Compare a shadow agent against its production agent
Return the recent (production vs shadow) response pairs the runtime logged while this agent was wired as a shadow of a production agent, sorted newest first. Use it for the side-by-side comparison panel: each row carries the user message, both responses, a token-similarity agreement score, and per-pair token/cost figures, plus a summary with exact-match percentage, average agreement, and aggregate cost/token economics (advisory — shadow runs are sandboxed and never billed). Query params: days (1–90, default 7) and limit (1–200, default 50). Responds 404 when the agent does not exist. Owner, admin, or developer role required (rows contain end-user chat transcripts).
Authorizations
Dashboard JWT token from Clerk
Headers
Sandbox 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.