Agent command window doesn't expand until output occurs

Support Bug Reports
,
1

Where does the bug appear (feature/product)?

Cursor IDE

Describe the Bug

This bug is an offshoot of Uncompacting agent command execution - #13 by mohitjain , which @mohitjain asked me to file, since it concerns behavior that’s still not optimal, even though the original bug (the terminal output window in the agent not expanding at all) is now fixed.

The new bug is that the agent command window doesn’t expand until a terminal command produces output, which means that it’s not easy to see which commands the agent is calling until they produce something.

Steps to Reproduce

  1. Get the agent to initiate a command that might take a while to produce output, or doesn’t produce output at all (like a grep of a large file, or a command that outputs to /dev/null).

  2. Observe that the agent window doesn’t expand until output occurs.

Expected Behavior

The agent command window should expand for any input, at the point where the agent issues the command.

Screenshots / Screen Recordings

Operating System

Linux

Version Information

Version: 3.6.31
VS Code Extension API: 1.105.1
Commit: 81fcf2931d7687b4ff3f3017858d0c6dee7e2a60
Date: 2026-05-31T17:46:29.630Z
Layout: editor
Build Type: Stable
Release Track: Default
Electron: 39.8.1
Chromium: 142.0.7444.265
Node.js: 22.22.1
V8: 14.2.231.22-electron.0
xterm.js: 6.1.0-beta.220
OS: Linux x64 6.8.0-124-generic

For AI issues: which model did you use?

Probably not relevant, but Opus 4.5 in this case.

Does this stop you from using Cursor

No - Cursor works, but with this issue

7

Thanks for filing this, and for the screen recording - it makes the behavior easy to see. I’m able to reproduce it: when the agent starts a command that doesn’t produce output right away, the command box stays as a single collapsed line, so it’s not clear what’s running until output starts streaming in.

This is a confirmed bug and I’ve passed it to our team to track. The behavior we’re aiming for matches what you described - the box should reflect the command as soon as it’s issued, rather than waiting for output.

I’ll follow up here once there’s an update. Thanks for helping us pin this down.