[Suggestion] update AGENT_SYS_MSG_PROMPT in version 0.2

[davidxwwang]

when using AGENT_SYS_MSG_PROMPT in AgentBuilder~build() to generate agent`s system message, the generated system message may loss TERMINATE info, this could make some tool calls to enter an infinite loop when using other model even the task is finished( the LLM does not return TERMINATE , but the tool function over and over again ).（Not GPT, but other large models（ l use deepseek）， maybe other large models might not have the same level of understanding and analysis ability as GPT）

the generated system message using AGENT_SYS_MSG_PROMPT will be like this

` ## Your role

Email_Expert is a specialized expert designed to handle tasks related to email communication, data calculation, and browser automation. This expert is proficient in performing mathematical calculations, sending emails, and managing browser operations to ensure seamless task execution.

Task and skill instructions:

Task description: Calculate the sum of numbers from 1 to 50, send the result to David's email, and open the browser to allow the user to check the email content.

Skill description:

Mathematical Calculation: Accurately compute the sum of a sequence of numbers.
Email Communication: Send the calculated result to a specified email address.
Browser Automation: Open a web browser to facilitate the user in checking the email content.
Other information: Ensure that the email is sent successfully and that the browser opens to the correct email interface for the user to verify the content.

This expert is equipped to handle the entire workflow efficiently, ensuring that each step is executed correctly and that the user can easily verify the results. `

I suggest adding some statement to AGENT_SYS_MSG_PROMPT to make the agent clearly understand when the task ends it should return “TERMINATE”. for example:

Group chat instruction\nYou are now working in a group chat with different expert and a group chat manager.\nYou should refer to the previous message from other participant members or yourself, follow their topic and reply to them.When the task is complete and the result has been carefully verified, after obtaining agreement from the other members, you can end the conversation by replying only with "TERMINATE" ....

[ekzhu]

Thanks for the update. It makes sense.

Would you be interested in porting this to 0.4? It should be easy as the new API is considerably similar.

[davidxwwang]

yes, but l cannot find the AgentBuilder or similar classes in version 0.4😅， l am newer for version 0.4

[ekzhu]

It has not been ported yet. I was wondering if you would like to write a port.

[davidxwwang]

ok， l will try，but let me familiarize myself with the 0.4 version first， this will take time😅

[ekzhu]

Take your time! You can start a Discussion thread for this.