shy-refrigerator-15055
11/12/2025, 10:28 AMshy-refrigerator-15055
11/12/2025, 10:28 AMTask is starting. Data missing: Some input datastores are missing. Expected: 5
This is the offending flowspec:
from metaflow import FlowSpec, step
class DatastoreDebug(FlowSpec):
@step
def start(self):
self.next_step = "split_chunks"
self.next(
{
"split_chunks": self.split_chunks,
"aggregate": self.aggregate,
"end": self.end,
},
condition="next_step",
)
@step
def split_chunks(self):
self.grouped_work_list = list(range(3))
self.next(self.process_metrics_chunk, foreach="grouped_work_list")
@step
def process_metrics_chunk(self):
self.test = 123
self.next(self.join_process_metrics_chunk)
@step
def join_process_metrics_chunk(self, inputs):
self.merge_artifacts(inputs, exclude=["test"])
self.next(self.aggregate)
@step
def aggregate(self):
self.test_agg = 123
self.next(self.impacts)
@step
def impacts(self):
self.has_supplychain = True
self.next({True: self.evaluate, False: self.risk}, condition="has_supplychain")
@step
def evaluate(self):
self.next(self.risk)
@step
def risk(self):
self.risk_worklist = [1, 2, 3, 4, 5]
self.next(self.rc, foreach="risk_worklist")
@step
def rc(self):
self.test2 = self.input
self.next(self.jrc)
@step
def jrc(self, inputs):
self.next(self.collect)
@step
def collect(self):
self.next(self.end)
@step
def end(self): ...
if __name__ == "__main__":
DatastoreDebug()
Also note that when the foreach fanout is smaller (e.g. list of length 2), we get a different error:
Task is starting. Data store error: No completed attempts of the task was found for task 'DatastoreDebug/argo-datastoredebug-jkpzq/rc/t-e217a4cf'thankful-ambulance-42457
11/12/2025, 12:00 PMshy-refrigerator-15055
11/12/2025, 12:03 PM2.19.7shy-refrigerator-15055
11/14/2025, 5:47 PMthankful-ambulance-42457
11/14/2025, 6:20 PMshy-refrigerator-15055
11/14/2025, 6:32 PMthankful-ambulance-42457
11/19/2025, 11:39 PM