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>

docker-compose.yml

@@ -69,6 +69,11 @@ services:
       WHISPER_COMPUTE_TYPE: ${WHISPER_COMPUTE_TYPE:-float16}
       # Optional single-language lock for replies (empty = user's own language).
       OUTPUT_LANGUAGE: ${OUTPUT_LANGUAGE:-}
+      # Drop the pre-loop planner LLM call to cut voice-reply latency on small
+      # hardware (the planner adds a full model round-trip per turn).
+      PLANNER_ENABLED: ${PLANNER_ENABLED:-0}
+      # Lock STT to Korean (skip Whisper auto-detect).
+      STT_LANGUAGE: ${STT_LANGUAGE:-ko}
       BRIDGE_URL: http://127.0.0.1:8765
     depends_on:
       - ollama