fix Live Call: drop all audio chunks during ducking

The old ducking logic only skipped chunks below a threshold (RMS < 0.10),
but the S25 Ultra speakers leak enough audio into the mic to exceed that.
Gemini's server-side VAD picks it up as user speech, triggers interrupts,
and the model starts hallucinating a conversation with itself.

Now: when ducking is active (model speaking), NO mic chunks are sent.
The server-side VAD handles the real speech detection after ducking ends.

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

@@ -101,7 +101,7 @@ class AudioPipeline(private val context: Context) {
                 val rms = computeRms(buffer, read)
                 onAmplitude?.invoke(rms)
 
-                if (ducking && rms < DUCKING_GAIN) continue
+                if (ducking) continue
 
                 byteBuffer.clear()
                 for (i in 0 until read) byteBuffer.putShort(buffer[i])