMock()
+        mock_result.content = "reply"
+        mock_agent.run.return_value = mock_result
+        mock_create.return_value = mock_agent
+
+        from timmy_serve.app import create_timmy_serve_app
+
+        app = create_timmy_serve_app()
+        with TestClient(app) as client:
+            # Two requests — create_timmy should only be called once (at startup)
+            client.post("/serve/chat", json={"message": "hello"})
+            client.post("/serve/chat", json={"message": "world"})
+        mock_create.assert_called_once()