feat(storage): 数据保留补齐引擎运行与流水表,新增每天低峰的流水数据清理和 db-retention 脚本

- 保留规则改为声明式(retention.ts 每个任务的 rules),定时任务、立即清理、脚本 dry-run 共用一份条件;
  删得多(≥ 1000 行)的表删完 ANALYZE
- 引擎 run 单独保留期 engineRun(缺省 14 天):只删终态、过期、没被保留中业务任务引用、父 run 已结束的;
  step_attempts 级联,运行元数据 / 事实 / 信号跟随 run(原来按时间直接删,长时间运行的 run 会丢元数据)
- 业务任务被 agent_run / decision 等引用时不删(外键 set null,删了会断开引用)
- 新任务 storage.retention.pipeline(每天 04:40):已投递 outbox 事件(只删无幂等键或一次性幂等键)、
  识别尝试(每条资源留最近 3 次)、已识别且资源仍绑定作品的待识别条目(忽略 / 归档不删)、
  站点快照(每站最近一次成功的列表快照保留)
- settings.storage.retentionDays 追加 engineRun / outboxEvent / resolutionAttempt / identityResolved /
  siteSnapshot(旧库按缺省补),设置页「系统 → 数据保留」显示
- scripts/db-retention.ts:缺省 dry-run 输出每张表将删行数,--apply 执行,--only 选目标
- 测试:各表按规则删、被引用 / 未结束的不删、dry-run 与删除一致、分批;EXPLAIN 确认改写后的查询走索引

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Cxwgnn2pbzQ7rXv3rq7fei

apps/web/app/components/settings/system.tsx

@@ -80,6 +80,11 @@ const RETENTION_KEYS = [
   "audit",
   "capabilityStats",
   "identityPoolArchive",
+  "engineRun",
+  "outboxEvent",
+  "resolutionAttempt",
+  "identityResolved",
+  "siteSnapshot",
 ] as const;
 export const STORAGE_RETENTION_CARD: CardSpec = {
   anchor: "storage-retention",
@@ -99,6 +104,11 @@ export const STORAGE_RETENTION_CARD: CardSpec = {
       "未识别资源归档",
       "未命中的条目这么久没有新证据就归档，仍可手动指定",
     ),
+    dayField("retentionDays", "engineRun", "后台运行记录", "仍被任务记录引用的跟随任务保留"),
+    dayField("retentionDays", "outboxEvent", "已投递的内部事件"),
+    dayField("retentionDays", "resolutionAttempt", "识别尝试记录", "每个资源至少留最近 3 次"),
+    dayField("retentionDays", "identityResolved", "已识别的待识别条目", "忽略和归档的不删"),
+    dayField("retentionDays", "siteSnapshot", "站点快照", "每个站点最近一次成功的保留"),
   ],
   fromSettings: (s) =>
     Object.fromEntries(RETENTION_KEYS.map((k) => [`storage.retentionDays.${k}`, n(s.storage.retentionDays[k])])),

apps/web/app/components/status/storage-section.tsx

@@ -38,6 +38,7 @@ export const CLEANUP_LABEL: Record<StorageCleanupTarget, string> = {
   agent_event: "智能体事件",
   audit: "审计事件",
   capability_stats: "能力调用统计",
+  pipeline: "流水数据",
   identity_pool: "未识别资源归档",
   analyze: "数据库维护",
   images: "图片缓存容量",