workflow_run_replay

Tool

Re-run a held or failed run from the step that stopped it, on the run's own version and over its existing trace.

Re-run a held or failed run from the step that stopped it, on the run's own version and over its existing trace. Any other status is refused.

Name	Type	Required	Description
run_id	string	•	No description in the catalog.
reexecute	boolean	—	Re-execute the failed step instead of reusing its result: bumps `replay_generation`, which the action's Idempotency-Key carries. Defaults to false.

Field	Type	Always	Description
id	string	•
test	boolean	•	Started by `workflow_run_test` to watch the workflow work. It executed for real; the flag is what separates it from the Product’s own traffic.
status	string	•
version	number	•
ended_at	string	•
created_at	string	•
started_at	string	•
held_reason	string	—	Structured `{ code, tool\|name, hint }` while `status` is `held`; null otherwise.
subject_key	string	•	Who this run is about, rendered once from the definition’s `subject` at run start and frozen. Null when the workflow declares no subject.
workflow_id	string	•
trigger_event_id	string	•
replay_generation	number	•

Re-run a held or failed run from the step that stopped it, on the run's own version and over its existing trace.

When to use

Re-run a held or failed run from the step that stopped it, on the run's own version and over its existing trace. Any other status is refused.

Ask your agent something like this:

Re-run a held or failed run from the step that stopped it, on the run's own version and over its existing trace.

The agent will invoke workflow_run_replay with these arguments:

{
  "run_id": "<run_id>"
}