A valid request URL is required to generate request examples{
"runId": "<string>",
"agentRunId": "<string>",
"state": "queued",
"maxSteps": 123,
"deadlineAt": "<string>",
"executor": "phoneuse",
"vrxBaseUrl": "<string>"
}{
"error": {
"code": "backend_resolution_failed",
"message": "<string>",
"retryable": true
}
}{
"error": {
"code": "unauthorized",
"reason": "missing_credentials",
"hint": "<string>"
}
}{
"error": {
"code": "backend_resolution_failed",
"message": "<string>",
"retryable": true
}
}{
"error": {
"code": "backend_resolution_failed",
"message": "<string>",
"retryable": true
}
}{
"error": {
"code": "backend_resolution_failed",
"message": "<string>",
"retryable": true
}
}{
"error": {
"code": "payload_too_large",
"message": "<string>"
}
}{
"error": {
"code": "rate_limited",
"message": "<string>"
}
}{
"error": {
"code": "backend_resolution_failed",
"message": "<string>",
"retryable": true
}
}{
"error": {
"code": "backend_resolution_failed",
"message": "<string>",
"retryable": true
}
}Start a run on a device
Hand one device your organisation holds to a run with a goal and a budget. Your organisation must already hold it: starting a run is permission to let a loop act for you, not permission to take the device, and this route is the one place that difference is visible (a gesture DOES take).
executor says who drives it. phoneuse runs it for you and returns no url. self_hosted means your own worker drives it, and the response then carries the run scoped device surface url exactly once: treat it as a credential and give it to one worker only. Left out, it is self_hosted for an API key and phoneuse for a signed-in person. Your credential needs both runs:start and devices:act.
A valid request URL is required to generate request examples{
"runId": "<string>",
"agentRunId": "<string>",
"state": "queued",
"maxSteps": 123,
"deadlineAt": "<string>",
"executor": "phoneuse",
"vrxBaseUrl": "<string>"
}{
"error": {
"code": "backend_resolution_failed",
"message": "<string>",
"retryable": true
}
}{
"error": {
"code": "unauthorized",
"reason": "missing_credentials",
"hint": "<string>"
}
}{
"error": {
"code": "backend_resolution_failed",
"message": "<string>",
"retryable": true
}
}{
"error": {
"code": "backend_resolution_failed",
"message": "<string>",
"retryable": true
}
}{
"error": {
"code": "backend_resolution_failed",
"message": "<string>",
"retryable": true
}
}{
"error": {
"code": "payload_too_large",
"message": "<string>"
}
}{
"error": {
"code": "rate_limited",
"message": "<string>"
}
}{
"error": {
"code": "backend_resolution_failed",
"message": "<string>",
"retryable": true
}
}{
"error": {
"code": "backend_resolution_failed",
"message": "<string>",
"retryable": true
}
}Authorizations
The control surface credential. Send Authorization: Bearer <token>.
Two kinds of token are accepted and they are told apart by shape, not by a separate header. A token beginning pbk_ or puk_ is an org scoped API key, whose public half and secret half are generated together and of which only a hash of the secret is ever stored; anything else is treated as an OAuth 2.1 access token and verified against the authorization server's keys.
Both resolve to the same context: an org, a principal and a set of scopes. Nothing downstream branches on which channel you used, with one deliberate exception, key management, which requires a signed-in person so that a key can never mint another key.
Scopes are enforced when MCP tools are REGISTERED rather than when they are called, so a tool your credential cannot use is absent from tools/list rather than refused mid gesture.
Body
The device, the goal, and optional budget ceilings.
Ceiling on metered steps. A value above the deployment's own limit is capped to that limit, not refused: the limit is deployment configuration rather than a published number, so it cannot be asked for exactly. Read the run's maxSteps for the effective ceiling. A value of the wrong type is refused.
x >= 1Response
The run started.