diff --git a/autogen/agentchat/conversable_agent.py b/autogen/agentchat/conversable_agent.py
index 895eb7b5122..1f1b2ff489f 100644
--- a/autogen/agentchat/conversable_agent.py
+++ b/autogen/agentchat/conversable_agent.py
@@ -1108,9 +1108,9 @@ def generate_oai_reply(
         extracted_response = self._generate_oai_reply_from_client(
             client, self._oai_system_message + messages, self.client_cache
         )
-        return True, extracted_response
+        return (False, None) if extracted_response is None else (True, extracted_response)
 
-    def _generate_oai_reply_from_client(self, llm_client, messages, cache):
+    def _generate_oai_reply_from_client(self, llm_client, messages, cache) -> Union[str, Dict, None]:
         # unroll tool_responses
         all_messages = []
         for message in messages:
@@ -1132,8 +1132,8 @@ def _generate_oai_reply_from_client(self, llm_client, messages, cache):
         extracted_response = llm_client.extract_text_or_completion_object(response)[0]
 
         if extracted_response is None:
-            warnings.warn("Extracted_response is None.", UserWarning)
-            return False, None
+            warnings.warn("Extracted_response from {response} is None.", UserWarning)
+            return None
         # ensure function and tool calls will be accepted when sent back to the LLM
         if not isinstance(extracted_response, str) and hasattr(extracted_response, "model_dump"):
             extracted_response = model_dump(extracted_response)
diff --git a/test/agentchat/test_assistant_agent.py b/test/agentchat/test_assistant_agent.py
index 63cfff5e22a..af953d47c8a 100644
--- a/test/agentchat/test_assistant_agent.py
+++ b/test/agentchat/test_assistant_agent.py
@@ -68,18 +68,7 @@ def test_gpt35(human_input_mode="NEVER", max_consecutive_auto_reply=5):
     config_list = autogen.config_list_from_json(
         OAI_CONFIG_LIST,
         file_location=KEY_LOC,
-        filter_dict={
-            "model": {
-                "gpt-3.5-turbo",
-                "gpt-35-turbo",
-                "gpt-3.5-turbo-16k",
-                "gpt-3.5-turbo-16k-0613",
-                "gpt-3.5-turbo-0301",
-                "chatgpt-35-turbo-0301",
-                "gpt-35-turbo-v0301",
-                "gpt",
-            },
-        },
+        filter_dict={"tags": ["gpt-3.5-turbo", "gpt-3.5-turbo-16k"]},
     )
     llm_config = {
         "cache_seed": 42,
@@ -206,8 +195,8 @@ def generate_init_message(self, question) -> str:
 
 
 if __name__ == "__main__":
-    # test_gpt35()
-    test_create_execute_script(human_input_mode="TERMINATE")
+    test_gpt35()
+    # test_create_execute_script(human_input_mode="TERMINATE")
     # when GPT-4, i.e., the DEFAULT_MODEL, is used, conversation in the following test
     # should terminate in 2-3 rounds of interactions (because is_termination_msg should be true after 2-3 rounds)
     # although the max_consecutive_auto_reply is set to 10.
diff --git a/test/agentchat/test_cache_agent.py b/test/agentchat/test_cache_agent.py
index 8da9a919f84..52d5a11e102 100644
--- a/test/agentchat/test_cache_agent.py
+++ b/test/agentchat/test_cache_agent.py
@@ -6,6 +6,7 @@
 import autogen
 from autogen.agentchat import AssistantAgent, UserProxyAgent
 from autogen.cache import Cache
+from test_assistant_agent import KEY_LOC, OAI_CONFIG_LIST, here
 
 sys.path.append(os.path.join(os.path.dirname(__file__), ".."))
 from conftest import skip_openai, skip_redis  # noqa: E402
@@ -107,23 +108,11 @@ def test_disk_cache():
 
 
 def run_conversation(cache_seed, human_input_mode="NEVER", max_consecutive_auto_reply=5, cache=None):
-    KEY_LOC = "notebook"
-    OAI_CONFIG_LIST = "OAI_CONFIG_LIST"
-    here = os.path.abspath(os.path.dirname(__file__))
     config_list = autogen.config_list_from_json(
         OAI_CONFIG_LIST,
         file_location=KEY_LOC,
         filter_dict={
-            "model": {
-                "gpt-3.5-turbo",
-                "gpt-35-turbo",
-                "gpt-3.5-turbo-16k",
-                "gpt-3.5-turbo-16k-0613",
-                "gpt-3.5-turbo-0301",
-                "chatgpt-35-turbo-0301",
-                "gpt-35-turbo-v0301",
-                "gpt",
-            },
+            "tags": ["gpt-3.5-turbo", "gpt-3.5-turbo-16k"],
         },
     )
     llm_config = {
@@ -159,7 +148,7 @@ def run_conversation(cache_seed, human_input_mode="NEVER", max_consecutive_auto_
 
     # track how long this takes
     user.initiate_chat(assistant, message=coding_task, cache=cache)
-    return user.chat_messages[list(user.chat_messages.keys())[-0]]
+    return user.chat_messages[assistant]
 
 
 def run_groupchat_conversation(cache, human_input_mode="NEVER", max_consecutive_auto_reply=5):
@@ -170,16 +159,7 @@ def run_groupchat_conversation(cache, human_input_mode="NEVER", max_consecutive_
         OAI_CONFIG_LIST,
         file_location=KEY_LOC,
         filter_dict={
-            "model": {
-                "gpt-3.5-turbo",
-                "gpt-35-turbo",
-                "gpt-3.5-turbo-16k",
-                "gpt-3.5-turbo-16k-0613",
-                "gpt-3.5-turbo-0301",
-                "chatgpt-35-turbo-0301",
-                "gpt-35-turbo-v0301",
-                "gpt",
-            },
+            "tags": ["gpt-3.5-turbo", "gpt-3.5-turbo-16k"],
         },
     )
     llm_config = {
diff --git a/test/oai/test_client_stream.py b/test/oai/test_client_stream.py
index a3bfc6161a6..af03824495c 100644
--- a/test/oai/test_client_stream.py
+++ b/test/oai/test_client_stream.py
@@ -233,7 +233,7 @@ def test_chat_tools_stream() -> None:
     config_list = config_list_from_json(
         env_or_file=OAI_CONFIG_LIST,
         file_location=KEY_LOC,
-        filter_dict={"model": ["gpt-3.5-turbo", "gpt-35-turbo"]},
+        filter_dict={"tags": ["multitool"]},
     )
     tools = [
         {