root and Claude Opus 5.5
c2bf8a071a
feat(storage): 存储实例与 Alist 虚拟路径(迁移 0090、设置接口、注册表、vfs、健康检查)
...
- storage_instance 表 + secret 用途 storage_credential;令牌 / 密码 / 路径密码只写不读
- /storage-instances CRUD 与测试连接(版本、用户、根路径、容量);被库根引用不能删
- 远端路径 /@alist/<id>/<路径>,vfs 统一本地 / Alist 的 stat、列目录、建目录、读写、移动、删除
- 整理矩阵中涉及 Alist 的传输(storage/transfer.ts)与远端 ffprobe(直链只读头)
- 媒体库目录可登记在 Alist 上(不写哨兵,目录可访问即在线);健康检查列出存储实例
Co-Authored-By: Claude Opus 5.5 <[email protected] >
Claude-Session: https://claude.ai/code/session_01Cxwgnn2pbzQ7rXv3rq7fei
2026-10-06 23:52:20 +08:00
root and Claude Opus 5.5
63bbcf3cdb
feat(status): 启用 pg_stat_statements,运行状态页显示最慢 / 最频繁语句与各表死元组;PG 调低 random_page_cost
...
- docker-compose.yml 的 postgres 加 shared_preload_libraries=pg_stat_statements、pg_stat_statements.track=top;
要重建 postgres 容器才生效(docs/runbook/storage.md)
- GET /system/storage 的 db.statements:平均最慢(调用 ≥ 10 次)与调用最多各 5 条;没装扩展 / 没预加载时
enabled=false 并说明原因
- 运行状态页「存储」:体积最大的表加死元组列,新增「数据库语句统计」
- random_page_cost 4 → 1.1(PG_RANDOM_PAGE_COST):库整个在内存里,缺省值高估随机读
Co-Authored-By: Claude Opus 5.5 <[email protected] >
Claude-Session: https://claude.ai/code/session_01Cxwgnn2pbzQ7rXv3rq7fei
2026-10-06 20:24:34 +08:00
root and Claude Opus 5.5
8c8b252667
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
2026-10-06 20:24:26 +08:00
root and Claude Opus 5.5
da33cad81d
feat(worker): IO Worker 分道(WK-1)
...
io worker 进程内按任务声明的 lane 分文件 / 网络 / 维护三条道,各自并发(缺省 2/4/1)、
各自排队;维护道在文件道或网络道有排队/运行时让路(连续 10 分钟放行一个),调度器内联的
清理/回填/保留期裁剪也走维护道。并发在 设置 → 自动化 → 高级 热生效,env 覆盖;旧
WORKER_CONCURRENCY 映射到网络道。运行状态页按道显示运行中/并发/排队。归属表写进
docs/runbook/dev.md,ci 与注册表逐项核对。
Co-Authored-By: Claude Opus 5.5 <[email protected] >
2026-09-30 00:24:21 +08:00
root and Claude Opus 5.5
05b163ce32
feat(system): retention cleanup jobs, storage panel API and health storage level (CACHE-2)
...
Co-Authored-By: Claude Opus 5.5 <[email protected] >
2026-09-29 17:16:50 +08:00
root and Claude Opus 5.5
a00a9eaf5d
feat(agent): budget reminders, usage while waiting, budget-exceeded status and dedupe
...
- tool results carry a budget reminder near limits; text before the last tool
call is dropped as report when cut by budget/abort
- usage persisted when a run suspends, so waiting sessions show spent tokens
- task page shows budget_exceeded via business.outcome instead of completed
- budget-exceeded decisions merge by root cause (decision / schedule / goal
template); new summaries added to investigate allowlist
Co-Authored-By: Claude Opus 5.5 <[email protected] >
2026-09-29 01:58:28 +08:00
root and Claude Opus 5.5
b4c9b1ead2
fix(system): retired heartbeat rows no longer alarm on status page
...
- GET /system/health splits processes into current instances (hosts with
a beat in the last 10 min, newest per host+kind, not stopped) and
retiredProcesses[]; 45s stale and level only consider current ones
- heartbeat writer marks stopped_at on graceful exit (migration 0043),
upsert clears it; pure api role now stops its writer on SIGTERM
- scheduled job system.heartbeat_cleanup (maintain, 1h) deletes rows
without a beat for 24h and samples older than 7 days
- status page: per-role alarms ("io worker 45 秒没有心跳"), collapsible
retired instances; glossary/runbook updated
- bump all members to 0.2.2, CHANGELOG [0.2.2]
Co-Authored-By: Claude Opus 5.5 <[email protected] >
2026-09-28 23:31:21 +08:00
root and Claude Opus 5.5
363f85b1a1
feat(server,contracts,web): dashboard library counts and engine runs triggeredBy/multi-status filters
...
- GET /dashboard: automation.library {entities, movies, series, seasons,
episodes, assets} and automation.slotSatisfiedRate; home media overview
shows the counts instead of placeholders.
- GET /engine/runs: `status` accepts comma-separated values; new
`triggeredBy` filter (comma-separated) evaluated server-side by scanning
batches and paging with the last inspected row's cursor (scan cap 2000).
- Task stream: source filter and the "active" tab (running,pending) are now
one paginated server query.
Co-Authored-By: Claude Opus 5.5 <[email protected] >
2026-09-28 16:49:11 +08:00
root and Claude Opus 5.5
e8745115f4
feat(system): process heartbeat + /system/health, engine runs business fields (W9-I)
...
- process_heartbeat / process_heartbeat_sample (0034): api / worker / worker:agent / all
upsert every 15s (event loop lag last/max, concurrency, running runs, SSE connections, memory)
- GET /system/health (admin): processes with 45s stale flag, SSE, DB latency/size/connections,
disks (DATA_DIR / library roots / download dirs, cache thresholds), mount sentinel checks
with IO timeout, engine pending/oldest/24h failure rate, schedules
- GET /system/health/history?hours=: bucketed lag / running / SSE series
- /engine/runs and /engine/runs/{id}: business {kind, refId, title, triggeredBy} joined from
run input / task / agent_run / tasks_run_meta / outbox; businessKind / businessRefId filters
- docs/runbook/ops.md: field meanings and alert thresholds
Co-Authored-By: Claude Opus 5.5 <[email protected] >
2026-09-28 15:23:37 +08:00
root and Claude Opus 5.5
ff230e5da7
feat(server): W2-A login gate, secrets, settings, instances, audit, engine panel API and PG-backed SSE bus
...
- Admin login gate (docs/design/auth-reference.md): admin_user/admin_session/login_attempt
(migration 0015), one-time setup token logged once + conditional UPDATE, argon2id via
hash-wasm (WASM; compiled binary has no --allow-ffi), sha256-stored sessions in HttpOnly
SameSite=Lax cookie umt_session (fixed 12h TTL, soft revoke), HMAC-derived double-submit
CSRF, IP (5) + account (15) failure limits per 15 min, password change revokes other
sessions, optional TOTP with replay counter, AuditAction enum.
- Unified auth middleware: cookie session or Bearer API key -> c.var.actor
{type: admin|api_key, id, name, scopes}; requireScope works for both; requireAdminSession.
- ctx.secrets: AES-256-GCM, per-secret HKDF-SHA256 key from SECRET_MASTER_KEY, AAD bound
to (id, purpose); ctx.settings: 30s cache invalidated by settings.changed events.
- Endpoints: /auth/*, /settings, /api-keys, /secrets, /audit-events, library-roots,
downloader/media-server instances (+test), path-mappings (+verify),
PUT /sites/{id}/credentials, /engine/runs|stats|cancel (read-only openworkflow schema).
- SSE: PgEventBus (sse_event table, migration 0016, LISTEN/NOTIFY umt_events, catch-up by
seq, pruning, resync); EventBusPort is now async.
- Tests: login/rate limit/revocation/CSRF/TOTP, secrets round trip and no log leakage,
admin APIs against mock qB/Emby, SSE across two Deno subprocesses.
Co-Authored-By: Claude Opus 5.5 <[email protected] >
2026-09-27 19:59:54 +08:00
root and Claude Fable 5.1
304feea141
chore(deno): migrate toolchain from Node 24 + pnpm to Deno 2.9.7 + TypeScript 7.0.2 (W1.5)
...
- root deno.json workspace (nodeModulesDir auto), npm versions registered once in imports, deno.lock;
remove pnpm-lock/pnpm-workspace/root package.json; members keep minimal package.json (name/type/exports)
- tasks: dev, typecheck (tsc 7.0.2 per member + deno check), lint/fmt (biome, useImportExtensions),
test (vitest via deno), check:tokens, build (web + deno compile), ci, db:migrate/reset, gen:types
- tsconfig base moved to config/ (no root tsconfig.json); deno types -> types/deno.d.ts; web drops baseUrl
- server: Deno.serve entry with graceful shutdown, --role migrate|preflight|probe, WEB_ROOT static SPA hosting;
drop @hono/node-server, tsx, esbuild build.mjs
- logger: redact child() bindings and serialize err by message/stack; sync stdout destination; tests
- relative imports get explicit extensions (sites/mp-sync paths left for follow-up)
- crash-recovery tests spawn `deno run -A`; tasks tests use unique per-file schemas
- single-container Dockerfile + entrypoint (migrate -> preflight -> api+worker watchdog), docker-compose.yml
- docs: README, runbook, ADR-001 superseded, plan §1 validation row
Co-Authored-By: Claude Fable 5.1 <[email protected] >
2026-09-27 18:53:06 +08:00
root and Claude Fable 5.1
cc8b3a7df4
feat(db,contracts): full v0.1 data model migrations and shared zod contracts (W1-1)
...
- migrations 0002-0012 split by domain (foundation/instances/content/identity/
sources/assets/policy/execution/agent/ops/organization): 41 tables, uuid pk,
created_at/updated_at + touch trigger, text+CHECK status sets, pgcrypto/pg_trgm
- key constraints: source_release(site_id, site_release_id), observation(feed_id, guid),
external_identity accepted partial unique, download_task(instance_id, torrent_hash),
one active acquisition_plan per slot, one active path_binding per entity/season,
asset_location root+path uniqueness, organization_record change_seq/change_xid cursor
- secret table (ciphertext/nonce/kdf) + secret_ref columns; outbox dispatch fields (ADR-002)
- src/types.ts generated from the migrated schema (scripts/gen-types.ts), drift-checked in tests;
int8 -> number, date -> string parsers; migrator accepts migrationTableSchema
- contracts: Row/Create/Update schemas per domain, public organization-record API
(changeSeq cursor), GlobalSettings, CapabilityDescriptor + 14 capability IO schemas,
typed SSE events, Api endpoint table
- tests: migration up/down round trip on real PG in an isolated schema, constraint checks,
contracts<->db column/enum sync, positive/negative parse for every exported schema
Co-Authored-By: Claude Fable 5.1 <[email protected] >
2026-09-27 18:11:37 +08:00