@Marvin How does prefect 2 handle state transition across subflows in a flow DAG? Do I need a global parameter being passed across subflows? Im talking about a scenario like this where

subflow_b

must run after

subflow_a

and relies on state computations from

subflow_a

@flow(name="Subflow A")
def subflow_a():
    my_a_task()

@flow(name="Subflow B")
def subflow_b():
    my_b_task()

@flow(name="Main Flow")
def parent_flow():
    subflow_a()
    subflow_b()

if __name__ == "__main__":
    parent_flow()

In Prefect 2, you can handle state transitions across subflows in a flow DAG without needing a global parameter. You can pass results from one task or subflow to another within your workflow. This means that

subflow_b

can rely on state computations from

subflow_a

by passing the results as parameters. Here's a modified version of your code to illustrate this:

@flow(name="Subflow A")
def subflow_a():
    return my_a_task()

@flow(name="Subflow B")
def subflow_b(param_from_a):
    return my_b_task(param_from_a)

@flow(name="Main Flow")
def parent_flow():
    result_a = subflow_a()
    subflow_b(result_a)

if __name__ == "__main__":
    parent_flow()

In this example,

subflow_a

returns the result of

my_a_task()

, which is then passed as a parameter to

subflow_b

. Remember, it's recommended to write tasks that do a discrete, specific piece of work in your workflow. The more granular you create your tasks, the easier it is to troubleshoot and parallelize your workflow. For more detailed information, you can refer to the Prefect documentation.