Preserve llm-connect run config in server mode

tests/test_server.py

@@ -125,10 +125,28 @@ class TestExecute:
         try:
             status, body = _post(
                 f"http://127.0.0.1:{s.port}/execute",
-                {"prompt": "hi", "config": {"model_name": "gpt-3.5-turbo", "max_tokens": 100}},
+                {
+                    "prompt": "hi",
+                    "config": {
+                        "model_name": "gpt-3.5-turbo",
+                        "max_tokens": 100,
+                        "max_depth": 2,
+                        "model_params": {"reasoning_effort": "medium"},
+                    },
+                },
             )
             assert status == 200
             assert adapter.last_config.model_name == "gpt-3.5-turbo"
             assert adapter.last_config.max_tokens == 100
+            assert adapter.last_config.max_depth == 2
+            assert adapter.last_config.model_params == {"reasoning_effort": "medium"}
         finally:
             s.stop()
+
+    def test_config_must_be_object(self, server):
+        status, body = _post(
+            f"http://127.0.0.1:{server.port}/execute",
+            {"prompt": "hi", "config": "not an object"},
+        )
+        assert status == 400
+        assert "config" in body["error"]