-
Notifications
You must be signed in to change notification settings - Fork 878
New issue
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
subflow can't be resume by main flow #1144
Comments
@cjdxhjj we’re working on it, stay tuned! |
thanks @vbarda |
another question, if the subflow occur an error, how can i stop all graph(jump to main workflow end) |
this should happen by default! |
the subflow jump to end just jump to the end of subflow, is there any way jump to main flow end node? for example the remote inteface return a error code not python code throw an error @hwchase17 |
Blocked by the same issue. Is there a workaround to handle interrupt + state updates in sub graphs? |
I also tried the compile the sub graph separately so that I can update it's state. I was able to update the state of the sub graph without any issues but doing this updated the the state of parent graph and set |
hi all -- we've added support for adding subgraph interrupts, resuming the subgraphs from the interrupts and updating the subgraph state. please check out this how-to guide for more information https://langchain-ai.github.io/langgraph/how-tos/subgraphs-manage-state/ |
Checked other resources
Example Code
Error Message and Stack Trace (if applicable)
Description
my sub flow has some human node to collect manual feedback, when i add the message to main flow, the subflow can't resume.
i can't invoke the subflow invoke to resume it because i dosn't know the graph step to which node, if i hava many subflow, i have to
record it interrupt at which node and put every subflow at global variable
System Info
python 3.12 langraph 0.1.14
The text was updated successfully, but these errors were encountered: