Is this a new feature, an improvement, or a change to existing functionality?
New Feature
How would you describe the priority of this feature request
Medium
Please provide a clear description of problem this feature solves
Non-technical users find the Intermediate Steps displayed in agent responses to be too complicated and business users don't want to see the "technical mumbo-jumbo". However if we disable the intermediate steps, there is no sense of progression aside from the tiny spinner and "Stop Generating" button. Some tools in our workflow take a minute to run so it feels like the agent is not responding without the intermediate steps being displayed.
Describe your ideal solution
I propose adding a simple thought output as a user-friendly alternative to the intermediate steps UI. It would display LLM thoughts, show tool/function calls, and allow agent developers to emit custom process updates.
Additional context
No response
Code of Conduct
Is this a new feature, an improvement, or a change to existing functionality?
New Feature
How would you describe the priority of this feature request
Medium
Please provide a clear description of problem this feature solves
Non-technical users find the Intermediate Steps displayed in agent responses to be too complicated and business users don't want to see the "technical mumbo-jumbo". However if we disable the intermediate steps, there is no sense of progression aside from the tiny spinner and "Stop Generating" button. Some tools in our workflow take a minute to run so it feels like the agent is not responding without the intermediate steps being displayed.
Describe your ideal solution
I propose adding a simple thought output as a user-friendly alternative to the intermediate steps UI. It would display LLM thoughts, show tool/function calls, and allow agent developers to emit custom process updates.
Additional context
No response
Code of Conduct