About Message Forwarding

[karankakwani]

Message Forwarding mentions – "we can equip the supervisor with a tool to directly forward the last message received from a worker agent straight to the final output of the graph using create_forward_message_tool. This is useful when the supervisor determines that the worker's response is sufficient and doesn't require further processing or summarization by the supervisor itself."

How can we reliably make sure in all instances that supervisor simply forwards the response of the sub-agent or the tool directly to output without ever trying to further processing or paraphrasing it?

[karan-kakwani]

@hinthornw

[ovantee]

I have the same question

[sidh-cbt]

I am really unsure on this.
Is supervisor injects the name in from_agent as normal tool call?
Did anyone implemented it?