Guardrails

Post Check Endpoint

Check content against guardrails for an application.

The v1 shape: v2-only fields such as streaming_allowed are dropped.

post/v1/check

Request

Request body

application_idstring nullable
check_type'input' | 'output' required

A point in the request lifecycle a guardrail policy can check.

The single registry every check_types key and CheckRequest.check_type must belong to. Adding a checkpoint (tool_input, tool_output, ...) means adding one member here plus its effect-table row, not new branching at each call site.

inputstring required
unreferenced_image_countinteger
if_unconfigured'error' | 'allow'

Response

Successful Response

safeboolean required
action'allow' | 'label' | 'block'

What happens to a message a guardrail flagged.

ALLOW passes it to the model untouched. LABEL passes it together with a notice naming the flagged categories, so the model can decline or answer only the harmless part. BLOCK stops the request before it reaches the model.

evaluatedboolean
configured_checkpointsCheckpoint[] nullable

Changes

No recorded changes to this operation across all 1 revision of this API.