from functools import lru_cache
from typing import Optional

from pydantic import BaseModel

from app.model_catalog import load_app_config


class Settings(BaseModel):
    config_file: str = "config.json"
    model_key: Optional[str] = None
    selected_model: Optional[str] = None
    model_name: str = ""
    served_model_name: Optional[str] = None
    host: str = "0.0.0.0"
    port: int = 8000
    openai_host: str = "0.0.0.0"
    openai_port: int = 8001
    vllm_openai_internal_url: str = "http://127.0.0.1:8001/v1"
    public_model_name: str = "Qwen_local_model"
    default_enable_thinking: bool = False
    reasoning_enabled: bool = False
    model_root: str = "/opt/model"
    offline_mode: bool = True
    max_model_len: int = 8192
    gpu_memory_utilization: float = 0.92
    tensor_parallel_size: int = 2
    max_num_seqs: int = 64
    max_tokens: int = 4096
    dtype: str = "bfloat16"
    enforce_eager: bool = False
    trust_remote_code: bool = False
    tool_call_parser: Optional[str] = None
    enable_auto_tool_choice: bool = False
    revision: Optional[str] = None
    api_key: Optional[str] = None
    quantization: Optional[str] = None
    model_impl: Optional[str] = None
    reasoning_parser: Optional[str] = None
    kv_cache_dtype: Optional[str] = None
    enable_prefix_caching: bool = False
    max_num_batched_tokens: int = 0


@lru_cache(maxsize=1)
def get_settings() -> Settings:
    config = load_app_config("config.json")
    return Settings(
        config_file="config.json",
        model_key=config.get("model_key"),
        selected_model=config.get("selected_model"),
        model_name=config.get("model_name", ""),
        served_model_name=config.get("served_model_name"),
        host=config.get("host", "0.0.0.0"),
        port=config.get("port", 8000),
        openai_host=config.get("openai_host", "0.0.0.0"),
        openai_port=config.get("openai_port", 8001),
        vllm_openai_internal_url=config.get("vllm_openai_internal_url", "http://127.0.0.1:8001/v1"),
        public_model_name=config.get("public_model_name", "Qwen_local_model"),
        default_enable_thinking=config.get("default_enable_thinking", False),
        reasoning_enabled=config.get("reasoning_enabled", False),
        model_root=config.get("model_root", "/opt/model"),
        offline_mode=config.get("offline_mode", True),
        max_model_len=config.get("max_model_len", 8192),
        gpu_memory_utilization=config.get("gpu_memory_utilization", 0.92),
        tensor_parallel_size=config.get("tensor_parallel_size", 2),
        max_num_seqs=config.get("max_num_seqs", 64),
        max_tokens=config.get("max_tokens", 4096),
        dtype=config.get("dtype", "bfloat16"),
        enforce_eager=config.get("enforce_eager", False),
        trust_remote_code=config.get("trust_remote_code", False),
        tool_call_parser=config.get("tool_call_parser"),
        enable_auto_tool_choice=config.get("enable_auto_tool_choice", False),
        revision=config.get("revision"),
        api_key=config.get("api_key"),
        quantization=config.get("quantization"),
        model_impl=config.get("model_impl"),
        reasoning_parser=config.get("reasoning_parser"),
        kv_cache_dtype=config.get("kv_cache_dtype"),
        enable_prefix_caching=config.get("enable_prefix_caching", False),
        max_num_batched_tokens=config.get("max_num_batched_tokens", 0),
    )