langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-22 12:36:14 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

Customized Input Field Value Only Updates on Initial Conversation, Subsequent Changes Not Reflected #8059

New Issue
Closed
opened 2026-02-21 18:23:42 -05:00 by yindo · 2 comments
yindo commented 2026-02-21 18:23:42 -05:00
Owner
Copy Link
Copy Source

Originally created by @Halfknow on GitHub (Feb 7, 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

v0.15.2

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

Customized Input Field Value Only Updates on Initial Conversation, Subsequent Changes Not Reflected.

Example

Image

The Input Field model_name can only be set during the initial dialogue exchange. Any subsequent attempts to modify the value do not persist or apply to the following conversations.

✔️ Expected Behavior

The following workflow is the one we set for the deepseek r1 and qwen llm to implement the deep thinking method during the multi-round dialogue. But what we encountered is the input field model_name only works in the first round, so we cannot change the llm during the dialogue.

Image

Example

First Round Q&A
Choose(by model_name): DeepSeek R1
Query: Introduce yourself.
Answer: < think >xxxx < /think >xxxx

Second Round Q&A
Choose(by model_name): Qwen
Query: Introduce yourself.
Answer: < think >xxxx < /think >xxxx

We found the model_name set to Qwen is not worked.

❌ Actual Behavior

We hope the function is like the example below:

Example

Second Round Q&A
Choose(by model_name): Qwen
Query: Introduce yourself.
Answer: xxxx (with no < think > tag)

Originally created by @Halfknow on GitHub (Feb 7, 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 v0.15.2 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce Customized Input Field Value Only Updates on Initial Conversation, Subsequent Changes Not Reflected. ### Example ![Image](https://github.com/user-attachments/assets/55a4f064-2e23-4a11-bc83-8823b7b817af) The Input Field `model_name` can only be set during the initial dialogue exchange. Any subsequent attempts to modify the value do not persist or apply to the following conversations. ### ✔️ Expected Behavior The following workflow is the one we set for the deepseek r1 and qwen llm to implement the deep thinking method during the multi-round dialogue. But what we encountered is the input field `model_name` only works in the first round, so we cannot change the llm during the dialogue. ![Image](https://github.com/user-attachments/assets/c8cf654e-8584-4c50-b605-91cc9bc53036) ### Example First Round Q&A Choose(by `model_name`): DeepSeek R1 Query: Introduce yourself. Answer: < think >xxxx < /think >xxxx Second Round Q&A Choose(by `model_name`): Qwen Query: Introduce yourself. Answer: < think >xxxx < /think >xxxx We found the `model_name` set to Qwen is not worked. ### ❌ Actual Behavior We hope the function is like the example below: ### Example Second Round Q&A Choose(by `model_name`): Qwen Query: Introduce yourself. Answer: xxxx (with no < think > tag)
yindo added the 🐞 bug label 2026-02-21 18:23:42 -05:00
yindo closed this issue 2026-02-21 18:23:42 -05:00
yindo commented 2026-02-21 18:23:42 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Feb 7, 2025):

I found a similar unsolved discussion that might be relevant to your issue: In a multi-round conversation, when using a post request, how can I change the value of the input parameter after the second round? [1].

In the Dify platform, dynamic changes to input parameters during a conversation are managed using conversation variables. These variables allow you to store and reference specific information across multiple rounds within the same session. However, if you're experiencing issues with the model_name input field not updating after the initial conversation, it might be related to how these variables are being managed or updated in your workflow.

Ensure that you are using the conversation_id correctly to maintain the conversation flow. For ongoing conversations, the existing conversation_id should be used, and any new inputs will be ignored, focusing only on the query for the ongoing conversation [2][3]. This might be affecting the ability to change the model_name during the conversation.

Consider reviewing your implementation to ensure that the conversation variables are being updated correctly and that the conversation_id is being used as intended.

To continue talking to Dosu, mention @dosu.

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

@dosubot[bot] commented on GitHub (Feb 7, 2025): <!-- Answer --> I found a similar unsolved discussion that might be relevant to your issue: [In a multi-round conversation, when using a post request, how can I change the value of the input parameter after the second round?](https://github.com/langgenius/dify/discussions/10036) <sup>[[1]](https://github.com/langgenius/dify/discussions/10036)</sup>. In the Dify platform, dynamic changes to input parameters during a conversation are managed using conversation variables. These variables allow you to store and reference specific information across multiple rounds within the same session. However, if you're experiencing issues with the `model_name` input field not updating after the initial conversation, it might be related to how these variables are being managed or updated in your workflow. Ensure that you are using the `conversation_id` correctly to maintain the conversation flow. For ongoing conversations, the existing `conversation_id` should be used, and any new `inputs` will be ignored, focusing only on the `query` for the ongoing conversation <sup>[[2]](https://github.com/langgenius/dify-docs/blob/main/en/guides/application-publishing/developing-with-apis.md)</sup><sup>[[3]](https://github.com/langgenius/dify-docs/blob/main/en/guides/workflow/variables.md)</sup>. This might be affecting the ability to change the `model_name` during the conversation. Consider reviewing your implementation to ensure that the conversation variables are being updated correctly and that the `conversation_id` is being used as intended. <!-- 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/63efa436-8336-4219-8bb0-157b43b2bbcf?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/63efa436-8336-4219-8bb0-157b43b2bbcf?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/63efa436-8336-4219-8bb0-157b43b2bbcf?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/63efa436-8336-4219-8bb0-157b43b2bbcf?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/63efa436-8336-4219-8bb0-157b43b2bbcf?feedback_type=hallucination) | [Other](https://app.dosu.dev/response-feedback/63efa436-8336-4219-8bb0-157b43b2bbcf?feedback_type=other)</sup>
yindo commented 2026-02-21 18:23:43 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Feb 7, 2025):

See https://github.com/langgenius/dify/pull/7955

This is an designed behavior for now, we are still in discussion.

@crazywoola commented on GitHub (Feb 7, 2025): See https://github.com/langgenius/dify/pull/7955 This is an designed behavior for now, we are still in discussion.
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#8059
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?