docker-compose.override.yml: VAD tuning (RMS threshold, min speech, trailing
silence), no-speech reprompt, immediate_short ack mode, media idle timeout --
all previously live on prod but uncommitted. AI_VOICE_V2_EMOTIVE_ACK_ENABLED
flipped 0 -> 1: this flag was silently disabling filler-phrase rotation
regardless of the app-level 36c2acb fix.
docker-compose.minimal.yml: removed the voice-ai (Magzhan legacy) service
and its dependency, matching what was actually running.
docker-compose.yml: added common_network to api-gateway.