[Discussion]: How to display LLM thinking process and verify "Skill" invocation? · CherryHQ/cherry-studio#14455

2026-04-21T18:44:35.000Z

### Issue Checklist - [x] I understand that issues are meant for feedback and problem-solving, not for venting, and I will provide as much detail as possible to help resolve the issue. - [x] I have checked the pinned issues and searched through the existing [open issues](https://github.com/CherryHQ/cherry-studio/issues), [closed issues](https://github.com/CherryHQ/cherry-studio/issues?q=is%3Aissue%20state%3Aclosed), and [discussions](https://github.com/CherryHQ/cherry-studio/discussions) and did not find a similar suggestion. - [x] I confirm that I am here to ask questions and discuss issues, not to report bugs or request features. ### Platform macOS ### Version 1.9.2 ### Your Question Hello\! Thank you very much to the development team for creating such an excellent tool like Cherry Studio. During usage, I have two questions/suggestions about feature usage and interface display, and I hope to get answers: 1. How to display the LLM's thinking/reasoning process in the chat interface? Currently, when using large models with deep thinking capabilities, major official web interfaces (like DeepSeek) display or collapse the model's "thinking process" before answering. May I ask if there is currently a setting in Cherry Studio to enable the display of the thinking process? If not, is there consideration to add UI support for this interface in the future? 2. How to explicitly confirm that "Skills" functionality is actually being invoked? I have installed some "skills" I want to use in the software's skills options. However, in daily question-and-answer conversations, I cannot determine whether the LLM's response indeed references and uses this "skill" (such as consulting specific settings, calling searches, etc.), or if it is just a conventional response based on its own pre-trained data. Suggestion/Expectation: Is it possible to add a visual indicator (such as a small icon, status bar, or invocation log) in the chat interface to clearly show whether the current response triggered a specific "skill", so that users can judge whether the skill has taken effect? ### Context _No response_ ### Additional Information ```shell ``` ### Priority Medium (Would like a response soon) --- > [\!NOTE] > This issue/comment/review was translated by Claude. --- Original Content ### Issue Checklist - [x] I understand that issues are meant for feedback and problem-solving, not for venting, and I will provide as much detail as possible to help resolve the issue. - [x] I have checked the pinned issues and searched through the existing [open issues](https://github.com/CherryHQ/cherry-studio/issues), [closed issues](https://github.com/CherryHQ/cherry-studio/issues?q=is%3Aissue%20state%3Aclosed), and [discussions](https://github.com/CherryHQ/cherry-studio/discussions) and did not find a similar suggestion. - [x] I confirm that I am here to ask questions and discuss issues, not to report bugs or request features. ### Platform macOS ### Version 1.9.2 ### Your Question 你好！非常感谢开发团队带来 Cherry Studio 这么优秀的工具。在使用过程中，我有两个关于功能使用和界面展示的疑问/建议，希望得到解答： 1. 如何在对话框中显示出 LLM 的思考/推理过程？目前在使用带有深度思考能力的大模型时，各大官网的网页端（如DeepSeek等）都会在回答前展示或折叠模型的"思考过程"。请问在 Cherry Studio 中，目前是否有设置可以开启显示思考过程的功能？如果没有，未来是否考虑加入该界面的UI支持？ 2. 如何明确确认"技能 (Skills)"功能被实际调用？我在软件的技能选项中，安装了一些自己想用的"skill"。但是在日常的问答对话中，我无法确定 LLM 的回答是确实参考并使用了这个"技能"（比如查阅了特定设定、调用了搜索等），还是仅仅基于它自身的预训练数据做出的常规回答。建议/期待：是否可以在对话框中增加一个视觉提示（比如小图标、状态栏或调用日志），明确展示当前回答是否触发了某个具体"技能"，以便用户判断技能是否生效？ ### Context _No response_ ### Additional Information ```shell ``` ### Priority Medium (Would like a response soon)

(2 comments) (1 reaction) (0 assignees)TypeScript (45,688 stars) (4,338 forks)batch import

AssistantUI/UXdiscussionhelp wantedinactive

Description

Issue Checklist

I understand that issues are meant for feedback and problem-solving, not for venting, and I will provide as much detail as possible to help resolve the issue.
I have checked the pinned issues and searched through the existing open issues, closed issues, and discussions and did not find a similar suggestion.
I confirm that I am here to ask questions and discuss issues, not to report bugs or request features.

Platform

macOS

Version

1.9.2

Your Question

Hello! Thank you very much to the development team for creating such an excellent tool like Cherry Studio. During usage, I have two questions/suggestions about feature usage and interface display, and I hope to get answers:

How to display the LLM's thinking/reasoning process in the chat interface? Currently, when using large models with deep thinking capabilities, major official web interfaces (like DeepSeek) display or collapse the model's "thinking process" before answering. May I ask if there is currently a setting in Cherry Studio to enable the display of the thinking process? If not, is there consideration to add UI support for this interface in the future?
How to explicitly confirm that "Skills" functionality is actually being invoked? I have installed some "skills" I want to use in the software's skills options. However, in daily question-and-answer conversations, I cannot determine whether the LLM's response indeed references and uses this "skill" (such as consulting specific settings, calling searches, etc.), or if it is just a conventional response based on its own pre-trained data.

Suggestion/Expectation: Is it possible to add a visual indicator (such as a small icon, status bar, or invocation log) in the chat interface to clearly show whether the current response triggered a specific "skill", so that users can judge whether the skill has taken effect?

Context

No response

Additional Information

Priority

Medium (Would like a response soon)

[!NOTE] This issue/comment/review was translated by Claude.