Route Guardian inference through dedicated endpoints (#40892)
## What changed - Add the opt-in `features.guardianv2.free_guardian` setting to route eligible Guardian reviews to `/guardian` and asynchronous classifications to `/guardian-classifier`. - Support endpoint selection for both HTTP and WebSocket Responses clients, including endpoint-aware connection reuse. - Keep `/responses` for API-key authentication, custom provider URLs, non-Guardian models, and configurations where the option is disabled. - Omit routing hints and `service_tier` from requests sent to the dedicated Guardian endpoints. ## Testing - Cover route selection across authentication modes, provider URLs, HTTP fallback, WebSocket review sessions, and classifier sampling. GitOrigin-RevId: 9c88673c710d009e0239559b9245a4e6c4f4befc
J
jif committed
62fb56ee569e8ed6a9ad7ec575b0e78c25df4b17
Parent: 10d5a60
Committed by copyberry <copyberry@app.openai.com>
on 8/26/2026, 2:36:48 PM