Guardrail
import type { Guardrail } from "https://googleapis.deno.dev/v1/ces:v1.ts";Guardrail contains a list of checks and balances to keep the agents safe and secure.
§Properties
Optional. Action to take when the guardrail is triggered.
Optional. Guardrail that potentially blocks the conversation based on the result of the callback execution.
Optional. Guardrail that bans certain content from being used in the conversation.
Etag used to ensure the object hasn't changed during a read-modify-write operation. If the etag is empty, the update will overwrite any concurrent changes.
Optional. Guardrail that blocks the conversation if the LLM response is considered violating the policy based on the LLM classification.
Optional. Guardrail that blocks the conversation if the prompt is considered unsafe based on the LLM classification.
Optional. Guardrail that blocks the conversation if the LLM response is considered unsafe based on the model safety settings.