[BUG] thinking or redacted_thinking blocks in the latest assistant message cannot be modified

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?

<img width="1049" height="572" alt="Image" src="https://github.com/user-attachments/assets/36a1b6e7-3c0d-4774-997a-a96097e7cb8a" />

What Should Happen?

This is an Anthropic API error indicating that the conversation history became corrupted - specifically, the internal "thinking" blocks from a previous response were modified when they shouldn't have been.

Error Messages/Logs

Steps to Reproduce

<img width="823" height="300" alt="Image" src="https://github.com/user-attachments/assets/f9b6217c-083a-4293-898f-ff75998f7472" />

Claude Model

None

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

claude-opus-4-5-20251101

Platform

Anthropic API

Operating System

macOS

Terminal/Shell

Terminal.app (macOS)

Additional Information

_No response_