[BUG] Anthropic API error: thinking blocks

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?

On Opus 4.8 with extended thinking, on a clean build with the latest update, there is a client-side bug where the cryptographic signature on the thinking blocks is not being returned intact. It may be truncating thinking blocks (?) As a result every message after starts to brick and that instance of Claude Code bricks as well

What Should Happen?

Claude Code should be returning thinking blocks exactly + signed, so instances can continue as normal

Error Messages/Logs

messages.1.content.19: 'thinking' blocks in the latest assistant message cannot be modified

Steps to Reproduce

Have it set up homebrew from a completely clean/new Mac

Claude Model

Opus

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

macOS

Terminal/Shell

iTerm2

Additional Information

_No response_