from functools import lru_cache
import os
from typing import Optional

from pydantic import BaseModel

from app.model_catalog import load_catalog, resolve_model_profile, resolve_runtime_settings


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
    public_model_name: str = "Qwen_local_model"
    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


@lru_cache(maxsize=1)
def get_settings() -> Settings:
    catalog = load_catalog("config.json")
    runtime = resolve_runtime_settings(catalog)
    settings = Settings(
        config_file="config.json",
        model_key=runtime["model_key"],
        host=runtime["host"],
        port=runtime["port"],
        openai_host=runtime["openai_host"],
        openai_port=runtime["openai_port"],
        public_model_name=runtime["public_model_name"],
        model_root=runtime["model_root"],
        offline_mode=runtime["offline_mode"],
        api_key=runtime["api_key"],
        tensor_parallel_size=runtime["tensor_parallel_size"],
        dtype=runtime["dtype"],
        revision=runtime["revision"],
    )
    _, updates, env_vars = resolve_model_profile(
        content=catalog,
        requested_model=settings.model_key,
        requested_tp=settings.tensor_parallel_size,
    )
    for key, value in env_vars.items():
        os.environ[key] = value
    return settings.model_copy(update=updates | runtime)