Why is there a timeout on invididually run long running nodes inside Workflows #4194
bekhruz-ti
started this conversation in
General
Replies: 0 comments
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
-
Reproducing the Issue
On Self Host Docker
Dify Cloud
Note: If the node is executed as part of the entire flow instead of being run individually, the flow will run and not timeout on the tool call.
Expected vs Actual Behavior
After some time, the node execution times out without any output, associated metrics (in case of self hosting), or status update. The node should be allowed to execute until a response is received, and the response should appear along with the associated metrics relating to elapsed time and total tokens.
Question
Why is there a timeout on the execution of individual workflow nodes?
Is this a recommended practice or necessary from the design perspective?
What would happen if this timeout were removed?
Beta Was this translation helpful? Give feedback.
All reactions