Start a Dag-failure diagnosis run
Starts an asynchronous AI-powered diagnosis run for a failed Dag run (or specific task within it) and returns a run ID. Use the run ID to poll status and stream events.
Authorizations
Bearer authentication header of the form Bearer <token>, where <token> is your auth token.
Path Parameters
The ID of the Organization to which the Deployment belongs.
The Deployment's ID.
Query Parameters
Skip DB session dedup + Redis cache and force a fresh diagnosis run
Body
The request body for starting a Dag-failure diagnosis run.
The ID of the Dag that failed.
"my_dag"
The ID of the Dag run that failed.
"scheduled__2026-05-13T00:00:00+00:00"
If true, bypass any previously cached diagnosis for this Dag/run/task and force a fresh run.
The ID of the task that failed. Optional; if omitted, the agent diagnoses the run as a whole.
"my_task"
The specific task try numbers to diagnose. Optional.
Response
OK
The RFC3339 timestamp when the run was created.
"2026-05-14T12:34:56Z"
The unique identifier of the diagnosis run. Use this to poll status and stream events.
"7f3b6f5d-2c4e-4f2b-9c1d-1a2b3c4d5e6f"
The current status of the diagnosis run.
pending, running, completed, failed, timed_out "pending"