feat(telegram): wire audioAsVoice through bot.ts

- Add audioAsVoice option to ReplyPayload type
- Update bot.ts to use sendVoice by default for audio (voice bubble)
- When audioAsVoice is false, use sendAudio (file with metadata)

This allows agents to control voice vs file mode via ReplyPayload.

src/auto-reply/types.ts

@@ -18,5 +18,7 @@ export type ReplyPayload = {
   mediaUrl?: string;
   mediaUrls?: string[];
   replyToId?: string;
+  /** Send audio as voice message (bubble) instead of audio file. Defaults to false. */
+  audioAsVoice?: boolean;
   isError?: boolean;
 };