group_fqcd_jr/tests/unit/infrastructure/test_milvus_profile_projection.py

"""`MilvusProfileProjection` 的定向测试。

前 4 个用例移植自同事 `ZSY_develop` 的
`tests/unit/infrastructure/test_milvus_profile_projection.py`；
后 4 个覆盖本仓对其做的**两处契约放宽**（`customer_id` 兼容字符串、
不可投影键跳过而非整批失败）与脱敏，这些是移植时必须钉住的差异点。
"""

from uuid import uuid4

import pytest

from app.core.errors import RecoverableAgentError
from app.infrastructure.milvus_profile_projection import MilvusProfileProjection


class FakeMilvus:
    def __init__(self, existing: list[dict[str, object]] | None = None) -> None:
        self.existing = existing or []
        self.queries: list[dict[str, object]] = []
        self.upserts: list[dict[str, object]] = []

    async def query(self, **kwargs: object) -> list[dict[str, object]]:
        self.queries.append(kwargs)
        return self.existing

    async def upsert(self, **kwargs: object) -> None:
        self.upserts.append(kwargs)


def payload() -> dict[str, object]:
    return {
        "customer_id": 7,
        "profile_version": 1,
        "memory_sources": [{
            "memory_uuid": str(uuid4()),
            "memory_key": "preference:risk_level",
            "content": "稳健型",
            "memory_type": "preference",
            "confidence": 0.9,
            "version": 2,
            "valid_until": None,
        }],
    }


def _source(data: dict[str, object]) -> dict[str, object]:
    sources = data["memory_sources"]
    assert isinstance(sources, list)
    source = sources[0]
    assert isinstance(source, dict)
    return source


@pytest.mark.asyncio
async def test_upsert_writes_schema_fields_and_vector() -> None:
    client = FakeMilvus()
    projection = MilvusProfileProjection(client, _embed)

    await projection.upsert(payload())

    assert len(client.upserts) == 1
    row = client.upserts[0]["data"][0]
    assert row["customer_id"] == 7
    assert row["status"] == "active"
    assert len(row["embedding"]) == 1024


@pytest.mark.asyncio
async def test_lower_memory_version_is_not_overwritten() -> None:
    data = payload()
    memory_uuid = _source(data)["memory_uuid"]
    client = FakeMilvus(existing=[{
        "memory_uuid": memory_uuid, "customer_id": 7, "version": 3,
    }])

    await MilvusProfileProjection(client, _embed).upsert(data)

    assert client.upserts == []


@pytest.mark.asyncio
async def test_embedding_dimension_is_enforced() -> None:
    with pytest.raises(RecoverableAgentError, match="维度"):
        await MilvusProfileProjection(client=FakeMilvus(), embed=_embed_short).upsert(
            payload()
        )


@pytest.mark.asyncio
async def test_non_uuid_memory_id_is_rejected() -> None:
    data = payload()
    _source(data)["memory_uuid"] = "unsafe\" or true"

    with pytest.raises(ValueError, match="memory_uuid"):
        await MilvusProfileProjection(FakeMilvus(), _embed).upsert(data)


# --- 本仓放宽的契约（移植差异点） -------------------------------------------


@pytest.mark.asyncio
async def test_string_customer_id_is_accepted() -> None:
    """本仓三处生产者写的都是 `str(customer_id)`；不接受字符串则事件必然全部失败。"""
    data = payload()
    data["customer_id"] = "9102"

    client = FakeMilvus()
    await MilvusProfileProjection(client, _embed).upsert(data)

    assert client.upserts[0]["data"][0]["customer_id"] == 9102


@pytest.mark.asyncio
async def test_non_numeric_customer_id_is_rejected() -> None:
    """放宽不等于不校验：uuid 之类的非数字串必须拒绝，不能当成客户号写进向量库。"""
    data = payload()
    data["customer_id"] = "957c0552-7fa2-4f2a-924d-d2d2e133b245"

    with pytest.raises(ValueError, match="customer_id"):
        await MilvusProfileProjection(FakeMilvus(), _embed).upsert(data)


@pytest.mark.asyncio
async def test_version_key_fallback_is_supported() -> None:
    """本仓生产端 payload 用 `version`；适配器契约用 `profile_version`。两个都要认。"""
    data = payload()
    del data["profile_version"]
    data["version"] = 5

    client = FakeMilvus()
    await MilvusProfileProjection(client, _embed).upsert(data)

    assert len(client.upserts) == 1


@pytest.mark.asyncio
async def test_non_projectable_memory_key_is_skipped_not_fatal() -> None:
    """`constraint:*` / `profile:*` 不在可投影前缀内。

    关键：一条不可投影的键**不得**毒死同一客户其余可投影记忆。
    """
    data = payload()
    good = _source(data)
    data["memory_sources"] = [
        {
            "memory_uuid": str(uuid4()),
            "memory_key": "constraint:liquidity",
            "content": "半年内需要流动性",
            "memory_type": "constraint",
            "confidence": 0.8,
            "version": 1,
            "valid_until": None,
        },
        good,
    ]

    client = FakeMilvus()
    await MilvusProfileProjection(client, _embed).upsert(data)

    assert len(client.upserts) == 1
    rows = client.upserts[0]["data"]
    assert [row["memory_key"] for row in rows] == ["preference:risk_level"]


@pytest.mark.asyncio
async def test_all_keys_non_projectable_writes_nothing() -> None:
    """全部不可投影时不写 Milvus，但也不报错（不是失败，是无需投影）。"""
    data = payload()
    _source(data)["memory_key"] = "profile:occupation"

    client = FakeMilvus()
    await MilvusProfileProjection(client, _embed).upsert(data)

    assert client.upserts == []


@pytest.mark.asyncio
async def test_sensitive_credentials_are_sanitized_before_write() -> None:
    """落外部存储前必须脱敏：手机号不得原样写进向量库。"""
    data = payload()
    _source(data)["content"] = "我的手机号是 13800138000，稳健型"

    client = FakeMilvus()
    await MilvusProfileProjection(client, _embed).upsert(data)

    content = client.upserts[0]["data"][0]["content"]
    assert "13800138000" not in content
    assert "[手机号已隐藏]" in content


def _vector(size: int = 1024) -> list[float]:
    return [0.0] * size


async def _embed(_: str) -> list[float]:
    return _vector()


async def _embed_short(_: str) -> list[float]:
    return _vector(3)