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。
142 lines
6.5 KiB
Python
142 lines
6.5 KiB
Python
"""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.infrastructure.milvus_profile_projection import PROFILE_COLLECTION
|
||
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:
|
||
# 集合名与投影写入路径**同一个常量**（`PROFILE_COLLECTION`）。此前读的是
|
||
# 已删除的 `settings.milvus_collection`（`jr_memory`），该集合不存在
|
||
# ⇒ 这里每次都走下面的 `vector_collection_absent` 分支、
|
||
# **报清理成功但一个向量都没删**，陈旧向量永久留存。
|
||
if PROFILE_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=PROFILE_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
|