langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-22 20:45:26 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

How to reply to a conversation about the results of an Agent strategy #11862

New Issue
Closed
opened 2026-02-21 19:04:26 -05:00 by yindo · 1 comment
yindo commented 2026-02-21 19:04:26 -05:00
Owner
Copy Link
Copy Source

Originally created by @HZJprince on GitHub (Mar 20, 2025).

Self Checks

  • 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.

Content

As shown in the figure, I use agent policy in workflow to get the result successfully, but it doesn't reply the result to the conversation normally, how to configure to realize this?
image

Originally posted by @HZJprince in https://github.com/langgenius/dify/discussions/16323

Originally created by @HZJprince on GitHub (Mar 20, 2025). ### Self Checks - [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. ### Content As shown in the figure, I use agent policy in workflow to get the result successfully, but it doesn't reply the result to the conversation normally, how to configure to realize this? ![image](https://github.com/user-attachments/assets/754c3c67-68fd-4a97-b6c0-dc9b7569698e) _Originally posted by @HZJprince in https://github.com/langgenius/dify/discussions/16323_
yindo added the 🙋‍♂️ question label 2026-02-21 19:04:26 -05:00
yindo closed this issue 2026-02-21 19:04:26 -05:00
yindo commented 2026-02-21 19:04:26 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Mar 20, 2025):

I couldn't find specific information on configuring the output of an agent's action to be sent back to the conversation in Dify. However, I found a related discussion about an agent not getting results from a workflow tool, which might provide some insights. You can check the discussion here [1].

For handling JSON-like responses, Dify uses a method called _fetch_jinja_inputs to parse and process these structures. Ensure that the variables are correctly fetched and parsed using this method by setting up the jinja2_variables in the prompt_config of the LLMNodeData to specify which variables should be processed as JSON-like structures [2].

If you need further assistance, reviewing the workflow configuration and ensuring that the output variables are correctly defined might help.

To continue talking to Dosu, mention @dosu.

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

@dosubot[bot] commented on GitHub (Mar 20, 2025): <!-- Answer --> I couldn't find specific information on configuring the output of an agent's action to be sent back to the conversation in Dify. However, I found a related discussion about an agent not getting results from a workflow tool, which might provide some insights. You can check the discussion [here](https://github.com/langgenius/dify/discussions/12107) <sup>[[1]](https://github.com/langgenius/dify/discussions/12107)</sup>. For handling JSON-like responses, Dify uses a method called `_fetch_jinja_inputs` to parse and process these structures. Ensure that the variables are correctly fetched and parsed using this method by setting up the `jinja2_variables` in the `prompt_config` of the `LLMNodeData` to specify which variables should be processed as JSON-like structures <sup>[[2]](https://github.com/langgenius/dify/blob/ed5596a8f45a5669fc7e63d7db443db7962cfead/api/core/workflow/nodes/llm/node.py)</sup>. If you need further assistance, reviewing the workflow configuration and ensuring that the output variables are correctly defined might help. <!-- 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/c2e3c689-9f37-4e51-89fe-6531fd3bf1e1?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/c2e3c689-9f37-4e51-89fe-6531fd3bf1e1?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/c2e3c689-9f37-4e51-89fe-6531fd3bf1e1?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/c2e3c689-9f37-4e51-89fe-6531fd3bf1e1?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/c2e3c689-9f37-4e51-89fe-6531fd3bf1e1?feedback_type=hallucination) | [Bug Report](https://app.dosu.dev/response-feedback/c2e3c689-9f37-4e51-89fe-6531fd3bf1e1?feedback_type=bug_report) | [Other](https://app.dosu.dev/response-feedback/c2e3c689-9f37-4e51-89fe-6531fd3bf1e1?feedback_type=other)</sup>
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 🙋‍♂️ question
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#11862
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?