Skip to main content
The kill switch is an org-scoped emergency stop. Killing an agent, run, or mission causes the SDK’s pre-execution check to refuse all further @guarded_action calls for that target until it is revived.

Endpoints

All endpoints live under /api/v1/kill-switch and require either a session cookie (Clerk) or an API key (Authorization: Bearer ...).

Kill a target

Returns the full KillSwitchPublic record. Returns 409 Conflict if the target is already killed.

Revive a target

Returns 404 Not Found if there is no active kill switch for the target.

Check kill status (SDK)

The SDK calls this before each guarded action executes. Response:

List active kill switches

Returns all currently-active kill switches for the caller’s organization, ordered by killed_at descending.

SDK behaviour

When the SDK’s pre-action check returns is_killed: true, the next @guarded_action raises PolicyViolationError with a kill-switch reason — the action body never runs. All blocked attempts are recorded as HARD_BLOCK interventions referencing the killing user.

Console

The console exposes /kill-switch as a top-level route — see Console → Kill Switch.

See also