langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 20:15:31 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

deepseek r1 model dialog format questions for local or cloud services #8221

New Issue
Closed
opened 2026-02-21 18:24:33 -05:00 by yindo · 2 comments
yindo commented 2026-02-21 18:24:33 -05:00
Owner
Copy Link
Copy Source

Originally created by @shatang123 on GitHub (Feb 13, 2025).

Self Checks

  • This is only for bug report, if you would like to ask a question, please head to Discussions.
  • I have searched for existing issues search for existing issues, including closed ones.
  • I confirm that I am using English to submit this report (我已阅读并同意 Language Policy).
  • [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:）
  • Please do not modify this template :) and fill in all the required fields.

Dify version

0.15.3

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

经过测试发现，不管是本地部署的deepseek r1（ollama），还是其它提供商，比如阿里云。我发现dify都没有使用下面的对话格式，在历史记录中每次的思考过程都会被传递
Image
下面是当前dify中的对话历史记录，我不清楚dify是否真的将全部轮次的思考过程都传递给了模型，还是只是在对话历史中展示
Image、

Image

✔️ Expected Behavior

思考过程不该传递给模型

❌ Actual Behavior

在对话历史中展示了，我不清楚dify是否会将思考过程传递给模型

Originally created by @shatang123 on GitHub (Feb 13, 2025). ### Self Checks - [x] This is only for bug report, if you would like to ask a question, please head to [Discussions](https://github.com/langgenius/dify/discussions/categories/general). - [x] I have searched for existing issues [search for existing issues](https://github.com/langgenius/dify/issues), including closed ones. - [x] I confirm that I am using English to submit this report (我已阅读并同意 [Language Policy](https://github.com/langgenius/dify/issues/1542)). - [x] [FOR CHINESE USERS] 请务必使用英文提交 Issue，否则会被关闭。谢谢！:） - [x] Please do not modify this template :) and fill in all the required fields. ### Dify version 0.15.3 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce 经过测试发现，不管是本地部署的deepseek r1（ollama），还是其它提供商，比如阿里云。我发现dify都没有使用下面的对话格式，在历史记录中每次的思考过程都会被传递 ![Image](https://github.com/user-attachments/assets/a01bcf77-0088-40db-8951-02911859f13a) 下面是当前dify中的对话历史记录，我不清楚dify是否真的将全部轮次的思考过程都传递给了模型，还是只是在对话历史中展示 ![Image](https://github.com/user-attachments/assets/021f262a-2052-4078-95fd-21377661c9ec)、 ![Image](https://github.com/user-attachments/assets/2bd2229b-90f1-4c1a-b66a-cdca7c950ff1) ### ✔️ Expected Behavior 思考过程不该传递给模型 ### ❌ Actual Behavior 在对话历史中展示了，我不清楚dify是否会将思考过程传递给模型
yindo added the 🐞 bug label 2026-02-21 18:24:33 -05:00
yindo closed this issue 2026-02-21 18:24:33 -05:00
yindo commented 2026-02-21 18:24:33 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Feb 13, 2025):

I found a similar unsolved discussion regarding the use of DeepSeek's API and the display of its thought process [1]. This might be relevant to your question about whether Dify transmits the reasoning content to the model or just displays it in the conversation history.

In Dify, users can customize the conversation history sent to the model, especially in Expert Mode. This includes the ability to rearrange the placement of Context and History, and set necessary parameters, which allows for a highly customized prompt design. However, the specific configuration or setting that controls whether the reasoning process is included in the conversation history sent to the model wasn't found in the available documentation [2][3].

To continue talking to Dosu, mention @dosu.

Help Dosu learn! Give it feedback: Great Response | Irrelevant Answer | Incorrect Sources | Too Verbose | Hallucination | Other | Bug Report

@dosubot[bot] commented on GitHub (Feb 13, 2025): <!-- Answer --> I found a similar unsolved discussion regarding the use of DeepSeek's API and the display of its thought process <sup>[[1]](https://github.com/langgenius/dify/discussions/13125)</sup>. This might be relevant to your question about whether Dify transmits the reasoning content to the model or just displays it in the conversation history. In Dify, users can customize the conversation history sent to the model, especially in Expert Mode. This includes the ability to rearrange the placement of `Context` and `History`, and set necessary parameters, which allows for a highly customized prompt design. However, the specific configuration or setting that controls whether the reasoning process is included in the conversation history sent to the model wasn't found in the available documentation <sup>[[2]](https://github.com/langgenius/dify-docs/blob/main/en/learn-more/prompt-engineering/prompt-engineering-1/README.md)</sup><sup>[[3]](https://github.com/langgenius/dify-docs/blob/main/en/guides/application-orchestrate/prompt-engineering/prompt-engineering-expert-mode.md)</sup>. <!-- Dosu Comment Footer --> *To continue talking to [Dosu](https://dosu.dev), mention @dosu.* --- <sup>Help Dosu learn! Give it feedback: [Great Response](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=hallucination) | [Other](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=other) | [Bug Report](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=bug_report)</sup>
yindo commented 2026-02-21 18:24:33 -05:00
Author
Owner
Copy Link
Copy Source

@shatang123 commented on GitHub (Feb 13, 2025):

我发现了一个类似的未解决的讨论，关于 DeepSeek 的 API 的使用和其思维过程的显示[1].这可能与您关于 Dify 是将推理内容传输到模型还是仅将其显示在对话历史记录中的问题相关。

在 Dify 中，用户可以自定义发送到模型的对话历史记录，尤其是在专家模式下。这包括重新排列 和 的放置以及设置必要的参数的能力，从而允许高度自定义的提示设计。但是，在可用文档中找不到控制推理过程是否包含在发送到模型的对话历史记录中的特定配置或设置Context``History[2][3].

要继续与 Dosu 交谈，请提及 。

帮助 Dosu 学习！给它反馈：伟大的回应 |无关紧要的答案 |不正确的来源 |太冗长 |幻觉 |其他 |Bug 报告

我的dify没有专家模式，这可能是由于我的dify版本问题

@shatang123 commented on GitHub (Feb 13, 2025): > 我发现了一个类似的未解决的讨论，关于 DeepSeek 的 API 的使用和其思维过程的显示[[1]](https://github.com/langgenius/dify/discussions/13125).这可能与您关于 Dify 是将推理内容传输到模型还是仅将其显示在对话历史记录中的问题相关。 > > 在 Dify 中，用户可以自定义发送到模型的对话历史记录，尤其是在专家模式下。这包括重新排列 和 的放置以及设置必要的参数的能力，从而允许高度自定义的提示设计。但是，在可用文档中找不到控制推理过程是否包含在发送到模型的对话历史记录中的特定配置或设置`Context``History`[[2]](https://github.com/langgenius/dify-docs/blob/main/en/learn-more/prompt-engineering/prompt-engineering-1/README.md)[[3]](https://github.com/langgenius/dify-docs/blob/main/en/guides/application-orchestrate/prompt-engineering/prompt-engineering-expert-mode.md). > > _要继续与 [Dosu](https://dosu.dev) 交谈，请提及 。_ > > 帮助 Dosu 学习！给它反馈：[伟大的回应](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=great_response) |[无关紧要的答案](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=irrelevant_answer) |[不正确的来源](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=incorrect_sources) |[太冗长](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=too_verbose) |[幻觉](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=hallucination) |[其他](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=other) |[Bug 报告](https://app.dosu.dev/response-feedback/93aff41d-e22d-4d31-93d7-738c03bba0d3?feedback_type=bug_report) 我的dify没有专家模式，这可能是由于我的dify版本问题
Sign in to join this conversation.
No Branch/Tag Specified
Branches Tags
Labels
Clear labels
Knowledge Pipeline
Proposal
WIP
cloud
dependencies
feat:webapp
good first issue
outdated
performance
pull-request
Mirrored from GitHub Pull Request
 python:uv
refactor
size:L
stale
status: accepting prs
status: blocked
status: in discussion
stt & tts
vulnerablity
web
wont-fix
🌊 feat:workflow
🌚 invalid
🐞 bug
👻 feat:rag
💪 enhancement
📚 documentation
🔨 feat:tools
🙋‍♂️ question
🙏 help wanted
🤔 cant-reproduce
🤖 feat:agent
No Label 🐞 bug
Milestone
No items
No Milestone
Projects
Clear projects
No project
Assignees
Clear assignees
yindo
No Assignees
1 Participants
Notifications
Due Date
No due date set.
Dependencies

No dependencies set.

Reference: langgenius/dify#8221
Delete Branch "%!s()"

Deleting a branch is permanent. Although the deleted branch may continue to exist for a short time before it actually gets removed, it CANNOT be undone in most cases. Continue?