import httpx, asyncio
from typing import List, Dict

class LLMClient:
    def __init__(self, base_url: str, api_key: str):
        self.base = base_url.rstrip("/")
        self.key = api_key
    
    async def chat(self, messages: List[Dict[str, str]], model: str, 
                   temperature: float = 0.2, max_tokens: int = 512) -> str:
        url = f"{self.base}/chat/completions"
        headers = {"Authorization": f"Bearer {self.key}", "Content-Type": "application/json"}
        payload = {
            "model": model,
            "messages": messages,
            "temperature": temperature,
            "max_tokens": max_tokens
        }
        
        for attempt in range(3):
            try:
                async with httpx.AsyncClient(timeout=httpx.Timeout(30.0, connect=10.0)) as client:
                    resp = await client.post(url, headers=headers, json=payload)
                    resp.raise_for_status()
                    data = resp.json()
                    return data["choices"][0]["message"]["content"]
            except Exception as e:
                if attempt == 2:
                    raise
                await asyncio.sleep(0.6 * (attempt + 1))
        return ""