dosubot[bot]
commented
3 weeks ago @hurrykee Hello there! I'm Dosu, a bot here to help you with bug solving, answering questions, and becoming a contributor. I'm here to assist you while you wait for a human maintainer.
To ensure that the workflow task execution status is updated to paused, error, or timeout if the network is interrupted during an API call, you can handle exceptions and update the status accordingly. The current implementation already includes methods for handling different statuses, such as _workflow_node_execution_failed for failed executions.
Here is an example of how you can modify the code to handle network interruptions and update the status:
import requests
from requests.exceptions import RequestException
def _make_api_call(self, url: str, payload: dict) -> dict:
try:
response = requests.post(url, json=payload)
response.raise_for_status()
return response.json()
except RequestException as e:
self._handle_network_interruption(str(e))
raise
def _handle_network_interruption(self, error: str):
task_id = self._task_state.task_id
workflow_node_execution = self._get_current_workflow_node_execution()
if workflow_node_execution:
self._workflow_node_execution_failed(
workflow_node_execution=workflow_node_execution,
start_at=self._task_state.latest_node_execution_info.start_at,
error=error
)
def _get_current_workflow_node_execution(self) -> Optional[WorkflowNodeExecution]:
if not self._task_state.latest_node_execution_info:
return None
return db.session.query(WorkflowNodeExecution).filter(
WorkflowNodeExecution.id == self._task_state.latest_node_execution_info.workflow_node_execution_id
).first()
def _workflow_node_execution_failed(self, workflow_node_execution: WorkflowNodeExecution,
start_at: float, error: str) -> WorkflowNodeExecution:
workflow_node_execution.status = WorkflowNodeExecutionStatus.FAILED.value
workflow_node_execution.error = error
workflow_node_execution.elapsed_time = time.perf_counter() - start_at
workflow_node_execution.finished_at = datetime.now(timezone.utc).replace(tzinfo=None)
db.session.commit()
db.session.refresh(workflow_node_execution)
db.session.close()
return workflow_node_executionIn this example, _make_api_call is a method that makes the API call and handles any network-related exceptions. If a network interruption occurs, it calls _handle_network_interruption, which in turn calls _workflow_node_execution_failed to update the status to FAILED. The _get_current_workflow_node_execution method retrieves the current workflow node execution from the database.
Additionally, the Result component in the Dify platform's codebase shows how the workflow handles various states, including network interruptions. The sendWorkflowMessage function includes callbacks like onWorkflowFinished and onError to handle the completion and error states, respectively. If a network interruption occurs, the onError callback is triggered, which stops the response and marks the workflow as failed.
sendWorkflowMessage(
data,
{
onWorkflowFinished: ({ data }) => {
if (data.error) {
notify({ type: 'error', message: data.error })
setWorkflowProccessData(produce(getWorkflowProccessData()!, (draft) => {
draft.status = WorkflowRunningStatus.Failed
}))
setRespondingFalse()
onCompleted(getCompletionRes(), taskId, false)
isEnd = true
return
}
// Handle success case
},
onError() {
setRespondingFalse()
onCompleted(getCompletionRes(), taskId, false)
isEnd = true
},
},
isInstalledApp,
installedAppInfo?.id,
)These mechanisms ensure that the workflow task status is updated appropriately even in the case of network disconnections or other interruptions [1][2][3].
To continue talking to Dosu, mention @dosu.
hurrykee
crazywoola
Self Checks
Dify version
0.7.3
Cloud or Self Hosted
Cloud
Steps to reproduce
Using Postman to call the workflow API, if the local network is disconnected during the running process, and then retrieving the current execution result based on the workflow execution ID, the workflow status will remain in the running state indefinitely.
✔️ Expected Behavior
My expected outcome is that as long as the workflow task is created, the server will complete the task execution, and the execution results can still be retrieved later using the workflow execution ID. Alternatively, if the request is disconnected on the frontend for any reason, the workflow task status will be updated to paused, error, or timeout.
❌ Actual Behavior
If the workflow cannot remain running on the server until completion, it would be better to update the status to timeout, paused, or error. This would facilitate batch management of workflow tasks.