release: v2.2.0

mateclaw-desktop/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mateclaw-desktop",
-  "version": "2.2.0-SNAPSHOT",
+  "version": "2.2.0",
   "description": "MateClaw Desktop - AI Assistant powered by Spring AI Alibaba",
   "author": "MateClaw Team",
   "license": "Apache-2.0",

mateclaw-server/src/main/resources/docs/en/index.md

@@ -20,12 +20,15 @@ hero:
       link: https://github.com/mateaix/mateclaw
 
 features:
+  - icon: ⚙️
+    title: Employee runtimes, not one Agent loop
+    details: 2.2.0 uses a shared Runtime Contract to decouple employee identity from execution. Native and DeepSeek Harness share conversations, workspaces, tool governance, and event projection; durable Goals recover across requests and backend restarts, while A2A connects external agents.
   - icon: 🧑‍💼
     title: Digital employees, not chatbots
     details: You hire coworkers, not a chat box. Each one has a role, a goal, a backstory, a pixel-art avatar, and a color of their own — six built-in templates ship ready to use. ReAct + Plan-and-Execute, parallel delegation between employees.
   - icon: 🤝
     title: Teams, not lone wolves
-    details: One team request becomes one Team Run — objective, task DAG, worker execution, final synthesis, and deliverables stay together. Chat delivers outcomes, Agents observes live work, and Teams governs history and approvals. In 2.1.0, one round of collaboration is one complete work record.
+    details: One team request becomes one Team Run — objective, task DAG, worker execution, final synthesis, and deliverables stay together. Chat delivers, Agents observes, and Teams governs; 2.2.0 further hardens checkpoint recovery and deliverable completion gates.
   - icon: 🧩
     title: Skills are the skeleton, not a plugin
     details: One SKILL.md plus one LESSONS.md that grows with use. Eight starter templates, a five-step creation wizard, pre-flight checks before install. MCP and ACP bridges — even Claude Code and Codex show up as employees.

mateclaw-server/src/main/resources/docs/en/releases.md

@@ -10,6 +10,7 @@ For historical diffs, check the corresponding git tag. For the "why" behind a fe
 
 | Version | Date | Highlights |
 |---------|------|------------|
+| [v2.2.0](./releases/2.2.0) | 2026-08-29 | **Runtime mainline** — employee runtime contract + provider registry + session lifecycle decouple employees from the built-in reasoning loop; **DeepSeek Harness** joins through an authenticated JSON-RPC child process while tools remain governed by host workspace policy and Tool Guard, with install/configure/verify/enable management; **durable Goals recover across bounded segments and backend restarts** (database queue · supervisor · leases · attempts · accepted-input queue · provider backoff · evidence-gated checklist completion); **bidirectional A2A** (Agent Cards · message send/stream · task get/cancel · `call_a2a_agent` · SSRF/timeout/response caps); hardened Team checkpoints, board recovery, deliverable gates, worker attachments, and long-form output; optional OfficeCLI + ACP prompt timeout + tighter workspace boundaries |
 | [v2.1.0](./releases/2.1.0) | 2026-08-15 | **Unified Team Runs** — one request, task DAG, worker execution, final synthesis, and deliverables share a `runId`; Chat delivery / Agents observation / Teams governance consume one projection, while worker conversations stay out of the normal sidebar · **closed skill-evolution loop** (cross-session recurring-request mining · reflection · constrained auto-binding · curator governance handover · origin policy · snapshots and restore points, workspace-scoped and conservative by default) · **replayable reasoning** (live `<think>` extraction · UI wall-clock duration · all/terminal display controls · plain-text trajectory export) · proactive channel push + targeted Cron delivery · context-window override/probe/catalog budgeting · progressive tool bridge + action completion policy · hardened browser refs/navigation/waits · WebChat/SSE/LLM stream cleanup and timeouts · Feishu execution progress · Qwen3-ASR HTTP · batch session deletion · date-partitioned files · 64-bit id and numeric tool-schema precision fixes |
 | [v2.0.0](./releases/2.0.0) | 2026-07-31 | **Agent Teams with a shared task board** — the lead decomposes, members execute in parallel (teams/roles · eight-status kanban · `blockedBy` dependency orchestration · automatic prerequisite hand-off · settled results wake the lead · deliverable registration & download · task timeline + team SSE live board · execution lease heartbeat + cancel-interrupt + `in_review` approval gates) · **Plan-Execute plans hand over to the board** (steps→tasks · dependencies→parallelism · parked-plan resume gate for deterministic synthesis) · Workspace isolation fully sealed (channel-scoped conversation ids · same-named skills coexist per workspace with conversation-scoped runtime resolution) · Channel magic commands (`/new` `/clear` `/status` `/stop` `/model` `/help`) + WeCom event-driven progress bubble (live tool trace · per-stage rolling narration) · Server-side rewind/regenerate semantics · Explainable auto-approval misses (reason codes on audit rows + one-click grant creation + anti-footgun forms) · Policy-driven LLM error recovery (overload vs rate-limit split · `Retry-After`-aware backoff · provider TTL readmission · jitter against retry storms) · In-chat attachment preview (pdf/docx/xlsx/html/text) · Single-source SKILL.md + console bundle-file management · Optional Mem0 plugin memory provider · Knowledge-graph relation schema whitelist |
 | [v1.8.0](./releases/1.8.0) | 2026-07-12 | Content Studio — one sentence to a publishable post (seeded "Content Studio" employee runs pick-topic → research → draft → illustrate → de-AI → layout → deliver) · **WeChat Official Account (公众号)** image-text articles (`gzh_article` · inline-style HTML · draft-box publish via `gzh_publish`) + **Xiaohongshu (小红书)** image-first notes (`xhs_note` · ≥3 vertical 3:4 cards · online preview) · Measurable **de-AI-ification** (heuristic AI-trace score → detect/rewrite/re-check loop, max 3 rounds) · Publish chain hardened (body images uploaded into WeChat · AES-GCM secret encryption · WeChat service+token reuse · retry + Chinese error hints · fallback cover) · **Content Calendar** (deliver = compliance-scan + auto-record · topic-fingerprint dedup · read-only page) · Browser agent **accessibility-tree ref interaction** + real-browser privacy guardrails + controlled CDP hatch · Attention anchoring + tool-call loop guard + post-mutation verify reminder · Fast-load (~78% smaller initial bundle) · Context-occupancy panel · Cross-KB wikilinks · MCP progress notifications · Volcano Engine provider · PostgreSQL 16 |

mateclaw-server/src/main/resources/docs/en/roadmap.md

@@ -156,15 +156,28 @@ Full story: [v2.0.0 release notes](./releases/2.0.0.md); user guide: [Agent Team
 
 Full story: [v2.1.0 release notes](./releases/2.1.0.md); guides: [Team Runs](./teams) and [Skills](./skills).
 
+### v2.2 — Replaceable runtimes, recoverable long work ✅ Released (2026-08-29)
+
+2.1 defined a complete run. 2.2 turns “what executes it, how it resumes after interruption, and how it collaborates with external agents” into infrastructure.
+
+- **Employee Runtime Contract**: provider registry, session factory, capability declarations, and normalized events let native and external runtimes share conversations, workspaces, tool governance, and UI projection
+- **DeepSeek Harness Runtime**: authenticated JSON-RPC process bridge, thinking/text/tool/lifecycle events, host tool policy, managed installation and configuration, and child-environment isolation
+- **Durable Goal execution**: bounded segments + database scheduler + supervisor + leases / attempts / accepted-input queue recover unfinished goals after backend restarts
+- **A2A interoperability**: MateClaw acts as both A2A server and client with Agent Cards, streamed tasks, get/cancel, and constrained outbound calls
+- **Runtime reliability and boundaries**: Team delivery gates, checkpoint recovery, long-form output, approval-time input, generated files, and workspace-scoped administration are hardened
+- Optional OfficeCLI, ACP prompt timeout, and plugin-tool discovery round out external-runtime operations
+
+Full story: [v2.2.0 release notes](./releases/2.2.0.md); guides: [DeepSeek Harness](./deepseek-harness), [Persistent Goals](./goals), and [A2A](./a2a).
+
 ---
 
-## Next: Agent Loop & Team follow-through
+## Next: Resident runtimes & Team follow-through
 
 > "Great things in business are never done by one person. They're done by a team of people."
 
-Look back along the line: v1.2 gave employees an identity, v1.3 made flows orchestratable, v1.4 made employees follow goals and spin up delegation trees, v1.7 made long tasks visible, v2.0 made teams a standing roster, and **v2.1 made every round deliverable, learnable, and governable**.
+Look back along the line: v1.2 gave employees an identity, v1.3 made flows orchestratable, v1.4 made employees follow goals and spin up delegation trees, v1.7 made long tasks visible, v2.0 made teams a standing roster, v2.1 made every round deliverable, learnable, and governable, and **v2.2 made execution engines replaceable, long goals recoverable across requests and restarts, and agents interoperable across systems**.
 
-One "stop" remains: **employees are reactive.** Goal auto-followup only lives **within a single run**; cron and triggers can wake an employee up, but every wake-up is an isolated response. No employee is truly **on duty** — continuously watching its area of responsibility and deciding for itself when to act.
+One “stop” remains: **durable Goals can continue, but employees still lack a general resident responsibility loop.** Cron and triggers can wake them, and the Goal supervisor can recover one objective, but there is no unified inbox, heartbeat, duty journal, or priority policy across objectives. The next step generalizes 2.2's runtime / queue / recovery foundation into a true on-duty state.
 
 ### Agent Team follow-through — the roster exists; now it grows skills
 
@@ -183,7 +196,7 @@ A new state for employees: **on duty**. Not waiting for you to speak, but cyclin
 
 - [ ] **Resident loop runtime**: an employee can be set "on duty," waking on a configurable heartbeat (minutes to days) to check its area of responsibility
 - [ ] **Task inbox**: channel messages, trigger events, delegations from other employees, to-dos you toss over — one queue, consumed by priority on each wake-up
-- [ ] **Cross-session goal continuation**: v1.4/v1.5 auto-followup lives inside a single run; the loop carries goals across sessions and across days until every criterion is checked
+- [x] **Cross-request and restart-safe Goal continuation (2.2)**: the Goal supervisor, durable queue, leases / attempts, and recovery carry goals across bounded execution segments and service restarts until the checklist passes or execution explicitly pauses
 - [ ] **Budgets and circuit breakers**: per-loop token / cost / turn budgets; consecutive failures trip the breaker into sleep pending your decision; ToolGuard approval gates still intercept sensitive actions — autonomy is not loss of control
 - [ ] **Loop journal**: what it did each wake-up, why it chose not to act, what it spent — human-readable and replayable, what DREAMS.md is to memory
 - [ ] **Pause / resume / clock-out**: controllable from the UI and from channel commands; the Run Overview sidebar shows every on-duty employee's loop state
@@ -239,7 +252,8 @@ A leader on a loop, members summoned on demand — that's a **self-running digit
 | **v1.8** | It does a whole job | Content Studio — one sentence to a publishable 公众号 / 小红书 post + browser ref interaction | ✅ Released |
 | **v2.0** | **It leads a team** | **Agent Teams + a shared task board — the lead decomposes and dispatches, members run in parallel, deliverables and full observability** | ✅ Released |
 | **v2.1** | **It turns collaboration into a run** | **Unified Team Runs + closed skill evolution + replayable reasoning trajectories + proactive channel delivery** | ✅ Released |
-| **Next** | **It's on duty** | **Agent Loop resident cycles + team follow-through (peer review / team goals / group binding / retrospectives) = a department that runs itself** | 📋 Planned |
+| **v2.2** | **It reshapes the runtime** | **Pluggable runtimes + DeepSeek Harness + durable Goal recovery + A2A interoperability** | ✅ Released |
+| **Next** | **It's on duty** | **Resident runtime (heartbeat / inbox / journal / circuit breakers) + team follow-through = a department that runs itself** | 📋 Planned |
 
 ---
 
@@ -251,7 +265,7 @@ We're building it because we believe one thing:
 
 **AI shouldn't be a chat box on a webpage. It should be your second brain.**
 
-It lives in your DingTalk, your Feishu, your Telegram. It's read every document you have. It remembers what you said three months ago. It uses your company's internal tools. It consolidates memory while you sleep. It runs an entire business flow on your behalf. **It can now deliver one complete round of team work and learn from it; next, that team stays on duty and watches over the things you can't get to.**
+It lives in your DingTalk, your Feishu, your Telegram. It's read every document you have. It remembers what you said three months ago. It uses your company's internal tools. It consolidates memory while you sleep. It runs an entire business flow on your behalf. **Its runtime is now replaceable, its long goals recoverable, and its external agents interoperable; next, that foundation becomes a digital department that stays on duty.**
 
 Someday, you'll forget it's a program.
 

mateclaw-server/src/main/resources/docs/zh/index.md

@@ -20,12 +20,15 @@ hero:
       link: https://github.com/mateaix/mateclaw
 
 features:
+  - icon: ⚙️
+    title: 员工 Runtime，不只一种 Agent Loop
+    details: 2.2.0 用统一 Runtime Contract 把员工身份与推理引擎解耦。Native 与 DeepSeek Harness 共用会话、工作空间、工具治理和事件投影；持久目标跨请求与后端重启恢复，A2A 连接外部 Agent。
   - icon: 🧑‍💼
     title: 数字员工，不是聊天机器人
     details: 你雇佣同事，不是开聊天框。每位有角色 / 目标 / 背景故事、像素艺术头像与专属配色——6 个内置模板开箱可用。ReAct + Plan-and-Execute 双模式，员工之间并行委派。
   - icon: 🤝
     title: 团队，不是单打独斗
-    details: 一次团队请求对应一个 Team Run：目标、任务 DAG、成员执行、最终汇总与交付物统一追踪。Chat 交付成果、Agents 观察实时运行、Teams 管理历史与审批——2.1.0 起，一轮协作就是一份完整工作记录。
+    details: 一次团队请求对应一个 Team Run：目标、任务 DAG、成员执行、最终汇总与交付物统一追踪。Chat 交付成果、Agents 观察实时运行、Teams 管理历史与审批；2.2.0 进一步加固 checkpoint 恢复与交付物完成门。
   - icon: 🧩
     title: 技能是骨架，不是插件
     details: 一份 SKILL.md + 一份 LESSONS.md（用得越多越聪明）。8 个起步模板，向导 5 步出包，安装前自动 Pre-flight 检查。MCP / ACP 双桥接，连 Claude Code、Codex 都能进来当员工。

mateclaw-server/src/main/resources/docs/zh/releases.md

@@ -10,6 +10,7 @@
 
 | 版本 | 日期 | 亮点 |
 |------|------|------|
+| [v2.2.0](./releases/2.2.0) | 2026-08-29 | **Runtime 主线**——员工运行时 contract + provider registry + session 生命周期，把员工与内置推理循环解耦；**DeepSeek Harness** 以认证 JSON-RPC 子进程接入，工具继续经过宿主工作空间策略与 Tool Guard，并提供安装/配置/校验/启停管理；**持久目标跨有界片段和后端重启恢复**（数据库队列 · supervisor · lease · attempt · 输入排队 · provider 退避 · checklist 证据完成门）；**A2A 双向互联**（Agent Card · message/send/stream · task 查询/取消 · `call_a2a_agent` · SSRF/超时/响应上限）；Team checkpoint / 任务板恢复 / 交付物完成门 / worker 附件与长回答加固；可选 OfficeCLI 引擎 + ACP prompt timeout + 工作空间边界收口 |
 | [v2.1.0](./releases/2.1.0) | 2026-08-15 | **统一 Team Run**——一次团队请求、任务 DAG、成员执行、最终汇总与交付物共用 `runId`，Chat 成果交付 / Agents 实时观察 / Teams 历史治理读取同一投影，成员子会话不再污染普通会话列表 · **Skill 自进化闭环**（跨会话重复请求 mining · reflection · 受约束自动绑定 · curator 治理移交 · origin 策略 · 快照与恢复点，按工作空间隔离且默认保守） · **推理轨迹可回放**（实时 `<think>` 提取 · UI 真实耗时 · 全部/最终轮次控制 · 纯文本 trajectory 导出） · 主动渠道消息 + Cron 定向投递 · 模型窗口覆盖/探测/目录预算 · 渐进式工具桥 + 行动完成约束 · 浏览器 ref/导航/等待加固 · WebChat/SSE/LLM 流回收与超时 · 飞书执行进度 · Qwen3-ASR HTTP · 会话批量删除 · 按日文件目录 · 64 位 id 与数值工具 schema 精度修复 |
 | [v2.0.0](./releases/2.0.0) | 2026-07-31 | **Agent 团队与共享任务板**——Lead 拆任务、成员并行执行（团队/角色 · 八状态看板 · `blockedBy` 依赖编排 · 前置结果自动传递 · 结果通报唤醒 Lead · 交付物登记下载 · 任务时间线 + 团队 SSE 实时看板 · 执行租约心跳 + 取消即中断 + `in_review` 审批卡点） · **Plan-Execute 计划整体移交任务板**（步骤→任务 · 依赖→并行 · 停靠恢复门确定性汇总） · 工作空间隔离全面收口（渠道会话 id 编入渠道 · 同名技能跨工作空间共存且运行时按会话工作空间解析） · 渠道魔法命令（`/new` `/clear` `/status` `/stop` `/model` `/help`）+ 企微事件驱动进度气泡（实时工具轨迹 · 分阶段滚动叙述） · 会话回退/重新生成服务端语义 · 自动批准未命中可解释（原因码落审计行 + 一键补策略 + 表单防呆） · LLM 错误恢复策略化（过载/限流分治 · `Retry-After` 回馈退避 · provider TTL 回收 · 抖动防重试风暴） · 聊天附件在线预览（pdf/docx/xlsx/html/文本） · SKILL.md 单一事实源 + 捆绑文件控制台管理 · Mem0 可选插件记忆 provider · 知识图谱关系模式白名单 |
 | [v1.8.0](./releases/1.8.0) | 2026-07-12 | 内容工作室——一句话到可发布成品（预置「内容工作室」员工跑通 选题→搜集→成文→配图→去AI化→排版→交付） · **微信公众号（公众号）** 图文文章（`gzh_article` · 内联样式 HTML · `gzh_publish` 推进草稿箱）+ **小红书** 以图为主图文笔记（`xhs_note` · ≥3 张竖版 3:4 卡片 · 在线预览） · 可度量**去 AI 化**（启发式 AI 痕迹评分 → 检测/改写/复检闭环,硬上限 3 轮） · 发布链加固（正文图上传进微信 · AES-GCM 密钥加密 · 微信服务+token 复用 · 重试 + 中文错误提示 · 兜底封面） · **内容日历**（交付即合规扫描 + 自动落台账 · 选题指纹去重 · 只读页） · 浏览器 Agent **无障碍树 ref 交互** + 真实浏览器隐私护栏 + 受控 CDP 逃生舱 · 注意力锚定 + 工具调用循环护栏 + 改动后校验提醒 · 快加载（初始包体 ↓约 78%） · 上下文占用面板 · 跨知识库 wikilink · MCP 进度通知 · 火山方舟供应商 · PostgreSQL 16 |

mateclaw-server/src/main/resources/docs/zh/roadmap.md

@@ -156,15 +156,28 @@ MateClaw 就是这个东西。
 
 完整故事：[v2.1.0 Release Notes](./releases/2.1.0.md)，使用指南：[Team Run 与团队协作](./teams)、[技能系统](./skills)。
 
+### v2.2 —— 运行时可替换、长任务可恢复 ✅ 已发布（2026-08-29）
+
+2.1 定义了什么是一份完整运行；2.2 让“由谁来运行、如何在中断后继续、怎样与外部 Agent 协作”成为基础设施能力。
+
+- **员工 Runtime Contract**：provider registry、session factory、能力声明与统一事件流，让 native / 外部 runtime 共用会话、工作空间、工具治理和 UI 投影
+- **DeepSeek Harness Runtime**：认证 JSON-RPC 子进程桥、思考/文本/工具/生命周期事件、宿主工具策略、受管理安装配置与环境隔离
+- **持久目标执行**：有界 segment + 数据库调度队列 + supervisor + lease / attempt / 输入排队，服务重启后恢复未完成目标
+- **A2A 互联**：MateClaw 同时成为 A2A server 和 client，支持 Agent Card、流式任务、查询/取消以及受限出站调用
+- **运行时可靠性与边界**：Team 交付完成门、checkpoint 恢复、长回答、审批输入、生成文件和管理视图的工作空间隔离全面加固
+- 可选 OfficeCLI 文档引擎、ACP prompt timeout 与插件工具发现补齐扩展运行时的日常能力
+
+完整故事：[v2.2.0 Release Notes](./releases/2.2.0.md)，使用指南：[DeepSeek Harness](./deepseek-harness)、[持久化目标](./goals)、[A2A 协议](./a2a)。
+
 ---
 
-## 下一站：Agent Loop 与团队进阶
+## 下一站：常驻 Runtime 与团队进阶
 
 > "伟大的事业不是一个人做成的，是一个团队做成的。"
 
-回头看这条线：v1.2 员工有了身份，v1.3 流程能编排，v1.4 员工会自主跟目标、能临时拉起委派树，v1.7 长任务看得见，v2.0 团队成了常设编制，**v2.1 又让每轮团队工作可交付、可学习、可治理**。
+回头看这条线：v1.2 员工有了身份，v1.3 流程能编排，v1.4 员工会自主跟目标、能临时拉起委派树，v1.7 长任务看得见，v2.0 团队成了常设编制，v2.1 让每轮团队工作可交付、可学习、可治理，**v2.2 则让执行引擎可替换、长目标能跨请求和重启恢复、Agent 能跨系统互联**。
 
-还剩一个"停"：**员工是被动的。** 目标的自动延续只活在**单次运行内**；cron 和触发器能定时叫醒它，但每次醒来都是一次孤立的响应。没有一个员工真正"在岗"——持续盯着自己的职责范围，自己决定什么时候该干什么。
+还剩一个“停”：**持久目标已经会继续，但员工还没有通用的常驻职责循环。** cron 和触发器能定时叫醒它，Goal supervisor 能恢复一项目标，却还没有统一 inbox、心跳、值班日志和跨目标的优先级决策。下一步是把 2.2 的 runtime / queue / recovery 基础推广成真正的“在岗”状态。
 
 ### Agent Team 进阶 —— 编制有了，接下来长本事
 
@@ -183,7 +196,7 @@ MateClaw 就是这个东西。
 
 - [ ] **常驻循环运行时**：员工可以被设为"在岗"，按可配置的心跳（分钟级到天级）自主醒来检查职责范围
 - [ ] **任务收件箱（Inbox）**：渠道消息、触发器事件、其他员工的委派、你随手丢的待办——统一进一个队列，循环醒来按优先级消化
-- [ ] **跨会话目标延续**：v1.4 / v1.5 的自动延续只活在单次运行内；loop 让目标跨会话、跨天持续推进，直到清单全勾完
+- [x] **跨请求与重启的目标延续（2.2）**：Goal supervisor、持久队列、lease / attempt 和恢复逻辑把目标带过有界执行片段与服务重启，直到清单通过或明确暂停
 - [ ] **预算与熔断**：每循环有 token / 成本 / 轮次预算，连续失败自动熔断进入休眠等你处置；ToolGuard 审批门禁照常拦截敏感操作——自主不等于失控
 - [ ] **循环日志（Loop Journal）**：每次醒来干了什么、为什么决定不干、花了多少——人类可读、可回放，像 DREAMS.md 之于记忆
 - [ ] **暂停 / 恢复 / 一键下班**：UI 和渠道命令都能控制；运行总览侧栏显示每个在岗员工的循环状态
@@ -239,7 +252,8 @@ MateClaw 就是这个东西。
 | **v1.8** | 它干完一整件活 | 内容工作室 —— 一句话到可发布的公众号 / 小红书成品 + 浏览器 ref 交互 | ✅ 已发布 |
 | **v2.0** | **它带队干活** | **Agent 团队 + 共享任务板 —— Lead 拆解派发、成员并行执行、交付物与全程可观测** | ✅ 已发布 |
 | **v2.1** | **它把协作变成运行** | **统一 Team Run + Skill 自进化闭环 + 可回放推理轨迹 + 主动渠道投递** | ✅ 已发布 |
-| **下一站** | **它长期在岗** | **Agent Loop 常驻循环 + 团队进阶（互审 / 团队目标 / 群绑定 / 复盘）= 会自己运转的数字部门** | 📋 规划中 |
+| **v2.2** | **它重塑运行时** | **可插拔 Runtime + DeepSeek Harness + 持久 Goal 恢复 + A2A 互联** | ✅ 已发布 |
+| **下一站** | **它长期在岗** | **通用常驻 Runtime（心跳 / inbox / journal / 熔断）+ 团队进阶 = 会自己运转的数字部门** | 📋 规划中 |
 
 ---
 
@@ -251,7 +265,7 @@ MateClaw 就是这个东西。
 
 **AI 不应该是一个网页上的对话框。它应该是你的第二个大脑。**
 
-它住在你的钉钉里、你的飞书里、你的 Telegram 里。它读过你所有的文档。它记得你三个月前说过的话。它会用你公司的内部工具。它在你睡觉的时候整理记忆。它能替你跑一整条业务流程。**现在它已经能把一轮团队工作完整交付并从中学习；下一步，是让这支团队长期在岗，替你盯着那些你顾不上的事。**
+它住在你的钉钉里、你的飞书里、你的 Telegram 里。它读过你所有的文档。它记得你三个月前说过的话。它会用你公司的内部工具。它在你睡觉的时候整理记忆。它能替你跑一整条业务流程。**现在它的运行时可替换、长目标可恢复、外部 Agent 可互联；下一步，是把这套底座推进成长期在岗的数字部门。**
 
 总有一天，你会忘记它是一个程序。
 

mateclaw-ui/package.json

@@ -1,6 +1,6 @@
 {
   "name": "mateclaw-ui",
-  "version": "2.2.0-SNAPSHOT",
+  "version": "2.2.0",
   "private": true,
   "type": "module",
   "description": "MateClaw - Personal AI Assistant Web Console",

pom.xml

@@ -23,7 +23,7 @@
 
     <properties>
         <!-- MateClaw release version shared by all Maven modules. -->
-        <revision>2.2.0-SNAPSHOT</revision>
+        <revision>2.2.0</revision>
 
         <!-- Java -->
         <java.version>21</java.version>