[Bug]: Internal thinking process leaked in Grok responses after recent update

[Lingelsh]

Issue Checklist

• I understand that issues are for feedback and problem solving, not for complaining in the comment section, and will provide as much information as possible to help solve the problem.
• My issue is not listed in the FAQ.
• I've looked at pinned issues and searched for existing Open Issues, Closed Issues, and Discussions, no similar issue or discussion was found.
• I've filled in short, clear headings so that developers can quickly identify a rough idea of what to expect when flipping through the list of issues. And not "a suggestion", "stuck", etc.
• I've confirmed that I am using the latest version of Cherry Studio.

Platform

Windows

Version

v1.8.0

Bug Description

After updating Cherry Studio to the latest version, Grok models (specifically grok-4.1, and grok-4.2-beta) are displaying their internal reasoning/thinking traces directly in the chat output.

Example of leaked content that appears at the beginning of the response:

Steps To Reproduce

1.Update Cherry Studio to the latest version.
2.Connect to any of the affected Grok models (grok-4.1 / grok-4.20-beta / grok-4.2-beta).
3.Send a simple message (e.g. a greeting in Chinese or English).
4.The reply now starts with the internal thinking text before the actual answer.

Expected Behavior

The Grok response should ONLY show the final clean answer to the user's query. All internal thinking/reasoning traces (e.g. "Thinking about your requestRecognizing greeting- You greeted in Chinese...") must be completely hidden and never visible in the chat output.
This is the normal and expected behavior:

• It worked perfectly in previous versions of Cherry Studio (before the most recent update).
• It still works perfectly in every other client (official X app, Poe, direct API calls, etc.) — no leaked thinking at all.

Relevant Log Output

Additional Context

No response