Skip to main content
Automatic intervention defines guardrails that fire when training metrics deviate from baselines. Configure rules for reward spikes, KL divergence explosions, response length surges, and repetition increases. Only running jobs accept auto-intervention updates. This path has no GET, so read the current config from the job payload (auto_intervention).

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).

Request body

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

Request body example

Request example

Response

Returns 202 with the updated configuration inside the standard PIN envelope.
integer
required
0 on success, nonzero on error.
object
required

Example response

Errors