EJClaw 0e4e7c6bb2 feat(voice): configurable user voice-recognition time (bargeInMs, default 700ms) ...

Expose the barge-in sustained-speech threshold as a dashboard bot setting
"유저 음성 인식 시간" (ms). Server clamps 0..5000, persists via state_store,
and the bot reads it each report round-trip; WSAI_BARGE_IN_MS/700 stays the
fallback default.

Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>

2026-08-27 11:35:01 +09:00

..

backends

feat(stt/voice): better recognition, sustained barge-in, fragment discard

2026-08-27 02:13:50 +09:00

__init__.py

feat: scaffold watch-screen AI pipeline (mock-runnable skeleton)

2026-08-09 02:16:14 +09:00

__main__.py

feat(dashboard): 4-way roster (user/bot/voice/role), persistence, TTS all-emotions, layout

2026-08-27 00:14:24 +09:00

bot_control.py

feat(voice): configurable user voice-recognition time (bargeInMs, default 700ms)

2026-08-27 11:35:01 +09:00

config.py

feat(stt): real Korean STT via persistent faster-whisper worker

2026-08-18 18:29:32 +09:00

dashboard.py

feat(voice): configurable user voice-recognition time (bargeInMs, default 700ms)

2026-08-27 11:35:01 +09:00

factory.py

feat(stt): real Korean STT via persistent faster-whisper worker

2026-08-18 18:29:32 +09:00

interfaces.py

feat(dashboard): show Claude usage (tokens + requests) since server start

2026-08-22 16:40:25 +09:00

monitor.py

feat(dashboard): delete conversation turns (per-turn ✕ + 전체 삭제)

2026-08-27 02:17:16 +09:00

pipeline.py

feat(dashboard): per-stage STT/LLM/TTS timing + rename 두뇌 -> LLM

2026-08-27 00:03:34 +09:00

prompt_store.py

feat(dashboard): live-editable bot prompt via popup (view/edit/save)

2026-08-22 11:20:57 +09:00

state_store.py

feat(dashboard): 4-way roster (user/bot/voice/role), persistence, TTS all-emotions, layout

2026-08-27 00:14:24 +09:00

state.py

feat: scaffold watch-screen AI pipeline (mock-runnable skeleton)

2026-08-09 02:16:14 +09:00

usage_store.py

feat(dashboard): show Claude usage per day/week instead of per session

2026-08-22 22:20:30 +09:00