Model parameter now included on gateway WebSocket URLs

Patch Changes

• fix(openai): include ?model= on Responses-API and realtime STT WebSocket URLs - #1467 (@enriqueespaillat-gyde)

  OpenAI-compatible gateways (LiteLLM, Cloudflare AI Gateway, Helicone, Portkey, etc.) can only see the URL at the WebSocket upgrade — they cannot read the subsequent session.update / response.create frame to determine which backend to dial. The realtime/realtime_model.ts conversational endpoint already includes the model in the upgrade URL; this aligns the Responses-API LLM and realtime STT paths with the same convention. OpenAI's native endpoints accept and ignore the parameter, so this is a no-op for direct connections.

• Updated dependencies [cdcb4ba17a61981292c9b8e816bc624e7064f6af, 10236d90533600f5eee65c40792499d937cb48ba, 26716df780ee8334dd4975add698e4c562bdc9d6, a379a2ad67b9af06c2943d191173184c009f6ad1, 63d1c7e88bc542223e4386585ac14efa94903992, 60ddb656072ab34ec5dad8274e8f9bf96ff37c8e, b7fdbe1f93b9551406c754cfb1f3273cf97efbcc, 213385270e23d70b97d330be87fa30c3eb5d92d1, a8361c16c595226815e64293796544a23a35d14d, 01da76ac68fe82f81442247d7c6a088edda78505, abb23c88e9e597d4047324c0af9295ada2fb03c9, a48c822fbdbc39b403966f80f23207e57a542e91, 6402cbc91741fb0c4808d81e82f51f8f6b46780e]:

  • @livekit/agents@1.4.3