Where does the bug appear (feature/product)?
Cursor IDE
Describe the Bug
I asked Cursor to run claude CI command:
Ran:
claude --agent test-runner -p "Run these tests: Integrations/VoiceCall/DrachtioBridge"It’s still running after about 2 minutes and the terminal log doesn’t show any stdout/stderr yet—only that the process started. So either the agent is slow to start or its output isn’t being captured there.
Check the terminal where it’s running for live output. If it stays blank or never finishes, that may match the “cli agents freeze” behavior in
.notes/cliAgentsFreezeInCursorReport.md.
Nothing happens, after a while separate shell is spawned with this command:
Interesting observation: I have detailed logs from this Claude subprocess, bt they only start to run *after I manually terminate this terminal Window Cursor spawned.
Steps to Reproduce
Run this example Claude Code headless command:
claude --agent test-runner -p "Run these tests: Integrations/VoiceCall/DrachtioBridge"
Request ID:
d2fd302a-8761-454f-9a06-a5f4b1049caa
Expected Behavior
Shell subprocess spawns and completes, returning success. Or even error - but not hang indefinitely.
When I run same command manually, I get some output (even though approvals are not configured with this setup in mind).:
$ claude --agent test-runner -p "Run these tests: Integrations/VoiceCall/DrachtioBridge"
I need approval to run the test command. This is a security measure in your environment. The command I'm attempting to run is:
Operating System
Windows 10/11
Version Information
Version: 2.6.11 (user setup)
VSCode Version: 1.105.1
Commit: 8c95649f251a168cc4bb34c89531fae7db4bd990
Date: 2026-03-03T18:57:48.001Z
Build Type: Stable
Release Track: Default
Electron: 39.6.0
Chromium: 142.0.7444.265
Node.js: 22.22.0
V8: 14.2.231.22-electron.0
OS: Windows_NT x64 10.0.26200
Additional Information
This was introduced around February, this setup used to work for me for few months then.
Does this stop you from using Cursor
Sometimes - I can sometimes use Cursor