Remote subgraph fails to resume from checkpoint after interrupt node #4088
Unanswered
Aniruddha521
asked this question in
Q&A
Replies: 3 comments
-
I have same isssue. do you have the answer yet? |
Beta Was this translation helpful? Give feedback.
0 replies
-
No, I too won't able to solve this yet. |
Beta Was this translation helpful? Give feedback.
0 replies
-
I have created an issue about this, you can go there to discuss further. |
Beta Was this translation helpful? Give feedback.
0 replies
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Uh oh!
There was an error while loading. Please reload this page.
-
I'm encountering an issue with an orchestrator graph that integrates a remote subgraph for handling outbound agent tasks. The graph leverages a remote execution node (via RemoteGraph) along with a checkpointer (MemorySaver) to persist state. When an interrupt node is triggered within the remote subgraph, instead of resuming from the last checkpoint (i.e., from the same node where the interruption occurred), the remote subgraph restarts from the beginning.
I have confirmed that when remote graphs are run independently, they resume correctly from the exact node at which they were interrupted. However, when this remote graph is integrated as a subgraph within the orchestrator, the resume functionality fails to behave as expected. The error messages indicate that the subgraph is not recognized during the resume operation.
Has anyone experienced similar behavior or have any insights on ensuring that remote subgraphs properly resume from their saved state after an interruption within an orchestrator? Any guidance or workaround would be greatly appreciated.
Beta Was this translation helpful? Give feedback.
All reactions