diff --git a/autogen/agentchat/conversable_agent.py b/autogen/agentchat/conversable_agent.py
index 6a3d7f4228bf..70783376452f 100644
--- a/autogen/agentchat/conversable_agent.py
+++ b/autogen/agentchat/conversable_agent.py
@@ -107,7 +107,7 @@ def __init__(
                     If False, the code will be executed in the current environment.
                     We strongly recommend using docker for code execution.
                 - timeout (Optional, int): The maximum execution time in seconds.
-                - last_n_messages (Experimental, Optional, int or str): The number of messages to look back for code execution. Default to 1. If set to 'auto', it will scan backwards through all messages arriving since the agent last spoke (typically this is the last time execution was attempted).
+                - last_n_messages (Experimental, Optional, int or str): The number of messages to look back for code execution. If set to 'auto', it will scan backwards through all messages arriving since the agent last spoke, which is typically the last time execution was attempted. (Default: auto)
             llm_config (dict or False): llm inference configuration.
                 Please refer to [OpenAIWrapper.create](/docs/reference/oai/client#create)
                 for available options.
@@ -839,7 +839,10 @@ def generate_code_execution_reply(
             return False, None
         if messages is None:
             messages = self._oai_messages[sender]
-        last_n_messages = code_execution_config.pop("last_n_messages", 1)
+        last_n_messages = code_execution_config.pop("last_n_messages", "auto")
+
+        if not (isinstance(last_n_messages, (int, float)) and last_n_messages >= 0) and last_n_messages != "auto":
+            raise ValueError("last_n_messages must be either a non-negative integer, or the string 'auto'.")
 
         messages_to_scan = last_n_messages
         if last_n_messages == "auto":
diff --git a/test/agentchat/test_conversable_agent.py b/test/agentchat/test_conversable_agent.py
index 2fa10602d4e8..64b8473cf694 100644
--- a/test/agentchat/test_conversable_agent.py
+++ b/test/agentchat/test_conversable_agent.py
@@ -323,6 +323,15 @@ def test_generate_code_execution_reply():
     )
     assert agent._code_execution_config["last_n_messages"] == "auto"
 
+    # scenario 8: if last_n_messages is misconfigures, we expect to see an error
+    with pytest.raises(ValueError):
+        agent._code_execution_config = {"last_n_messages": -1, "use_docker": False}
+        agent.generate_code_execution_reply([code_message])
+
+    with pytest.raises(ValueError):
+        agent._code_execution_config = {"last_n_messages": "hello world", "use_docker": False}
+        agent.generate_code_execution_reply([code_message])
+
 
 def test_max_consecutive_auto_reply():
     agent = ConversableAgent("a0", max_consecutive_auto_reply=2, llm_config=False, human_input_mode="NEVER")
@@ -987,6 +996,6 @@ def test_no_llm_config():
     # test_trigger()
     # test_context()
     # test_max_consecutive_auto_reply()
-    # test_generate_code_execution_reply()
+    test_generate_code_execution_reply()
     # test_conversable_agent()
-    test_no_llm_config()
+    # test_no_llm_config()