group_fqcd_jr/tests/unit/service/test_customer_service_suitability.py

"""客服适当性出口的单元测试。

这个出口会给出「能不能买」的结论，所以每条分支都必须锁住——写错一条就是误导客户。
用例里的数字取自真实链路：南方季季盈90天是 R2，来自产品手册的「风险等级」行。
"""

from typing import Any, cast

import pytest

from app.core.contracts import AgentRequest, ConversationTurn, RequestContext
from app.service.agent.implementations.customer_service import CustomerServiceAgent

FALLBACK = "抱歉，这个问题我暂时无法给出准确答复。建议您拨打客服热线 400-XXX-XXXX 转人工客服咨询。"


def _decision(**overrides: Any) -> dict[str, Any]:
    base: dict[str, Any] = {
        "allowed": True, "reason_code": "MATCHED", "required_disclosure": False,
        "requires_confirmation": False, "requires_recording": False,
        "customer_risk_level": 2, "assessment_valid_until": None,
    }
    base.update(overrides)
    return base


def _agent() -> CustomerServiceAgent:
    """跳过 __init__ 造实例：本组用例只碰话术与 call_tool 替身。"""
    return object.__new__(CustomerServiceAgent)


def _request(*history: tuple[str, str]) -> AgentRequest:
    turns = tuple(
        ConversationTurn(role=cast(Any, role), content=content) for role, content in history
    )
    return AgentRequest(
        agent_type="customer_service", session_id="s", message="c1客户能买它吗",
        idempotency_key="1234567890123456", history=turns,
    )


def _hit(title: str, content: str) -> dict[str, Any]:
    return {"doc_id": "PROD-007-03", "title": title, "content": content, "score": 0.9}


# ---- 话术 ----

def test_allowed_reply_names_product_level_and_customer_level() -> None:
    text = CustomerServiceAgent._suitability_text("南方季季盈90天", 2, _decision())

    assert "南方季季盈90天" in text
    assert "R2（中低风险）" in text
    assert "可以购买" in text
    assert "C2" in text


def test_disclosure_and_recording_are_disclosed_when_required() -> None:
    text = CustomerServiceAgent._suitability_text(
        "南方稳健增利180天", 4, _decision(required_disclosure=True, requires_recording=True)
    )

    assert "风险揭示书" in text
    assert "双录" in text


def test_one_level_up_is_not_described_as_within_capacity() -> None:
    """C1 买 R2 是矩阵允许的，但不能说成"在您的风险承受能力范围内"——它超出了等级。

    这句错话会让客户以为自己的测评等级本来就覆盖 R2，下次买 R3 时就更难解释为什么不行。
    """
    text = CustomerServiceAgent._suitability_text(
        "南方季季盈90天", 2, _decision(customer_risk_level=1)
    )

    assert "在您的风险承受能力范围内" not in text
    assert "匹配矩阵允许购买的范围内" in text


def test_disclosure_tier_explains_the_condition() -> None:
    """C3 买 R4 属豁免档：要说清"高于您的等级"以及"签揭示书后可买"这个条件。"""
    text = CustomerServiceAgent._suitability_text(
        "南方稳健增利180天",
        4,
        _decision(
            customer_risk_level=3,
            reason_code="SUITABLE_WITH_DISCLOSURE",
            required_disclosure=True,
            requires_recording=True,
        ),
    )

    assert "高于您的风险承受能力等级" in text
    assert "签署产品风险揭示书后可以购买" in text
    assert "在您的风险承受能力范围内" not in text


def test_same_level_still_uses_the_capacity_wording() -> None:
    text = CustomerServiceAgent._suitability_text(
        "南方季季盈90天", 2, _decision(customer_risk_level=2)
    )

    assert "在您的风险承受能力范围内" in text


def test_rejection_does_not_assert_a_reason() -> None:
    """拒绝的原因可能是等级不匹配、测评过期或未测评，不能一律说成"超出承受能力"。"""
    text = CustomerServiceAgent._suitability_text(
        "南方季季盈90天", 3, _decision(allowed=False)
    )

    assert "暂时无法购买" in text
    assert "超出" not in text


def test_missing_assessment_is_said_in_plain_words() -> None:
    """档案里没有测评结果时不能写"您的等级为未记录"——客户看不懂。"""
    text = CustomerServiceAgent._suitability_text(
        "南方季季盈90天", 2, _decision(allowed=False, customer_risk_level=None)
    )

    assert "没有在有效期内的风险测评结果" in text
    assert "未记录" not in text


def test_validity_is_shortened_to_a_plain_date() -> None:
    text = CustomerServiceAgent._suitability_text(
        "南方季季盈90天", 2, _decision(assessment_valid_until="2027-01-15T00:00:00+00:00")
    )

    assert "2027-01-15" in text
    assert "T00:00" not in text


def test_unknown_level_falls_back_to_the_code() -> None:
    text = CustomerServiceAgent._suitability_text("某产品", 9, _decision())

    assert "R9" in text


# ---- 客户自述等级 ----

def test_self_claimed_level_is_detected_case_insensitively() -> None:
    """客户自述等级只用来在回答里说明判断依据，绝不参与裁决。"""
    assert CustomerServiceAgent._self_claimed_level("C3 客户能买它吗") == "C3"
    assert CustomerServiceAgent._self_claimed_level("我是c1客户，能买吗") == "C1"
    assert CustomerServiceAgent._self_claimed_level("那我能买它吗") == ""


# ---- 产品名来源 ----

def test_previous_topic_takes_the_subject_of_the_last_answer() -> None:
    topic = CustomerServiceAgent._previous_topic(_request(
        ("user", "季季盈90天起投多少"),
        ("assistant", "南方季季盈90天：起投金额 1万元"),
    ))

    assert topic == "南方季季盈90天"


def test_previous_topic_ignores_user_turns() -> None:
    """客户的问句不是可信的产品名来源，只能从回答里取。"""
    assert CustomerServiceAgent._previous_topic(
        _request(("user", "季季盈90天起投多少"))
    ) == ""


def test_previous_topic_is_empty_after_a_fallback_answer() -> None:
    """上一轮是兜底话术时取不出主语，调用方据此转人工（而不是瞎猜一个产品）。"""
    assert CustomerServiceAgent._previous_topic(
        _request(("user", "随便问点什么"), ("assistant", FALLBACK))
    ) == ""


# ---- 产品风险等级 ----

async def _level(hits: list[dict[str, Any]]) -> int | None:
    agent = _agent()

    async def fake_call_tool(name: str, arguments: dict[str, Any], **kwargs: Any) -> Any:
        return {"hits": hits, "degraded": False}

    agent.call_tool = fake_call_tool  # type: ignore[method-assign]
    return await agent._product_risk_level(
        "南方季季盈90天", RequestContext(user_id="9001", trace_id="t")
    )


@pytest.mark.asyncio
async def test_level_is_read_from_the_risk_level_row() -> None:
    level = await _level([
        _hit("手册 · 2.1 南方季季盈90天 · 风险等级", "南方季季盈90天：风险等级 R2（中低风险）")
    ])

    assert level == 2


@pytest.mark.asyncio
async def test_row_about_another_product_is_rejected() -> None:
    """命中别的产品的等级行时必须放弃，否则会拿别人的等级去给客户做裁决。"""
    level = await _level([
        _hit("手册 · 3.1 南方稳健增利180天 · 风险等级", "南方稳健增利180天：风险等级 R3（中风险）")
    ])

    assert level is None


@pytest.mark.asyncio
async def test_enumeration_row_is_rejected() -> None:
    """C1 的 FAQ 里写着"可购买 R1、R2"这种列举，那不是产品等级。"""
    level = await _level([
        _hit(
            "C1 客户能买什么产品?",
            "C1（保守型）客户可以购买 R1（低风险）、R2（中低风险）等级的产品。",
        )
    ])

    assert level is None


@pytest.mark.asyncio
async def test_degraded_search_yields_no_level() -> None:
    """检索降级时不能返回一个等级——那会让裁决建立在"其实没查到"之上。"""
    agent = _agent()

    async def fake_call_tool(name: str, arguments: dict[str, Any], **kwargs: Any) -> Any:
        return {"hits": [], "degraded": True, "reason": "search_failed"}

    agent.call_tool = fake_call_tool  # type: ignore[method-assign]

    assert await agent._product_risk_level(
        "南方季季盈90天", RequestContext(user_id="9001", trace_id="t")
    ) is None


@pytest.mark.asyncio
async def test_tool_failure_yields_no_level() -> None:
    """工具抛异常时返回 None（由调用方转人工），不能让异常冒到主链路。"""
    agent = _agent()

    async def fake_call_tool(name: str, arguments: dict[str, Any], **kwargs: Any) -> Any:
        raise RuntimeError("milvus 挂了")

    agent.call_tool = fake_call_tool  # type: ignore[method-assign]

    assert await agent._product_risk_level(
        "南方季季盈90天", RequestContext(user_id="9001", trace_id="t")
    ) is None