fix: resolve architecture disconnects and codebase weaknesses

- Add TEXT_CHANNEL_ID and TEXT_GUILD_ID to config schema (fix silent channel monitoring)
- Remove dead files: message-capture/broadcaster.ts, voice-recording/index.ts
- Fix WebSocket voice_command payload to forward from frontend
- Implement moderation:action handler in commandHandler
- Fix useMascotChat to use canonical request() wrapper
- Fix useAudioPlayback userId hash collision (use string not parseInt)
- Add catch blocks to useMediaControl.skip/stop
- Add typed broadcast functions (messageAnalyzed, voicePcmData, voiceActiveUser)
- Apply Biome formatting and lint fixes

Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>

services/frontend/src/shared/hooks/useAudioPlayback.ts

@@ -10,7 +10,7 @@ export function useAudioPlayback() {
     Array.from({ length: 32 }, () => 0.04),
   );
   const audioContextRef = useRef<AudioContext | null>(null);
-  const userTimelinesRef = useRef(new Map<number, number>());
+  const userTimelinesRef = useRef(new Map<string, number>());
 
   const handleIncomingPcm = useCallback(
     (data: { userId: string; pcm: string }) => {
@@ -57,13 +57,12 @@ export function useAudioPlayback() {
       source.connect(audioContext.destination);
 
       // Schedule playback per user to avoid overlaps
-      const userIdHash = parseInt(data.userId, 10);
       const currentTime = audioContext.currentTime;
-      let nextStart = userTimelinesRef.current.get(userIdHash) || 0;
+      let nextStart = userTimelinesRef.current.get(data.userId) || 0;
       if (nextStart < currentTime) nextStart = currentTime + 0.05;
       source.start(nextStart);
       userTimelinesRef.current.set(
-        userIdHash,
+        data.userId,
         nextStart + audioBuffer.duration,
       );
     },