"""思考模式必须显式声明（deepseek-v4 默认开启）。

保护的是两件事：漏传 ``thinking`` 会让对话延迟从约 2s 涨到 13s 以上（实测同一个单句
问答），并且思考 token 按输出价计费 —— 一个用户看不到的字段同时打破响应时间目标
与成本模型。
"""

from __future__ import annotations

import json
from typing import Any

import httpx
import pytest

from packages.llm.providers.deepseek import DeepSeekProvider
from packages.llm.routing import build_scene_configs
from packages.llm.types import Message, ProviderRequest, Scene


def _request(*, thinking: bool) -> ProviderRequest:
    return ProviderRequest(
        model="deepseek-v4-flash",
        messages=(Message(role="user", content="面试穿什么"),),
        temperature=0.7,
        max_tokens=800,
        timeout_seconds=30.0,
        thinking=thinking,
    )


def _provider(captured: dict[str, Any]) -> DeepSeekProvider:
    def handler(request: httpx.Request) -> httpx.Response:
        captured.update(json.loads(request.content))
        return httpx.Response(
            200,
            json={
                "choices": [{"message": {"content": "ok"}, "finish_reason": "stop"}],
                "usage": {
                    "prompt_tokens": 12,
                    "completion_tokens": 34,
                    "completion_tokens_details": {"reasoning_tokens": 20},
                },
            },
        )

    return DeepSeekProvider(
        api_key="test-key",
        client=httpx.AsyncClient(transport=httpx.MockTransport(handler)),
    )


@pytest.mark.parametrize(("thinking", "expected"), [(False, "disabled"), (True, "enabled")])
async def test_thinking_is_always_sent_explicitly(thinking: bool, expected: str) -> None:
    captured: dict[str, Any] = {}
    provider = _provider(captured)

    await provider.complete(_request(thinking=thinking))

    # 关键是这个字段一定存在：省略它就等于接受供应商的"开启"默认值
    assert captured["thinking"] == {"type": expected}
    await provider.aclose()


async def test_reasoning_tokens_are_recorded_for_cost_visibility() -> None:
    provider = _provider({})
    response = await provider.complete(_request(thinking=True))

    # 思考 token 已计入 tokens_out，单独留一份用于回答"输出成本有多少花在推理上"
    assert response.usage.tokens_out == 34
    assert response.usage.tokens_reasoning == 20
    await provider.aclose()


def test_no_v1_scene_enables_thinking_by_default() -> None:
    configs = build_scene_configs(primary_provider="deepseek")
    assert [s for s, c in configs.items() if c.thinking] == []
    # 且每个场景都显式给了值，不存在"忘了配"的场景
    assert set(configs) == set(Scene)