Incorrect chat titles generated for reasoning/thinking mode chats

[Ayushraj6202]

Before submitting your bug report

• I've tried using the "Ask AI" feature on the Continue docs site to see if the docs have an answer
• I'm not able to find a related conversation on GitHub discussions that reports the same bug
• I'm not able to find an open issue that reports the same bug
• I've seen the troubleshooting guide on the Continue Docs

Relevant environment info

- OS: windows
- Continue version: 1.2.22
- IDE version:vscode 1.118
- Model:
- config:
  
Model for role: chat  is qwen 3.6 31B
  
  OR link to agent in Continue hub:

Description

When using reasoning/thinking mode, the generated chat titles are often inaccurate or unrelated to the actual conversation context.

This appears to happen because the title generation logic includes reasoning/internal thinking content instead of only the user-visible conversation.

I’ve identified the root cause and can submit a fix.

To reproduce

No response

Log output

Chat title is this: 
Here is Thinking Process ,