[BUG] Model reasoning doesn't appear to be triggered despite Thinking/Verbose both being enabled

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?

Can't tell if the model is using its reasoning budget - reasoning traces aren't being revealed in verbose mode with thinking enabled. Previously in Claude Code basically everything got a reasoning trace with thinking enabled.

What Should Happen?

With thinking and verbose enabled, I should see reasoning traces on basically every turn. I used to up until the last few hours.

Error Messages/Logs

Steps to Reproduce

discuss things tangentially related to code with the model - it seems like reasoning no longer applies to most messages.

Claude Model

Opus

Is this a regression?

Yes, this worked in a previous version

Last Working Version

_No response_

Claude Code Version

2.1.29

Platform

Anthropic API

Operating System

Windows

Terminal/Shell

PowerShell

Additional Information

_No response_