feat: 语音流式输入管线 + VAD前端集成 + 插件-工具合并清理

- 前端: VAD语音检测(@ricky0123/vad-web) + useVoiceInput双模式(流式WS/REST)
- Gateway: VoiceStreamManager代理WS流式STT到voice-service
- Voice-service: DashScope REST → Realtime WS → Whisper三级引擎 + ffmpeg转码
- 共享模块: pkg/audio(音频转换) + pkg/dashscope(ASR REST客户端)
- 清理: 移除旧plugin-manager和pkg/plugins，完成插件→工具合并
- 文档: 完善gateway-api.md和voice-service.md语音API文档
- 工具: scripts/voice/ 语音转换脚本集

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

backend/ai-core/internal/background/thinker.go

@@ -18,8 +18,8 @@ import (
 	"git.yeij.top/AskaEth/Cyrene/ai-core/internal/persona"
 	"git.yeij.top/AskaEth/Cyrene/ai-core/internal/tools"
 
-	plgManager "git.yeij.top/AskaEth/Cyrene/pkg/plugins/manager"
-	plgSDK "git.yeij.top/AskaEth/Cyrene/pkg/plugins/sdk"
+	plgManager "git.yeij.top/AskaEth/Cyrene-Plugins/manager"
+	plgSDK "git.yeij.top/AskaEth/Cyrene-Plugins/sdk"
 )
 
 // PendingThought 待推送的后台思考