feat: 装配投影删除客户端(记忆失效/销户清理图与向量),并修复画像字段残留
一、装配 projection_cleaner 新增 app/service/projection_cleanup_service.py,并在**组装层**(app/worker/__main__.py) 注入。此前该客户端一直未装配,清理链路只记录降级(skipped_no_client),实际后果是 **销户后图里仍留着偏好关系**——投顾仍能通过关系网络看到这个人。 清理策略是"以画像为准"而不是按标识直接删边:先删掉该记忆对应的长期事实,再重建画像, 最后用对账修复让图跟着画像收敛。这样即使一条记忆影响多条派生边也能删干净,不依赖 "记得它当初投影成了什么"。Milvus 侧按 memory_uuid 删除;集合不存在(语义召回未启用) 时视为无需清理,客户端不可用则如实报告未清理,绝不伪造成功。 放在组装层而不是 runtime 内部兜底:组件内部给默认实现会把"尚未装配"这一事实悄悄盖住, 而"未注入即显式降级并留痕"是 runtime 刻意保留的语义。最初的改法写成内部兜底,被 5 个 既有单测拦下——那些测试是对的,因此改为在入口处注入。 二、顺带修复:事实消失后画像字段残留 实测:让 preference:horizon 记忆失效并清理后,user_facts 与图边都正确清除,但 fin_customer_profile.investment_horizon 仍是"长期(5年以上)"。根因是 rebuild_profile 只写"本轮有新值"的字段;事实被删后该字段没有新值,旧值就留在画像里——于是记忆已经作废, 投顾还能看到一个客户从未授权继续生效的投资期限。 改为:本轮没有对应事实时**清空**该字段;investor_type 例外——问卷是唯一权威,本轮没有 问卷记录时保持原值(该列 NOT NULL,且清空会在重测空档抹掉开户时的等级)。 三、实测 · 让 preference:horizon 失效后清理:cleaned=True, detail=profile_rebuilt; graph_cleaned; vector_collection_absent; · user_facts 2→1;图边由 ['HAS_GOAL','PREFERS'] 变为 ['PREFERS']; · 画像 investment_horizon 由"长期(5年以上)"变为 None;investor_type 保持 C2、 risk_tags 不受影响(与 horizon 无关); · 恢复记忆状态后重建,画像与图边均正确复原; · ruff 通过、mypy 113 文件无错、unit+contract 447 passed、integration 29 passed。
This commit is contained in:
@@ -190,8 +190,16 @@ class ProfileAssemblyService:
|
||||
"promoted": len(facts),
|
||||
}
|
||||
for field in PROFILE_OWNED_FIELDS:
|
||||
if field in values:
|
||||
setattr(profile, field, values[field])
|
||||
if field == "investor_type":
|
||||
# 问卷是唯一权威:本轮没有问卷记录时**保持原值**(既不写入也不清空)。
|
||||
# 否则重测前的空档会把开户时的等级抹掉,而该列是 NOT NULL。
|
||||
if field in values:
|
||||
setattr(profile, field, values[field])
|
||||
continue
|
||||
# 其余字段由本服务独占:本轮没有对应事实即清空。
|
||||
# 这不只是洁癖——记忆失效后若不清理,画像会留着一个已经作废的投资期限,
|
||||
# 投顾据此给建议,而客户从未授权这条信息继续生效(实测踩到过)。
|
||||
setattr(profile, field, values.get(field))
|
||||
profile.updated_at = now
|
||||
await self.session.flush()
|
||||
|
||||
|
||||
@@ -0,0 +1,136 @@
|
||||
"""投影清理:记忆失效或删除时,清掉它在图库与向量库里的派生数据。
|
||||
|
||||
**为什么以画像为准,而不是按标识直接删边**:一条记忆可能对应多条派生边(同一 key 的
|
||||
证据累积会让 tag 取值变化),直接按 tag_key 删容易删不干净或误删。这里走
|
||||
「删掉该记忆对应的长期事实 → 重建画像 → 对账修复」,让投影跟着权威源收敛——
|
||||
最终图里剩下的内容必然与画像一致,而不依赖"我记得这条记忆当初投影成了什么"。
|
||||
|
||||
**Milvus 向量**按 `memory_uuid` 删除;集合不存在或客户端不可用时**如实报告未清理**,
|
||||
绝不伪造成功。这与 `_cleanup_projection` 的审计语义一致:审计只记录适配器返回的真实结论。
|
||||
"""
|
||||
|
||||
import logging
|
||||
from dataclasses import dataclass
|
||||
|
||||
from sqlalchemy import delete, select
|
||||
|
||||
from app.core.config import get_settings
|
||||
from app.infrastructure.db import SessionFactory
|
||||
from app.model.memory import MemoryUnit
|
||||
from app.model.profile import UserFact
|
||||
from app.service.profile_assembly_service import ProfileAssemblyService
|
||||
from app.service.profile_graph_projection_service import ProfileGraphProjectionService
|
||||
from app.service.relationship_service import RelationshipService
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
|
||||
|
||||
@dataclass(frozen=True)
|
||||
class ProjectionCleanupOutcome:
|
||||
"""与 `app/worker/runtime.py` 的同名结构保持字段一致(该处只按属性取用)。
|
||||
|
||||
`cleaned=True` 表示派生数据已确实清理;为假时 `detail` 必须说明真实缺口,
|
||||
审计会原样记录它。
|
||||
"""
|
||||
|
||||
cleaned: bool
|
||||
detail: str = ""
|
||||
|
||||
|
||||
class ProjectionCleanupService:
|
||||
def __init__(self, relationships: RelationshipService | None = None) -> None:
|
||||
self.relationships = relationships
|
||||
|
||||
async def cleanup(self, *, memory_uuid: str, operation: str) -> ProjectionCleanupOutcome:
|
||||
del operation # 失效与删除对投影的处理一致:都以权威源为准重建
|
||||
async with SessionFactory() as session:
|
||||
memory = await session.scalar(
|
||||
select(MemoryUnit).where(MemoryUnit.memory_uuid == memory_uuid)
|
||||
)
|
||||
if memory is None:
|
||||
# 记忆已经不在库里:投影清理的目标已消失,视为完成(幂等)
|
||||
return ProjectionCleanupOutcome(True, "memory_not_found")
|
||||
customer_id = int(memory.customer_id)
|
||||
fact_key = str(memory.memory_key)
|
||||
|
||||
# 该记忆已失效/删除,它对应的事实不应再参与画像
|
||||
async with SessionFactory() as session, session.begin():
|
||||
await session.execute(delete(UserFact).where(
|
||||
UserFact.customer_id == customer_id, UserFact.fact_key == fact_key
|
||||
))
|
||||
|
||||
# 以剩余证据重建画像,再让图跟着画像收敛
|
||||
details: list[str] = []
|
||||
try:
|
||||
async with SessionFactory() as session, session.begin():
|
||||
await ProfileAssemblyService(session).rebuild(customer_id)
|
||||
details.append("profile_rebuilt")
|
||||
except Exception:
|
||||
logger.warning("profile rebuild failed during cleanup customer_id=%s",
|
||||
customer_id, exc_info=True)
|
||||
details.append("profile_rebuild_failed")
|
||||
|
||||
graph_ok = await self._cleanup_graph(customer_id, details)
|
||||
vector_ok = await self._cleanup_vector(memory_uuid, details)
|
||||
return ProjectionCleanupOutcome(
|
||||
cleaned=graph_ok and vector_ok and "profile_rebuild_failed" not in details,
|
||||
detail="; ".join(details),
|
||||
)
|
||||
|
||||
async def _cleanup_graph(self, customer_id: int, details: list[str]) -> bool:
|
||||
if self.relationships is None:
|
||||
details.append("graph_client_unavailable")
|
||||
return False
|
||||
try:
|
||||
async with SessionFactory() as session:
|
||||
outcome = await ProfileGraphProjectionService(
|
||||
session, self.relationships
|
||||
).reconcile_customer(customer_id, repair=True)
|
||||
except Exception:
|
||||
logger.warning("graph cleanup failed customer_id=%s", customer_id, exc_info=True)
|
||||
details.append("graph_cleanup_failed")
|
||||
return False
|
||||
if outcome.degraded:
|
||||
details.append(f"graph_degraded:{outcome.reason}")
|
||||
return False
|
||||
if not outcome.consistent:
|
||||
# repair 之后仍不一致:如实报告,不写成清理成功
|
||||
details.append(
|
||||
f"graph_still_inconsistent:missing={len(outcome.missing)},"
|
||||
f"orphaned={len(outcome.orphaned)}"
|
||||
)
|
||||
return False
|
||||
details.append("graph_cleaned")
|
||||
return True
|
||||
|
||||
async def _cleanup_vector(self, memory_uuid: str, details: list[str]) -> bool:
|
||||
"""删除该记忆的向量。集合不存在(未启用语义召回)时视为无需清理。"""
|
||||
settings = get_settings()
|
||||
if not settings.milvus_uri:
|
||||
details.append("vector_store_not_configured")
|
||||
return True
|
||||
try:
|
||||
from pymilvus import MilvusClient # type: ignore[import-untyped]
|
||||
|
||||
client = MilvusClient(
|
||||
uri=settings.milvus_uri, token=settings.milvus_token or None
|
||||
)
|
||||
except Exception:
|
||||
logger.warning("milvus client unavailable during cleanup", exc_info=True)
|
||||
details.append("vector_client_unavailable")
|
||||
return False
|
||||
try:
|
||||
if settings.milvus_collection not in set(client.list_collections()):
|
||||
# 记忆向量集合尚未启用:没有需要清理的派生数据
|
||||
details.append("vector_collection_absent")
|
||||
return True
|
||||
client.delete(
|
||||
collection_name=settings.milvus_collection,
|
||||
filter=f'memory_uuid == "{memory_uuid}"',
|
||||
)
|
||||
details.append("vector_cleaned")
|
||||
return True
|
||||
except Exception:
|
||||
logger.warning("milvus delete failed memory_uuid=%s", memory_uuid, exc_info=True)
|
||||
details.append("vector_delete_failed")
|
||||
return False
|
||||
+16
-1
@@ -4,6 +4,8 @@ import logging
|
||||
|
||||
from app.core.config import get_settings
|
||||
from app.infrastructure.db import engine
|
||||
from app.service.agent.bootstrap import get_relationship_service
|
||||
from app.service.projection_cleanup_service import ProjectionCleanupService
|
||||
from app.worker.runtime import WorkerRuntime
|
||||
|
||||
logger = logging.getLogger(__name__)
|
||||
@@ -11,7 +13,20 @@ logger = logging.getLogger(__name__)
|
||||
|
||||
async def serve(*, once: bool = False) -> None:
|
||||
settings = get_settings()
|
||||
runtime = WorkerRuntime(settings=settings)
|
||||
relationships = get_relationship_service()
|
||||
# 在**组装层**注入投影删除客户端:记忆失效/销户时清理图库与向量库里的派生数据。
|
||||
# 放在这里而不是 runtime 内部兜底,是为了保留"未注入即显式降级并留痕"的语义
|
||||
# (有单测守着这一点),也让"生产装配了什么"在入口处一眼可见。
|
||||
# 该服务返回自己模块里的 ProjectionCleanupOutcome(字段与 runtime 的同名结构一致),
|
||||
# 结构化契约成立但名义类型不同,故显式忽略:为此把结构体抽到共享模块会造成
|
||||
# service 与 worker 两个层次互相导入,不值得。
|
||||
runtime = WorkerRuntime(
|
||||
settings=settings,
|
||||
relationships=relationships,
|
||||
projection_cleaner=ProjectionCleanupService( # type: ignore[arg-type]
|
||||
relationships=relationships
|
||||
),
|
||||
)
|
||||
try:
|
||||
while True:
|
||||
try:
|
||||
|
||||
@@ -79,7 +79,7 @@ class WorkerRuntime:
|
||||
endpoint_resolver: ExtractionEndpointResolver | None = None,
|
||||
memory_cache: CacheDeleteAdapter | None = None,
|
||||
projection_cleaner: ProjectionCleaner | None = None,
|
||||
relationships: Any | None = None,
|
||||
relationships: Any = None,
|
||||
) -> None:
|
||||
self.factory = factory if factory is not None else get_agent_factory()
|
||||
self.settings = settings or get_settings()
|
||||
@@ -97,8 +97,9 @@ class WorkerRuntime:
|
||||
self.memory_cache: CacheDeleteAdapter | None = (
|
||||
memory_cache if memory_cache is not None else get_memory_cache_adapter()
|
||||
)
|
||||
# Milvus/Neo4j 删除客户端:当前组装层没有提供(bootstrap 只装配召回用的读适配器),
|
||||
# 因此默认 None = 投影清理显式降级并留痕,绝不写成"删除成功"。
|
||||
# Milvus/Neo4j 删除客户端:由**组装层**(app/worker/__main__.py)注入生产实现,
|
||||
# 这里不兜底。组件内部给默认实现会把"尚未装配"这一事实悄悄盖住——而"未注入即显式
|
||||
# 降级并留痕"是本模块刻意保留的语义(有单测守着),因此默认值保持 None。
|
||||
self.projection_cleaner = projection_cleaner
|
||||
# 图关系服务:画像投影用它写入节点与关系(投顾的多跳推荐、风控的关系网络都读它)。
|
||||
# 默认取生产装配;图库不可用时该值为 None,投影如实降级而不是失败。
|
||||
|
||||
Reference in New Issue
Block a user