javis-bot
b52ffd2b18
Release / semantic-release (push) Successful in 19s
Release / build-windows (push) Has been cancelled
Release / build-macos (arm64, macos-latest) (push) Has been cancelled
Release / build-macos (x64, macos-15-intel) (push) Has been cancelled
Release / build-linux (push) Has been cancelled
Release / release-main (push) Has been cancelled
Release / release-develop (push) Has been cancelled
tests / Unit tests (Linux, Python 3.11) (push) Has been cancelled
perf: run auxiliary LLM calls on a small model, big model only for the answer
...
Intent judging, tool routing and arg extraction are classification/JSON calls,
not the spoken answer, yet the stack aliased OLLAMA_INTENT_MODEL back to the big
chat model — so each command paid the big model's cost 2-3 times for routing
before the reply even ran. With the GPU on, that round-trip stacking is the main
remaining per-turn latency. Default OLLAMA_INTENT_MODEL to qwen2.5:3b (the
project's reference small model, clean Korean on classification) and have
ollama-init pull it. The reply engine already routes these calls through
intent_judge_model, so answer quality is untouched; set OLLAMA_INTENT_MODEL =
OLLAMA_CHAT_MODEL to fold back onto one resident model.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com >
2026-06-23 17:35:40 +09:00
..
2026-06-09 14:51:05 +09:00
2026-06-12 21:59:42 +09:00
2026-06-09 14:51:05 +09:00
2026-06-13 01:28:37 +09:00
2026-06-13 14:53:54 +09:00
2026-06-23 15:33:45 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-12 23:45:16 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-23 17:35:40 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-23 15:33:45 +09:00
2026-06-16 19:47:26 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-22 18:05:22 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-11 10:08:30 +09:00
2026-06-16 19:56:13 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-23 03:49:53 +09:00
2026-06-12 21:59:26 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-23 03:27:33 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-09 14:51:05 +09:00
2026-06-11 01:17:50 +09:00