张胜宇
e239eb778b
1) 客服 Agent 四份交付文档 + 构建脚手架：品牌由包装占位 XX科技 / 旧名 南方财富 统一为南方基金（热线 400-889-8899 / 官网 nffund.com），系统名改为「智能服务系统」； 同步追加 §0.4 修订记录行，工程记录行保留原占位字面以支撑硬编码扫描验收。 2) 开发文档：清理 28 份已作废/残留文档（14 份移出归档 + 14 份仓库副本）， 新增《文档规整方案与开发前待决事项-2026-09-17》。 3) 客服agent 四份交付文档首次纳入本分支。
202 lines
6.1 KiB
Python
202 lines
6.1 KiB
Python
"""`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 15936583816，稳健型"
|
||
|
||
client = FakeMilvus()
|
||
await MilvusProfileProjection(client, _embed).upsert(data)
|
||
|
||
content = client.upserts[0]["data"][0]["content"]
|
||
assert "15936583816" 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)
|