from SimpleLLMFunc import OpenAICompatible

# 从 provider.json 加载
models = OpenAICompatible.load_from_json_file("provider.json")
llm = models["openrouter"]["openai/gpt-4o"]

# 直接构造
from SimpleLLMFunc import APIKeyPool

llm = OpenAICompatible(
    api_key_pool=APIKeyPool(api_keys=["sk-key"], provider_id="openai"),
    model_name="gpt-4o",
    base_url="https://api.openai.com/v1",
    max_retries=3,
    retry_delay=1.0,
    rate_limit_capacity=20,
    rate_limit_refill_rate=3.0,
    context_window=128_000,
)

from SimpleLLMFunc import OpenAIResponsesCompatible

llm = OpenAIResponsesCompatible(
    api_key_pool=APIKeyPool(api_keys=["sk-key"], provider_id="openai"),
    model_name="gpt-4o",
    base_url="https://api.openai.com/v1",
)

from SimpleLLMFunc import APIKeyPool

pool = APIKeyPool(
    api_keys=["sk-key-1", "sk-key-2", "sk-key-3"],
    provider_id="openrouter-gpt4",
)

# 通过构造函数配置
llm = OpenAICompatible(
    ...,
    rate_limit_capacity=20,       # 桶中的最大并发"令牌"数
    rate_limit_refill_rate=3.0,   # 每秒补充的令牌数
)

# 查看状态
status = llm.get_rate_limit_status()
# {"available": 15, "capacity": 20, "refill_rate": 3.0}

# 在速率限制错误后重置
llm.reset_rate_limit()

@llm_chat(
    llm_interface=llm,
    temperature=0.7,
    max_tokens=4096,
    top_p=0.9,
)
async def agent(message: str, history: list | None = None):
    """My agent."""
    pass

@llm_chat(
    llm_interface=llm,
    reasoning_effort="high",
)
async def reasoning_agent(message: str, history: list | None = None):
    """An agent that reasons deeply."""
    pass

llm = OpenAICompatible(
    ...,
    context_window=128_000,  # GPT-4o 的上下文窗口
)