Commit Graph
17 Commits
Author SHA1 Message Date
rootandClaude Opus 5.5 3692793dff feat(agent): 抽屉与会话页统一成一个对话界面,子会话在父会话里实时可见
- 抽屉和会话页渲染同一套 GoalComposer / AgentRunPanel;抽屉标题即最近会话切换,
  头部只有新对话、在页面打开、关闭;去掉右下角悬浮按钮和最小化小窗
- 会话列表合一:对话与巡检混排带类型小标签,搜索 + 一个状态下拉,只列顶层会话
  (GET /agent/runs?roots=true,新增可选参数)
- 子会话卡片:由镜像的 subagent_* 事件折成,显示任务、状态、当前步骤、用时、调用次数、费用,
  可展开看过程、可打开;顶部「N 个子会话运行中」跳到卡片;subagent_completed 加可选 durationMs
- 回答去内部字段:汇报规则禁止照抄键值与字段表;展示层 stripInternalFields 把字段行 / 字段表移进技术信息
- 开场建议按页面给 2 条完整问法、点了直接发;指令只留 /先给方案,/重跑 改成「重新运行」按钮

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Cxwgnn2pbzQ7rXv3rq7fei
2026-10-08 13:56:38 +08:00
rootandClaude Opus 5.5 414ea7c890 feat(智能体): 不设硬性预算上限,花费改为可见
- 去掉每天次数、每天花费、单次花费、单次 token 四个上限的拦截;设置项登记为弃用,旧值兼容读取、不生效
- 保留单次工具调用次数与时长两个防跑飞限制,缺省调宽(120 次 / 1800 秒,后台调查 20 次)
- 新增 GET /agent/usage:今天与最近 7 天按会话类型(对话 / 巡检 / 后台调查 / 整理识别 / 子会话)的次数、token 与费用
- 设置 agent.autoIdentifyOrganize(整理识别不到时叫智能体识别,缺省开)一并加在智能体设置里
- runner 里加整理识别会话的能力白名单与调查会话去重键解析(investigationDecisionId)

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Cxwgnn2pbzQ7rXv3rq7fei
2026-10-06 16:47:18 +08:00
rootandClaude Opus 5.5 4bb19433ad feat(手动下载): 保存目录选项接口与下载前指定作品
- GET /download-save-paths:按下载器列出默认保存目录与路径映射的下载器侧目录,并给出「自动」会用的下载器(站点指定 > 默认 > 第一个)
- POST /acquisition-plans 新增 identity(本地作品或 TMDB 外部身份):转调 /source-releases/{id}/identity 建 / 绑作品并加人工锁,再按该作品下载
- 测试 harness 支持装配 agent 模块;pg 测试覆盖保存目录选项与指定身份下载

Co-Authored-By: Claude Opus 5.5 <[email protected]>
Claude-Session: https://claude.ai/code/session_01Cxwgnn2pbzQ7rXv3rq7fei
2026-10-06 12:10:03 +08:00
rootandClaude Opus 5.5 8eb8a68295 feat(web): 站点按类型分组、列表模式修样式、下掉自定义 RSS 源与索引器入口;智能体会话分对话 / 自动巡检两栏
Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-02 23:56:27 +08:00
rootandClaude Opus 5.5 ceb66f8c77 feat: v0.3.8–v0.3.14 工作区汇总(依赖升级、整理来源、手动入库、原地入库等)
生产 v0.3.8~v0.3.13 均由 8013196 加工作区修改构建部署,此前未提交;本提交补齐源码,
并含未部署的 v0.3.14 原地入库。中间各版本源码状态未保存,无法逐版拆分,详见
docs/plan/17-full-upgrade.md 与 docs/plan/18-organize-release.md。

- v0.3.8 全面升级:Deno workspace 依赖、Router 8 / Vite 8、camofox 1.18.0 / Node 24、
  PostgreSQL 18.6、备份客户端 18.6、演示 qB 5.2.4
- v0.3.9 媒体整理:分类规则、整理来源与目录快照(0059)、文件管理整理入口
- v0.3.10 手动下载与入库:独立手动下载、详情页资源下载、TMDB / Local 元数据兜底
  (metadata.resolve_organize)、正常多版本 / 一次性洗版(0060)
- v0.3.11 搜索详情与桌面黑边修复
- v0.3.12 列表分页、搜索历史、首页概况
- v0.3.13 统一整理弹窗与队列
- v0.3.14 原地入库(0061,未部署)

同批审计修复:
- 刮削入队:确认原记录存在后才删重放产生的新记录;写回 run 关联失败时保持 queued,
  由处理器补关联(对齐 MP 先登记、只在入队失败时记失败)
- 识别升级链只在结果更确定时采用,不再用 no_match 顶替原有歧义候选
- bluray_dir 资产以原盘目录本身为刮削根(MP 同做法)
- metadata.resolve_organize 登记到入库排障 Skill 与能力地图
- db/src/types.ts 按迁移重新生成;contracts 整理动作枚举顺序与数据库对齐
- 测试:原地入库用例改为直接查记录表;domain 测试模板补 version
- 前端:通知铃铛弹层与用户菜单统一样式;站点卡片共用卡头、底栏贴底、分页间距

依赖升级证据只提交摘要文件,registry-snapshot.json 移至 .local/(SHA-256 记于文档)。

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-10-02 15:47:17 +08:00
rootandClaude Opus 5.5 4e0e6712da feat(agent): 选定方案即批准,服务端绑定计划(AGUI-3)
- agent.propose_options 的方案可带 action(capabilityId + planId)。提出方案时服务端按计划当前的
  payload hash + revision 绑定,并用计划本身生成动作要点(对象、大小 / 文件数)发给界面,不用模型的说法。
- 控制台管理员会话选定绑定了计划的方案时,建一份 scope.via=option 的已批准单次审批(审计 approval.approved);
  执行时授权器 optionApproval 核对能力、计划类型 + ID、payload hash、revision、有效期后放行,用后 consumed,
  不再出第二张审批卡。API Key 作答、超时自动选、计划已变化都不算批准;移动 / 替换文件的整理与发布策略
  (删除、覆盖类)选定后仍单独确认。会话停止时撤销没用掉的这类审批。
- contracts:CAPABILITY_ACTIVITY 给每个能力加 verb / noun(会话进度行的人话计数);agent.plan /
  agent.propose_options 标为 hidden。
- e12 补测试:管理员选定 → 无 approval_requested、审批绑定同一计划并 consumed、换 hash 不放行;
  API Key 选定 → 仍出审批卡。

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-09-29 22:40:57 +08:00
rootandClaude Opus 5.5 4480fc346d refactor(copy): 术语统一——收录版本、模型服务、智能体等(DEAI-2)
- 版本目标 → 收录版本(前后端用户可见字符串、能力描述、给模型的提示)
- Agent 上游 / 上游 → 模型服务;界面上的 Agent / Agent 会话 → 智能体 / 智能体会话
- 身份歧义 / 识别有歧义 / 无法确定作品 → 没识别出作品;待识别(池) → 未识别
- 建档 → 加入媒体库;资产 → 文件;库根 → 媒体库目录;纳管 → 本工具 / 外部任务;
  哨兵 → 标记文件 / 检查目录;站点快照 → 抓取;Feed / RSS 订阅 / 来源健康 → RSS
- 代码标识符、API 字段名、迁移文件不改;glossary.md 同步;smoke 选择器跟随

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-09-29 20:35:43 +08:00
rootandClaude Opus 5.5 fb84a71f80 style(copy): fix remaining punctuation violations and make check:copy strict
Auto-fix of 602 string literals across 74 files (half-width punctuation next to
Chinese, parenthesised Chinese, quotes); biome reflow; e2/e6 assertions follow
the new full-width summaries. check:copy now runs with --strict in ci.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-09-28 21:34:51 +08:00
rootandClaude Opus 5.5 cf2c4ff0e6 feat(agent): automation-first sessions with step plan, option choice and inline approval
- agent.plan emits plan_updated; system prompt asks for a plan first and updates while executing
- agent.propose_options registers a decision and suspends the run (waitForFact, no worker slot);
  the answer or timeout (recommended/stop) resumes it as the tool result
- console-session runs get inline approvals for plan-bound capabilities: approve replays the call
  with the approval, reject fails it with the reason and records it on the decision
- proposeFirst blocks execute capabilities until an option is chosen; E12 covers all paths

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-09-28 21:07:01 +08:00
rootandClaude Opus 5.5 31a54186c7 copy: second-round copy review across console, settings, agent and server messages
- Trim descriptions, empty states, confirm buttons and toasts to facts
- Unify terms per glossary: 待处理/待识别/整理记录/运行记录/凭证/子会话/Agent 上游
- Subscription-login termsNote states facts only (borrowed client identity, ToS/ban risk)
- Shorter, concrete goal templates for built-in Agent checks
- Human-readable nouns instead of table names in instance CRUD errors
- Audit labels for pi_upstream / schedule / automation_grant actions
- Glossary: add 上游、订阅登录、凭证、定时任务、巡检、运行记录、子会话、停止、持续授权

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-09-28 13:29:42 +08:00
rootandClaude Opus 5.5 459991421e feat(agent): Pi subagents via agent.spawn / agent.await
- agent_run gains depth / spawn_reason (0029); agent_run_event types
  subagent_spawned / subagent_event / subagent_completed
- agent.spawn (propose, medium, replay never): allowlist ⊆ parent, mode not
  above parent, budget carved from parent's remainder, idempotent per run+input;
  settings.pi.subagents {enabled, maxConcurrent, maxDepth} (subagentsEnabled kept as alias)
- child runs claim a concurrency slot under an advisory lock (waitForFact while
  queued); agent.await polls business tables without calling the model
- parent abort cascades to all descendants; parent runtime budget counts
  descendant usage; child events mirrored into the parent stream by parent seq
- authorize caps every child call by all ancestors' allowlists/kinds
- session page shows parent link, inherited info and the subagent tree
- e2e E11; runbook section on subagents

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-09-28 02:49:37 +08:00
rootandClaude Fable 5.1 16ab2a6c84 docs(plan): v0.2 adds Pi subagents and scheduled-jobs board
Co-Authored-By: Claude Fable 5.1 <[email protected]>
2026-09-28 02:09:39 +08:00
rootandClaude Opus 5.5 b4560be48b fix(files): S-6 identify goes through the shared TMDB limiter and caps remote queries
- invoke-limits: sharedInvokeLimiter() (one semaphore set per process); agent
  capability routes default to it
- /files/identify: catalog.lookup with includeRemote runs under the shared
  TMDB semaphore + 15s timeout; at most 20 distinct remote queries per
  request, further items fall back to local recall with a warning

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-09-28 00:48:45 +08:00
rootandClaude Opus 5.5 f48e1aac96 fix(security): W4-E1 approvals admin-session only, shared redact table, TMDB key redaction, prod mock gate
- POST /approvals and PATCH /approvals/{id} require a console admin session
  (EndpointDef auth:"session"); API keys incl. admin scope get 403, so an
  organize.execute key can no longer approve its own plan (S1)
- tests for single-use approval checks: expired, revision/payload hash
  mismatch, consumed, revoked, pending/rejected, plan mismatch; re-approve
  after plan change succeeds once and cannot be replayed (S4)
- one redact key table in @umt/contracts shared by server logger and agent
  redactForModel: rsskey, torrent_pass, authkey, downhash, c_secure_pass,
  passkey variants, x-api-key, cookie headers, nested objects/arrays (S2)
- TMDB network errors: message and cause redacted via redactUrl (S3)
- web Agent ?mock=1 only in DEV builds or when pi.provider is fake (S7)
- EndpointDef auth annotations for /auth/*, asserted against
  PUBLIC_AUTH_PATHS (S10); doc drift fixes (S11)

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-09-27 22:24:44 +08:00
rootandClaude Opus 5.5 473c5e94a5 feat(server): io/agent worker groups, invoke limits for external IO capabilities, loop lag probe
- WORKER_CONCURRENCY / WORKER_AGENT_CONCURRENCY; --role worker (io), worker:agent, all (both)
- HTTP invoke of release.search/inspect, identity.resolve, catalog.lookup(remote):
  15s timeout + per-upstream semaphore (site 2, TMDB 4)
- worker event-loop lag probe: warn + count when drift > 5s

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-09-27 22:12:16 +08:00
rootandClaude Opus 5.5 d3ab54f2bd feat(server): W4-A integration endpoints and contract gaps
- POST /acquisition-plans: manual submit via download.plan -> download.submit
  (same authorization/audit/idempotency path as the agent), slotId or entityId
- read-only /media-assets, /asset-locations, /asset-unit-coverage, /path-bindings,
  /reconcile-runs, /server-mappings, /artifacts, GET /title-aliases/{id};
  unimplemented write endpoints removed from api.ts; registry test now checks both directions
- candidate evaluation upsert per (slot, source_release) + migration 0022 dedupe/unique index
- organization records expose downloadTaskId (+ list filter); inventory adds
  subscribed/candidateReasons; feed sources expose derived possibleGap
- GET /events?after=&limit= JSON replay page for API key callers (same sse_event table)
- preference tag revision history from audit_event; subscriptions/identities/aliases
  lists carry mediaEntityTitle; subscription q/mediaKind search; slot subscriptionId
  filter + currentAsset summary; policy preview samples carry title/reasons
- DecisionSummary, IdentityRevisionList, ReleaseIdentityResult, PolicyPreviewSummary exported from contracts

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-09-27 21:10:02 +08:00
rootandClaude Opus 5.5 6280d52ec3 feat(server): W2-D agent assembly, session API, runAgent/resolveDecision and backend e2e
- Capabilities: all 14 registered (AO: inventory.query, download.plan/submit, organize.plan/execute,
  policy.preview/apply; agent: task.inspect/retry/cancel); startup asserts count == 14.
  Registry injects server-side authorize (automation_grant by action/scope/policy version/budget,
  one-shot approval bound to plan id + payload hash + revision + expiry; model claims ignored;
  automation switch), audit_event, server idempotency keys and a capability_invocation op ledger
  (migration 0021) used for crash reconciliation. download.plan creates draft plans only;
  download.submit promotes draft -> reserved after authorization.
- Agent session API: POST/GET /agent/runs, GET /agent/runs/{id} (events by seq, messages, report),
  POST .../messages (wake), POST .../abort; automation-grants, approvals, capabilities invoke, tasks.
- runAgent task: Pi or fake provider from settings (apiKey via secrets), events persisted to
  agent_run_event then published, resume + ledger reconciliation when pendingOperations > 0,
  waits for goal-linked downloads/imports and reports from business tables (submitted != imported).
- Background triggers: decision.created -> bounded plan_only investigation (dedupe per decision);
  decision.updated(resolved) -> resolveDecision executes chosen option.
- W2 closure: all OpenAPI routes registered in contracts api.ts (+ subset test); TMDB key from
  settings secret_ref with env fallback; PUT /sites/{id}/credentials documented as alias of
  /site-accounts; completion events documented as existing status events.
- e2e (real PG + OpenWorkflow + testkit mocks): RSS->library, agent delegation with grant/deny,
  background continuation, worker kill -9 recovery (single qB add), auto investigation dedupe.

Co-Authored-By: Claude Opus 5.5 <[email protected]>
2026-09-27 20:52:12 +08:00