Run a multi-turn dry-run scenario
Replay a scripted scenario against the agent in sandbox mode: the LLM call is real, but mutative tool side effects (calendar bookings, handoffs, memory writes) are short-circuited and billing is skipped, ending with a pass/fail verdict across the turn-by-turn trace and assertion results. The scenario.turns[] array supplies scripted user messages; optional assertions expected_tool_calls (every named tool must appear), must_contain / must_not_contain (transcript substring checks), plus LangSmith-style trajectory grading. Max 20 turns per scenario, 30s per turn. Matches the dashboard Practice Studio contract.
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
The agent id.
1