workflow_run_replay_all

Tool

workflow_run_replay_all

Re-run every held or failed run of one workflow, oldest first — what an operator reaches for after turning the kill-switch off or granting a tool.

Re-run every held or failed run of one workflow, oldest first — what an operator reaches for after turning the kill-switch off or granting a tool. Runs that cannot be replayed are reported with their reason instead of stopping the rest.

Behavior

HTTP: POST /workflow/runs/replay-all

Arguments

Name	Type	Required	Description
limit	integer	—	How many runs to restart, oldest first; 1-200, defaults to 200.
status	string	•	Which stopped runs to restart. `held` is what a kill-switch or a missing grant left behind.
workflow_id	string	•	No description in the catalog.

Response

Field	Type	Always	Description
refused	array	•
replayed	array	•

Try it

Re-run every held or failed run of one workflow, oldest first — what an operator reaches for after turning the kill-switch off or granting a tool.

When to use

Example

Ask your agent something like this:

Re-run every held or failed run of one workflow, oldest first — what an operator reaches for after turning the kill-switch off or granting a tool.

The agent will invoke workflow_run_replay_all with these arguments:

{
  "status": "<status>",
  "workflow_id": "<workflow_id>"
}