dify icon indicating copy to clipboard operation
dify copied to clipboard

The workflow of Dify may sometimes get stuck at a certain node (remaining in the "running" state).

Open HanXM715 opened this issue 1 year ago • 1 comments

Self Checks

  • [x] This is only for bug report, if you would like to ask a question, please head to Discussions.
  • [x] I have searched for existing issues search for existing 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).
  • [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

0.14.2

Cloud or Self Hosted

Self Hosted (Docker)

Steps to reproduce

The Alibaba Cloud server is deployed with k8s, and the Dify version is 0.14.2. The following is the bug image. Image Image

✔️ Expected Behavior

The workflow can complete the process normally instead of occasionally remaining in the "running" state at a certain node.

❌ Actual Behavior

Occasionally, it gets stuck at a certain point and remains in the "running" state all the time.

HanXM715 avatar Mar 06 '25 03:03 HanXM715

Hello @HanXM715! I'm here to help you with any bugs, questions, or contributions you have for Dify. I'm an expert in solving bugs and answering questions. Let's work together to resolve your issue.

There are similar open issues related to workflows getting stuck in the "running" state in Dify:

  1. One issue suggests that the problem might be due to event handling, parallel node execution, or API events. It recommends checking event handlers, ensuring proper synchronization for parallel nodes, and reviewing logging for insights [1].

  2. Another issue discusses implementing an asynchronous execution mechanism using a queue system and a worker service like Celery to handle tasks independently, which might help in preventing workflows from getting stuck [2].

For your specific case with Dify version 0.14.2, there is a known issue related to workflow execution that might be causing this problem. It involves a DetachedInstanceError in a self-hosted Docker environment, which affects workflow logs and API responses. Upgrading to Dify version 0.15.0 or later is recommended to resolve this issue [3].

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] avatar Mar 06 '25 03:03 dosubot[bot]