Notebook optional user input

autogen/agentchat/conversable_agent.py

@@ -937,6 +937,7 @@ def my_summary_method(
                 One example key is "summary_prompt", and value is a string of text used to prompt a LLM-based agent (the sender or receiver agent) to reflect
                 on the conversation and extract a summary when summary_method is "reflection_with_llm".
                 The default summary_prompt is DEFAULT_SUMMARY_PROMPT, i.e., "Summarize takeaway from the conversation. Do not add any introductory phrases. If the intended request is NOT properly addressed, please point it out."
+                Another available key is "summary_role", which is the role of the message sent to the agent in charge of summarizing. Default is "system".
             message (str, dict or Callable): the initial message to be sent to the recipient. Needs to be provided. Otherwise, input() will be called to get the initial message.
                 - If a string or a dict is provided, it will be used as the initial message.        `generate_init_message` is called to generate the initial message for the agent based on this string and the context.
                     If dict, it may contain the following reserved fields (either content or tool_calls need to be provided).
@@ -1168,8 +1169,13 @@ def _reflection_with_llm_as_summary(sender, recipient, summary_args):
             raise ValueError("The summary_prompt must be a string.")
         msg_list = recipient.chat_messages_for_summary(sender)
         agent = sender if recipient is None else recipient
+        role = summary_args.get("summary_role", None)
+        if role and not isinstance(role, str):
+            raise ValueError("The summary_role in summary_arg must be a string.")
         try:
-            summary = sender._reflection_with_llm(prompt, msg_list, llm_agent=agent, cache=summary_args.get("cache"))
+            summary = sender._reflection_with_llm(
+                prompt, msg_list, llm_agent=agent, cache=summary_args.get("cache"), role=role
+            )
         except BadRequestError as e:
             warnings.warn(
                 f"Cannot extract summary using reflection_with_llm: {e}. Using an empty str as summary.", UserWarning
@@ -1178,7 +1184,12 @@ def _reflection_with_llm_as_summary(sender, recipient, summary_args):
         return summary
 
     def _reflection_with_llm(
-        self, prompt, messages, llm_agent: Optional[Agent] = None, cache: Optional[AbstractCache] = None
+        self,
+        prompt,
+        messages,
+        llm_agent: Optional[Agent] = None,
+        cache: Optional[AbstractCache] = None,
+        role: Union[str, None] = None,
     ) -> str:
         """Get a chat summary using reflection with an llm client based on the conversation history.
 
@@ -1187,10 +1198,14 @@ def _reflection_with_llm(
             messages (list): The messages generated as part of a chat conversation.
             llm_agent: the agent with an llm client.
             cache (AbstractCache or None): the cache client to be used for this conversation.
+            role (str): the role of the message, usually "system" or "user". Default is "system".
         """
+        if not role:
+            role = "system"
+
         system_msg = [
             {
-                "role": "system",
+                "role": role,
                 "content": prompt,
             }
         ]
@@ -1203,7 +1218,7 @@ def _reflection_with_llm(
         else:
             raise ValueError("No OpenAIWrapper client is found.")
         response = self._generate_oai_reply_from_client(llm_client=llm_client, messages=messages, cache=cache)
-        return response
+        return self.generate_oai_reply(messages=messages, config=llm_client)
 
     def _check_chat_queue_for_sender(self, chat_queue: List[Dict[str, Any]]) -> List[Dict[str, Any]]:
         """