mirror of
https://github.com/NousResearch/hermes-agent.git
synced 2026-04-28 23:11:37 +08:00
Base adapter auto-TTS already generates and sends audio for voice messages in _process_message_background. The gateway runner's _send_voice_reply was causing double audio on all platforms (not just Web). Now skip_double applies to any voice input regardless of platform.