fix Live Call: restore USAGE_ASSISTANT for clearer audio output

USAGE_VOICE_COMMUNICATION applies telephony DSP (compression, bandwidth
limiting, noise suppression) that degrades audio clarity. Since we now
have hard ducking (zero mic chunks during model speech) + AEC on the
capture side, we don't need aggressive playback-side processing.

USAGE_ASSISTANT gives full-quality audio output while echo protection
comes from ducking + AcousticEchoCanceler on the AudioRecord.

app/src/main/java/dev/kaizen/app/live/AudioPipeline.kt

@@ -185,7 +185,7 @@ class AudioPipeline(private val context: Context) {
         val t = AudioTrack.Builder()
             .setAudioAttributes(
                 AudioAttributes.Builder()
-                    .setUsage(AudioAttributes.USAGE_VOICE_COMMUNICATION)
+                    .setUsage(AudioAttributes.USAGE_ASSISTANT)
                     .setContentType(AudioAttributes.CONTENT_TYPE_SPEECH)
                     .build()
             )