backend/config.py

"""
Configuration settings for the Edge LLM API
"""
import os
from dotenv import load_dotenv

# Load environment variables
load_dotenv()

# API Configuration
API_KEY = os.getenv("api_key", "")
BASE_URL = os.getenv("base_url", "https://aihubmix.com/v1")

# Available models configuration
AVAILABLE_MODELS = {
    # API models (AiHubMix) - Prioritized first
    "Qwen/Qwen3-30B-A3B": {
        "name": "Qwen3-30B-A3B",
        "supports_thinking": True,
        "description": "API: Qwen3 with dynamic thinking modes",
        "size_gb": "API",
        "type": "api"
    },
    # Local models (for local development)
    "Qwen/Qwen3-4B-Thinking-2507": {
        "name": "Qwen3-4B-Thinking-2507",
        "supports_thinking": True,
        "description": "Local: Shows thinking process",
        "size_gb": "~8GB",
        "type": "local"
    },
    "Qwen/Qwen3-4B-Instruct-2507": {
        "name": "Qwen3-4B-Instruct-2507", 
        "supports_thinking": False,
        "description": "Local: Direct instruction following",
        "size_gb": "~8GB",
        "type": "local"
    },
    "qwen2.5-vl-72b-instruct": {
        "name": "Qwen2.5-VL-72B-Instruct",
        "supports_thinking": False,
        "description": "API: Multimodal model with vision",
        "size_gb": "API", 
        "type": "api"
    },
    "Qwen/QVQ-72B-Preview": {
        "name": "QVQ-72B-Preview",
        "supports_thinking": True,
        "description": "API: Visual reasoning with thinking",
        "size_gb": "API",
        "type": "api"
    }
}

# CORS settings
CORS_ORIGINS = ["*"]  # Allow all origins for HF Space

# Static files directory - point directly to frontend build
FRONTEND_DIST_DIR = "frontend/dist"
ASSETS_DIR = "frontend/dist/assets"

# Server settings (port will be dynamically determined)
HOST = "0.0.0.0"
DEFAULT_PORT = int(os.getenv("PORT", "0"))  # 0 means auto-assign a free port