Skip to main content
Automatic intervention lets you define guardrails that fire when training metrics deviate from baselines. You can configure rules for reward spikes, KL divergence explosions, response length surges, and repetition increases. Only running jobs can have their auto-intervention config updated.

Method + Path

Authentication

Include your PIN API token or JWT in the Authorization header as a Bearer token.

Path parameters

string
required
The job identifier (e.g., jb_abc123def456).

GET response

Returns the current auto-intervention configuration for the job inside the standard PIN envelope.
integer
required
0 on success, nonzero on error.
object
required

Example GET response

PUT request body

boolean
required
Turn auto-intervention on or off.
array
required
List of rule objects (see schema above).
integer
required
Minimum seconds between repeated triggers for the same rule (must not be negative).

Request body example

PUT request example

PUT response

Returns the updated configuration inside the standard PIN envelope.
integer
required
0 on success, nonzero on error.
object
required

Example PUT response

Errors