fix(voice): restore voice features and apply critical optimizations

Voice Feature Restoration:
- Implemented full Redis pub/sub pipeline for real-time voice data
- Added VOICE_PCM and VOICE_ACTIVE_USER Redis channels
- Implemented EventBroadcaster.voicePcmData() and voiceActiveUser() methods
- Extended backend redis-bridge to subscribe to voice channels
- Updated backend WebSocket server for binary PCM broadcast
- Replaced globalThis PcmBroadcaster pattern with proper EventBroadcaster DI
- Fixed root cause: PcmBroadcaster functions were never initialized

Bug Fixes:
- Fixed prism-media version conflict (2.0.0-alpha.0 → 1.3.5)
- Fixed type inconsistency in commandHandler.ts (AudioPlayerStatus → string)

Critical Optimizations:
- P1.1: Fixed unbounded memory growth in aiAnalyzer (added LRU caching, max 10K entries)
- P1.2: Converted sync file I/O to async in audio hot paths (recorder, sessionRecording)
- P1.3: Replaced process.exit(1) with proper error handling (bootstrap, aiAnalysisWorker)

Code Quality:
- Removed unused logger field in EventBroadcaster
- Replaced console.* with structured logger.* calls (player, decoder)
- Fixed typos and removed commented debug code
- Added DatabaseError class for better error handling

Files Modified: 18 (discord-gateway: 14, backend: 3, root: 1)
Architecture: Discord → EventBroadcaster → Redis → Backend WebSocket → Frontend

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

pnpm-lock.yaml

@@ -173,8 +173,8 @@ importers:
         specifier: ^5.1.4
         version: 5.1.4
       prism-media:
-        specifier: 2.0.0-alpha.0
-        version: 2.0.0-alpha.0
+        specifier: ^1.3.5
+        version: 1.3.5(@discordjs/opus@0.10.0)(opusscript@0.0.8)
       sharp:
         specifier: ^0.34.5
         version: 0.34.5