# models_config.py
# UPDATED: Novita AI API only - no local models
LLM_CONFIG = {
    "primary_provider": "novita_api",
    "models": {
        "reasoning_primary": {
            "model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B:de-1a706eeafbf3ebc2",
            "task": "general_reasoning",
            "max_tokens": 4096,
            "temperature": 0.6,  # Recommended for DeepSeek-R1
            "top_p": 0.95,
            "force_reasoning_prefix": True,
            "is_chat_model": True
        },
        "classification_specialist": {
            "model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B:de-1a706eeafbf3ebc2",
            "task": "intent_classification",
            "max_tokens": 512,
            "temperature": 0.5,  # Lower for consistency
            "top_p": 0.9,
            "force_reasoning_prefix": False,
            "is_chat_model": True
        },
        "safety_checker": {
            "model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B:de-1a706eeafbf3ebc2",
            "task": "content_moderation",
            "max_tokens": 1024,
            "temperature": 0.5,
            "top_p": 0.9,
            "force_reasoning_prefix": False,
            "is_chat_model": True
        },
        "embedding_specialist": {
            "model_id": "deepseek-ai/DeepSeek-R1-Distill-Qwen-7B:de-1a706eeafbf3ebc2",
            "task": "embeddings",
            "note": "Embeddings via Novita API - may require special handling",
            "is_chat_model": True
        }
    },
    "routing_logic": {
        "strategy": "novita_api_only",
        "fallback_chain": [],
        "load_balancing": "single_endpoint"
    }
}