fix(voice): update Qwen Realtime model, voice, and endpoint for intl service

Live-tested against DashScope international API:
- Model: qwen3-omni-flash-realtime → qwen3.5-omni-flash-realtime
  (previous model ID did not exist on DashScope)
- Default voice: Cherry → Tina
  (confirmed from session.created response on qwen3.5-omni-flash-realtime)
- Default WS base: dashscope.aliyuncs.com → dashscope-intl.aliyuncs.com
  (international accounts use the -intl endpoint; China endpoint rejects
  international API keys; QWEN_REALTIME_WS_URL env var still overrides)

Author: heavygee

hub/src/web/server.ts

@@ -123,7 +123,7 @@ function createGeminiProxyWebSocketHandler() {
 
 // Qwen Realtime WebSocket proxy — bridges browser (no custom headers) to DashScope (requires Authorization header)
 function createQwenProxyWebSocketHandler() {
-    const QWEN_WS_BASE = 'wss://dashscope.aliyuncs.com/api-ws/v1/realtime'
+    const QWEN_WS_BASE = 'wss://dashscope-intl.aliyuncs.com/api-ws/v1/realtime'
     const upstreamMap = new WeakMap<ServerWebSocket<unknown>, WebSocket>()
     // Holds the hub-owned session.update payload until session.created arrives from DashScope.
     // Sending session.update before session.created violates the Qwen Realtime protocol ordering.

shared/src/voice.ts

@@ -289,8 +289,8 @@ export function buildVoiceAgentConfig(): VoiceAgentConfig {
 
 export type VoiceBackendType = 'elevenlabs' | 'gemini-live' | 'qwen-realtime'
 
-export const QWEN_REALTIME_MODEL = 'qwen3-omni-flash-realtime'
-export const QWEN_REALTIME_VOICE = 'Cherry'
+export const QWEN_REALTIME_MODEL = 'qwen3.5-omni-flash-realtime'
+export const QWEN_REALTIME_VOICE = 'Tina'
 
 export const DEFAULT_VOICE_BACKEND: VoiceBackendType = 'elevenlabs'