Issue Station
Sign In
Tools hereToolbox

claude-code - 💡(How to fix) Fix [BUG] Terminal corruption when permission prompt appears while navigating Agent Teams agent selection menu

Official PRs (…)
ON THIS PAGE

Recommended Tools

×6

Utilities matched from this issue’s tags and category — try them while you read without losing context.

GitHub issue graph ai analysis

Paste a GitHub issue URL. We fetch that issue, discover linked issues from bodies/comments/timeline, collect linked pull requests, and produce a structured English report.

The report is written in English Markdown for sharing and archival.

Helpful · Quick feedback

Loading…

Error Message

Error Messages/Logs

RAW_BUFFERClick to expand / collapse

Preflight Checklist

  • I have searched existing issues and this hasn't been reported yet
  • This is a single bug report (please file separate reports for different bugs)
  • I am using the latest version of Claude Code

What's Wrong?

When using Claude Agent Teams, when I press shift+<down arrow>, Claude Code displays an expanded UI where I can use shift+<up/down> to select between the running agents. If a permission prompt appears while I am navigating the agent select UI, the terminal output becomes garbled.

Screenshot of normal output, where I have positioned my cursor in the Agent Teams UI: <img width="885" height="856" alt="Image" src="https://github.com/user-attachments/assets/45a7235f-be26-47d1-aaf7-7699382f4721" />

Screenshot of the garbled output after a permission prompt appeared while my cursor was in the Agent Team UI: <img width="885" height="856" alt="Image" src="https://github.com/user-attachments/assets/b4a15fed-bdce-4e74-a311-a1fce2cde2b1" /> (notice the garbled text in the "Let me..." bullet)

What Should Happen?

I should be able to navigate the Agent Teams UI without the terminal output becoming garbled.

Error Messages/Logs

Steps to Reproduce

  1. Start Claude Code with CLAUDE_CODE_EXPERIMENTAL_AGENT_TEAMS=1 in the environment
  2. Execute a prompt that instructs Claude to form an agent team. I asked Claude to implement an internal dashboard, with both a web frontend and backend server component.
  3. Once Claude spawns the agents, press shift+<down arrow> to open the expanded agent list UI
  4. Position the cursor on one of the agents in the menu. Leave it in this position.
  5. Wait for a permission prompt to appear. It does not appear whether the currently selected agent is the one that generated the permission prompt.

Claude Model

Opus

Is this a regression?

I don't know

Last Working Version

No response

Claude Code Version

2.1.153

Platform

AWS Bedrock

Operating System

macOS

Terminal/Shell

iTerm2

Additional Information

The screenshots were captured on Ghostty, but I was also able to produce the issue on iTerm2 and another terminal emulator.

Vote matrix · Quick signals

Works
Did the solution work? Tap to confirm.
Easy Fix
Was it a quick fix?
Time Saver
Did it save you time?
Blocking
Was it severely blocking?
Common Issue
Are others likely hitting this too?
Flaky / Intermittent
Is it intermittent?
Verified / Reproducible
Can you reproduce it reliably?
Loading…

Still need to ship something?

×6

Another batch ranked right after the header list — different links, same matching logic.

Back to top recommendations

TRENDING