[BUG] Sub agents spamming output in terminal

Preflight Checklist

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

What's Wrong?

When I use multiple sub agents at once, they seem to spam the terminal with the name of the agent over and over again. They also all seem to be live, though I know from the work they are doing that it is still only a handful instead of the flood shown on screen. Here is a screenshot:

What Should Happen?

Each subagent should have a single persistent line in the terminal where their output snippets are shown.

Error Messages/Logs

Steps to Reproduce

1. Ask claude code to spin up multiple developer agents to tackle multiple features in the same project at once.

Claude Model

Sonnet (default)

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

1.0.117

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

<img width="500" height="1340" alt="Image" src="https://github.com/user-attachments/assets/545ca220-3941-4104-aa28-f26cae7a0431" />