import pytest
import httpx

from genesis.inference.client import HttpLLMClient, LLMClient
from genesis.inference.exceptions import (
    LLMNetworkError,
    LLMNotConfiguredError,
    LLMResponseError,
    LLMTimeoutError,
)
from genesis.inference.types import ChatMessage


def make_client(handler, *, api_key="sk-test", retry_backoff=(0.0, 0.0)):
    return HttpLLMClient(
        base_url="https://api.test.local",
        api_key=api_key,
        timeout_sec=0.1,
        retry_backoff=retry_backoff,
        transport=httpx.MockTransport(handler),
    )


def _ok_handler(request):
    return httpx.Response(200, json={
        "choices": [{"message": {"content": "Hello"}}],
        "usage": {"prompt_tokens": 10, "completion_tokens": 5},
    })


def test_client_implements_protocol():
    # 结构性断言：HttpLLMClient.chat 的关键字参数签名与 LLMClient Protocol 一致
    import inspect

    proto_params = set(inspect.signature(LLMClient.chat).parameters)
    impl_params = set(inspect.signature(HttpLLMClient.chat).parameters)
    assert proto_params.issubset(impl_params)


def test_chat_success():
    client = make_client(_ok_handler)
    text, usage = client.chat(
        model="deepseek-chat",
        messages=[ChatMessage(role="user", content="hi")],
        temperature=0.2,
        max_tokens=100,
    )
    assert text == "Hello"
    assert usage.input_tokens == 10 and usage.output_tokens == 5


def test_chat_requires_api_key():
    with pytest.raises(LLMNotConfiguredError):
        HttpLLMClient(base_url="https://x", api_key="")


def test_chat_timeout():
    def slow(request):
        raise httpx.ReadTimeout("slow")

    with pytest.raises(LLMTimeoutError):
        make_client(slow, retry_backoff=(0, 0)).chat(
            model="m", messages=[ChatMessage(role="user", content="x")],
            temperature=0.2, max_tokens=100,
        )


def test_chat_5xx_retry_then_network_error():
    calls = {"n": 0}

    def handler(request):
        calls["n"] += 1
        return httpx.Response(500, text="boom")

    with pytest.raises(LLMNetworkError):
        make_client(handler, retry_backoff=(0, 0)).chat(
            model="m", messages=[ChatMessage(role="user", content="x")],
            temperature=0.2, max_tokens=100,
        )
    assert calls["n"] == 3  # 初始 + 2 次退避重试（间隔 0/0.01）


def test_chat_network_error_retry_then_network_error():
    # 非超时的网络错误走 httpx.HTTPError 分支，重试耗尽后抛 LLMNetworkError
    def handler(request):
        raise httpx.ConnectError("connection refused")

    with pytest.raises(LLMNetworkError):
        make_client(handler, retry_backoff=(0, 0)).chat(
            model="m", messages=[ChatMessage(role="user", content="x")],
            temperature=0.2, max_tokens=100,
        )


def test_chat_4xx_no_retry():
    calls = {"n": 0}

    def handler(request):
        calls["n"] += 1
        return httpx.Response(429, text="rate limit")

    with pytest.raises(LLMNetworkError):
        make_client(handler).chat(
            model="m", messages=[ChatMessage(role="user", content="x")],
            temperature=0.2, max_tokens=100,
        )
    assert calls["n"] == 1  # 4xx 不重试


def test_chat_3xx_no_retry():
    # 3xx（重定向，httpx 不自动跟随）不得被当作成功，应立即抛 LLMNetworkError
    calls = {"n": 0}

    def handler(request):
        calls["n"] += 1
        return httpx.Response(302, headers={"Location": "https://elsewhere"})

    with pytest.raises(LLMNetworkError):
        make_client(handler).chat(
            model="m", messages=[ChatMessage(role="user", content="x")],
            temperature=0.2, max_tokens=100,
        )
    assert calls["n"] == 1  # 3xx 不重试


def test_chat_malformed_response_raises_llm_response_error():
    # 2xx 但响应体结构损坏（非 JSON / 缺 choices/message/content）→ LLMResponseError
    def not_json(request):
        return httpx.Response(200, text="not-json")

    def missing_key(request):
        return httpx.Response(200, json={"choices": []})

    for handler in (not_json, missing_key):
        with pytest.raises(LLMResponseError):
            make_client(handler).chat(
                model="m", messages=[ChatMessage(role="user", content="x")],
                temperature=0.2, max_tokens=100,
            )