Feature Request: Parameter in LlmAgent to prevent showing output to user in the chat UI

Often I want to enforce a schema in the output from a subagent and save the output as a state variable, i.e. use both output_schema and output_key parameters in an LlmAgenrt definitly. However I don't necessarily want the user to see the output in the chat UI. Can we add a boolean parameter such as `response_to_user` which will silence the output in the chat UI, but still save it to the state variable (enforced by a schema where desired)?