[BUG] STOP CHANGING THE TERMINAL OUTPUT WHEN THE AGENT CORRECTS ITSELF
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?
I am literally reading Claude Code output, then it does something to figure out what it wrote was wrong, then the text I am reading LITERALLY GETS CHANGED, the thing I am reading DISSAPEARS AND NEW VERSION OF THE OUTPUT IN THE TERMINAL GETS OUTPUTTED!
THIS IS INSANE! STOP DOING THIS! IT DRIVES ME CRAZY! I am reading the output the opus 4.8 wrote only to see it disappear as I am reading it and "newer corrected output" usurp the very thing I am reading! It's insanity!
What Should Happen?
LEAVE THE OUTPUT UNALTERED -- WRITE UPDATES TO THE END OF THE CONSOLE WINDOW WHERE THEY BELONG!
Error Messages/Logs
Steps to Reproduce
Write something - watch output -- ask it something to course correct -- watch output change 🤯
Claude Model
None
Is this a regression?
Yes, this worked in a previous version
Last Working Version
_No response_
Claude Code Version
2.1.154
Platform
Anthropic API
Operating System
Ubuntu/Debian Linux
Terminal/Shell
WSL (Windows Subsystem for Linux)
Additional Information
THIS IS CRAZY!
This issue has 2 comments on GitHub. Read the full discussion on GitHub ↗