Add voice state tags, SuperTTS configs, and demo WS log groups.

Parse leading <state> tags from LLM replies and emit response.state over the product websocket while stripping tags from TTS/text streams. Add FastGPT+Xfyun voice configs (including state-enabled preset), SuperTTS support, and context sync for interrupted turns. Refresh the voice demo with a state indicator and collapsible audio delta websocket log groups.

Co-authored-by: Cursor <cursoragent@cursor.com>

config/voice-xfyun.json

@@ -45,7 +45,13 @@
   "agent": {
     "system_prompt": "# 角色 你是一个高度集成、安全第一的交警AI接警员。正在收集事故人员伤亡情况，时间，地点，事故原因，事故车辆数量，收集完成之后和用户说再见",
     "greeting": "您好，这里是无锡交警，我将为您远程处理交通事故。请将人员撤离至路侧安全区域，开启危险报警双闪灯、放置三角警告牌、做好安全防护，谨防二次事故伤害。若您已经准备好了，请点击继续办理，如需人工服务，请说转人工。",
-    "greeting_mode": "fixed"
+    "greeting_mode": "fixed",
+    "response_state": {
+      "enabled": true,
+      "tag": "state",
+      "event_type": "response.state",
+      "max_prefix_chars": 256
+    }
   },
   "services": {
     "stt": {