Score and persist a retrieval-benchmark run
Score a golden query set against the caller-supplied retrieval results — per-query recall@k, MRR, and nDCG@k over optional custom k_values — and persist the outcome as a new benchmark run. When regression_thresholds is supplied and a baseline is pinned, the deterministic regression gate also evaluates in the same call, so a single round trip answers both “score this run” and “should this KB reindex or reranker change be blocked”. Owner, admin, and developer roles only; 404 when the agent is unknown.
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.