Files
group_fqcd_jr/app/service/config_release_service.py
T
lzf_0626 38a9bc8285 fix(platform): 配置发布激活时点名"将被丢掉的配置项"
config_release 是**整版本替换**语义:激活新版本后,旧版本的配置项全部不再生效。
所以新版本只要漏了某项,它就是**无声消失**的——agent_tools 里的工具白名单一少,
相关 Agent 的工具就被 fail-closed 拒掉,而现场表现只是"客服/风控什么都答不了",
没人会想到是发布配置少了一条。

本项目已经两次靠"发布前手工继承"规避(客服与风控的发布脚本里各写了一遍继承逻辑),
说明这个风险真实且反复出现。

改为在 activate 时先比对"被取代版本的配置项"与"新版本的配置项",把将被丢掉的逐条
写进 warning 日志。**不阻断激活**——有时确实是要主动撤下某项配置,拒绝会让正常运维
做不了事;这里要的是"事后能查到是谁把它弄没的"。

新增 tests/unit/service/test_config_release_dropped_items.py(3 条):丢项时点名、
完整继承时无噪音(否则运维会习惯性忽略这条日志)、首个版本不报丢项。

ruff / mypy(135 文件) / 610 unit+contract 全绿。
2026-09-11 13:01:58 +08:00

219 lines
9.5 KiB
Python

import logging
from datetime import UTC, datetime
from uuid import uuid4
from sqlalchemy import select
from sqlalchemy.ext.asyncio import AsyncSession
from app.model.audit import InteractionAudit
from app.model.configuration import ConfigRelease, PlatformConfigItem
from app.model.platform import DomainEventOutbox
logger = logging.getLogger(__name__)
class ConfigReleaseError(ValueError):
pass
class ConfigReleaseService:
def __init__(self, session: AsyncSession) -> None:
self.session = session
async def submit_for_review(self, release_id: int, actor_id: int) -> ConfigRelease:
release = await self._get(release_id)
if release.created_by != actor_id or release.status != "draft":
raise ConfigReleaseError("only draft owner can submit")
release.status = "pending_review"
release.updated_at = self._now()
self._audit("config.submit_review", actor_id, release)
await self.session.flush()
return release
async def approve(self, release_id: int, reviewer_id: int) -> ConfigRelease:
# 只保留状态机约束:必须处于待审核状态才能审核通过;不再要求审核人不同于创建人
# (单管理员部署下自审是唯一可行路径)。数据库侧原本还有
# `chk_config_release_separation` 强制双人复核,已于迁移
# `20260910_drop_review_separation` 撤下,因此自审现在与多人复核一样**如实写入
# `reviewer_id`**:该列的含义就是"审核人",留空会让"谁审的"只能靠审计表追溯,
# 一旦有人只读业务表就会误判这条版本尚未复核。
release = await self._get(release_id)
if release.status != "pending_review":
raise ConfigReleaseError("release is not pending review")
release.status = "approved"
release.reviewer_id = reviewer_id
release.reviewed_at = self._now()
release.updated_at = release.reviewed_at
self._audit("config.approve", reviewer_id, release)
await self.session.flush()
return release
async def _warn_dropped_items(
self, release: ConfigRelease, previous_active: list[ConfigRelease]
) -> None:
"""列出"旧版本有、新版本没有"的配置项——它们在激活后会静默失效。
`config_release` 是**整版本替换**语义:激活新版本后,旧版本的所有配置项都不再生效。
所以只要新版本漏了某一项,它就是**无声消失**的——工具白名单随之变成空集、相关
Agent 的工具被 fail-closed 拒掉,而现场表现只是"客服/风控什么都答不了",
没人会想到是发布配置少了一条。
本项目已经两次靠"发布前手工继承"规避(客服与风控的发布脚本里各写了一遍继承逻辑),
这说明风险是真实且反复出现的。这里不阻断激活(有时确实是要撤下某项配置),
但把它显式写进日志,让运维事后能查到"是谁把它弄没的"。
"""
if not previous_active:
return
rows = (await self.session.execute(
select(
PlatformConfigItem.namespace,
PlatformConfigItem.config_key,
PlatformConfigItem.release_id,
).where(PlatformConfigItem.release_id.in_(
[previous.id for previous in previous_active] + [release.id]
))
)).all()
new_keys = {(namespace, key) for namespace, key, rid in rows if rid == release.id}
for previous in previous_active:
old_keys = {(namespace, key) for namespace, key, rid in rows if rid == previous.id}
dropped = sorted(old_keys - new_keys)
if dropped:
logger.warning(
"配置发布 %s 取代 %s:以下 %d 条配置项在新版本中不存在,激活后即失效 → %s",
release.release_no,
previous.release_no,
len(dropped),
[f"{namespace}/{key}" for namespace, key in dropped],
)
async def activate(self, release_id: int, actor_id: int) -> ConfigRelease:
release = await self._get(release_id)
if release.status != "approved":
raise ConfigReleaseError("only approved release can activate")
active = await self.session.scalars(
select(ConfigRelease).where(ConfigRelease.status == "active")
)
now = self._now()
previous_active = [previous for previous in active if previous.id != release.id]
# 把"本次激活会让哪些配置项失效"显式记进日志,见 _warn_dropped_items 的说明。
await self._warn_dropped_items(release, previous_active)
for previous in previous_active:
previous.status = "superseded"
previous.updated_at = now
release.status = "active"
release.activated_at = now
release.updated_at = now
# 记录"本版本取代了谁"。`supersedes_release_id` 的列含义就是被取代的版本,但此前
# 从未写入,导致版本链断裂:清理或回滚旧数据时无法知道"谁顶掉了谁",一旦某次实验
# 创建的临时版本被删掉,平台就会静默停在"零个 active 版本"的状态(工具白名单随之
# 变成空集,所有 Agent 工具按 fail-closed 被拒)。唯一键 `uk_config_release_active_one`
# 保证同时最多一个 active,所以这里最多记录一条。
if len(previous_active) == 1:
release.supersedes_release_id = previous_active[0].id
self._audit("config.activate", actor_id, release)
self.session.add(
DomainEventOutbox(
id=0,
event_id=str(uuid4()),
event_type="config.cache_invalidate_requested",
aggregate_type="config_release",
aggregate_id=str(release.id),
trace_id=release.release_no,
payload={"release_id": release.id, "release_no": release.release_no},
status="pending",
retry_count=0,
occurred_at=now,
created_at=now,
updated_at=now,
)
)
await self.session.flush()
return release
async def rollback(self, release_id: int, actor_id: int) -> ConfigRelease:
target = await self._get(release_id)
if target.status not in {"active", "superseded"}:
raise ConfigReleaseError("release cannot be rolled back")
now = self._now()
current = await self.session.scalars(
select(ConfigRelease).where(ConfigRelease.status == "active")
)
for release in current:
release.status = "superseded"
release.updated_at = now
await self.session.flush()
rollback = ConfigRelease(
release_no=f"rollback-{uuid4().hex[:16]}",
title=f"Rollback {target.release_no}",
change_summary=f"Rollback to {target.release_no}",
status="active",
created_by=actor_id,
reviewer_id=None,
reviewed_at=None,
activated_at=now,
created_at=now,
updated_at=now,
rollback_of_release_id=target.id,
)
self.session.add(rollback)
await self.session.flush()
self.session.add(
DomainEventOutbox(
event_id=str(uuid4()),
event_type="config.cache_invalidate_requested",
aggregate_type="config_release",
aggregate_id=str(target.id),
trace_id=target.release_no,
payload={"release_id": target.id, "release_no": target.release_no},
status="pending",
retry_count=0,
occurred_at=now,
created_at=now,
updated_at=now,
)
)
self._audit("config.rollback", actor_id, rollback)
await self.session.flush()
return rollback
async def get_value(
self, release_id: int, namespace: str, config_key: str
) -> dict[str, object] | None:
item = await self.session.scalar(
select(PlatformConfigItem).where(
PlatformConfigItem.release_id == release_id,
PlatformConfigItem.namespace == namespace,
PlatformConfigItem.config_key == config_key,
)
)
return item.value_json if item else None
@staticmethod
def assert_if_match(current_version: str, if_match: str | None) -> None:
if if_match is None or if_match.strip('"') != current_version:
raise ConfigReleaseError("CONFIG_VERSION_CONFLICT")
async def _get(self, release_id: int) -> ConfigRelease:
release = await self.session.get(ConfigRelease, release_id)
if release is None:
raise ConfigReleaseError("release not found")
return release
def _audit(self, action: str, actor_id: int, release: ConfigRelease) -> None:
self.session.add(
InteractionAudit(
actor_type="user",
actor_id=actor_id,
target_customer_id=None,
session_id=None,
portal="admin",
action_type=action,
detail={"release_id": release.id, "release_no": release.release_no},
created_at=self._now(),
)
)
@staticmethod
def _now() -> datetime:
return datetime.now(UTC).replace(tzinfo=None)