Plugin

Miglioramento dei prompt con un clic (5 modalità, catena di memoria, fallback multi-modello) più riconoscimento vocale (Qwen3-ASR cloud / SenseVoice offline, arresto automatico al silenzio) per il composer, con riavvio del servizio DSH con un clic.

Local English-to-Chinese simultaneous interpretation: on-device Qwen3-ASR bilingual captions with automatic language detection, crash-safe meeting records with minutes, and Obsidian export.

Voice input plugin (dual-face): mic button beside the composer send action, live recording bubble streaming PCM to a local Qwen3-ASR python service managed by the host, plus an ASR environment settings page (clone runtime/model repos, create venv, run ser