Apply a guardrail policy to an agent
Apply a named policy from the guardrail-policy library (GET /agents/guardrail-policies) to one agent: merges the policy’s safety_config patch onto the agent’s existing safety settings (preserving per-agent keys the policy does not govern), optionally sets its per-conversation cost cap, and stamps config.guardrails.applied_policy = { id, name, version, applied_at } so the agent records its source policy. Body: { policy_id }. 404 when the policy id or the agent is unknown. Owner, admin, or developer role; tightly rate-limited because it mutates agent config and writes an audit log row.
Authorizations
Dashboard JWT token from Clerk
Headers
Stripe-style idempotency token. Pass a stable, client-generated value (1-255 chars) to dedupe retries on transient timeouts. The same key+credential+path replays the original response for 24h on 2xx (5min on 4xx, 30s on 5xx). Returns 409 if a concurrent request with the same key is already in flight; replayed responses include the Idempotency-Replay: true response header.
1 - 255Sandbox opt-in for Clerk-session-authenticated requests. Set to true to route the call through the test-mode pipeline: no real provider delivery, no credits deducted, response meta.test_mode: true. Ignored for live API keys (dv_live_sk_*) — server-to-server clients must use a test-prefixed key (dv_test_sk_*) to exercise sandbox. Test-prefixed keys unconditionally enable sandbox regardless of this header.
true, false Path Parameters
Response
Successful response.