[BUG] Claude Code fails BASH invocations
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?
Claude code started to complain about bash invocations being buffered, or bash output seems to not reach the model anymore?
Since yesterday Claude is just executing random bash commands in between real commands, see screenshots.
<img width="562" height="229" alt="Image" src="https://github.com/user-attachments/assets/7e4ee392-98b0-4ee0-88d7-e6fbff346ffa" />
<img width="463" height="236" alt="Image" src="https://github.com/user-attachments/assets/8ee4aa01-9447-4a97-a339-ea6a551cd4db" />
<img width="287" height="318" alt="Image" src="https://github.com/user-attachments/assets/d6a8cab3-db80-4f2c-93e2-a3ad460a229f" />
After all these commands, Claude seems to acknowledge the issue Tools are responsive again — and I now have the full scheduler/task/command/query picture plus both agents' analyses.
What Should Happen?
Claude should not have problems executing bash
Error Messages/Logs
Steps to Reproduce
ask claude to do anything
Claude Model
Opus
Is this a regression?
Yes, this worked in a previous version
Last Working Version
_No response_
Claude Code Version
2.1.156 (Claude Code)
Platform
Anthropic API
Operating System
macOS
Terminal/Shell
Other
Additional Information
_No response_
This issue has 3 comments on GitHub. Read the full discussion on GitHub ↗