f3a1d92620
The config template never set intent_judge_model, so it fell back to the code default gemma4:e2b. That model is not pulled by this stack (Ollama only has qwen2.5:3b, qwen3:8b, nomic-embed-text), so every auxiliary small-model call — intent judge, tool router, weather place extraction, query decomposition — targeted a non-existent model, silently failed, and fell open. This crippled tool routing and argument extraction on the 3B brain. Render intent_judge_model from a new OLLAMA_INTENT_MODEL env var that defaults to OLLAMA_CHAT_MODEL, so the auxiliary calls reuse the already-warm chat model (one resident model, no extra load). tool_router_model="" then resolves through the chain to the same model. Verified: rendered jarvis.json now has intent_judge_model=qwen2.5:3b, and the weather place extractor returns "서울" / "Tokyo" (it returned None for everything while pointed at the missing gemma4:e2b).
20 lines
636 B
JSON
20 lines
636 B
JSON
{
|
|
"db_path": "${JARVIS_DB_PATH}",
|
|
"sqlite_vss_path": null,
|
|
"ollama_base_url": "${OLLAMA_BASE_URL}",
|
|
"ollama_embed_model": "${OLLAMA_EMBED_MODEL}",
|
|
"ollama_chat_model": "${OLLAMA_CHAT_MODEL}",
|
|
"intent_judge_model": "${OLLAMA_INTENT_MODEL}",
|
|
"tts_enabled": true,
|
|
"tts_engine": "piper",
|
|
"tts_piper_model_path": "${TTS_PIPER_MODEL_PATH}",
|
|
"whisper_model": "${WHISPER_MODEL}",
|
|
"whisper_backend": "faster-whisper",
|
|
"whisper_device": "${WHISPER_DEVICE}",
|
|
"whisper_compute_type": "${WHISPER_COMPUTE_TYPE}",
|
|
"location_enabled": true,
|
|
"web_search_enabled": true,
|
|
"wikipedia_fallback_enabled": true,
|
|
"mcps": {}
|
|
}
|