javis-bot 3a4776c709 perf(brain): env to disable pre-loop planner; cut voice latency ...

Warm per-turn timing showed STT 0.1s, TTS ~1-3s, but the reply engine (LLM) was
8-17s — even a simple "고마워" took 16.7s — because it makes multiple model calls
per turn. Add a PLANNER_ENABLED env override (config.py) and default it to 0 in
the userbot compose so the pre-loop planner's extra LLM round-trip is dropped on
this latency-sensitive voice deployment. Also pins STT_LANGUAGE=ko in compose.

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

2026-06-13 21:59:35 +09:00

5.3 KiB

Raw Blame History

View Raw