from __future__ import annotations

import pytest

from services.litellm.service import LiteLLMService


def test_calculate_cost_uses_first_qwen_tier() -> None:
    service = LiteLLMService()

    cost = service.calculate_cost(
        model="dashscope/qwen3.5-flash",
        prompt_tokens=100_000,
        completion_tokens=1_000,
        cached_prompt_tokens=10_000,
    )

    assert cost == pytest.approx(0.0202)


def test_calculate_cost_uses_second_qwen_tier() -> None:
    service = LiteLLMService()

    cost = service.calculate_cost(
        model="dashscope/qwen3.5-flash",
        prompt_tokens=200_000,
        completion_tokens=5_000,
        cached_prompt_tokens=20_000,
    )

    assert cost == pytest.approx(0.1856)


def test_build_usage_metadata_calculates_cost_from_usage_summary() -> None:
    service = LiteLLMService()

    metadata = service.build_usage_metadata(
        model="dashscope/qwen3.5-flash",
        usage_summary={
            "input_tokens": 2000,
            "output_tokens": 100,
            "latency_ms": 321,
            "cached_prompt_tokens": 500,
        },
    )

    assert metadata == {
        "model": "dashscope/qwen3.5-flash",
        "inputTokens": 2000,
        "outputTokens": 100,
        "cost": pytest.approx(0.00051),
        "latencyMs": 321,
    }