Allow AI Agents to return the original output instead of summarizing

Feature Requests
1

AI Agent, Conversation Agent, ReAct Agent, Basic LLM Chain.

The idea is:

Allow AI Agents to return the original output instead of summarizing

My use case:

With the Customized workflow/tool it would return the information to the AI Agent (Conversation Agent/React Agent), but the AI Agent will summarize the information returned by the tool, it is not able to Hard control the output format via prompts.

It is able to have a parameter/option to allow the returned information are strictkly being formated with user’s expection, with summarize or w/o summairze is in the parameter control.

2

Also, if an Agent is running multiple workflow tools then the ability to provide intermittent updates to user via the chat between each workflow tool.

This will give the user a progress feedback instead of waiting until the end of all processes.

3

Hey @WTeeth

I’m experiencing the same issue. Have you managed to find a fix for it yet?