Keep thought process expanded when agent has made new changes

Feature request for product/service

Cursor IDE

Describe the request

Whenever I read the thinking output tokens to understand what it has thought through, whenever a new thinking output section starts, or when the agent has made code changes, it immediately unexpands the current thinking section that I was reading through.

Operating System (if it applies)

MacOS

Hey @ZoellaB!

Yeah, it’s unfortunate that we don’t respect the user having manually expanded. A team member just reported this last week! I’ve shared your comment on that internal thread.

Do you typically use the Editor the Agents Window?

I’m still currently using the legacy IDE window, so not using Agents Window.

Does this exist in the Agents Window?

No, the behavior is the same.