langgenius/dify
1
0
Fork 0
mirror of https://github.com/langgenius/dify.git synced 2026-07-21 03:55:25 -04:00
Code Issues 775 Packages Projects Releases 10 Wiki Activity

Use Agent API to generate answer but agent reply nothing in Logs & Annotations of Front-end interface #7612

New Issue
Closed
opened 2026-02-21 18:21:29 -05:00 by yindo · 4 comments
yindo commented 2026-02-21 18:21:29 -05:00
Owner
Copy Link
Copy Source

Originally created by @lzhdjb on GitHub (Jan 9, 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

version 0.13.2

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

We are trying to use agent to generate answer about whether the given log data is anomaly.
We build the agent with some input variables and two core workflow tool. In our task, we need to give all the information of log as input and the query to the agent. Agent first use the tool "log_decoder" to deal with the data , then use the tool "log_classifier" to abtain the final label answer.
agent编排
However, when we use api to get the answer of some log in Python environment, the response = requests.post(url, headers=headers,json=json_data)get the response.textof following:
response
We put together all the answer of the agent_message event and get the final answer:
answer
Notice in the response.text, except for the beginning <agent_thought> and the end <message_end> there are only <agent_message> events.
We then check the Logs & Annotations of Front-end interface. It seems the agent didn't answer correctly and reply nothing in this interface.
日志与标注

✔️ Expected Behavior

We alse get some correct replies
correct日志

❌ Actual Behavior

We don't expect the agent didn't reply anything and unable to call the tool correctly
日志与标注

Originally created by @lzhdjb on GitHub (Jan 9, 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 version 0.13.2 ### Cloud or Self Hosted Self Hosted (Docker) ### Steps to reproduce We are trying to use agent to generate answer about whether the given log data is anomaly. We build the agent with some input variables and two core workflow tool. In our task, we need to give all the information of log as input and the query to the agent. Agent first use the tool "log_decoder" to deal with the data , then use the tool "log_classifier" to abtain the final label answer. <img width="1146" alt="agent编排" src="https://github.com/user-attachments/assets/0aa6b406-ef6a-4653-8897-e037f2c54bcc" /> However, when we use api to get the answer of some log in Python environment, the response = requests.post(url, headers=headers,json=json_data)get the response.textof following: <img width="994" alt="response" src="https://github.com/user-attachments/assets/81e74082-495b-4603-b434-99a095580c05" /> We put together all the answer of the agent_message event and get the final answer: <img width="1055" alt="answer" src="https://github.com/user-attachments/assets/d1f4b639-30b1-45ea-8db6-5f6cac9a5b20" /> Notice in the response.text, except for the beginning <agent_thought> and the end <message_end> there are only <agent_message> events. We then check the Logs & Annotations of Front-end interface. It seems the agent didn't answer correctly and reply nothing in this interface. <img width="1154" alt="日志与标注" src="https://github.com/user-attachments/assets/94bed6da-5db5-4c75-bc51-6b65e4133efd" /> ### ✔️ Expected Behavior We alse get some correct replies <img width="1127" alt="correct日志" src="https://github.com/user-attachments/assets/5aef4808-4b16-4d41-86b7-d571e46bf8f5" /> ### ❌ Actual Behavior We don't expect the agent didn't reply anything and unable to call the tool correctly <img width="1154" alt="日志与标注" src="https://github.com/user-attachments/assets/dc40db11-eaed-47c3-ae3c-305ae6cd0cfb" />
yindo added the 🐞 bug label 2026-02-21 18:21:29 -05:00
yindo closed this issue 2026-02-21 18:21:29 -05:00
yindo commented 2026-02-21 18:21:29 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Jan 9, 2025):

Hey @lzhdjb! I'm here to help you with any bugs, questions, or contributions. Let's work together to resolve this issue.

I found a similar unsolved discussion titled "Help：Agent NEVER get any result from workflow tool" which might be related to your issue [1].

To troubleshoot the issue where the agent does not produce any output in the Logs & Annotations interface, you can follow these steps:

  1. Check for System Errors: Ensure there are no system errors such as a disabled sandbox service or network connection issues. Verify the network service quality and start the sandbox service if necessary.

  2. Review Code Node Errors: If using a Code Node, check for runtime errors like missing variables or incorrect input types. Use error messages to locate and fix issues.

  3. Validate Output Types: Ensure the output variable type matches the expected type to avoid validation errors.

  4. Inspect LLM Node Errors: Check for errors such as Variable Not Found, Invalid Context Structure, or Model Not Exist. Ensure all necessary variables and models are correctly configured.

  5. Check HTTP Node Errors: Verify that authorization is configured, the HTTP method is valid, and the response size is within limits.

  6. Examine Tool Node Errors: Ensure tool node parameters are valid and required files are accessible.

  7. Use Debugging Mode: Utilize the debugging mode in Dify Workflow by clicking "Preview" for conversational applications or "Run" for workflow applications. This mode helps identify and resolve issues effectively [2][3].

These steps should help you identify and resolve the issue with the agent not producing output.

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 (Jan 9, 2025): <!-- Greeting --> Hey @lzhdjb! I'm here to help you with any bugs, questions, or contributions. Let's work together to resolve this issue. <!-- Answer --> I found a similar unsolved discussion titled "[Help：Agent NEVER get any result from workflow tool](https://github.com/langgenius/dify/discussions/12107)" which might be related to your issue <sup>[[1]](https://github.com/langgenius/dify/discussions/12107)</sup>. To troubleshoot the issue where the agent does not produce any output in the Logs & Annotations interface, you can follow these steps: 1. **Check for System Errors**: Ensure there are no system errors such as a disabled sandbox service or network connection issues. Verify the network service quality and start the sandbox service if necessary. 2. **Review Code Node Errors**: If using a Code Node, check for runtime errors like missing variables or incorrect input types. Use error messages to locate and fix issues. 3. **Validate Output Types**: Ensure the output variable type matches the expected type to avoid validation errors. 4. **Inspect LLM Node Errors**: Check for errors such as Variable Not Found, Invalid Context Structure, or Model Not Exist. Ensure all necessary variables and models are correctly configured. 5. **Check HTTP Node Errors**: Verify that authorization is configured, the HTTP method is valid, and the response size is within limits. 6. **Examine Tool Node Errors**: Ensure tool node parameters are valid and required files are accessible. 7. **Use Debugging Mode**: Utilize the debugging mode in Dify Workflow by clicking "Preview" for conversational applications or "Run" for workflow applications. This mode helps identify and resolve issues effectively <sup>[[2]](https://github.com/langgenius/dify-docs/blob/main/en/guides/workflow/error-handling/error-type.md)</sup><sup>[[3]](https://github.com/langgenius/dify-docs/blob/main/en/guides/workflow/debug-and-preview/yu-lan-yu-yun-hang.md)</sup>. These steps should help you identify and resolve the issue with the agent not producing output. <!-- 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/48567603-c8bb-4621-b4cd-6f8a867d3314?feedback_type=great_response) | [Irrelevant Answer](https://app.dosu.dev/response-feedback/48567603-c8bb-4621-b4cd-6f8a867d3314?feedback_type=irrelevant_answer) | [Incorrect Sources](https://app.dosu.dev/response-feedback/48567603-c8bb-4621-b4cd-6f8a867d3314?feedback_type=incorrect_sources) | [Too Verbose](https://app.dosu.dev/response-feedback/48567603-c8bb-4621-b4cd-6f8a867d3314?feedback_type=too_verbose) | [Hallucination](https://app.dosu.dev/response-feedback/48567603-c8bb-4621-b4cd-6f8a867d3314?feedback_type=hallucination) | [Other](https://app.dosu.dev/response-feedback/48567603-c8bb-4621-b4cd-6f8a867d3314?feedback_type=other)</sup>
yindo commented 2026-02-21 18:21:29 -05:00
Author
Owner
Copy Link
Copy Source

@lzhdjb commented on GitHub (Jan 9, 2025):

Supplement the Agent Log in the Front-end
agent日志
agent日志1

@lzhdjb commented on GitHub (Jan 9, 2025): Supplement the Agent Log in the Front-end <img width="283" alt="agent日志" src="https://github.com/user-attachments/assets/d1215cfc-2984-451c-873f-5511293135c6" /> <img width="270" alt="agent日志1" src="https://github.com/user-attachments/assets/815c7d46-b640-46a9-b9cc-61ee9548b464" />
yindo commented 2026-02-21 18:21:29 -05:00
Author
Owner
Copy Link
Copy Source

@crazywoola commented on GitHub (Jan 9, 2025):

It seems there is no input or output in the LLM node. I think that's why it showed nothing.

@crazywoola commented on GitHub (Jan 9, 2025): It seems there is no input or output in the LLM node. I think that's why it showed nothing.
yindo commented 2026-02-21 18:21:29 -05:00
Author
Owner
Copy Link
Copy Source

@dosubot[bot] commented on GitHub (Feb 9, 2025):

Hi, @lzhdjb. I'm Dosu, and I'm helping the Dify team manage their backlog. I'm marking this issue as stale.

Issue Summary

  • You reported an issue with an agent not producing output in the Logs & Annotations section on a self-hosted environment using version 0.13.2.
  • I suggested troubleshooting steps, including checking for system errors and validating output types.
  • User crazywoola noted the issue might be due to the absence of input or output in the LLM node, which could explain the lack of output.

Next Steps

  • Please confirm if this issue is still relevant to the latest version of the Dify repository. If so, you can keep the discussion open by commenting on the issue.
  • Otherwise, the issue will be automatically closed in 15 days.

Thank you for your understanding and contribution!

@dosubot[bot] commented on GitHub (Feb 9, 2025): Hi, @lzhdjb. I'm [Dosu](https://dosu.dev), and I'm helping the Dify team manage their backlog. I'm marking this issue as stale. **Issue Summary** - You reported an issue with an agent not producing output in the Logs & Annotations section on a self-hosted environment using version 0.13.2. - I suggested troubleshooting steps, including checking for system errors and validating output types. - User crazywoola noted the issue might be due to the absence of input or output in the LLM node, which could explain the lack of output. **Next Steps** - Please confirm if this issue is still relevant to the latest version of the Dify repository. If so, you can keep the discussion open by commenting on the issue. - Otherwise, the issue will be automatically closed in 15 days. Thank you for your understanding and contribution!
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#7612
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?