[BUG] Claude code should briefly block input when prompting for user input

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'm writing a prompt and are about te hit enter, Claude Code can inject a permission prompt that I will then approve without even being able to read it.

What Should Happen?

Claude should block confirming inputs for a 1 or 2 seconds to prevent unintended approvals

Error Messages/Logs

Steps to Reproduce

Have claude run an action in the background that will eventually require user input.
Start writing a prompt, hit enter as soon as the user input request appears.

Claude Model

None

Is this a regression?

No, this never worked

Last Working Version

_No response_

Claude Code Version

2.1.220 (Claude Code)

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

iTerm2

Additional Information

_No response_