ruff3

Add a "Join our Discord" entry to the account dropdown's external-links
group, opening https://discord.gg/wdNEHETs87 in a new tab. lucide-react
has no Discord brand glyph, so include a small inline Discord SVG icon
(brand color). Add the joinDiscord label to all 8 locales.

Co-Authored-By: Claude Opus 4.8 (1M context) <noreply@anthropic.com>

.github/ISSUE_TEMPLATE/bug-report.yml

@@ -10,6 +10,15 @@ body:
       placeholder: 例如：v3.3.0、CentOS x64 Python 3.10.3、Docker
     validations:
       required: true
+  - type: dropdown
+    attributes:
+      label: 部署版本
+      description: 请选择您使用的 LangBot 部署版本。
+      options:
+        - 社区版
+        - 云服务
+    validations:
+      required: true
   - type: textarea
     attributes:
       label: 异常情况

.github/ISSUE_TEMPLATE/bug-report_en.yml

@@ -10,6 +10,15 @@ body:
       placeholder: "For example: v3.3.0, CentOS x64 Python 3.10.3, Docker"
     validations:
       required: true
+  - type: dropdown
+    attributes:
+      label: Deployment version
+      description: Please select the LangBot deployment version you are using.
+      options:
+        - Community Edition
+        - Cloud Service
+    validations:
+      required: true
   - type: textarea
     attributes:
       label: Exception

Dockerfile

@@ -14,10 +14,22 @@ COPY . .
 
 COPY --from=node /app/web/dist ./web/dist
 
-RUN apt update \
-    && apt install gcc -y \
+RUN apt-get update \
+    && apt-get install -y --no-install-recommends gcc ca-certificates curl gnupg \
+    # Install the Docker CLI (client only) so the optional langbot_box
+    # service can drive the mounted host Docker socket and create sandbox
+    # containers. The same image powers langbot / plugin_runtime / box; only
+    # box uses the client. Arch-aware via dpkg so multi-arch builds work.
+    && install -m 0755 -d /etc/apt/keyrings \
+    && curl -fsSL https://download.docker.com/linux/debian/gpg -o /etc/apt/keyrings/docker.asc \
+    && chmod a+r /etc/apt/keyrings/docker.asc \
+    && echo "deb [arch=$(dpkg --print-architecture) signed-by=/etc/apt/keyrings/docker.asc] https://download.docker.com/linux/debian $(. /etc/os-release && echo \"$VERSION_CODENAME\") stable" > /etc/apt/sources.list.d/docker.list \
+    && apt-get update \
+    && apt-get install -y --no-install-recommends docker-ce-cli \
     && python -m pip install --no-cache-dir uv \
     && uv sync \
+    && apt-get purge -y --auto-remove curl gnupg \
+    && rm -rf /var/lib/apt/lists/* \
     && touch /.dockerenv
 
 CMD [ "uv", "run", "--no-sync", "main.py" ]

README_CN.md

@@ -38,7 +38,7 @@ LangBot 是一个**开源的生产级平台**，用于构建 AI 驱动的即时
 
 ### 核心能力
 
-- **AI 对话与 Agent** — 多轮对话、工具调用、多模态、流式输出。自带 RAG（知识库），深度集成 [Dify](https://dify.ai)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org) 等 LLMOps 平台。
+- **AI 对话与 Agent** — 多轮对话、工具调用、多模态、流式输出。自带 RAG（知识库），深度集成 [Dify](https://dify.ai)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org)、[Deerflow](https://deerflow.tech)、[Weknora](https://weknora.weixin.qq.com)等 LLMOps 平台。
 - **全平台支持** — 一套代码，覆盖 QQ、微信、企业微信、飞书、钉钉、Discord、Telegram、Slack、LINE、KOOK 等平台。
 - **生产就绪** — 访问控制、限速、敏感词过滤、全面监控与异常处理，已被多家企业采用。
 - **插件生态** — 数百个插件，跨进程的事件驱动架构，组件扩展，适配 [MCP 协议](https://modelcontextprotocol.io/)。

README_ES.md

@@ -37,7 +37,7 @@ LangBot es una **plataforma de código abierto y grado de producción** para con
 
 ### Capacidades Clave
 
-- **Conversaciones e Agentes IA** — Diálogos de múltiples turnos, llamadas a herramientas, soporte multimodal, salida en streaming. RAG (base de conocimientos) incorporado con integración profunda con [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org).
+- **Conversaciones e Agentes IA** — Diálogos de múltiples turnos, llamadas a herramientas, soporte multimodal, salida en streaming. RAG (base de conocimientos) incorporado con integración profunda con [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org), [Deerflow](https://deerflow.tech)、[Weknora](https://weknora.weixin.qq.com).
 - **Soporte Universal de Plataformas de MI** — Un solo código base para Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK.
 - **Listo para Producción** — Control de acceso, limitación de velocidad, filtrado de palabras sensibles, monitoreo completo y manejo de excepciones. De confianza para empresas.
 - **Ecosistema de Plugins** — Cientos de plugins, arquitectura basada en eventos, extensiones de componentes y soporte del [protocolo MCP](https://modelcontextprotocol.io/).

README_FR.md

@@ -37,7 +37,7 @@ LangBot est une **plateforme open-source de niveau production** pour créer des
 
 ### Capacités Clés
 
-- **Conversations IA & Agents** — Dialogues multi-tours, appels d'outils, support multimodal, sortie en streaming. RAG (base de connaissances) intégré avec intégration profonde de [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org).
+- **Conversations IA & Agents** — Dialogues multi-tours, appels d'outils, support multimodal, sortie en streaming. RAG (base de connaissances) intégré avec intégration profonde de [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org), [Deerflow](https://deerflow.tech), [Weknora](https://weknora.weixin.qq.com).
 - **Support Universel des Plateformes de MI** — Un seul code pour Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK.
 - **Prêt pour la Production** — Contrôle d'accès, limitation de débit, filtrage de mots sensibles, surveillance complète et gestion des exceptions. Approuvé par les entreprises.
 - **Écosystème de Plugins** — Des centaines de plugins, architecture événementielle, extensions de composants, et support du [protocole MCP](https://modelcontextprotocol.io/).

README_JP.md

@@ -37,7 +37,7 @@ LangBot は、AI搭載のインスタントメッセージングボットを構
 
 ### 主な機能
 
-- **AI対話とエージェント** — マルチターン対話、ツール呼び出し、マルチモーダル対応、ストリーミング出力。RAG（ナレッジベース）を内蔵し、[Dify](https://dify.ai)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org) と深く統合。
+- **AI対話とエージェント** — マルチターン対話、ツール呼び出し、マルチモーダル対応、ストリーミング出力。RAG（ナレッジベース）を内蔵し、[Dify](https://dify.ai)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org)、[Deerflow](https://deerflow.tech)、[Weknora](https://weknora.weixin.qq.com) と深く統合。
 - **ユニバーサルIMプラットフォーム対応** — 単一のコードベースで Discord、Telegram、Slack、LINE、QQ、WeChat、WeCom、Lark、DingTalk、KOOK に対応。
 - **本番環境対応** — アクセス制御、レート制限、センシティブワードフィルタリング、包括的な監視、例外処理を搭載。エンタープライズの信頼に応える品質。
 - **プラグインエコシステム** — 数百のプラグイン、イベント駆動アーキテクチャ、コンポーネント拡張、[MCPプロトコル](https://modelcontextprotocol.io/)対応。

README_KO.md

@@ -37,7 +37,7 @@ LangBot은 AI 기반 인스턴트 메시징 봇을 구축하기 위한 **오픈
 
 ### 핵심 기능
 
-- **AI 대화 및 에이전트** — 멀티턴 대화, 도구 호출, 멀티모달 지원, 스트리밍 출력. 내장 RAG(지식 베이스)와 [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org) 심층 통합.
+- **AI 대화 및 에이전트** — 멀티턴 대화, 도구 호출, 멀티모달 지원, 스트리밍 출력. 내장 RAG(지식 베이스)와 [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org), [Deerflow](https://deerflow.tech), [Weknora](https://weknora.weixin.qq.com) 심층 통합.
 - **유니버설 IM 플랫폼 지원** — 단일 코드베이스로 Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK 지원.
 - **프로덕션 레디** — 접근 제어, 속도 제한, 민감어 필터링, 종합 모니터링 및 예외 처리. 기업 환경에서 검증됨.
 - **플러그인 생태계** — 수백 개의 플러그인, 이벤트 기반 아키텍처, 컴포넌트 확장, [MCP 프로토콜](https://modelcontextprotocol.io/) 지원.

README_RU.md

@@ -37,7 +37,7 @@ LangBot — это **платформа с открытым исходным к
 
 ### Ключевые возможности
 
-- **ИИ-диалоги и агенты** — Многораундовые диалоги, вызов инструментов, мультимодальная поддержка, потоковый вывод. Встроенная реализация RAG (база знаний) с глубокой интеграцией в [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org).
+- **ИИ-диалоги и агенты** — Многораундовые диалоги, вызов инструментов, мультимодальная поддержка, потоковый вывод. Встроенная реализация RAG (база знаний) с глубокой интеграцией в [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org), [Deerflow](https://deerflow.tech), [Weknora](https://weknora.weixin.qq.com).
 - **Универсальная поддержка IM-платформ** — Единая кодовая база для Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK.
 - **Готовность к продакшену** — Контроль доступа, ограничение скорости, фильтрация чувствительных слов, комплексный мониторинг и обработка исключений. Проверено в корпоративной среде.
 - **Экосистема плагинов** — Сотни плагинов, событийно-ориентированная архитектура, расширения компонентов и поддержка [протокола MCP](https://modelcontextprotocol.io/).

README_TW.md

@@ -39,7 +39,7 @@ LangBot 是一個**開源的生產級平台**，用於建構 AI 驅動的即時
 
 ### 核心能力
 
-- **AI 對話與 Agent** — 多輪對話、工具調用、多模態、流式輸出。自帶 RAG（知識庫），深度整合 [Dify](https://dify.ai)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org) 等 LLMOps 平台。
+- **AI 對話與 Agent** — 多輪對話、工具調用、多模態、流式輸出。自帶 RAG（知識庫），深度整合 [Dify](https://dify.ai)、[Coze](https://coze.com)、[n8n](https://n8n.io)、[Langflow](https://langflow.org)、 [Deerflow](https://deerflow.tech)、[Weknora](https://weknora.weixin.qq.com)等 LLMOps 平台。
 - **全平台支援** — 一套程式碼，覆蓋 QQ、微信、企業微信、飛書、釘釘、Discord、Telegram、Slack、LINE、KOOK 等平台。
 - **生產就緒** — 存取控制、限速、敏感詞過濾、全面監控與異常處理，已被多家企業採用。
 - **外掛生態** — 數百個外掛，事件驅動架構，組件擴展，適配 [MCP 協議](https://modelcontextprotocol.io/)。

README_VI.md

@@ -37,7 +37,7 @@ LangBot là một **nền tảng mã nguồn mở, cấp sản xuất** để x
 
 ### Khả năng chính
 
-- **Hội thoại AI & Agent** — Đối thoại nhiều lượt, gọi công cụ, hỗ trợ đa phương thức, đầu ra streaming. RAG (cơ sở kiến thức) tích hợp sẵn với tích hợp sâu vào [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org).
+- **Hội thoại AI & Agent** — Đối thoại nhiều lượt, gọi công cụ, hỗ trợ đa phương thức, đầu ra streaming. RAG (cơ sở kiến thức) tích hợp sẵn với tích hợp sâu vào [Dify](https://dify.ai), [Coze](https://coze.com), [n8n](https://n8n.io), [Langflow](https://langflow.org), [Deerflow](https://deerflow.tech), [Weknora](https://weknora.weixin.qq.com).
 - **Hỗ trợ đa nền tảng IM** — Một mã nguồn cho Discord, Telegram, Slack, LINE, QQ, WeChat, WeCom, Lark, DingTalk, KOOK.
 - **Sẵn sàng cho sản xuất** — Kiểm soát truy cập, giới hạn tốc độ, lọc từ nhạy cảm, giám sát toàn diện và xử lý ngoại lệ. Được doanh nghiệp tin dùng.
 - **Hệ sinh thái Plugin** — Hàng trăm plugin, kiến trúc hướng sự kiện, mở rộng thành phần, và hỗ trợ [giao thức MCP](https://modelcontextprotocol.io/).

docs/review/box-architecture.md

@@ -1,8 +1,9 @@
 # Box 系统架构深度分析
 
-> 更新日期: 2026-05-19
+> 更新日期: 2026-06-02
+> 状态更新: 自部署社区版已具备发布条件（box 可选、降级完善、无迁移欠债）；工具调用循环上限、配额遍历异步化、`host_path` 挂载白名单等已落地。剩余多租户 / 安全硬化项见 [SaaS 阻塞项清单](./box-issues.md)。
 > 分支: `feat/sandbox` (LangBot + langbot-plugin-sdk)
-> 相关文档: [问题清单](./box-issues.md) | [Session 作用域](./box-session-scope.md) | [Runtime 对比](./box-vs-plugin-runtime.md) | [测试覆盖](./box-test-coverage.md) | [toB 分析](./box-tob-analysis.md)
+> 相关文档: [SaaS 阻塞项](./box-issues.md) | [Session 作用域](./box-session-scope.md) | [Runtime 对比](./box-vs-plugin-runtime.md) | [测试覆盖](./box-test-coverage.md) | [toB 分析](./box-tob-analysis.md)
 
 ---
 
@@ -163,7 +164,7 @@ BoxService
 
 ### 2.4 policy.py (`pkg/box/policy.py`, 98 行) — 仍是死代码
 
-三层安全策略设计（`SandboxPolicy` / `ToolPolicy` / `ElevatedPolicy`），全项目无任何导入或调用。详见 [问题清单 #1](./box-issues.md)。
+三层安全策略设计（`SandboxPolicy` / `ToolPolicy` / `ElevatedPolicy`），全项目无任何导入或调用。详见 [SaaS 阻塞项 S2](./box-issues.md)。
 
 ### 2.5 SkillManager (`pkg/skill/manager.py`, 186 行)
 
@@ -364,7 +365,7 @@ GitHub 安装路径：HTTP 层（`api/http/service/skill.py`）先 `git clone`
 
 `validate_sandbox_security()`: 黑名单校验 host_path，阻止挂载 `/etc`/`/proc`/`/sys`/`/dev`/`/root`/`/boot` 及 Docker/Podman socket。
 
-**已知缺陷**: 根路径 `/` 未拦截，用户 home 目录未拦截，是 denylist 而非 allowlist 策略。详见 [问题清单 #5](./box-issues.md)。
+**已知缺陷**: 根路径 `/` 未拦截，用户 home 目录未拦截，是 denylist 而非 allowlist 策略。详见 [SaaS 阻塞项 S5](./box-issues.md)。
 
 ### 3.9 Errors (`box/errors.py`, 33 行)
 
@@ -512,7 +513,7 @@ box:
                           #  - skill 列表/读取保持只读可用
                           # BOX__ENABLED 环境变量可覆盖（统一约定）
     backend: 'local'      # 'local' (探测) / 'docker' / 'nsjail' / 'e2b'
-                          # BOX_BACKEND 环境变量优先级更高
+                          # 由 box.backend / BOX__BACKEND 选择后端
     runtime:
         endpoint: ''      # 外部 Runtime 的 WS 基地址 'ws://host:5410'
                           # 留空 = 本地自管 Runtime

docs/review/box-issues.md

@@ -1,157 +1,76 @@
-# Box 系统架构问题清单
+# Box 系统 — SaaS 发布前阻塞项
 
-> 更新日期: 2026-05-19
+> 更新日期: 2026-06-02
 > 分支: `feat/sandbox` (LangBot + langbot-plugin-sdk)
+> 相关文档: [架构分析](./box-architecture.md) | [Session 作用域](./box-session-scope.md) | [Runtime 对比](./box-vs-plugin-runtime.md) | [测试覆盖](./box-test-coverage.md) | [toB 分析](./box-tob-analysis.md)
+
+## 范围说明
+
+**自部署社区版已具备发布条件**：默认 stdio 模式、box 为可选项；box 关闭 / 不可用时后端、前端、工具、skill、stdio-MCP 均能干净降级（清晰报错、不崩溃）；配置向后兼容（旧 `data/config.yaml` 可直接启动）；无新增 ORM 模型、无迁移欠债；市场安装失败不会破坏实例。CI 全绿。
+
+本清单**只保留发布 SaaS / 多租户 / 公网暴露前必须处理的阻塞项**。社区版（可信、单运营者、内网）不受这些项阻塞——它们的风险面在"不可信调用方能直接触达 Box 控制面"或"多租户共享资源"的场景才成立。
+
+## 已解决（社区版发布前）
+
+| 项 | 处理 |
+|----|------|
+| 工具调用循环无上限 (原 #13) | `localagent.py` 增加 `MAX_TOOL_CALL_ROUNDS=128`，超限优雅终止（`cafef1a3`） |
+| 配额校验同步遍历阻塞事件循环 (原 #10) | `_enforce_workspace_quota` 改 async，工作区遍历走 `asyncio.to_thread`（`cafef1a3`） |
+| `host_path` 挂载白名单 (原 #3 的 LangBot 侧) | `pkg/box/service.py` `allowed_mount_roots` 白名单，空列表时拒绝一切宿主挂载 |
+| 重复的 `_is_path_under` (原 #12) | 已去重，仅保留一处定义 |
+| 重连 / 心跳 / Windows 兼容 / nsjail image 字段 / 前端 Box 状态接入 | 见上一轮 review 记录，均已合入 |
 
 ---
 
-## 已解决（自上一轮 review）
+## SaaS 阻塞项
 
-下列原 P0/P1 项在最新分支已被修复，仅作记录：
+### S1. Box 控制面无认证 — Critical
 
-| 原编号 | 问题 | 处理 commit / 说明 |
-|--------|------|---------------------|
-| #3 | Box 无重连机制 | `_make_connection_callback` 已接入 `runtime_disconnect_callback`；`BoxService._reconnect_loop()` 实现指数退避重连 (`2dfd9d5d`、`c6882cf`) |
-| #4 | Box 无心跳 | `BoxRuntimeConnector._heartbeat_loop()`，间隔 20s（沿用 Plugin 模式） |
-| #10 | Windows 兼容 | connector 增加 Windows 分支 (subprocess + WS)，backend 适配 Windows Docker (`120817a`、`fafb7a4`) |
-| #12 | nsjail image 字段冲突 | `_assert_session_compatible()` 在不支持自定义镜像的 backend 跳过 image 字段 |
-| #22 | 前端无 Box UI | 监控页 `SystemStatusCards.tsx` 已接入 `/api/v1/box/status`；Skill 管理页接入了全部 skill API（sessions/errors API 仍未接入） |
+- **位置**: SDK `box/server.py` — Action RPC WS (`/rpc/ws`) 与 managed-process relay (`/v1/sessions/{id}/managed-process/{pid}/ws`)
+- **现状**: 两个 WS handler 在 `ws.prepare` 后直接服务，无任何 token / 鉴权；box 默认绑定 `0.0.0.0:5410`。任何能触达该端口者可发起 `EXEC`、创建 session、attach 任意 session 的 managed-process stdin/stdout、甚至 `SHUTDOWN`。LangBot→box 的 INIT 也未下发任何凭证。
+- **缓解现状**: 默认 `docker-compose.yaml` 的 `langbot_box` 未把 5410 发布到宿主（爆炸半径限于内网 bridge）；但 box 挂载了 `/var/run/docker.sock`，同网络的任意服务（含被攻破的插件）→ 宿主 root。若运营者把 5410 发布到宿主或独立以 `0.0.0.0` 起 box，则完全裸奔。
+- **要求**: INIT 时下发 token，两个 WS 路由按连接校验（query/header）。这是 SaaS 的**头号**阻塞项。
 
----
+### S2. 无 exec 授权模型（policy.py 死代码） — High
 
-## P0 — 合并前建议修复
+- **位置**: LangBot `pkg/box/policy.py`（`SandboxPolicy` / `ToolPolicy` / `ElevatedPolicy` 全项目无引用）；`pkg/provider/tools/loaders/native.py`；`pkg/provider/tools/toolmgr.py`
+- **现状**: 原生工具（`exec/read/write/edit/glob/grep`）按"box 是否可用"全有或全无地暴露，**无 per-pipeline 的 exec 网关 / 工具白名单 / 沙箱模式 / 权限提升控制**。只要 box 可用，任何使用 local-agent + 函数调用模型的 pipeline 都能跑任意 shell。
+- **要求**: 接入 policy.py（或等价机制），按 pipeline 控制是否暴露 `exec`、可用工具白名单、沙箱网络/只读模式。
 
-### 1. policy.py 是死代码
+### S3. 会话资源无界（DoS） — High
 
-- **位置**: `pkg/box/policy.py` (98 行)
-- **现状**: `SandboxPolicy`、`ToolPolicy`、`ElevatedPolicy` 三个类已定义，但全项目无任何导入或调用
-- **影响**: 三层安全策略（沙箱模式 / 工具白名单 / 权限提升）完全未生效。当前实际策略仍是"Box 可用就暴露全部 6 个 native tool，不可用就全部隐藏"
-- **建议**: 要么删除死代码，要么接入 NativeToolLoader 的工具暴露 / exec 调用链。如果短期不会接入，至少在 `pkg/box/__init__.py` 显式标注其状态
+- **#5 session 数量无上限**: SDK `box/runtime.py` `_get_or_create_session` 的 `_sessions` dict 无容量限制——可变 `session_id` 的恶意调用可无限创建容器，耗尽宿主 CPU/内存/PID/磁盘。
+- **#8 无定时回收**: 过期 session 仅在 `_get_or_create_session` 时机会性清理，无独立周期任务；一波创建后转静默会永久泄漏容器。
+- **要求**: `max_sessions` 上限（拒绝或 LRU），加独立周期 reaper（如 60s）。
 
-### 2. WebSocket relay 无认证
+### S4. 工作区配额无内核级限制（TOCTOU） — Med-High
 
-- **位置**: SDK `box/server.py` — Action RPC 路径 `/rpc/ws` 与 managed-process relay `/v1/sessions/{id}/managed-process/{pid}/ws`
-- **现状**: 任何能访问 5410 端口的客户端都可以连接，attach 任意 session 的 managed process stdin/stdout，或直接发起 EXEC
-- **影响**: 容器化 / Docker compose 部署中，若 Box runtime 端口外暴露，网络内的攻击者可直接控制沙箱
-- **建议**: 至少加 token 认证（INIT 时下发，WS 连接 query string 或 header 校验）；多 process 后 attach 面更大，更不能裸奔
+- **位置**: LangBot `pkg/box/service.py` `_enforce_workspace_quota`（应用层 read-then-check）；SDK 侧 `workspace_quota_mb` 仅记录/透传，无 `--storage-opt size=` 等内核/FS 限额
+- **现状**: 执行前后两次检查之间存在竞态窗口；单条命令（`dd`/`fallocate`）可在检查间隙撑爆磁盘，事后检查只能补救。
+- **要求**: Docker `--storage-opt size=` 做内核级限制，或 Redis 原子计数预留式配额。
 
-### 3. security.py 根路径未拦截
+### S5. 挂载校验缺口 — Med-High
 
-- **位置**: SDK `box/security.py` `BLOCKED_HOST_PATHS_POSIX`
-- **现状**: 黑名单中没有 `/`，`host_path="/"` 可通过校验并挂载整个主机文件系统；用户 home 目录、`/var` 等也未拦截
-- **建议**: 将 `/` 加入黑名单，或改用白名单策略与 LangBot 侧 `allowed_mount_roots` 二次拦截
+- **位置**: SDK `box/security.py` `_BLOCKED_HOST_PATHS_POSIX`；`box/backend.py` 的 `extra_mounts` 处理
+- **现状**: ① SDK 黑名单仍不含 `/`（前缀匹配，`host_path="/"` 可通过，挂载整个宿主 fs）；用户 home、`/usr`、`/opt`、`/tmp` 也未拦截。② `validate_sandbox_security` 只校验 `spec.host_path`，**从不遍历 `spec.extra_mounts`**——LangBot 侧 `allowed_mount_roots` 也只校验 `host_path`。当前 `extra_mounts` 仅由 `build_skill_extra_mounts` 内部填充（agent 不可达），但缺乏纵深防御：一旦 S1 的无认证 RPC 被触达，extra_mounts 可挂任意宿主路径，两层都不拦。
+- **要求**: SDK 黑名单加入 `/`（或改白名单）；`extra_mounts` 在 SDK 与 LangBot 两侧都纳入挂载校验。
 
-### 4. INIT 与 backend 初始化的竞态
+### S6. 容器加固缺失 — Med
 
-- **位置**: SDK `box/runtime.py` `init()` 在握手后才下发实际配置；`backend` 在 INIT 之前可能已经按默认值实例化
-- **现状**: commit `5029d9c` 修复了 "init config before backend reuse" 的部分场景，但 backend 重新实例化时若有正在执行的 session，可能命中旧 backend
-- **建议**: 整理 init/handshake 顺序——要么 INIT 完成前不接受任何业务 action，要么允许 backend 配置变更时显式清理现有 session
+- **位置**: SDK `box/backend.py` 的 `docker run` 组装
+- **现状**: 未设置 `--cap-drop=ALL`、`--security-opt=no-new-privileges`、非 root `--user`；叠加挂载 docker.sock，逃逸面偏大。
+- **要求**: 默认加上上述加固 flag（需回归常用 skill 不被破坏）。
 
----
+### S7. 全局锁内执行慢操作（扩展性） — Med
 
-## P1 — 合并后优先跟进
+- **位置**: SDK `box/runtime.py` `_get_or_create_session`：`self._lock` 持有期间调用 `backend.start_session()`（`docker run` / nsjail 启动 / E2B `Sandbox.create`）
+- **影响**: 冷启动（镜像拉取数秒、E2B >1s）期间串行阻塞所有并发请求——多租户负载下整个 Box runtime 停顿。降级表现是延迟而非失败。
+- **要求**: 锁内只做状态检查与注册，容器创建移到锁外。
 
-### 5. Session 数量无上限
+### S8. 其他硬化 / 跟进 — Low
 
-- **位置**: SDK `box/runtime.py` `_get_or_create_session()`
-- **现状**: `_sessions` dict 无容量限制，恶意或异常调用可创建无限 session
-- **建议**: 加 `max_sessions` 配置项，达到上限时拒绝新建或按 LRU 清理
-
-### 6. Quota 检查存在 TOCTOU
-
-- **位置**: `pkg/box/service.py` `_enforce_workspace_quota()`
-- **现状**: 应用层先读磁盘大小再执行命令，两步之间有竞态窗口
-- **建议**: 短期用 Docker `--storage-opt size=` 做内核级限制；长期用 Redis 原子计数器做预留式配额
-
-### 7. 全局锁持有期间执行慢操作
-
-- **位置**: SDK `box/runtime.py` `_get_or_create_session()` — `self._lock` 下调用 `backend.start_session()` (即 `docker run` / `nsjail` 进程启动 / E2B `Sandbox.create`)
-- **影响**: `docker run` 可能耗时数秒（含镜像拉取）、E2B 冷启动通常 > 1s，期间阻塞所有并发请求
-- **建议**: 在 `_lock` 下仅做状态检查和 session 注册，容器创建在锁外执行
-
-### 8. Session 清理是机会性的
-
-- **位置**: SDK `box/runtime.py` `_reap_expired_sessions_locked()` — 仅在 `_get_or_create_session()` 时调用
-- **影响**: 如果长时间无新 session 请求，过期 session（含容器）不会被清理
-- **建议**: 加一个独立的 `asyncio.create_task` 定时清理（如每 60s 一次）
-
-### 9. server.py 直接访问 runtime 私有字段
-
-- **位置**: SDK `box/server.py` — managed-process WS handler 直接读 `runtime._sessions`
-- **影响**: 绕过锁和封装，在并发场景下可能读到不一致状态
-- **建议**: 在 BoxRuntime 上增加公共方法（如 `get_session_managed_process(session_id, process_id)`）
-
-### 10. workspace quota 检查阻塞事件循环
-
-- **位置**: `pkg/box/service.py` `_get_workspace_size_bytes()` — 使用同步 `os.scandir` 递归遍历
-- **影响**: 大工作区可能阻塞 asyncio event loop
-- **建议**: 用 `asyncio.to_thread()` 包装，或用 `aiofiles` 异步扫描
-
-### 11. extra_mounts 一旦容器创建即固定
-
-- **位置**: SDK `box/runtime.py` 的兼容性检查；`pkg/box/service.py:build_skill_extra_mounts()`
-- **现状**: Skill 挂载在容器创建时一次性写入；同一 session 后续 pipeline 切换 skill 列表时，新挂载不会生效（除非销毁重建）
-- **影响**: 用户长时间共享 session 的场景下，新激活的 skill 可能挂不上
-- **建议**: 要么在创建时把 pipeline 绑定的所有 skill 都挂上（实际现状）+ 写入文档；要么变更挂载时强制销毁 session 重建（已被 commit `5029d9c` 部分覆盖，需校验）
-
----
-
-## P2 — 后续迭代
-
-### 12. 重复的 `_is_path_under` 函数
-
-- **位置**: `pkg/box/service.py` 行 30 附近 — 同名函数定义两次
-- **建议**: 删除重复定义
-
-### 13. localagent.py 工具循环无迭代上限
-
-- **位置**: `pkg/provider/runners/localagent.py` `while pending_tool_calls` 循环
-- **影响**: 恶意或混乱的 LLM 可无限产生 tool call，消耗资源
-- **建议**: 加 `max_tool_iterations` 配置项（如默认 50 次）
-
-### 14. localagent.py 中的死代码
-
-- **位置**: `pkg/provider/runners/localagent.py:29-35` 附近 — 旧命名 `SANDBOX_EXEC_TOOL_NAME` 和 `SANDBOX_EXEC_SYSTEM_GUIDANCE`
-- **现状**: 旧命名方案的遗留常量，从未被引用（实际使用 `EXEC_TOOL_NAME` from native.py）
-- **建议**: 删除
-
-### 15. @loader_class 装饰器未使用
-
-- **位置**: `pkg/provider/tools/loader.py` — `preregistered_loaders` 列表和 `@loader_class` 装饰器
-- **现状**: 各 loader 的 `@loader_class` 多数被注释掉，ToolManager 手动实例化所有 loader
-- **建议**: 要么启用装饰器自动注册，要么删除未用的机制
-
-### 16. 工具名冲突风险
-
-- **位置**: `pkg/provider/tools/toolmgr.py` `execute_func_call()` — 按优先级 native → plugin → mcp → skill → skill_authoring 分发
-- **影响**: 如果 plugin 或 MCP 有名为 `exec`/`read`/`write`/`edit`/`glob`/`grep`/`activate` 的工具，会被前序 loader 静默遮蔽
-- **建议**: 加命名空间前缀或冲突检测告警
-
-### 17. client.py 反序列化不一致
-
-- **位置**: SDK `box/client.py` — `execute()` 与其他方法对返回值的反序列化方式不统一（部分手动构造 model，部分用 `model_validate`）
-- **建议**: 统一使用 `model_validate`
-
-### 18. 错误类型还原基于字符串前缀匹配
-
-- **位置**: SDK `box/client.py` `_translate_action_error()`
-- **影响**: 如果 server 端错误消息格式变化，client 会回退到通用 `BoxError`，丢失类型信息
-- **建议**: 在 ActionResponse 中增加结构化的错误类型字段（如 `error_code` 枚举）
-
-### 19. 前端只用到了 status
-
-- **位置**: `web/src/app/home/monitoring/...` 已接入 `/api/v1/box/status`
-- **现状**: `/api/v1/box/sessions` 与 `/api/v1/box/errors` 后端可用、前端未消费
-- **建议**: 在监控页或独立 Box 详情页展示活跃 session 列表与最近错误，提升运维体感
-
-### 20. skill_store 测试覆盖偏薄
-
-- **位置**: SDK `tests/box/test_skill_store.py` 仅 88 行
-- **现状**: 相对 `skill_store.py` 的 647 行实现，单测覆盖度不够；GitHub 安装路径、`source_subdir` / `target_suffix` 组合、损坏 zip 的错误处理等场景未覆盖
-- **建议**: 至少补到核心 path 覆盖（preview/install/list/file CRUD 各 2~3 个 case）
-
-### 21. 集成测试未进 CI
-
-- **位置**: LangBot `tests/integration_tests/box/test_box_integration.py`、`test_box_mcp_integration.py`，SDK 端的 E2B 真机测试
-- **现状**: 容器实际执行、E2B 真实 sandbox、Managed process WS attach 均仅本地能跑
-- **建议**: 加一个可选的 Docker-in-Docker CI stage，或在合并前手动跑 checklist
+- **#9** SDK `box/server.py` 直接读 `runtime._sessions` 私有字段、绕过锁，并发下可能读到不一致状态——应加公共访问方法。
+- **#16** `pkg/provider/tools/toolmgr.py` `execute_func_call` 按优先级分发，plugin/MCP 若有同名 `exec/read/write/...` 工具会被静默遮蔽——应加命名空间或冲突告警。
+- **#4** SDK `box/runtime.py` INIT/handshake 与 backend 实例化的残留竞态（仅"纯远程 WS box 先启动、LangBot 后连"场景成立；stdio/compose 路径下 config 经 env 在 spawn 时已就位，无竞态）——应在 INIT 完成前拒绝业务 action。
+- **#11** `extra_mounts` 在容器创建时固定（SDK `runtime.py` 兼容性检查不含 extra_mounts）；长生命周期共享 session 后续新激活的 skill 不会挂上（当前缓解：创建时挂上 pipeline 绑定的全部 skill）——动态绑定场景需销毁重建或文档说明。
+- **#21** 集成测试未进 CI：容器实际执行、E2B 真机、managed-process WS attach 仅本地可跑。安全关键路径缺自动化覆盖——SaaS 前建议加 Docker-in-Docker CI stage 或合并前手动 checklist。

docs/review/box-session-scope.md

@@ -1,6 +1,7 @@
 # Box Session Scope Design
 
-> Date: 2026-04-18 (last reviewed 2026-05-19)
+> Date: 2026-04-18 (last reviewed 2026-06-02)
+> Status (2026-06-02): the self-hosted community edition is release-ready (box optional, clean degradation, no migration debt). Tool-call loop cap, async quota scan, and the host_path mount allowlist have landed. Remaining multi-tenant / security hardening is tracked in [box-issues.md](./box-issues.md).
 > Branch: `feat/sandbox` (LangBot + langbot-plugin-sdk)
 > Related: [Box Architecture](./box-architecture.md) | [Box vs Plugin Runtime](./box-vs-plugin-runtime.md)
 

docs/review/box-test-coverage.md

@@ -1,6 +1,7 @@
 # Box 系统测试覆盖分析
 
-> 更新日期: 2026-05-19
+> 更新日期: 2026-06-02
+> 状态更新: 自部署社区版已具备发布条件（box 可选、降级完善、无迁移欠债）；工具调用循环上限、配额遍历异步化、`host_path` 挂载白名单等已落地。剩余多租户 / 安全硬化项见 [SaaS 阻塞项清单](./box-issues.md)。
 > 分支: `feat/sandbox` (LangBot + langbot-plugin-sdk)
 
 ---

docs/review/box-tob-analysis.md

@@ -1,6 +1,7 @@
 # Box 系统 toB 商业化分析
 
-> 更新日期: 2026-05-19
+> 更新日期: 2026-06-02
+> 状态更新: 自部署社区版已具备发布条件（box 可选、降级完善、无迁移欠债）；工具调用循环上限、配额遍历异步化、`host_path` 挂载白名单等已落地。剩余多租户 / 安全硬化项见 [SaaS 阻塞项清单](./box-issues.md)。
 > 分支: `feat/sandbox` (LangBot + langbot-plugin-sdk)
 
 ---

docs/review/box-vs-plugin-runtime.md

@@ -1,6 +1,7 @@
 # Box Runtime vs Plugin Runtime: 连接架构对比
 
-> 更新日期: 2026-05-19
+> 更新日期: 2026-06-02
+> 状态更新: 自部署社区版已具备发布条件（box 可选、降级完善、无迁移欠债）；工具调用循环上限、配额遍历异步化、`host_path` 挂载白名单等已落地。剩余多租户 / 安全硬化项见 [SaaS 阻塞项清单](./box-issues.md)。
 > 分支: `feat/sandbox` (LangBot + langbot-plugin-sdk)
 
 ---

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langbot"
-version = "4.10.0-beta.1"
+version = "4.10.0"
 description = "Production-grade platform for building agentic IM bots"
 readme = "README.md"
 license-files = ["LICENSE"]
@@ -70,7 +70,7 @@ dependencies = [
     "chromadb>=1.0.0,<2.0.0",
     "qdrant-client (>=1.15.1,<2.0.0)",
     "pyseekdb==1.1.0.post3",
-    "langbot-plugin==0.4.0b1",
+    "langbot-plugin==0.4.1",
     "asyncpg>=0.30.0",
     "line-bot-sdk>=3.19.0",
     "matrix-nio>=0.25.2",

src/langbot/__init__.py

@@ -1,3 +1,3 @@
 """LangBot - Production-grade platform for building agentic IM bots"""
 
-__version__ = '4.10.0-beta.1'
+__version__ = '4.10.0'

src/langbot/libs/deerflow_api/__init__.py

@@ -0,0 +1,5 @@
+from .client import AsyncDeerFlowClient
+from .errors import DeerFlowAPIError
+from . import stream_utils
+
+__all__ = ['AsyncDeerFlowClient', 'DeerFlowAPIError', 'stream_utils']

src/langbot/libs/deerflow_api/client.py

@@ -0,0 +1,204 @@
+"""DeerFlow LangGraph HTTP API 客户端
+
+参考 astrbot 的 deerflow_api_client 实现，使用 httpx 适配 LangBot 风格。
+"""
+
+from __future__ import annotations
+
+import codecs
+import json
+import typing
+from collections.abc import AsyncGenerator
+
+import httpx
+
+from .errors import DeerFlowAPIError
+
+
+SSE_MAX_BUFFER_CHARS = 1_048_576
+
+
+def _normalize_sse_newlines(text: str) -> str:
+    """规范化 CRLF/CR 为 LF，确保 SSE 块分割稳定"""
+    return text.replace('\r\n', '\n').replace('\r', '\n')
+
+
+def _parse_sse_data_lines(data_lines: list[str]) -> typing.Any:
+    raw_data = '\n'.join(data_lines)
+    try:
+        return json.loads(raw_data)
+    except json.JSONDecodeError:
+        # 某些 LangGraph 兼容服务端会在单个 SSE 事件中用多个 data 行
+        # 发送多段 JSON 片段（例如 tuple payload）
+        parsed_lines: list[typing.Any] = []
+        can_parse_all = True
+        for line in data_lines:
+            line = line.strip()
+            if not line:
+                continue
+            try:
+                parsed_lines.append(json.loads(line))
+            except json.JSONDecodeError:
+                can_parse_all = False
+                break
+        if can_parse_all and parsed_lines:
+            return parsed_lines[0] if len(parsed_lines) == 1 else parsed_lines
+        return raw_data
+
+
+def _parse_sse_block(block: str) -> dict[str, typing.Any] | None:
+    if not block.strip():
+        return None
+
+    event_name = 'message'
+    data_lines: list[str] = []
+    for line in block.splitlines():
+        if line.startswith('event:'):
+            event_name = line[6:].strip()
+        elif line.startswith('data:'):
+            data_lines.append(line[5:].lstrip())
+
+    if not data_lines:
+        return None
+    return {'event': event_name, 'data': _parse_sse_data_lines(data_lines)}
+
+
+class AsyncDeerFlowClient:
+    """DeerFlow LangGraph HTTP API 客户端"""
+
+    api_base: str
+    headers: dict[str, str]
+
+    def __init__(
+        self,
+        api_base: str = 'http://127.0.0.1:2026',
+        api_key: str = '',
+        auth_header: str = '',
+    ) -> None:
+        self.api_base = api_base.rstrip('/')
+        self.headers: dict[str, str] = {}
+        if auth_header:
+            self.headers['Authorization'] = auth_header
+        elif api_key:
+            self.headers['Authorization'] = f'Bearer {api_key}'
+
+    async def create_thread(self, timeout: float = 20) -> dict[str, typing.Any]:
+        """创建一个新的 LangGraph thread
+
+        Returns:
+            包含 thread_id 等信息的字典
+        """
+        url = f'{self.api_base}/api/langgraph/threads'
+        payload = {'metadata': {}}
+
+        async with httpx.AsyncClient(
+            trust_env=True,
+            timeout=timeout,
+        ) as client:
+            response = await client.post(
+                url,
+                headers=self.headers,
+                json=payload,
+            )
+            if response.status_code not in (200, 201):
+                raise DeerFlowAPIError(
+                    operation='create thread',
+                    status=response.status_code,
+                    body=response.text,
+                    url=url,
+                )
+            return response.json()
+
+    async def delete_thread(self, thread_id: str, timeout: float = 20) -> None:
+        """删除指定 thread"""
+        url = f'{self.api_base}/api/threads/{thread_id}'
+
+        async with httpx.AsyncClient(
+            trust_env=True,
+            timeout=timeout,
+        ) as client:
+            response = await client.delete(url, headers=self.headers)
+            if response.status_code not in (200, 202, 204, 404):
+                raise DeerFlowAPIError(
+                    operation='delete thread',
+                    status=response.status_code,
+                    body=response.text,
+                    url=url,
+                    thread_id=thread_id,
+                )
+
+    async def stream_run(
+        self,
+        thread_id: str,
+        payload: dict[str, typing.Any],
+        timeout: float = 120,
+    ) -> AsyncGenerator[dict[str, typing.Any], None]:
+        """运行一次 LangGraph stream 请求，逐事件 yield
+
+        Yields:
+            事件字典 {'event': event_name, 'data': parsed_data}
+        """
+        url = f'{self.api_base}/api/langgraph/threads/{thread_id}/runs/stream'
+
+        # 流式请求使用单独的 read timeout 控制
+        stream_timeout = httpx.Timeout(
+            connect=min(timeout, 30),
+            read=timeout,
+            write=timeout,
+            pool=timeout,
+        )
+
+        async with httpx.AsyncClient(
+            trust_env=True,
+            timeout=stream_timeout,
+        ) as client:
+            async with client.stream(
+                'POST',
+                url,
+                headers={
+                    **self.headers,
+                    'Accept': 'text/event-stream',
+                    'Content-Type': 'application/json',
+                },
+                json=payload,
+            ) as resp:
+                if resp.status_code != 200:
+                    body = await resp.aread()
+                    raise DeerFlowAPIError(
+                        operation='runs/stream request',
+                        status=resp.status_code,
+                        body=body.decode('utf-8', errors='replace'),
+                        url=url,
+                        thread_id=thread_id,
+                    )
+
+                decoder = codecs.getincrementaldecoder('utf-8')('replace')
+                buffer = ''
+
+                async for chunk in resp.aiter_bytes(8192):
+                    buffer += _normalize_sse_newlines(decoder.decode(chunk))
+
+                    while '\n\n' in buffer:
+                        block, buffer = buffer.split('\n\n', 1)
+                        parsed = _parse_sse_block(block)
+                        if parsed is not None:
+                            yield parsed
+
+                    if len(buffer) > SSE_MAX_BUFFER_CHARS:
+                        # 缓冲区过大，强制 flush
+                        parsed = _parse_sse_block(buffer)
+                        if parsed is not None:
+                            yield parsed
+                        buffer = ''
+
+                # flush 剩余内容
+                buffer += _normalize_sse_newlines(decoder.decode(b'', final=True))
+                while '\n\n' in buffer:
+                    block, buffer = buffer.split('\n\n', 1)
+                    parsed = _parse_sse_block(block)
+                    if parsed is not None:
+                        yield parsed
+                if buffer.strip():
+                    parsed = _parse_sse_block(buffer)
+                    if parsed is not None:
+                        yield parsed

src/langbot/libs/deerflow_api/errors.py

@@ -0,0 +1,30 @@
+from __future__ import annotations
+
+
+class DeerFlowAPIError(Exception):
+    """DeerFlow API 请求失败"""
+
+    def __init__(
+        self,
+        *,
+        operation: str = '',
+        status: int = 0,
+        body: str = '',
+        url: str = '',
+        thread_id: str | None = None,
+        message: str = '',
+    ) -> None:
+        self.operation = operation
+        self.status = status
+        self.body = body
+        self.url = url
+        self.thread_id = thread_id
+
+        if message:
+            super().__init__(message)
+            return
+
+        msg = f'DeerFlow {operation} failed: status={status}, url={url}, body={body}'
+        if thread_id is not None:
+            msg = f'DeerFlow {operation} failed: thread_id={thread_id}, status={status}, url={url}, body={body}'
+        super().__init__(msg)

src/langbot/libs/deerflow_api/stream_utils.py

@@ -0,0 +1,212 @@
+"""DeerFlow LangGraph 流式响应解析工具
+
+参考 astrbot 实现的 deerflow_stream_utils。
+"""
+
+from __future__ import annotations
+
+import typing
+from collections.abc import Iterable
+
+
+def extract_text(content: typing.Any) -> str:
+    """从消息 content 中提取纯文本"""
+    if isinstance(content, str):
+        return content
+    if isinstance(content, dict):
+        if isinstance(content.get('text'), str):
+            return content['text']
+        if 'content' in content:
+            return extract_text(content.get('content'))
+        if 'kwargs' in content and isinstance(content['kwargs'], dict):
+            return extract_text(content['kwargs'].get('content'))
+    if isinstance(content, list):
+        parts: list[str] = []
+        for item in content:
+            if isinstance(item, str):
+                parts.append(item)
+            elif isinstance(item, dict):
+                item_type = item.get('type')
+                if item_type == 'text' and isinstance(item.get('text'), str):
+                    parts.append(item['text'])
+                elif 'content' in item:
+                    parts.append(extract_text(item['content']))
+        return '\n'.join([p for p in parts if p]).strip()
+    return str(content) if content is not None else ''
+
+
+def extract_messages_from_values_data(data: typing.Any) -> list[typing.Any]:
+    """从 values 事件中提取 messages 列表"""
+    candidates: list[typing.Any] = []
+    if isinstance(data, dict):
+        candidates.append(data)
+        if isinstance(data.get('values'), dict):
+            candidates.append(data['values'])
+    elif isinstance(data, list):
+        candidates.extend([x for x in data if isinstance(x, dict)])
+
+    for item in candidates:
+        messages = item.get('messages')
+        if isinstance(messages, list):
+            return messages
+    return []
+
+
+def is_ai_message(message: dict[str, typing.Any]) -> bool:
+    """判断是否为 AI/assistant 消息"""
+    role = str(message.get('role', '')).lower()
+    if role in {'assistant', 'ai'}:
+        return True
+
+    msg_type = str(message.get('type', '')).lower()
+    if msg_type in {'ai', 'assistant', 'aimessage', 'aimessagechunk'}:
+        return True
+    if 'ai' in msg_type and all(token not in msg_type for token in ('human', 'tool', 'system')):
+        return True
+    return False
+
+
+def extract_latest_ai_text(messages: Iterable[typing.Any]) -> str:
+    """获取最近一条 AI 消息的文本内容"""
+    if isinstance(messages, (list, tuple)):
+        iterable = reversed(messages)
+    else:
+        iterable = reversed(list(messages))
+
+    for msg in iterable:
+        if not isinstance(msg, dict):
+            continue
+        if is_ai_message(msg):
+            text = extract_text(msg.get('content'))
+            if text:
+                return text
+    return ''
+
+
+def extract_latest_ai_message(messages: Iterable[typing.Any]) -> dict[str, typing.Any] | None:
+    """获取最近一条 AI 消息对象"""
+    if isinstance(messages, (list, tuple)):
+        iterable = reversed(messages)
+    else:
+        iterable = reversed(list(messages))
+
+    for msg in iterable:
+        if not isinstance(msg, dict):
+            continue
+        if is_ai_message(msg):
+            return msg
+    return None
+
+
+def is_clarification_tool_message(message: dict[str, typing.Any]) -> bool:
+    """判断是否为澄清问题工具消息"""
+    msg_type = str(message.get('type', '')).lower()
+    tool_name = str(message.get('name', '')).lower()
+    return msg_type == 'tool' and tool_name == 'ask_clarification'
+
+
+def extract_latest_clarification_text(messages: Iterable[typing.Any]) -> str:
+    """提取最近的澄清问题文本"""
+    if isinstance(messages, (list, tuple)):
+        iterable = reversed(messages)
+    else:
+        iterable = reversed(list(messages))
+
+    for msg in iterable:
+        if not isinstance(msg, dict):
+            continue
+        if is_clarification_tool_message(msg):
+            text = extract_text(msg.get('content'))
+            if text:
+                return text
+    return ''
+
+
+def get_message_id(message: typing.Any) -> str:
+    """提取消息 ID"""
+    if not isinstance(message, dict):
+        return ''
+    msg_id = message.get('id')
+    return msg_id if isinstance(msg_id, str) else ''
+
+
+def extract_event_message_obj(data: typing.Any) -> dict[str, typing.Any] | None:
+    """从事件 data 中提取消息对象"""
+    msg_obj = data
+    if isinstance(data, (list, tuple)) and data:
+        msg_obj = data[0]
+    if isinstance(msg_obj, dict) and isinstance(msg_obj.get('data'), dict):
+        msg_obj = msg_obj['data']
+    return msg_obj if isinstance(msg_obj, dict) else None
+
+
+def extract_ai_delta_from_event_data(data: typing.Any) -> str:
+    """从 messages-tuple 事件中提取 AI delta 文本"""
+    msg_obj = extract_event_message_obj(data)
+    if not msg_obj:
+        return ''
+    if is_ai_message(msg_obj):
+        return extract_text(msg_obj.get('content'))
+    return ''
+
+
+def extract_clarification_from_event_data(data: typing.Any) -> str:
+    """从事件中提取澄清问题"""
+    msg_obj = extract_event_message_obj(data)
+    if not msg_obj:
+        return ''
+    if is_clarification_tool_message(msg_obj):
+        return extract_text(msg_obj.get('content'))
+    return ''
+
+
+def _iter_custom_event_items(data: typing.Any) -> list[dict[str, typing.Any]]:
+    items: list[dict[str, typing.Any]] = []
+    if isinstance(data, dict):
+        return [data]
+    if isinstance(data, list):
+        for item in data:
+            if isinstance(item, dict):
+                items.append(item)
+            elif isinstance(item, (list, tuple)):
+                for nested in item:
+                    if isinstance(nested, dict):
+                        items.append(nested)
+    return items
+
+
+def extract_task_failures_from_custom_event(data: typing.Any) -> list[str]:
+    """从 custom 事件中提取子任务失败信息"""
+    failures: list[str] = []
+    for item in _iter_custom_event_items(data):
+        event_type = str(item.get('type', '')).lower()
+        if event_type not in {'task_failed', 'task_timed_out'}:
+            continue
+
+        task_id = str(item.get('task_id', '')).strip()
+        error_text = extract_text(item.get('error')).strip()
+        if task_id and error_text:
+            failures.append(f'{task_id}: {error_text}')
+        elif error_text:
+            failures.append(error_text)
+        elif task_id:
+            failures.append(f'{task_id}: unknown error')
+        else:
+            failures.append('unknown task failure')
+    return failures
+
+
+def build_task_failure_summary(failures: list[str]) -> str:
+    """构建任务失败摘要"""
+    if not failures:
+        return ''
+    deduped: list[str] = []
+    seen: set[str] = set()
+    for failure in failures:
+        if failure not in seen:
+            seen.add(failure)
+            deduped.append(failure)
+    if len(deduped) == 1:
+        return f'DeerFlow subtask failed: {deduped[0]}'
+    joined = '\n'.join([f'- {item}' for item in deduped[:5]])
+    return f'DeerFlow subtasks failed:\n{joined}'

src/langbot/libs/weknora_api/__init__.py

@@ -0,0 +1,4 @@
+from .client import AsyncWeKnoraClient
+from .errors import WeKnoraAPIError
+
+__all__ = ['AsyncWeKnoraClient', 'WeKnoraAPIError']

src/langbot/libs/weknora_api/client.py

@@ -0,0 +1,180 @@
+from __future__ import annotations
+
+import httpx
+import typing
+import json
+
+from .errors import WeKnoraAPIError
+
+
+class AsyncWeKnoraClient:
+    """WeKnora API 客户端"""
+
+    api_key: str
+    base_url: str
+
+    def __init__(
+        self,
+        api_key: str,
+        base_url: str = 'http://localhost:80/api/v1',
+    ) -> None:
+        self.api_key = api_key
+        self.base_url = base_url
+
+    async def create_session(
+        self,
+        title: str = '',
+        description: str = '',
+        timeout: float = 30.0,
+    ) -> str:
+        """创建会话，返回 session_id"""
+        async with httpx.AsyncClient(
+            base_url=self.base_url,
+            trust_env=True,
+            timeout=timeout,
+        ) as client:
+            payload: dict[str, typing.Any] = {}
+            if title:
+                payload['title'] = title
+            if description:
+                payload['description'] = description
+
+            response = await client.post(
+                '/sessions',
+                headers={
+                    'X-API-Key': self.api_key,
+                    'Content-Type': 'application/json',
+                },
+                json=payload,
+            )
+
+            if response.status_code not in (200, 201):
+                raise WeKnoraAPIError(f'{response.status_code} {response.text}')
+
+            data = response.json()
+            return data['data']['id']
+
+    async def agent_chat(
+        self,
+        session_id: str,
+        query: str,
+        user: str,
+        agent_id: str = '',
+        knowledge_base_ids: list[str] | None = None,
+        web_search_enabled: bool = False,
+        timeout: float = 120.0,
+    ) -> typing.AsyncGenerator[dict[str, typing.Any], None]:
+        """
+        Agent 智能对话（SSE 流式）
+
+        响应事件类型:
+        - agent_query: Agent 开始处理
+        - thinking: 思考过程
+        - tool_call: 工具调用
+        - tool_result: 工具结果
+        - references: 知识库引用
+        - answer: 回答内容
+        - reflection: 反思
+        - session_title: 会话标题
+        - error: 错误
+        """
+        if knowledge_base_ids is None:
+            knowledge_base_ids = []
+
+        async with httpx.AsyncClient(
+            base_url=self.base_url,
+            trust_env=True,
+            timeout=timeout,
+        ) as client:
+            payload: dict[str, typing.Any] = {
+                'query': query,
+                'agent_enabled': True,
+                'channel': 'im',
+            }
+            if agent_id:
+                payload['agent_id'] = agent_id
+            if knowledge_base_ids:
+                payload['knowledge_base_ids'] = knowledge_base_ids
+            if web_search_enabled:
+                payload['web_search_enabled'] = True
+
+            async with client.stream(
+                'POST',
+                f'/agent-chat/{session_id}',
+                headers={
+                    'X-API-Key': self.api_key,
+                    'Content-Type': 'application/json',
+                },
+                json=payload,
+            ) as r:
+                async for chunk in r.aiter_lines():
+                    if r.status_code != 200:
+                        raise WeKnoraAPIError(f'{r.status_code} {chunk}')
+                    if chunk.strip() == '':
+                        continue
+                    if chunk.startswith('data:'):
+                        try:
+                            data = json.loads(chunk[5:].strip())
+                        except json.JSONDecodeError:
+                            continue
+                        yield data
+                        # 收到 error 事件后主动结束流，避免上层未 raise 时持续等待
+                        if data.get('response_type') == 'error':
+                            return
+
+    async def knowledge_chat(
+        self,
+        session_id: str,
+        query: str,
+        user: str,
+        agent_id: str = 'builtin-quick-answer',
+        knowledge_base_ids: list[str] | None = None,
+        timeout: float = 120.0,
+    ) -> typing.AsyncGenerator[dict[str, typing.Any], None]:
+        """
+        知识库 RAG 问答（SSE 流式）
+
+        响应事件类型:
+        - references: 知识库引用
+        - answer: 回答内容
+        """
+        if knowledge_base_ids is None:
+            knowledge_base_ids = []
+
+        async with httpx.AsyncClient(
+            base_url=self.base_url,
+            trust_env=True,
+            timeout=timeout,
+        ) as client:
+            payload: dict[str, typing.Any] = {
+                'query': query,
+                'channel': 'im',
+            }
+            if agent_id:
+                payload['agent_id'] = agent_id
+            if knowledge_base_ids:
+                payload['knowledge_base_ids'] = knowledge_base_ids
+
+            async with client.stream(
+                'POST',
+                f'/knowledge-chat/{session_id}',
+                headers={
+                    'X-API-Key': self.api_key,
+                    'Content-Type': 'application/json',
+                },
+                json=payload,
+            ) as r:
+                async for chunk in r.aiter_lines():
+                    if r.status_code != 200:
+                        raise WeKnoraAPIError(f'{r.status_code} {chunk}')
+                    if chunk.strip() == '':
+                        continue
+                    if chunk.startswith('data:'):
+                        try:
+                            data = json.loads(chunk[5:].strip())
+                        except json.JSONDecodeError:
+                            continue
+                        yield data
+                        # 收到 error 事件后主动结束流，避免上层未 raise 时持续等待
+                        if data.get('response_type') == 'error':
+                            return

src/langbot/libs/weknora_api/errors.py

@@ -0,0 +1,6 @@
+class WeKnoraAPIError(Exception):
+    """WeKnora API 请求失败"""
+
+    def __init__(self, message: str = ''):
+        self.message = message
+        super().__init__(self.message)

src/langbot/pkg/api/http/controller/groups/pipelines/websocket_chat.py

@@ -43,8 +43,12 @@ class WebSocketChatRouterGroup(group.RouterGroup):
                     await quart.websocket.send(json.dumps({'type': 'error', 'message': 'WebSocket adapter not found'}))
                     return
 
-                # Find the owning bot for this pipeline (e.g. a web_page_bot)
-                owner_bot = self._find_owner_bot(pipeline_uuid)
+                # Dashboard pipeline-debug sessions must always run under the
+                # built-in websocket_proxy_bot identity. We deliberately do NOT
+                # resolve a web_page_bot owner here — even if one is bound to
+                # the same pipeline, debug requests must not be attributed to
+                # it. The embed widget path (`/api/v1/embed/<bot>/ws/connect`)
+                # is the one that carries the page-bot identity.
 
                 # 注册连接
                 connection = await ws_connection_manager.add_connection(
@@ -73,7 +77,7 @@ class WebSocketChatRouterGroup(group.RouterGroup):
                 )
 
                 # 创建接收和发送任务
-                receive_task = asyncio.create_task(self._handle_receive(connection, websocket_adapter, owner_bot))
+                receive_task = asyncio.create_task(self._handle_receive(connection, websocket_adapter))
                 send_task = asyncio.create_task(self._handle_send(connection))
 
                 # 等待任务完成
@@ -181,14 +185,7 @@ class WebSocketChatRouterGroup(group.RouterGroup):
             except Exception as e:
                 return self.http_status(500, -1, f'Internal server error: {str(e)}')
 
-    def _find_owner_bot(self, pipeline_uuid: str):
-        """Find a user-created bot (e.g. web_page_bot) that owns this pipeline."""
-        for bot in self.ap.platform_mgr.bots:
-            if bot.bot_entity.adapter == 'web_page_bot' and bot.bot_entity.use_pipeline_uuid == pipeline_uuid:
-                return bot
-        return None
-
-    async def _handle_receive(self, connection, websocket_adapter, owner_bot=None):
+    async def _handle_receive(self, connection, websocket_adapter):
         """处理接收消息的任务"""
         try:
             while connection.is_active:
@@ -213,7 +210,10 @@ class WebSocketChatRouterGroup(group.RouterGroup):
                         logger.debug(f'收到消息: {data} from {connection.connection_id}')
 
                         # 处理消息（不等待响应，响应会通过broadcast异步发送）
-                        await websocket_adapter.handle_websocket_message(connection, data, owner_bot=owner_bot)
+                        # owner_bot is intentionally NOT passed: the dashboard
+                        # debug WebSocket must always run under the proxy bot,
+                        # never under a coincidentally-bound web_page_bot.
+                        await websocket_adapter.handle_websocket_message(connection, data)
 
                     elif message_type == 'disconnect':
                         # 客户端主动断开

src/langbot/pkg/api/http/controller/groups/platform/adapters.py

@@ -179,8 +179,6 @@ class AdaptersRouterGroup(group.RouterGroup):
             """Start WeChat QR code login. Returns session_id + QR code data URL."""
             import uuid
             import time
-            import io
-            import base64
 
             from langbot.libs.openclaw_weixin_api.client import OpenClawWeixinClient, DEFAULT_BASE_URL
 
@@ -208,60 +206,32 @@ class AdaptersRouterGroup(group.RouterGroup):
 
             async def run_login():
                 try:
-                    import qrcode as qr_lib
 
-                    for _attempt in range(3):
-                        qr_resp = await client.fetch_qrcode()
-                        if not qr_resp.qrcode or not qr_resp.qrcode_img_content:
-                            raise Exception('Failed to get QR code from server')
-
-                        # Generate QR code image locally
-                        qr = qr_lib.QRCode(error_correction=qr_lib.constants.ERROR_CORRECT_L)
-                        qr.add_data(qr_resp.qrcode_img_content)
-                        qr.make(fit=True)
-                        img = qr.make_image(fill_color='black', back_color='white')
-                        buf = io.BytesIO()
-                        img.save(buf, format='PNG')
-                        b64 = base64.b64encode(buf.getvalue()).decode('utf-8')
-                        data_url = f'data:image/png;base64,{b64}'
-
-                        def _update_qr():
-                            session['qr_data_url'] = data_url
-                            session['expire_at'] = time.time() + 480  # 8 minutes
+                    def on_qrcode(qr_data_url: str, _qr_url: str):
+                        def _update():
+                            session['qr_data_url'] = qr_data_url
+                            session['expire_at'] = time.time() + 180
                             session['status'] = 'waiting'
 
-                        loop.call_soon_threadsafe(_update_qr)
-
-                        # Poll for scan status
-                        deadline = loop.time() + 180
-                        while loop.time() < deadline:
-                            try:
-                                status_resp = await client.poll_qrcode_status(qr_resp.qrcode)
-                            except Exception:
-                                await asyncio.sleep(2)
-                                continue
-
-                            if status_resp.status == 'confirmed' and status_resp.bot_token:
-                                session['status'] = 'success'
-                                session['token'] = status_resp.bot_token
-                                session['base_url'] = status_resp.baseurl or client.base_url
-                                session['account_id'] = status_resp.ilink_bot_id or ''
-                                return
-
-                            if status_resp.status == 'expired':
-                                break  # retry with new QR code
-
-                            await asyncio.sleep(1)
-                        else:
-                            pass  # timeout, retry
-
-                    # All retries exhausted
-                    session['status'] = 'error'
-                    session['error'] = 'QR code login failed: max retries exceeded'
+                        loop.call_soon_threadsafe(_update)
 
+                    result = await client.login(
+                        max_retries=1,
+                        poll_timeout_ms=180_000,
+                        on_qrcode=on_qrcode,
+                    )
+                    session['status'] = 'success'
+                    session['token'] = result.token
+                    session['base_url'] = result.base_url
+                    session['account_id'] = result.account_id
                 except Exception as e:
-                    session['status'] = 'error'
-                    session['error'] = str(e)
+                    error_message = str(e)
+                    if 'expired' in error_message.lower() or 'max retries exceeded' in error_message.lower():
+                        session['status'] = 'expired'
+                        session['error'] = 'QR code expired'
+                    else:
+                        session['status'] = 'error'
+                        session['error'] = error_message
                 finally:
                     await client.close()
 
@@ -295,7 +265,11 @@ class AdaptersRouterGroup(group.RouterGroup):
             if not session:
                 return self.http_status(404, -1, 'Session not found')
 
-            data = {'status': session['status']}
+            data = {
+                'status': session['status'],
+                'qr_data_url': session['qr_data_url'],
+                'expire_at': session['expire_at'],
+            }
 
             if session['status'] == 'success':
                 data['token'] = session['token']
@@ -305,6 +279,9 @@ class AdaptersRouterGroup(group.RouterGroup):
             elif session['status'] == 'error':
                 data['error'] = session['error']
                 _weixin_login_sessions.pop(session_id, None)
+            elif session['status'] == 'expired':
+                data['error'] = session['error']
+                _weixin_login_sessions.pop(session_id, None)
 
             return self.success(data=data)
 

src/langbot/pkg/box/service.py

@@ -168,7 +168,7 @@ class BoxService:
             f'spec={json.dumps(self._summarize_spec(spec), ensure_ascii=False)}'
         )
         try:
-            self._enforce_workspace_quota(spec, phase='before execution')
+            await self._enforce_workspace_quota(spec, phase='before execution')
         except BoxError as exc:
             self._record_error(exc, query)
             raise
@@ -178,7 +178,7 @@ class BoxService:
             self._record_error(exc, query)
             raise
         try:
-            self._enforce_workspace_quota(spec, phase='after execution')
+            await self._enforce_workspace_quota(spec, phase='after execution')
         except BoxError as exc:
             await self._cleanup_exceeded_session(spec)
             self._record_error(exc, query)
@@ -683,7 +683,7 @@ class BoxService:
         _walk(root)
         return total
 
-    def _enforce_workspace_quota(self, spec: BoxSpec, *, phase: str) -> None:
+    async def _enforce_workspace_quota(self, spec: BoxSpec, *, phase: str) -> None:
         if spec.host_path is None or spec.workspace_quota_mb <= 0:
             return
 
@@ -691,7 +691,10 @@ class BoxService:
         if not os.path.isdir(host_path):
             return
 
-        used_bytes = self._get_workspace_size_bytes(host_path)
+        # Walk the workspace off the event loop — this runs on every
+        # quota-enforced exec, and a large tree would otherwise block the whole
+        # asyncio runtime (all bots/pipelines) for the duration of the scan.
+        used_bytes = await asyncio.to_thread(self._get_workspace_size_bytes, host_path)
         limit_bytes = spec.workspace_quota_mb * _MIB
         if used_bytes <= limit_bytes:
             return

src/langbot/pkg/core/migrations/m042_weknora_api.py

@@ -0,0 +1,27 @@
+from __future__ import annotations
+
+from .. import migration
+
+
+@migration.migration_class('weknora-api-config', 42)
+class WeKnoraAPICfgMigration(migration.Migration):
+    """WeKnora API 配置迁移"""
+
+    async def need_migrate(self) -> bool:
+        """判断当前环境是否需要运行此迁移"""
+        return 'weknora-api' not in self.ap.provider_cfg.data
+
+    async def run(self):
+        """执行迁移"""
+        self.ap.provider_cfg.data['weknora-api'] = {
+            'base-url': 'http://localhost:8080/api/v1',
+            'app-type': 'agent',
+            'api-key': '',
+            'agent-id': 'builtin-smart-reasoning',
+            'knowledge-base-ids': [],
+            'web-search-enabled': False,
+            'timeout': 120,
+            'base-prompt': '请回答用户的问题。',
+        }
+
+        await self.ap.provider_cfg.dump_config()

src/langbot/pkg/core/migrations/m043_deerflow_api.py

@@ -0,0 +1,30 @@
+from __future__ import annotations
+
+from .. import migration
+
+
+@migration.migration_class('deerflow-api-config', 43)
+class DeerFlowAPICfgMigration(migration.Migration):
+    """DeerFlow API 配置迁移"""
+
+    async def need_migrate(self) -> bool:
+        """判断当前环境是否需要运行此迁移"""
+        return 'deerflow-api' not in self.ap.provider_cfg.data
+
+    async def run(self):
+        """执行迁移"""
+        self.ap.provider_cfg.data['deerflow-api'] = {
+            'api-base': 'http://127.0.0.1:2026',
+            'api-key': '',
+            'auth-header': '',
+            'assistant-id': 'lead_agent',
+            'model-name': '',
+            'thinking-enabled': False,
+            'plan-mode': False,
+            'subagent-enabled': False,
+            'max-concurrent-subagents': 3,
+            'timeout': 300,
+            'recursion-limit': 1000,
+        }
+
+        await self.ap.provider_cfg.dump_config()

src/langbot/pkg/platform/sources/lark.py

@@ -881,7 +881,8 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
 
         bot_account_id = config['bot_name']
 
-        bot = lark_oapi.ws.Client(config['app_id'], config['app_secret'], event_handler=event_handler)
+        domain = self._resolve_domain(config)
+        bot = lark_oapi.ws.Client(config['app_id'], config['app_secret'], event_handler=event_handler, domain=domain)
         api_client = self.build_api_client(config)
         cipher = AESCipher(config.get('encrypt-key', ''))
         self.request_app_ticket(api_client, config)
@@ -1014,13 +1015,28 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
 
         return None
 
+    @staticmethod
+    def _resolve_domain(config) -> str:
+        domain = config.get('domain', lark_oapi.FEISHU_DOMAIN)
+        if domain == 'custom':
+            domain = config.get('custom_domain', '')
+            if not domain:
+                raise ValueError('Custom domain is required when domain is set to "custom"')
+        return domain.rstrip('/')
+
     def build_api_client(self, config):
         app_id = config['app_id']
         app_secret = config['app_secret']
-        api_client = lark_oapi.Client.builder().app_id(app_id).app_secret(app_secret).build()
+        domain = self._resolve_domain(config)
+        api_client = lark_oapi.Client.builder().app_id(app_id).app_secret(app_secret).domain(domain).build()
         if 'isv' == config.get('app_type', 'self'):
             api_client = (
-                lark_oapi.Client.builder().app_id(app_id).app_secret(app_secret).app_type(lark_oapi.AppType.ISV).build()
+                lark_oapi.Client.builder()
+                .app_id(app_id)
+                .app_secret(app_secret)
+                .app_type(lark_oapi.AppType.ISV)
+                .domain(domain)
+                .build()
             )
         return api_client
 

src/langbot/pkg/platform/sources/lark.yaml

@@ -23,6 +23,57 @@ spec:
     en: https://link.langbot.app/en/platforms/lark
     ja: https://link.langbot.app/ja/platforms/lark
   config:
+    - name: domain
+      label:
+        en_US: Platform Domain
+        zh_Hans: 平台域名
+        zh_Hant: 平台域名
+        ja_JP: プラットフォームドメイン
+      description:
+        en_US: Select the open platform domain. Use Feishu for Chinese mainland, Lark for international
+        zh_Hans: 选择开放平台域名，国内使用飞书，海外使用 Lark
+        zh_Hant: 選擇開放平台域名，國內使用飛書，海外使用 Lark
+        ja_JP: オープンプラットフォームのドメインを選択。中国国内は飛書、海外は Lark を使用
+      type: select
+      options:
+        - name: https://open.feishu.cn
+          label:
+            en_US: Feishu (open.feishu.cn)
+            zh_Hans: 飞书 (open.feishu.cn)
+            zh_Hant: 飛書 (open.feishu.cn)
+            ja_JP: 飛書 (open.feishu.cn)
+        - name: https://open.larksuite.com
+          label:
+            en_US: Lark (open.larksuite.com)
+            zh_Hans: Lark (open.larksuite.com)
+            zh_Hant: Lark (open.larksuite.com)
+            ja_JP: Lark (open.larksuite.com)
+        - name: custom
+          label:
+            en_US: Custom
+            zh_Hans: 自定义
+            zh_Hant: 自定義
+            ja_JP: カスタム
+      required: false
+      default: https://open.feishu.cn
+    - name: custom_domain
+      label:
+        en_US: Custom Domain
+        zh_Hans: 自定义域名
+        zh_Hant: 自定義域名
+        ja_JP: カスタムドメイン
+      description:
+        en_US: "Enter the full domain URL, e.g. https://open.example.com"
+        zh_Hans: "输入完整的域名 URL，例如 https://open.example.com"
+        zh_Hant: "輸入完整的域名 URL，例如 https://open.example.com"
+        ja_JP: "完全なドメイン URL を入力（例: https://open.example.com）"
+      type: string
+      required: false
+      default: ""
+      show_if:
+        field: domain
+        operator: eq
+        value: custom
     - name: one-click-create
       label:
         en_US: One-Click Create App
@@ -140,10 +191,10 @@ spec:
         zh_Hant: 應用類型
         ja_JP: アプリタイプ
       description:
-        en_US: Default to self-built application, refer to https://open.feishu.cn/document/platform-overveiw/overview
-        zh_Hans: 默认为企业自建应用，参考 https://open.feishu.cn/document/platform-overveiw/overview
-        zh_Hant: 預設為企業自建應用，參考 https://open.feishu.cn/document/platform-overveiw/overview
-        ja_JP: デフォルトはカスタムアプリです。詳細は https://open.feishu.cn/document/platform-overveiw/overview を参照してください
+        en_US: "Default to self-built application, refer to https://open.feishu.cn/document/platform-overveiw/overview"
+        zh_Hans: "默认为企业自建应用，参考 https://open.feishu.cn/document/platform-overveiw/overview"
+        zh_Hant: "預設為企業自建應用，參考 https://open.feishu.cn/document/platform-overveiw/overview"
+        ja_JP: "デフォルトはカスタムアプリです。詳細は https://open.feishu.cn/document/platform-overveiw/overview を参照してください"
       type: select
       options:
         - name: self

src/langbot/pkg/plugin/connector.py

@@ -103,6 +103,16 @@ class PluginRuntimeConnector(ManagedRuntimeConnector):
 
             self.handler_task = asyncio.create_task(self.handler.run())
             _ = await self.handler.ping()
+            # Push the configured marketplace (Space) URL to the runtime so it
+            # downloads plugins from the same Space LangBot is bound to, rather
+            # than relying on the runtime's own env/default.
+            space_url = self.ap.instance_config.data.get('space', {}).get('url', '').rstrip('/')
+            if space_url:
+                try:
+                    await self.handler.set_runtime_config(cloud_service_url=space_url)
+                    self.ap.logger.info(f'Pushed marketplace URL to plugin runtime: {space_url}')
+                except Exception as e:
+                    self.ap.logger.warning(f'Failed to push runtime config: {e}')
             self.ap.logger.info('Connected to plugin runtime.')
             await self.handler_task
 
@@ -224,30 +234,23 @@ class PluginRuntimeConnector(ManagedRuntimeConnector):
         mcp_data: dict[str, Any],
         task_context: taskmgr.TaskContext | None = None,
     ):
-        """Install an MCP server from marketplace data."""
+        """Install an MCP server from marketplace data.
+
+        Marketplace MCP records carry the runtime-ready ``mode`` and
+        ``extra_args`` directly (the same shape LangBot stores in
+        ``mcp_servers``), so they are used as-is rather than reconstructed.
+        For ``stdio`` this preserves ``command``/``args``/``env``/``box``;
+        for ``http``/``sse`` it preserves ``url``/``headers``/``timeout``/
+        ``ssereadtimeout``.
+        """
         from ..entity.persistence import mcp as persistence_mcp
         import uuid
 
-        config = mcp_data.get('config', {})
-        url = config.get('url', '')
+        mode = mcp_data.get('mode') or 'stdio'
+        extra_args = mcp_data.get('extra_args') or {}
         # Use __ instead of / to avoid URL routing issues with slashes
         name = f'{mcp_data.get("author", "")}__{mcp_data.get("name", "")}'
 
-        # Determine mode from URL
-        if 'sse' in url.lower():
-            mode = 'sse'
-        elif url.startswith('http'):
-            mode = 'http'
-        else:
-            mode = 'stdio'
-
-        # Build extra_args from config
-        extra_args = {
-            'url': url,
-            'timeout': config.get('timeout', 30),
-            'sse_read_timeout': config.get('sse_read_timeout', 300),
-        }
-
         # Check if MCP server already exists
         existing = await self.ap.persistence_mgr.execute_async(
             sqlalchemy.select(persistence_mcp.MCPServer).where(persistence_mcp.MCPServer.name == name)
@@ -376,15 +379,22 @@ class PluginRuntimeConnector(ManagedRuntimeConnector):
                 mcp_resp = await client.get(f'{space_url}/api/v1/marketplace/mcps/{plugin_author}/{plugin_name}')
                 if mcp_resp.status_code == 200:
                     mcp_data = mcp_resp.json().get('data', {}).get('mcp', {})
-                    if mcp_data.get('config'):
+                    if mcp_data.get('mode'):
                         # It's an MCP - create server locally
                         self.ap.logger.info(f'Installing MCP from marketplace: {plugin_author}/{plugin_name}')
                         if task_context:
                             task_context.set_current_action('installing mcp server')
                         await self._install_mcp_from_marketplace(mcp_data, task_context)
+                        # Best-effort install report (bumps marketplace install_count).
+                        try:
+                            await client.post(
+                                f'{space_url}/api/v1/marketplace/mcps/{plugin_author}/{plugin_name}/install'
+                            )
+                        except Exception as report_err:
+                            self.ap.logger.debug(f'Failed to report MCP install: {report_err}')
                         return
                     else:
-                        raise Exception(f'MCP {plugin_author}/{plugin_name} has no config')
+                        raise Exception(f'MCP {plugin_author}/{plugin_name} has no mode')
                 elif mcp_resp.status_code == 404:
                     # Try skill endpoint - download ZIP and install
                     self.ap.logger.info(f'Trying skill endpoint for: {plugin_author}/{plugin_name}')
@@ -449,7 +459,7 @@ class PluginRuntimeConnector(ManagedRuntimeConnector):
                                         )
 
                                     file_bytes = download_resp.content
-                                    self._extract_deps_metadata(file_bytes, task_context)
+                                    self._inspect_plugin_package(file_bytes, task_context)
                                     file_key = await self.handler.send_file(file_bytes, 'lbpkg')
                                     install_info['plugin_file_key'] = file_key
                                     self.ap.logger.info(f'Transfered file {file_key} to plugin runtime')

src/langbot/pkg/plugin/handler.py

@@ -779,6 +779,16 @@ class RuntimeConnectionHandler(handler.Handler):
             timeout=10,
         )
 
+    async def set_runtime_config(self, cloud_service_url: str) -> dict[str, Any]:
+        """Push runtime configuration (e.g. marketplace URL) to the runtime."""
+        return await self.call_action(
+            LangBotToRuntimeAction.SET_RUNTIME_CONFIG,
+            {
+                'cloud_service_url': cloud_service_url,
+            },
+            timeout=10,
+        )
+
     async def install_plugin(
         self, install_source: str, install_info: dict[str, Any]
     ) -> typing.AsyncGenerator[dict[str, Any], None]:

src/langbot/pkg/provider/modelmgr/modelmgr.py

@@ -143,49 +143,83 @@ class ModelManager:
         # get the latest models from space
         space_models = await self.ap.space_service.get_models()
 
-        exists_llm_models_uuids = [m['uuid'] for m in await self.ap.llm_model_service.get_llm_models()]
-        exists_embedding_models_uuids = [
-            m['uuid'] for m in await self.ap.embedding_models_service.get_embedding_models()
-        ]
+        # Index existing models by uuid. Space reuses a model's uuid across
+        # renames / re-specs (e.g. the uuid that used to be ``claude-opus-4-6``
+        # may later become ``claude-opus-4-7``). So for Space-managed models we
+        # upsert: create when the uuid is new, otherwise update name/abilities/
+        # ranking to track Space. Models owned by other providers are never
+        # touched, even on an (unexpected) uuid collision.
+        existing_llm_models = {m['uuid']: m for m in await self.ap.llm_model_service.get_llm_models()}
+        existing_embedding_models = {
+            m['uuid']: m for m in await self.ap.embedding_models_service.get_embedding_models()
+        }
+
+        created = 0
+        updated = 0
 
         for space_model in space_models:
             if space_model.category == 'chat':
-                uuid = space_model.uuid
-
-                if uuid in exists_llm_models_uuids:
-                    continue
-
-                # model will be automatically loaded
-                await self.ap.llm_model_service.create_llm_model(
-                    {
-                        'uuid': space_model.uuid,
+                existing = existing_llm_models.get(space_model.uuid)
+                if existing is None:
+                    # model will be automatically loaded
+                    await self.ap.llm_model_service.create_llm_model(
+                        {
+                            'uuid': space_model.uuid,
+                            'name': space_model.model_id,
+                            'provider_uuid': space_model_provider.uuid,
+                            'abilities': space_model.llm_abilities or [],
+                            'extra_args': {},
+                            'prefered_ranking': space_model.featured_order,
+                        },
+                        preserve_uuid=True,
+                        auto_set_to_default_pipeline=False,
+                    )
+                    created += 1
+                elif existing.get('provider_uuid') == space_model_provider.uuid:
+                    desired = {
                         'name': space_model.model_id,
                         'provider_uuid': space_model_provider.uuid,
                         'abilities': space_model.llm_abilities or [],
-                        'extra_args': {},
                         'prefered_ranking': space_model.featured_order,
-                    },
-                    preserve_uuid=True,
-                    auto_set_to_default_pipeline=False,
-                )
+                    }
+                    if (
+                        existing.get('name') != desired['name']
+                        or list(existing.get('abilities') or []) != list(desired['abilities'])
+                        or existing.get('prefered_ranking') != desired['prefered_ranking']
+                    ):
+                        await self.ap.llm_model_service.update_llm_model(space_model.uuid, dict(desired))
+                        updated += 1
 
             elif space_model.category == 'embedding':
-                uuid = space_model.uuid
-
-                if uuid in exists_embedding_models_uuids:
-                    continue
-
-                # model will be automatically loaded
-                await self.ap.embedding_models_service.create_embedding_model(
-                    {
-                        'uuid': space_model.uuid,
+                existing = existing_embedding_models.get(space_model.uuid)
+                if existing is None:
+                    # model will be automatically loaded
+                    await self.ap.embedding_models_service.create_embedding_model(
+                        {
+                            'uuid': space_model.uuid,
+                            'name': space_model.model_id,
+                            'provider_uuid': space_model_provider.uuid,
+                            'extra_args': {},
+                            'prefered_ranking': space_model.featured_order,
+                        },
+                        preserve_uuid=True,
+                    )
+                    created += 1
+                elif existing.get('provider_uuid') == space_model_provider.uuid:
+                    desired = {
                         'name': space_model.model_id,
                         'provider_uuid': space_model_provider.uuid,
-                        'extra_args': {},
                         'prefered_ranking': space_model.featured_order,
-                    },
-                    preserve_uuid=True,
-                )
+                    }
+                    if (
+                        existing.get('name') != desired['name']
+                        or existing.get('prefered_ranking') != desired['prefered_ranking']
+                    ):
+                        await self.ap.embedding_models_service.update_embedding_model(space_model.uuid, dict(desired))
+                        updated += 1
+
+        if created or updated:
+            self.ap.logger.info(f'Synced models from LangBot Space: {created} added, {updated} updated.')
 
     async def init_temporary_runtime_llm_model(
         self,

src/langbot/pkg/provider/runners/deerflowapi.py

@@ -0,0 +1,511 @@
+"""DeerFlow LangGraph API Runner
+
+参考 astrbot 的 deerflow_agent_runner 实现，适配 LangBot 的 Runner 接口。
+
+特点：
+- 使用 LangGraph HTTP API 接入 deer-flow 后端
+- 自动管理 thread_id（按 session 隔离）
+- 支持 SSE 流式响应解析
+- 支持 streaming/非流式两种输出
+- 处理 values / messages-tuple / custom 三种事件
+"""
+
+from __future__ import annotations
+
+import asyncio
+import hashlib
+import json
+import typing
+from collections import deque
+from dataclasses import dataclass, field
+
+
+from langbot.pkg.provider import runner
+from langbot.pkg.core import app
+import langbot_plugin.api.entities.builtin.provider.message as provider_message
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+from langbot.libs.deerflow_api import client, errors, stream_utils
+
+
+_MAX_VALUES_HISTORY = 200
+
+
+@dataclass
+class _StreamState:
+    """流式状态跟踪"""
+
+    latest_text: str = ''
+    prev_text_for_streaming: str = ''
+    clarification_text: str = ''
+    task_failures: list[str] = field(default_factory=list)
+    seen_message_ids: set[str] = field(default_factory=set)
+    seen_message_order: deque[str] = field(default_factory=deque)
+    no_id_message_fingerprints: dict[int, str] = field(default_factory=dict)
+    baseline_initialized: bool = False
+    has_values_text: bool = False
+    run_values_messages: list[dict[str, typing.Any]] = field(default_factory=list)
+    timed_out: bool = False
+
+
+@runner.runner_class('deerflow-api')
+class DeerFlowAPIRunner(runner.RequestRunner):
+    """DeerFlow LangGraph API 对话请求器"""
+
+    deerflow_client: client.AsyncDeerFlowClient
+
+    def __init__(self, ap: app.Application, pipeline_config: dict):
+        super().__init__(ap, pipeline_config)
+
+        cfg = self.pipeline_config['ai']['deerflow-api']
+
+        api_base = cfg.get('api-base', '').strip()
+        if not api_base or not api_base.startswith(('http://', 'https://')):
+            raise errors.DeerFlowAPIError(
+                message='DeerFlow API Base URL 格式错误，必须以 http:// 或 https:// 开头',
+            )
+
+        self.api_base = api_base
+        self.api_key = cfg.get('api-key', '')
+        self.auth_header = cfg.get('auth-header', '')
+        self.assistant_id = cfg.get('assistant-id', 'lead_agent')
+        self.model_name = cfg.get('model-name', '')
+        self.thinking_enabled = bool(cfg.get('thinking-enabled', False))
+        self.plan_mode = bool(cfg.get('plan-mode', False))
+        self.subagent_enabled = bool(cfg.get('subagent-enabled', False))
+        self.max_concurrent_subagents = int(cfg.get('max-concurrent-subagents', 3))
+        self.timeout = int(cfg.get('timeout', 300))
+        self.recursion_limit = int(cfg.get('recursion-limit', 1000))
+
+        self.deerflow_client = client.AsyncDeerFlowClient(
+            api_base=self.api_base,
+            api_key=self.api_key,
+            auth_header=self.auth_header,
+        )
+
+    # ------------------------------------------------------------------
+    # 辅助方法
+    # ------------------------------------------------------------------
+
+    def _fingerprint_message(self, message: dict[str, typing.Any]) -> str:
+        try:
+            raw = json.dumps(message, sort_keys=True, ensure_ascii=False, default=str)
+        except (TypeError, ValueError):
+            raw = repr(message)
+        return hashlib.sha1(raw.encode('utf-8', errors='ignore')).hexdigest()
+
+    def _remember_seen_message_id(self, state: _StreamState, msg_id: str) -> None:
+        if not msg_id or msg_id in state.seen_message_ids:
+            return
+        state.seen_message_ids.add(msg_id)
+        state.seen_message_order.append(msg_id)
+        while len(state.seen_message_order) > _MAX_VALUES_HISTORY:
+            dropped = state.seen_message_order.popleft()
+            state.seen_message_ids.discard(dropped)
+
+    def _extract_new_messages_from_values(
+        self,
+        values_messages: list[typing.Any],
+        state: _StreamState,
+    ) -> list[dict[str, typing.Any]]:
+        new_messages: list[dict[str, typing.Any]] = []
+        no_id_indexes_seen: set[int] = set()
+        for idx, msg in enumerate(values_messages):
+            if not isinstance(msg, dict):
+                continue
+            msg_id = stream_utils.get_message_id(msg)
+            if msg_id:
+                if msg_id in state.seen_message_ids:
+                    continue
+                self._remember_seen_message_id(state, msg_id)
+                new_messages.append(msg)
+                continue
+
+            no_id_indexes_seen.add(idx)
+            fp = self._fingerprint_message(msg)
+            if state.no_id_message_fingerprints.get(idx) == fp:
+                continue
+            state.no_id_message_fingerprints[idx] = fp
+            new_messages.append(msg)
+
+        for idx in list(state.no_id_message_fingerprints.keys()):
+            if idx not in no_id_indexes_seen:
+                state.no_id_message_fingerprints.pop(idx, None)
+        return new_messages
+
+    # ------------------------------------------------------------------
+    # 用户输入处理
+    # ------------------------------------------------------------------
+
+    def _build_user_content(
+        self,
+        prompt: str,
+        image_urls: list[str],
+    ) -> typing.Any:
+        """构建 LangGraph 兼容的 user content（支持多模态）"""
+        if not image_urls:
+            return prompt
+
+        content: list[dict[str, typing.Any]] = []
+        if prompt:
+            content.append({'type': 'text', 'text': prompt})
+        for url in image_urls:
+            if not isinstance(url, str):
+                continue
+            url = url.strip()
+            if not url:
+                continue
+            if url.startswith(('http://', 'https://', 'data:')):
+                content.append({'type': 'image_url', 'image_url': {'url': url}})
+        return content if content else prompt
+
+    def _preprocess_user_message(
+        self,
+        query: pipeline_query.Query,
+    ) -> tuple[str, list[str]]:
+        """提取用户消息的纯文本与图片 URL 列表"""
+        plain_text = ''
+        image_urls: list[str] = []
+
+        if isinstance(query.user_message.content, str):
+            plain_text = query.user_message.content
+        elif isinstance(query.user_message.content, list):
+            for ce in query.user_message.content:
+                if ce.type == 'text':
+                    plain_text += ce.text
+                elif ce.type == 'image_base64':
+                    # 转换为 data URI 形式
+                    b64 = getattr(ce, 'image_base64', '')
+                    if b64:
+                        if not b64.startswith('data:'):
+                            b64 = f'data:image/png;base64,{b64}'
+                        image_urls.append(b64)
+                elif ce.type == 'image_url':
+                    url = getattr(ce, 'image_url', '')
+                    if url:
+                        image_urls.append(url)
+
+        return plain_text, image_urls
+
+    # ------------------------------------------------------------------
+    # 请求构造
+    # ------------------------------------------------------------------
+
+    def _build_messages(
+        self,
+        prompt: str,
+        image_urls: list[str],
+        system_prompt: str = '',
+    ) -> list[dict[str, typing.Any]]:
+        messages: list[dict[str, typing.Any]] = []
+        if system_prompt:
+            messages.append({'role': 'system', 'content': system_prompt})
+        messages.append(
+            {
+                'role': 'user',
+                'content': self._build_user_content(prompt, image_urls),
+            }
+        )
+        return messages
+
+    def _build_runtime_configurable(self, thread_id: str) -> dict[str, typing.Any]:
+        cfg: dict[str, typing.Any] = {
+            'thread_id': thread_id,
+            'thinking_enabled': self.thinking_enabled,
+            'is_plan_mode': self.plan_mode,
+            'subagent_enabled': self.subagent_enabled,
+        }
+        if self.subagent_enabled:
+            cfg['max_concurrent_subagents'] = self.max_concurrent_subagents
+        if self.model_name:
+            cfg['model_name'] = self.model_name
+        return cfg
+
+    def _build_payload(
+        self,
+        thread_id: str,
+        prompt: str,
+        image_urls: list[str],
+        system_prompt: str = '',
+    ) -> dict[str, typing.Any]:
+        runtime_configurable = self._build_runtime_configurable(thread_id)
+        return {
+            'assistant_id': self.assistant_id,
+            'input': {
+                'messages': self._build_messages(prompt, image_urls, system_prompt),
+            },
+            'stream_mode': ['values', 'messages-tuple', 'custom'],
+            # DeerFlow 2.0 从 config.configurable 读取运行时覆盖
+            # 同时保留 context 字段做向后兼容
+            'context': dict(runtime_configurable),
+            'config': {
+                'recursion_limit': self.recursion_limit,
+                'configurable': runtime_configurable,
+            },
+        }
+
+    # ------------------------------------------------------------------
+    # Session/Thread 管理
+    # ------------------------------------------------------------------
+
+    async def _ensure_thread_id(self, query: pipeline_query.Query) -> str:
+        """从 query.session 取/创建 deerflow thread_id
+
+        LangBot 使用 `query.session.using_conversation.uuid` 持久化 conversation id，
+        我们复用这个字段存储 deerflow thread_id（与 Dify Runner 同样做法）。
+        """
+        thread_id = query.session.using_conversation.uuid or ''
+        if thread_id:
+            return thread_id
+
+        thread = await self.deerflow_client.create_thread(timeout=min(30, self.timeout))
+        thread_id = thread.get('thread_id', '')
+        if not thread_id:
+            raise errors.DeerFlowAPIError(message=f'DeerFlow create thread 返回数据缺少 thread_id: {thread}')
+
+        query.session.using_conversation.uuid = thread_id
+        return thread_id
+
+    # ------------------------------------------------------------------
+    # 流式事件处理
+    # ------------------------------------------------------------------
+
+    def _handle_values_event(
+        self,
+        data: typing.Any,
+        state: _StreamState,
+    ) -> str | None:
+        """处理 values 事件，返回新的完整文本（增量基础上的全量）"""
+        values_messages = stream_utils.extract_messages_from_values_data(data)
+        if not values_messages:
+            return None
+
+        new_messages: list[dict[str, typing.Any]] = []
+        if not state.baseline_initialized:
+            state.baseline_initialized = True
+            for idx, msg in enumerate(values_messages):
+                if not isinstance(msg, dict):
+                    continue
+                new_messages.append(msg)
+                msg_id = stream_utils.get_message_id(msg)
+                if msg_id:
+                    self._remember_seen_message_id(state, msg_id)
+                    continue
+                state.no_id_message_fingerprints[idx] = self._fingerprint_message(msg)
+        else:
+            new_messages = self._extract_new_messages_from_values(values_messages, state)
+
+        latest_text = ''
+        if new_messages:
+            state.run_values_messages.extend(new_messages)
+            if len(state.run_values_messages) > _MAX_VALUES_HISTORY:
+                state.run_values_messages = state.run_values_messages[-_MAX_VALUES_HISTORY:]
+            latest_text = stream_utils.extract_latest_ai_text(state.run_values_messages)
+            if latest_text:
+                state.has_values_text = True
+            latest_clarification = stream_utils.extract_latest_clarification_text(
+                state.run_values_messages,
+            )
+            if latest_clarification:
+                state.clarification_text = latest_clarification
+
+        return latest_text or None
+
+    def _handle_message_event(
+        self,
+        data: typing.Any,
+        state: _StreamState,
+    ) -> str | None:
+        """处理 messages-tuple 事件，返回增量文本
+
+        当 values 事件已经提供完整文本时，跳过 messages-tuple 的增量
+        """
+        delta = stream_utils.extract_ai_delta_from_event_data(data)
+        if delta and not state.has_values_text:
+            state.latest_text += delta
+            return delta
+
+        maybe_clar = stream_utils.extract_clarification_from_event_data(data)
+        if maybe_clar:
+            state.clarification_text = maybe_clar
+        return None
+
+    def _build_final_text(self, state: _StreamState) -> str:
+        """构建最终输出文本"""
+        if state.clarification_text:
+            return state.clarification_text
+
+        # 优先使用最后一条 AI message 的文本
+        latest_ai = stream_utils.extract_latest_ai_message(state.run_values_messages)
+        if latest_ai:
+            text = stream_utils.extract_text(latest_ai.get('content'))
+            if text:
+                if state.timed_out:
+                    text += f'\n\nDeerFlow stream 在 {self.timeout}s 后超时，返回部分结果。'
+                return text
+
+        if state.latest_text:
+            text = state.latest_text
+            if state.timed_out:
+                text += f'\n\nDeerFlow stream 在 {self.timeout}s 后超时，返回部分结果。'
+            return text
+
+        # 提取任务失败信息作兜底
+        failure_text = stream_utils.build_task_failure_summary(state.task_failures)
+        if failure_text:
+            return failure_text
+
+        return 'DeerFlow 返回空响应'
+
+    # ------------------------------------------------------------------
+    # 主流程
+    # ------------------------------------------------------------------
+
+    async def _stream_messages_chunk(
+        self,
+        query: pipeline_query.Query,
+    ) -> typing.AsyncGenerator[provider_message.MessageChunk, None]:
+        """流式输出生成器"""
+        plain_text, image_urls = self._preprocess_user_message(query)
+
+        system_prompt = ''
+        # LangBot 的 pipeline 通常通过 prompt-preprocess 已注入 system prompt
+        # 这里保持空，让 prompt-preprocess 的内容作为 user message 一并送给 deerflow
+
+        thread_id = await self._ensure_thread_id(query)
+        payload = self._build_payload(
+            thread_id=thread_id,
+            prompt=plain_text or 'continue',
+            image_urls=image_urls,
+            system_prompt=system_prompt,
+        )
+
+        state = _StreamState()
+        prev_text = ''
+        message_idx = 0
+
+        try:
+            async for event in self.deerflow_client.stream_run(
+                thread_id=thread_id,
+                payload=payload,
+                timeout=self.timeout,
+            ):
+                event_type = event.get('event')
+                data = event.get('data')
+
+                if event_type == 'values':
+                    new_full = self._handle_values_event(data, state)
+                    if new_full and new_full != prev_text:
+                        delta = new_full[len(prev_text) :] if new_full.startswith(prev_text) else new_full
+                        prev_text = new_full
+                        if delta:
+                            message_idx += 1
+                            yield provider_message.MessageChunk(
+                                role='assistant',
+                                content=new_full,
+                                is_final=False,
+                            )
+                    continue
+
+                if event_type in {'messages-tuple', 'messages', 'message'}:
+                    delta = self._handle_message_event(data, state)
+                    if delta:
+                        prev_text = state.latest_text
+                        message_idx += 1
+                        yield provider_message.MessageChunk(
+                            role='assistant',
+                            content=prev_text,
+                            is_final=False,
+                        )
+                    continue
+
+                if event_type == 'custom':
+                    state.task_failures.extend(
+                        stream_utils.extract_task_failures_from_custom_event(data),
+                    )
+                    continue
+
+                if event_type == 'error':
+                    raise errors.DeerFlowAPIError(message=f'DeerFlow stream error event: {data}')
+
+                if event_type == 'end':
+                    break
+        except (asyncio.TimeoutError, TimeoutError):
+            self.ap.logger.warning(f'DeerFlow stream timed out after {self.timeout}s for thread_id={thread_id}')
+            state.timed_out = True
+
+        # 最终消息
+        final_text = self._build_final_text(state)
+        yield provider_message.MessageChunk(
+            role='assistant',
+            content=final_text,
+            is_final=True,
+        )
+
+    async def _messages(
+        self,
+        query: pipeline_query.Query,
+    ) -> typing.AsyncGenerator[provider_message.Message, None]:
+        """非流式聚合输出"""
+        plain_text, image_urls = self._preprocess_user_message(query)
+
+        thread_id = await self._ensure_thread_id(query)
+        payload = self._build_payload(
+            thread_id=thread_id,
+            prompt=plain_text or 'continue',
+            image_urls=image_urls,
+        )
+
+        state = _StreamState()
+
+        try:
+            async for event in self.deerflow_client.stream_run(
+                thread_id=thread_id,
+                payload=payload,
+                timeout=self.timeout,
+            ):
+                event_type = event.get('event')
+                data = event.get('data')
+
+                if event_type == 'values':
+                    self._handle_values_event(data, state)
+                    continue
+
+                if event_type in {'messages-tuple', 'messages', 'message'}:
+                    self._handle_message_event(data, state)
+                    continue
+
+                if event_type == 'custom':
+                    state.task_failures.extend(
+                        stream_utils.extract_task_failures_from_custom_event(data),
+                    )
+                    continue
+
+                if event_type == 'error':
+                    raise errors.DeerFlowAPIError(message=f'DeerFlow stream error event: {data}')
+
+                if event_type == 'end':
+                    break
+        except (asyncio.TimeoutError, TimeoutError):
+            self.ap.logger.warning(f'DeerFlow stream timed out after {self.timeout}s for thread_id={thread_id}')
+            state.timed_out = True
+
+        final_text = self._build_final_text(state)
+        yield provider_message.Message(
+            role='assistant',
+            content=final_text,
+        )
+
+    async def run(
+        self,
+        query: pipeline_query.Query,
+    ) -> typing.AsyncGenerator[provider_message.Message, None]:
+        """主入口：根据 adapter 是否支持流式输出，选择流式或非流式"""
+        if await query.adapter.is_stream_output_supported():
+            msg_idx = 0
+            async for msg in self._stream_messages_chunk(query):
+                msg_idx += 1
+                msg.msg_sequence = msg_idx
+                yield msg
+        else:
+            async for msg in self._messages(query):
+                yield msg

src/langbot/pkg/provider/runners/localagent.py

@@ -34,6 +34,13 @@ SANDBOX_EXEC_SYSTEM_GUIDANCE = (
 )
 
 
+# Hard cap on tool-call rounds within a single agent turn. A looping or
+# adversarial model can otherwise emit tool calls indefinitely (each potentially
+# a sandbox exec), yielding a non-terminating request and runaway cost. Set
+# generously so it never interrupts legitimate multi-step agentic workflows.
+MAX_TOOL_CALL_ROUNDS = 128
+
+
 @runner.runner_class('local-agent')
 class LocalAgentRunner(runner.RequestRunner):
     """Local agent request runner"""
@@ -363,7 +370,15 @@ class LocalAgentRunner(runner.RequestRunner):
 
         # Once a model succeeds, commit to it for the tool call loop
         # (no fallback mid-conversation — different models may interpret tool results differently)
+        tool_call_round = 0
         while pending_tool_calls:
+            tool_call_round += 1
+            if tool_call_round > MAX_TOOL_CALL_ROUNDS:
+                self.ap.logger.warning(
+                    f'Tool-call loop reached the {MAX_TOOL_CALL_ROUNDS}-round cap '
+                    f'(query_id={query.query_id}); stopping to avoid a non-terminating request.'
+                )
+                break
             for tool_call in pending_tool_calls:
                 try:
                     func = tool_call.function

src/langbot/pkg/provider/runners/weknoraapi.py

@@ -0,0 +1,351 @@
+from __future__ import annotations
+
+import typing
+import json
+
+
+from langbot.pkg.provider import runner
+from langbot.pkg.core import app
+import langbot_plugin.api.entities.builtin.provider.message as provider_message
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+from langbot.libs.weknora_api import client, errors
+
+
+@runner.runner_class('weknora-api')
+class WeKnoraAPIRunner(runner.RequestRunner):
+    """WeKnora API 对话请求器"""
+
+    weknora_client: client.AsyncWeKnoraClient
+
+    def __init__(self, ap: app.Application, pipeline_config: dict):
+        super().__init__(ap, pipeline_config)
+
+        valid_app_types = ['chat', 'agent']
+        if self.pipeline_config['ai']['weknora-api']['app-type'] not in valid_app_types:
+            raise errors.WeKnoraAPIError(
+                f'不支持的 WeKnora 应用类型: {self.pipeline_config["ai"]["weknora-api"]["app-type"]}'
+            )
+
+        api_key = self.pipeline_config['ai']['weknora-api'].get('api-key', '').strip()
+        if not api_key:
+            raise errors.WeKnoraAPIError(
+                'WeKnora API Key 未配置，请在流水线的 WeKnora API 配置中填入 API Key '
+                '(从 WeKnora 前端 设置 → API Keys 生成)'
+            )
+
+        base_url = self.pipeline_config['ai']['weknora-api'].get('base-url', '').strip()
+        if not base_url:
+            raise errors.WeKnoraAPIError('WeKnora Base URL 未配置，请填入服务器地址，例如 http://localhost:8080/api/v1')
+
+        self.weknora_client = client.AsyncWeKnoraClient(
+            api_key=api_key,
+            base_url=base_url,
+        )
+
+    async def _extract_plain_text(self, query: pipeline_query.Query) -> str:
+        """从用户消息中提取纯文本内容"""
+        plain_text = ''
+        if isinstance(query.user_message.content, str):
+            plain_text = query.user_message.content
+        elif isinstance(query.user_message.content, list):
+            for ce in query.user_message.content:
+                if ce.type == 'text':
+                    plain_text += ce.text
+
+        if not plain_text:
+            plain_text = self.pipeline_config['ai']['weknora-api'].get('base-prompt', '')
+
+        return plain_text
+
+    async def _ensure_session(self, query: pipeline_query.Query) -> str:
+        """确保会话存在，如果不存在则创建"""
+        session_id = query.session.using_conversation.uuid or ''
+
+        if not session_id:
+            user_tag = f'{query.session.launcher_type.value}_{query.session.launcher_id}'
+            session_id = await self.weknora_client.create_session(title=f'IM Chat - {user_tag}')
+            query.session.using_conversation.uuid = session_id
+
+        return session_id
+
+    async def _agent_chat_messages(
+        self, query: pipeline_query.Query
+    ) -> typing.AsyncGenerator[provider_message.Message, None]:
+        """调用 Agent 智能对话（非流式聚合输出）"""
+        session_id = await self._ensure_session(query)
+        plain_text = await self._extract_plain_text(query)
+        user_tag = f'{query.session.launcher_type.value}_{query.session.launcher_id}'
+
+        config = self.pipeline_config['ai']['weknora-api']
+        agent_id = config.get('agent-id', 'builtin-smart-reasoning')
+        knowledge_base_ids = config.get('knowledge-base-ids', [])
+        web_search_enabled = config.get('web-search-enabled', False)
+        timeout = config.get('timeout', 120)
+
+        full_answer = ''
+        chunk = None
+
+        async for chunk in self.weknora_client.agent_chat(
+            session_id=session_id,
+            query=plain_text,
+            user=user_tag,
+            agent_id=agent_id,
+            knowledge_base_ids=knowledge_base_ids,
+            web_search_enabled=web_search_enabled,
+            timeout=timeout,
+        ):
+            self.ap.logger.debug('weknora-agent-chunk: ' + str(chunk))
+
+            response_type = chunk.get('response_type', '')
+            content = chunk.get('content', '')
+
+            if response_type == 'tool_call':
+                # 工具调用
+                tool_data = chunk.get('data', {})
+                tool_name = tool_data.get('tool_name', '')
+                if tool_name:
+                    yield provider_message.Message(
+                        role='assistant',
+                        tool_calls=[
+                            provider_message.ToolCall(
+                                id=chunk.get('id', ''),
+                                type='function',
+                                function=provider_message.FunctionCall(
+                                    name=tool_name,
+                                    arguments=json.dumps(tool_data.get('arguments', {})),
+                                ),
+                            )
+                        ],
+                    )
+
+            elif response_type == 'answer':
+                if content:
+                    full_answer += content
+
+            elif response_type == 'error':
+                raise errors.WeKnoraAPIError(f'WeKnora 服务错误: {content}')
+
+        if chunk is None:
+            raise errors.WeKnoraAPIError('WeKnora API 没有返回任何响应，请检查网络连接和API配置')
+
+        if full_answer:
+            yield provider_message.Message(
+                role='assistant',
+                content=full_answer,
+            )
+
+    async def _chat_messages(
+        self, query: pipeline_query.Query
+    ) -> typing.AsyncGenerator[provider_message.Message, None]:
+        """调用知识库 RAG 问答（非流式聚合输出）"""
+        session_id = await self._ensure_session(query)
+        plain_text = await self._extract_plain_text(query)
+        user_tag = f'{query.session.launcher_type.value}_{query.session.launcher_id}'
+
+        config = self.pipeline_config['ai']['weknora-api']
+        agent_id = config.get('agent-id', 'builtin-quick-answer')
+        knowledge_base_ids = config.get('knowledge-base-ids', [])
+        timeout = config.get('timeout', 120)
+
+        full_answer = ''
+        chunk = None
+
+        async for chunk in self.weknora_client.knowledge_chat(
+            session_id=session_id,
+            query=plain_text,
+            user=user_tag,
+            agent_id=agent_id,
+            knowledge_base_ids=knowledge_base_ids,
+            timeout=timeout,
+        ):
+            self.ap.logger.debug('weknora-chat-chunk: ' + str(chunk))
+
+            response_type = chunk.get('response_type', '')
+            content = chunk.get('content', '')
+
+            if response_type == 'answer':
+                if content:
+                    full_answer += content
+
+            elif response_type == 'error':
+                raise errors.WeKnoraAPIError(f'WeKnora 服务错误: {content}')
+
+        if chunk is None:
+            raise errors.WeKnoraAPIError('WeKnora API 没有返回任何响应，请检查网络连接和API配置')
+
+        if full_answer:
+            yield provider_message.Message(
+                role='assistant',
+                content=full_answer,
+            )
+
+    async def _agent_chat_messages_chunk(
+        self, query: pipeline_query.Query
+    ) -> typing.AsyncGenerator[provider_message.MessageChunk, None]:
+        """调用 Agent 智能对话（流式输出）"""
+        session_id = await self._ensure_session(query)
+        plain_text = await self._extract_plain_text(query)
+        user_tag = f'{query.session.launcher_type.value}_{query.session.launcher_id}'
+
+        config = self.pipeline_config['ai']['weknora-api']
+        agent_id = config.get('agent-id', 'builtin-smart-reasoning')
+        knowledge_base_ids = config.get('knowledge-base-ids', [])
+        web_search_enabled = config.get('web-search-enabled', False)
+        timeout = config.get('timeout', 120)
+
+        pending_answer = ''
+        message_idx = 0
+        is_final = False
+        chunk = None
+
+        async for chunk in self.weknora_client.agent_chat(
+            session_id=session_id,
+            query=plain_text,
+            user=user_tag,
+            agent_id=agent_id,
+            knowledge_base_ids=knowledge_base_ids,
+            web_search_enabled=web_search_enabled,
+            timeout=timeout,
+        ):
+            self.ap.logger.debug('weknora-agent-chunk: ' + str(chunk))
+
+            response_type = chunk.get('response_type', '')
+            content = chunk.get('content', '')
+            done = chunk.get('done', False)
+
+            if response_type == 'tool_call':
+                tool_data = chunk.get('data', {})
+                tool_name = tool_data.get('tool_name', '')
+                if tool_name:
+                    message_idx += 1
+                    yield provider_message.MessageChunk(
+                        role='assistant',
+                        tool_calls=[
+                            provider_message.ToolCall(
+                                id=chunk.get('id', ''),
+                                type='function',
+                                function=provider_message.FunctionCall(
+                                    name=tool_name,
+                                    arguments=json.dumps(tool_data.get('arguments', {})),
+                                ),
+                            )
+                        ],
+                    )
+
+            elif response_type == 'answer':
+                message_idx += 1
+                if content:
+                    pending_answer += content
+
+                if done:
+                    is_final = True
+
+                # 每 8 个 chunk 输出一次，或最终输出
+                if message_idx % 8 == 0 or is_final:
+                    yield provider_message.MessageChunk(
+                        role='assistant',
+                        content=pending_answer,
+                        is_final=is_final,
+                    )
+
+            elif response_type == 'error':
+                raise errors.WeKnoraAPIError(f'WeKnora 服务错误: {content}')
+
+        if chunk is None:
+            raise errors.WeKnoraAPIError('WeKnora API 没有返回任何响应，请检查网络连接和API配置')
+
+        # 确保最终消息已发出
+        if not is_final and pending_answer:
+            yield provider_message.MessageChunk(
+                role='assistant',
+                content=pending_answer,
+                is_final=True,
+            )
+
+    async def _chat_messages_chunk(
+        self, query: pipeline_query.Query
+    ) -> typing.AsyncGenerator[provider_message.MessageChunk, None]:
+        """调用知识库 RAG 问答（流式输出）"""
+        session_id = await self._ensure_session(query)
+        plain_text = await self._extract_plain_text(query)
+        user_tag = f'{query.session.launcher_type.value}_{query.session.launcher_id}'
+
+        config = self.pipeline_config['ai']['weknora-api']
+        agent_id = config.get('agent-id', 'builtin-quick-answer')
+        knowledge_base_ids = config.get('knowledge-base-ids', [])
+        timeout = config.get('timeout', 120)
+
+        pending_answer = ''
+        message_idx = 0
+        is_final = False
+        chunk = None
+
+        async for chunk in self.weknora_client.knowledge_chat(
+            session_id=session_id,
+            query=plain_text,
+            user=user_tag,
+            agent_id=agent_id,
+            knowledge_base_ids=knowledge_base_ids,
+            timeout=timeout,
+        ):
+            self.ap.logger.debug('weknora-chat-chunk: ' + str(chunk))
+
+            response_type = chunk.get('response_type', '')
+            content = chunk.get('content', '')
+            done = chunk.get('done', False)
+
+            if response_type == 'answer':
+                message_idx += 1
+                if content:
+                    pending_answer += content
+
+                if done:
+                    is_final = True
+
+                if message_idx % 8 == 0 or is_final:
+                    yield provider_message.MessageChunk(
+                        role='assistant',
+                        content=pending_answer,
+                        is_final=is_final,
+                    )
+
+            elif response_type == 'error':
+                raise errors.WeKnoraAPIError(f'WeKnora 服务错误: {content}')
+
+        if chunk is None:
+            raise errors.WeKnoraAPIError('WeKnora API 没有返回任何响应，请检查网络连接和API配置')
+
+        if not is_final and pending_answer:
+            yield provider_message.MessageChunk(
+                role='assistant',
+                content=pending_answer,
+                is_final=True,
+            )
+
+    async def run(self, query: pipeline_query.Query) -> typing.AsyncGenerator[provider_message.Message, None]:
+        """运行请求"""
+        app_type = self.pipeline_config['ai']['weknora-api']['app-type']
+
+        if await query.adapter.is_stream_output_supported():
+            msg_idx = 0
+            if app_type == 'agent':
+                async for msg in self._agent_chat_messages_chunk(query):
+                    msg_idx += 1
+                    msg.msg_sequence = msg_idx
+                    yield msg
+            elif app_type == 'chat':
+                async for msg in self._chat_messages_chunk(query):
+                    msg_idx += 1
+                    msg.msg_sequence = msg_idx
+                    yield msg
+            else:
+                raise errors.WeKnoraAPIError(f'不支持的 WeKnora 应用类型: {app_type}')
+        else:
+            if app_type == 'agent':
+                async for msg in self._agent_chat_messages(query):
+                    yield msg
+            elif app_type == 'chat':
+                async for msg in self._chat_messages(query):
+                    yield msg
+            else:
+                raise errors.WeKnoraAPIError(f'不支持的 WeKnora 应用类型: {app_type}')

src/langbot/pkg/provider/tools/loaders/mcp.py

@@ -240,12 +240,13 @@ class RuntimeMCPSession:
                     return
                 if attempt >= self._MAX_RETRIES:
                     self.status = MCPSessionStatus.ERROR
-                    self.error_message = f'Failed after {self._MAX_RETRIES + 1} attempts: {e}'
+                    self.error_message = f'Failed after {self._MAX_RETRIES + 1} attempts: {self._describe_exception(e)}'
                     self._ready_event.set()
                     return
                 delay = self._RETRY_DELAYS[attempt]
                 self.ap.logger.warning(
-                    f'MCP session {self.server_name} failed (attempt {attempt + 1}), retrying in {delay}s: {e}'
+                    f'MCP session {self.server_name} failed (attempt {attempt + 1}), '
+                    f'retrying in {delay}s: {self._describe_exception(e)}'
                 )
                 await self._cleanup_box_stdio_session()
                 # Reset status for retry
@@ -254,6 +255,30 @@ class RuntimeMCPSession:
                 self.error_phase = None
                 await asyncio.sleep(delay)
 
+    @staticmethod
+    def _describe_exception(exc: BaseException) -> str:
+        """Flatten an exception into its underlying leaf messages.
+
+        anyio / the MCP client wrap real failures in a TaskGroup, whose own
+        message is the unhelpful "unhandled errors in a TaskGroup (N
+        sub-exception)". Recurse into ExceptionGroups so the actual cause
+        (e.g. ``httpx.HTTPStatusError: Client error '410 Gone'``) is surfaced.
+        """
+        leaves: list[str] = []
+
+        def visit(e: BaseException) -> None:
+            sub = getattr(e, 'exceptions', None)
+            if sub:  # ExceptionGroup / BaseExceptionGroup
+                for child in sub:
+                    visit(child)
+            else:
+                leaves.append(f'{type(e).__name__}: {e}')
+
+        visit(exc)
+        seen: set[str] = set()
+        unique = [m for m in leaves if not (m in seen or seen.add(m))]
+        return '; '.join(unique) if unique else f'{type(exc).__name__}: {exc}'
+
     _MONITOR_POLL_INTERVAL = 5
     _MONITOR_MAX_CONSECUTIVE_ERRORS = 3
 

src/langbot/templates/config.yaml

@@ -112,7 +112,7 @@ box:
     # skill tool, skill add/edit, and stdio-mode MCP servers. Skills can still
     # be listed read-only and http/sse MCP servers continue to work.
     enabled: true
-    backend: 'local'  # 'local' (Docker/nsjail), 'docker', 'nsjail', or 'e2b'. BOX_BACKEND env var takes precedence.
+    backend: 'local'  # 'local' (Docker/nsjail), 'docker', 'nsjail', or 'e2b'. Can be written via BOX__BACKEND.
     runtime:
         endpoint: ''  # External Box Runtime base URL, e.g. 'ws://127.0.0.1:5410'. Leave empty for local auto-managed runtime.
     local:

src/langbot/templates/metadata/pipeline/ai.yaml

@@ -47,6 +47,14 @@ stages:
             label:
               en_US: Langflow API
               zh_Hans: Langflow API
+          - name: weknora-api
+            label:
+              en_US: WeKnora API
+              zh_Hans: WeKnora API
+          - name: deerflow-api
+            label:
+              en_US: DeerFlow API
+              zh_Hans: DeerFlow API
       - name: expire-time
         label:
           en_US: Conversation expire time (seconds)
@@ -653,3 +661,215 @@ stages:
         type: json
         required: false
         default: '{}'
+  - name: weknora-api
+    label:
+      en_US: WeKnora API
+      zh_Hans: WeKnora API
+    description:
+      en_US: Configure the WeKnora API of the pipeline
+      zh_Hans: 配置 WeKnora API
+    config:
+      - name: base-url
+        label:
+          en_US: Base URL
+          zh_Hans: 基础 URL
+        description:
+          en_US: The base URL of the WeKnora server (with /api/v1)
+          zh_Hans: WeKnora 服务器的基础 URL（包含 /api/v1）
+        type: string
+        required: true
+        default: 'http://localhost:8080/api/v1'
+      - name: api-key
+        label:
+          en_US: API Key
+          zh_Hans: API 密钥
+        description:
+          en_US: The API key for WeKnora, generated from WeKnora frontend Settings → API Keys
+          zh_Hans: WeKnora 的 API 密钥，从 WeKnora 前端 设置 → API Keys 生成
+        type: string
+        required: true
+        default: ''
+      - name: app-type
+        label:
+          en_US: App Type
+          zh_Hans: 应用类型
+        type: select
+        required: true
+        default: agent
+        options:
+          - name: agent
+            label:
+              en_US: Agent (Smart Reasoning)
+              zh_Hans: Agent（智能推理）
+          - name: chat
+            label:
+              en_US: Chat (Knowledge Base RAG)
+              zh_Hans: 聊天（知识库 RAG）
+      - name: agent-id
+        label:
+          en_US: Agent ID
+          zh_Hans: 智能体 ID
+        description:
+          en_US: The Agent ID to use. Built-in agents include builtin-quick-answer, builtin-smart-reasoning, builtin-data-analyst
+          zh_Hans: 要使用的智能体 ID。内置智能体：builtin-quick-answer、builtin-smart-reasoning、builtin-data-analyst
+        type: string
+        required: true
+        default: 'builtin-smart-reasoning'
+      - name: knowledge-base-ids
+        label:
+          en_US: Knowledge Base IDs
+          zh_Hans: 知识库 ID 列表
+        description:
+          en_US: List of WeKnora knowledge base IDs to use (one per line)
+          zh_Hans: 要使用的 WeKnora 知识库 ID 列表（每行一个）
+        type: array
+        required: false
+        default: []
+      - name: web-search-enabled
+        label:
+          en_US: Enable Web Search
+          zh_Hans: 启用网络搜索
+        description:
+          en_US: Whether to enable web search in agent mode
+          zh_Hans: 在 Agent 模式下是否启用网络搜索
+        type: boolean
+        required: false
+        default: false
+      - name: timeout
+        label:
+          en_US: Timeout
+          zh_Hans: 超时时间
+        description:
+          en_US: Request timeout in seconds
+          zh_Hans: 请求超时时间（秒）
+        type: integer
+        required: false
+        default: 120
+      - name: base-prompt
+        label:
+          en_US: Base Prompt
+          zh_Hans: 基础提示词
+        description:
+          en_US: Default prompt when user message is empty (e.g. only images)
+          zh_Hans: 当用户消息为空（例如仅图片）时使用的默认提示词
+        type: string
+        required: false
+        default: '请回答用户的问题。'
+  - name: deerflow-api
+    label:
+      en_US: DeerFlow API
+      zh_Hans: DeerFlow API
+    description:
+      en_US: Configure the DeerFlow LangGraph API of the pipeline
+      zh_Hans: 配置 DeerFlow LangGraph API
+    config:
+      - name: api-base
+        label:
+          en_US: API Base URL
+          zh_Hans: API 基础 URL
+        description:
+          en_US: The base URL of the DeerFlow server (e.g. http://127.0.0.1:2026)
+          zh_Hans: DeerFlow 服务器的基础 URL（例如 http://127.0.0.1:2026）
+        type: string
+        required: true
+        default: 'http://127.0.0.1:2026'
+      - name: api-key
+        label:
+          en_US: API Key
+          zh_Hans: API 密钥
+        description:
+          en_US: Optional API key for DeerFlow (leave empty if not required)
+          zh_Hans: DeerFlow 的 API 密钥（如果不需要可留空）
+        type: string
+        required: false
+        default: ''
+      - name: auth-header
+        label:
+          en_US: Auth Header Name
+          zh_Hans: 鉴权请求头名称
+        description:
+          en_US: Custom auth header name. Leave empty to use "x-api-key"
+          zh_Hans: 自定义鉴权请求头名称，留空则使用 "x-api-key"
+        type: string
+        required: false
+        default: ''
+      - name: assistant-id
+        label:
+          en_US: Assistant ID
+          zh_Hans: 助手 ID
+        description:
+          en_US: The DeerFlow assistant/graph id (default lead_agent)
+          zh_Hans: DeerFlow 助手/图 ID（默认 lead_agent）
+        type: string
+        required: true
+        default: 'lead_agent'
+      - name: model-name
+        label:
+          en_US: Model Name
+          zh_Hans: 模型名称
+        description:
+          en_US: Optional model override forwarded to DeerFlow configurable
+          zh_Hans: 可选的模型名称覆盖，会作为 configurable 转发给 DeerFlow
+        type: string
+        required: false
+        default: ''
+      - name: thinking-enabled
+        label:
+          en_US: Enable Thinking
+          zh_Hans: 启用思考
+        description:
+          en_US: Whether to enable DeerFlow thinking mode
+          zh_Hans: 是否启用 DeerFlow 思考模式
+        type: boolean
+        required: false
+        default: false
+      - name: plan-mode
+        label:
+          en_US: Plan Mode
+          zh_Hans: 规划模式
+        description:
+          en_US: Whether to enable DeerFlow plan mode
+          zh_Hans: 是否启用 DeerFlow 规划模式
+        type: boolean
+        required: false
+        default: false
+      - name: subagent-enabled
+        label:
+          en_US: Enable Subagents
+          zh_Hans: 启用子代理
+        description:
+          en_US: Whether to enable parallel subagent execution
+          zh_Hans: 是否启用并行子代理执行
+        type: boolean
+        required: false
+        default: false
+      - name: max-concurrent-subagents
+        label:
+          en_US: Max Concurrent Subagents
+          zh_Hans: 最大并发子代理数
+        description:
+          en_US: Maximum number of concurrent subagents (only effective when subagents are enabled)
+          zh_Hans: 最大并发子代理数（仅在启用子代理时生效）
+        type: integer
+        required: false
+        default: 3
+      - name: timeout
+        label:
+          en_US: Timeout
+          zh_Hans: 超时时间
+        description:
+          en_US: Request timeout in seconds (DeerFlow runs may take a long time)
+          zh_Hans: 请求超时时间（秒），DeerFlow 运行可能耗时较长
+        type: integer
+        required: false
+        default: 300
+      - name: recursion-limit
+        label:
+          en_US: Recursion Limit
+          zh_Hans: 递归上限
+        description:
+          en_US: LangGraph recursion limit for a single run
+          zh_Hans: 单次运行的 LangGraph 递归上限
+        type: integer
+        required: false
+        default: 1000

uv.lock

@@ -1899,7 +1899,7 @@ wheels = [
 
 [[package]]
 name = "langbot"
-version = "4.10.0b1"
+version = "4.10.0"
 source = { editable = "." }
 dependencies = [
     { name = "aiocqhttp" },
@@ -2013,7 +2013,7 @@ requires-dist = [
     { name = "ebooklib", specifier = ">=0.18" },
     { name = "gewechat-client", specifier = ">=0.1.5" },
     { name = "html2text", specifier = ">=2024.2.26" },
-    { name = "langbot-plugin", specifier = "==0.4.0b1" },
+    { name = "langbot-plugin", specifier = "==0.4.1" },
     { name = "langchain", specifier = ">=0.2.0" },
     { name = "langchain-core", specifier = ">=1.2.28" },
     { name = "langchain-text-splitters", specifier = ">=1.1.2" },
@@ -2076,7 +2076,7 @@ dev = [
 
 [[package]]
 name = "langbot-plugin"
-version = "0.4.0b1"
+version = "0.4.1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiofiles" },
@@ -2096,9 +2096,9 @@ dependencies = [
     { name = "watchdog" },
     { name = "websockets" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/8a/e0/4bb2fd08813879d3da390f588b2927ae626edcfd45dca36900e2e54fb23c/langbot_plugin-0.4.0b1.tar.gz", hash = "sha256:f523c197ff9f5aa3db737e29765ebe1f7a8c96f973240ce3769ccccd0bfddde7", size = 216965, upload-time = "2026-05-21T05:23:27.682Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/b2/c1/b11ce66fb2537b257ff387b8b5b708e616e5a072ae04440e24807eb3b1cf/langbot_plugin-0.4.1.tar.gz", hash = "sha256:57d3f8cd6b6c33316792ebfa0c907b2240834a84f2b8c8034c6be7721b425059", size = 289249, upload-time = "2026-06-04T05:19:08.747Z" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/a0/59/9c6df7cd652d3434d1139ee8392e170108e5f980046b9a55bff324e094fe/langbot_plugin-0.4.0b1-py3-none-any.whl", hash = "sha256:b533407296399c7693255678a4d1390be957dabffa21ca2982e56d28a728854b", size = 194310, upload-time = "2026-05-21T05:23:26.215Z" },
+    { url = "https://files.pythonhosted.org/packages/72/e8/335023bb5e1310621c7b7d8ae4fcac179f119709eee9a8ba65b681f66a8e/langbot_plugin-0.4.1-py3-none-any.whl", hash = "sha256:a9c319a4abb6944ae3d9a491edbeb703842a87b42b4e3b1eafba666ec2beeee7", size = 203412, upload-time = "2026-06-04T05:19:09.936Z" },
 ]
 
 [[package]]

web/src/app/home/add-extension/page.tsx

@@ -23,6 +23,7 @@ import {
   FileArchive,
   Loader2,
   CircleHelp,
+  Package,
 } from 'lucide-react';
 import { Input } from '@/components/ui/input';
 import {
@@ -33,6 +34,8 @@ import {
 import React, { useState, useCallback, useEffect, useRef } from 'react';
 import { useNavigate, useSearchParams } from 'react-router-dom';
 import { httpClient, systemInfo } from '@/app/infra/http/HttpClient';
+import { getCloudServiceClientSync } from '@/app/infra/http';
+import { extractI18nObject } from '@/i18n/I18nProvider';
 import { toast } from 'sonner';
 import { useTranslation } from 'react-i18next';
 import { PluginV4 } from '@/app/infra/entities/plugin';
@@ -151,6 +154,14 @@ function AddExtensionContent() {
   const navigate = useNavigate();
   const [searchParams, setSearchParams] = useSearchParams();
   const { refreshPlugins, refreshMCPServers, refreshSkills } = useSidebarData();
+
+  // Localized label for an extension type, used in the install dialog.
+  const extensionTypeLabel = (type: string) =>
+    type === 'mcp'
+      ? t('market.typeMCP')
+      : type === 'skill'
+        ? t('market.typeSkill')
+        : t('market.typePlugin');
   const {
     addTask,
     setSelectedTaskId,
@@ -166,6 +177,20 @@ function AddExtensionContent() {
   const [pluginInstallStatus, setPluginInstallStatus] =
     useState<PluginInstallStatus>(PluginInstallStatus.ASK_CONFIRM);
   const [installError, setInstallError] = useState<string | null>(null);
+  const [installIconFailed, setInstallIconFailed] = useState(false);
+
+  // Marketplace icon URL for the extension being installed, by type.
+  const installIconURL = (() => {
+    const cloud = getCloudServiceClientSync();
+    const a = installInfo.plugin_author || '';
+    const n = installInfo.plugin_name || '';
+    if (installExtensionType === 'mcp')
+      return cloud.getMCPMarketplaceIconURL(a, n);
+    if (installExtensionType === 'skill')
+      return cloud.getSkillMarketplaceIconURL(a, n);
+    return cloud.getPluginIconURL(a, n);
+  })();
+
   const [popoverOpen, setPopoverOpen] = useState(false);
   const [popoverView, setPopoverView] = useState<PopoverView>('menu');
   const [isDragOver, setIsDragOver] = useState(false);
@@ -224,28 +249,88 @@ function AddExtensionContent() {
     );
   }, [searchParams, setSearchParams]);
 
+  // One-click install deep link from LangBot Space:
+  // /home/add-extension?install=1&extension_type=mcp&author=X&name=Y&version=Z
+  // Opens the install confirm dialog directly, then strips the params.
+  useEffect(() => {
+    if (searchParams.get('install') !== '1') return;
+    const author = searchParams.get('author');
+    const name = searchParams.get('name');
+    if (!author || !name) return;
+    const rawType =
+      searchParams.get('extension_type') ||
+      searchParams.get('type') ||
+      'plugin';
+    const extType = (
+      ['plugin', 'mcp', 'skill'].includes(rawType) ? rawType : 'plugin'
+    ) as 'plugin' | 'mcp' | 'skill';
+    const version = searchParams.get('version') || '';
+
+    setInstallInfo({
+      plugin_author: author,
+      plugin_name: name,
+      plugin_version: version,
+      plugin_label: name,
+    });
+    setInstallExtensionType(extType);
+    setPluginInstallStatus(PluginInstallStatus.ASK_CONFIRM);
+    setInstallError(null);
+    setInstallIconFailed(false);
+    setModalOpen(true);
+
+    setSearchParams(
+      (current) => {
+        const next = new URLSearchParams(current);
+        [
+          'install',
+          'extension_type',
+          'type',
+          'author',
+          'name',
+          'version',
+        ].forEach((k) => next.delete(k));
+        return next;
+      },
+      { replace: true },
+    );
+  }, [searchParams, setSearchParams]);
+
   useEffect(() => {
     const onComplete = (_taskId: number, success: boolean) => {
       if (success) {
-        toast.success(t('plugins.installSuccess'));
+        toast.success(t('addExtension.installSuccess'));
+        // Refresh every sidebar extension list so the newly-installed
+        // plugin / MCP / skill shows up immediately, regardless of type.
         refreshPlugins();
+        refreshMCPServers();
+        refreshSkills();
       }
     };
     registerOnTaskComplete(onComplete);
     return () => {
       unregisterOnTaskComplete(onComplete);
     };
-  }, [registerOnTaskComplete, unregisterOnTaskComplete, refreshPlugins, t]);
+  }, [
+    registerOnTaskComplete,
+    unregisterOnTaskComplete,
+    refreshPlugins,
+    refreshMCPServers,
+    refreshSkills,
+    t,
+  ]);
 
   const handleInstallPlugin = useCallback(async (plugin: PluginV4) => {
     setInstallInfo({
       plugin_author: plugin.author,
       plugin_name: plugin.name,
       plugin_version: plugin.latest_version,
+      plugin_label: extractI18nObject(plugin.label) || plugin.name,
+      plugin_description: extractI18nObject(plugin.description) || '',
     });
     setInstallExtensionType(plugin.type || 'plugin');
     setPluginInstallStatus(PluginInstallStatus.ASK_CONFIRM);
     setInstallError(null);
+    setInstallIconFailed(false);
     setModalOpen(true);
   }, []);
 
@@ -1145,22 +1230,52 @@ function AddExtensionContent() {
           <DialogHeader>
             <DialogTitle className="flex items-center gap-4">
               <Download className="size-6" />
-              <span>{t('plugins.installPlugin')}</span>
+              <span>
+                {t('addExtension.installTitle', {
+                  type: extensionTypeLabel(installExtensionType),
+                })}
+              </span>
             </DialogTitle>
           </DialogHeader>
 
           {pluginInstallStatus === PluginInstallStatus.ASK_CONFIRM && (
-            <div className="mt-4">
-              <p className="mb-2">
-                {installInfo.plugin_version
-                  ? t('plugins.askConfirm', {
-                      name: installInfo.plugin_name,
-                      version: installInfo.plugin_version,
-                    })
-                  : t('plugins.askConfirmNoVersion', {
-                      name: installInfo.plugin_name,
-                    })}
+            <div className="mt-4 space-y-3">
+              <p>
+                {t('addExtension.installConfirm', {
+                  type: extensionTypeLabel(installExtensionType),
+                  name: installInfo.plugin_label || installInfo.plugin_name,
+                })}
               </p>
+              <div className="flex gap-3 rounded-md bg-muted/40 p-3">
+                {installIconFailed ? (
+                  <div className="flex size-12 shrink-0 items-center justify-center rounded-lg border bg-background text-muted-foreground">
+                    <Package className="size-6" />
+                  </div>
+                ) : (
+                  <img
+                    src={installIconURL}
+                    alt={installInfo.plugin_name}
+                    className="size-12 shrink-0 rounded-lg border bg-background object-cover"
+                    onError={() => setInstallIconFailed(true)}
+                  />
+                )}
+                <div className="min-w-0 flex-1 space-y-0.5">
+                  <div className="truncate font-medium">
+                    {installInfo.plugin_label || installInfo.plugin_name}
+                  </div>
+                  <div className="truncate text-xs text-muted-foreground">
+                    {installInfo.plugin_author}/{installInfo.plugin_name}
+                    {installInfo.plugin_version
+                      ? ` · v${installInfo.plugin_version}`
+                      : ''}
+                  </div>
+                  {installInfo.plugin_description && (
+                    <div className="line-clamp-3 pt-0.5 text-xs text-muted-foreground">
+                      {installInfo.plugin_description}
+                    </div>
+                  )}
+                </div>
+              </div>
             </div>
           )}
 

web/src/app/home/components/home-sidebar/HomeSidebar.tsx

@@ -31,6 +31,7 @@ import {
   HardDrive,
   Server,
   Puzzle,
+  RefreshCcw,
 } from 'lucide-react';
 import { useTheme } from '@/components/providers/theme-provider';
 
@@ -118,6 +119,22 @@ function compareVersions(v1: string, v2: string): boolean {
   return false;
 }
 
+// Discord brand glyph (lucide-react has no Discord icon).
+function DiscordIcon({ className }: { className?: string }) {
+  return (
+    <svg
+      role="img"
+      viewBox="0 0 24 24"
+      fill="currentColor"
+      xmlns="http://www.w3.org/2000/svg"
+      className={className}
+      aria-hidden="true"
+    >
+      <path d="M20.317 4.3698a19.7913 19.7913 0 00-4.8851-1.5152.0741.0741 0 00-.0785.0371c-.211.3753-.4447.8648-.6083 1.2495-1.8447-.2762-3.68-.2762-5.4868 0-.1636-.3933-.4058-.8742-.6177-1.2495a.077.077 0 00-.0785-.037 19.7363 19.7363 0 00-4.8852 1.515.0699.0699 0 00-.0321.0277C.5334 9.0458-.319 13.5799.0992 18.0578a.0824.0824 0 00.0312.0561c2.0528 1.5076 4.0413 2.4228 5.9929 3.0294a.0777.0777 0 00.0842-.0276c.4616-.6304.8731-1.2952 1.226-1.9942a.076.076 0 00-.0416-.1057c-.6528-.2476-1.2743-.5495-1.8722-.8923a.077.077 0 01-.0076-.1277c.1258-.0943.2517-.1923.3718-.2914a.0743.0743 0 01.0776-.0105c3.9278 1.7933 8.18 1.7933 12.0614 0a.0739.0739 0 01.0785.0095c.1202.099.246.1981.3728.2924a.077.077 0 01-.0066.1276 12.2986 12.2986 0 01-1.873.8914.0766.0766 0 00-.0407.1067c.3604.698.7719 1.3628 1.225 1.9932a.076.076 0 00.0842.0286c1.961-.6067 3.9495-1.5219 6.0023-3.0294a.077.077 0 00.0313-.0552c.5004-5.177-.8382-9.6739-3.5485-13.6604a.061.061 0 00-.0312-.0286zM8.02 15.3312c-1.1825 0-2.1569-1.0857-2.1569-2.419 0-1.3332.9555-2.4189 2.157-2.4189 1.2108 0 2.1757 1.0952 2.1568 2.419 0 1.3332-.9555 2.4189-2.1569 2.4189zm7.9748 0c-1.1825 0-2.1569-1.0857-2.1569-2.419 0-1.3332.9554-2.4189 2.1569-2.4189 1.2108 0 2.1757 1.0952 2.1568 2.419 0 1.3332-.946 2.4189-2.1568 2.4189Z" />
+    </svg>
+  );
+}
+
 // IDs of sidebar entries that have collapsible entity sub-items
 const ENTITY_CATEGORY_IDS = [
   'bots',
@@ -325,6 +342,23 @@ function NavItems({
   );
   // Track popover open state for collapsed sidebar entity categories
   const [popoverOpen, setPopoverOpen] = useState<Record<string, boolean>>({});
+  // Spin state for the installed-extensions refresh button
+  const [extRefreshing, setExtRefreshing] = useState(false);
+
+  const handleRefreshExtensions = async (e: React.MouseEvent) => {
+    e.stopPropagation();
+    if (extRefreshing) return;
+    setExtRefreshing(true);
+    try {
+      await Promise.all([
+        sidebarData.refreshPlugins(),
+        sidebarData.refreshMCPServers(),
+        sidebarData.refreshSkills(),
+      ]);
+    } finally {
+      setExtRefreshing(false);
+    }
+  };
 
   // Plugin operation state
   const [showPluginOpModal, setShowPluginOpModal] = useState(false);
@@ -694,17 +728,21 @@ function NavItems({
                       </a>
                     </SidebarMenuSubButton>
                   </TooltipTrigger>
-                  {item.description && (
-                    <TooltipContent
-                      side="right"
-                      align="center"
-                      className="max-w-64"
-                    >
-                      {item.description.length > 80
-                        ? item.description.slice(0, 80) + '…'
-                        : item.description}
-                    </TooltipContent>
-                  )}
+                  <TooltipContent
+                    side="right"
+                    align="center"
+                    className="max-w-64"
+                  >
+                    {/* Full name — so truncated sidebar items are readable on hover */}
+                    <div className="break-words font-medium">{item.name}</div>
+                    {item.description && (
+                      <div className="mt-0.5 break-words text-xs text-muted-foreground">
+                        {item.description.length > 80
+                          ? item.description.slice(0, 80) + '…'
+                          : item.description}
+                      </div>
+                    )}
+                  </TooltipContent>
                 </Tooltip>
                 {/* Plugin context menu - shown on hover (not for debug plugins) */}
                 {itemIsPluginType && !item.debug && (
@@ -973,6 +1011,21 @@ function NavItems({
                     {config.name}
                   </span>
                   <div className="ml-auto flex items-center gap-0.5 -mr-1">
+                    {isExtensionsCategory && (
+                      <button
+                        type="button"
+                        title={t('common.refresh', '刷新')}
+                        className="p-1 rounded-sm text-sidebar-foreground/70 hover:bg-sidebar-accent hover:text-sidebar-accent-foreground [@media(hover:hover)]:opacity-0 group-hover/category-header:opacity-100 transition-all"
+                        onClick={handleRefreshExtensions}
+                      >
+                        <RefreshCcw
+                          className={cn(
+                            'size-3.5',
+                            extRefreshing && 'animate-spin',
+                          )}
+                        />
+                      </button>
+                    )}
                     {canCreate &&
                       (isPlugin ? (
                         <DropdownMenu>
@@ -1764,7 +1817,21 @@ export default function HomeSidebar({
                   className="size-8 rounded-lg"
                 />
                 <div className="grid flex-1 text-left text-sm leading-tight">
-                  <span className="truncate font-semibold">LangBot</span>
+                  <div className="flex items-center gap-1.5">
+                    <span className="truncate font-semibold">LangBot</span>
+                    <Badge
+                      variant="secondary"
+                      className={`shrink-0 px-1 py-0 h-3.5 text-[0.55rem] font-medium ${
+                        systemInfo?.edition === 'cloud'
+                          ? 'border-transparent bg-blue-500 text-white'
+                          : ''
+                      }`}
+                    >
+                      {systemInfo?.edition === 'cloud'
+                        ? t('sidebar.editionCloud')
+                        : t('sidebar.editionCommunity')}
+                    </Badge>
+                  </div>
                   <div className="flex items-center gap-1.5">
                     <span className="truncate text-xs text-muted-foreground">
                       {systemInfo?.version}
@@ -2026,6 +2093,14 @@ export default function HomeSidebar({
                         </Badge>
                       )}
                     </DropdownMenuItem>
+                    <DropdownMenuItem
+                      onClick={() => {
+                        window.open('https://discord.gg/wdNEHETs87', '_blank');
+                      }}
+                    >
+                      <DiscordIcon className="text-[#5865F2]" />
+                      {t('common.joinDiscord')}
+                    </DropdownMenuItem>
                   </DropdownMenuGroup>
                   <DropdownMenuSeparator />
 

web/src/app/home/components/models-dialog/components/AddModelPopover.tsx

@@ -18,7 +18,7 @@ import {
   PopoverContent,
   PopoverTrigger,
 } from '@/components/ui/popover';
-import { Tabs, TabsContent, TabsList, TabsTrigger } from '@/components/ui/tabs';
+import { Tabs, TabsList, TabsTrigger } from '@/components/ui/tabs';
 import { useTranslation } from 'react-i18next';
 import { ScannedProviderModel } from '@/app/infra/entities/api';
 import {
@@ -298,20 +298,8 @@ export default function AddModelPopover({
           </div>
 
           <div className="overflow-y-auto flex-1 min-h-0">
-            <Tabs
-              value={mode}
-              onValueChange={(v) => setMode(v as 'manual' | 'scan')}
-            >
-              {!trigger && (
-                <TabsList className="grid w-full grid-cols-2 mt-3">
-                  <TabsTrigger value="manual">
-                    {t('models.manualAdd')}
-                  </TabsTrigger>
-                  <TabsTrigger value="scan">{t('models.scanAdd')}</TabsTrigger>
-                </TabsList>
-              )}
-
-              <TabsContent value="manual" className="mt-3">
+            {mode === 'manual' ? (
+              <div className="mt-3">
                 <div className="space-y-3">
                   <div className="space-y-2">
                     <Label>{t('models.modelName')}</Label>
@@ -390,9 +378,9 @@ export default function AddModelPopover({
                     </Button>
                   </div>
                 </div>
-              </TabsContent>
-
-              <TabsContent value="scan" className="space-y-2 mt-0 pt-0">
+              </div>
+            ) : (
+              <div className="space-y-2 mt-3">
                 {scanLoading ? (
                   <div className="flex items-center justify-center py-4">
                     <RefreshCw className="h-4 w-4 mr-2 animate-spin text-muted-foreground" />
@@ -565,8 +553,8 @@ export default function AddModelPopover({
                     />
                   </Button>
                 </div>
-              </TabsContent>
-            </Tabs>
+              </div>
+            )}
           </div>
         </Tabs>
       </PopoverContent>

web/src/app/home/components/qrcode-login/QrCodeLoginDialog.tsx

@@ -4,11 +4,16 @@ import {
   DialogContent,
   DialogHeader,
   DialogTitle,
-  DialogFooter,
 } from '@/components/ui/dialog';
 import { Button } from '@/components/ui/button';
 import { useTranslation } from 'react-i18next';
-import { Loader2, RefreshCw, CheckCircle2, XCircle } from 'lucide-react';
+import {
+  Loader2,
+  RefreshCw,
+  RotateCw,
+  CheckCircle2,
+  XCircle,
+} from 'lucide-react';
 import QRCode from 'qrcode';
 
 export type QrLoginPlatform = 'feishu' | 'weixin' | 'dingtalk' | 'wecombot';
@@ -96,7 +101,7 @@ interface QrCodeLoginDialogProps {
   onSuccess: (credentials: Record<string, string>) => void;
 }
 
-type DialogState = 'connecting' | 'waiting' | 'success' | 'error';
+type DialogState = 'connecting' | 'waiting' | 'expired' | 'success' | 'error';
 
 const POLL_INTERVAL_MS = 3000;
 
@@ -115,8 +120,10 @@ export default function QrCodeLoginDialog({
   const [errorMessage, setErrorMessage] = useState('');
   const pollTimerRef = useRef<ReturnType<typeof setInterval> | null>(null);
   const countdownRef = useRef<ReturnType<typeof setInterval> | null>(null);
+  const checkExpiredRef = useRef<ReturnType<typeof setInterval> | null>(null);
   const abortRef = useRef<AbortController | null>(null);
   const sessionIdRef = useRef<string | null>(null);
+  const baseUrlRef = useRef('');
   const cleanedRef = useRef(false);
 
   const onSuccessRef = useRef(onSuccess);
@@ -140,11 +147,14 @@ export default function QrCodeLoginDialog({
       clearInterval(countdownRef.current);
       countdownRef.current = null;
     }
+    if (checkExpiredRef.current) {
+      clearInterval(checkExpiredRef.current);
+      checkExpiredRef.current = null;
+    }
     if (abortRef.current) {
       abortRef.current.abort();
       abortRef.current = null;
     }
-    // Cancel backend session
     if (sessionIdRef.current) {
       const token = localStorage.getItem('token');
       const baseUrl =
@@ -171,6 +181,7 @@ export default function QrCodeLoginDialog({
 
     const token = localStorage.getItem('token');
     const baseUrl = import.meta.env.VITE_API_BASE_URL || window.location.origin;
+    baseUrlRef.current = baseUrl;
     const cfg = platformConfigRef.current;
 
     try {
@@ -191,8 +202,6 @@ export default function QrCodeLoginDialog({
       const { session_id, qr_data_url, qr_url, expire_at } = json.data;
       sessionIdRef.current = session_id;
 
-      // qr_data_url is a pre-rendered data URL (WeChat);
-      // qr_url is a plain URL string (Feishu) that needs local QR generation.
       if (qr_data_url) {
         setQrDataUrl(qr_data_url);
       } else if (qr_url) {
@@ -204,11 +213,9 @@ export default function QrCodeLoginDialog({
       }
       setState('waiting');
 
-      // Calculate remaining seconds
       const remaining = Math.max(0, Math.floor(expire_at - Date.now() / 1000));
       setExpireIn(remaining);
 
-      // Start countdown
       countdownRef.current = setInterval(() => {
         setExpireIn((prev) => {
           if (prev <= 1) {
@@ -222,7 +229,35 @@ export default function QrCodeLoginDialog({
         });
       }, 1000);
 
-      // Start polling
+      // When countdown hits 0, stop polling and show expired state
+      checkExpiredRef.current = setInterval(() => {
+        setExpireIn((current) => {
+          if (current <= 0) {
+            if (checkExpiredRef.current) {
+              clearInterval(checkExpiredRef.current);
+              checkExpiredRef.current = null;
+            }
+            if (pollTimerRef.current) {
+              clearInterval(pollTimerRef.current);
+              pollTimerRef.current = null;
+            }
+            if (sessionIdRef.current) {
+              fetch(
+                `${baseUrlRef.current}${cfg.apiBase}/${sessionIdRef.current}`,
+                {
+                  method: 'DELETE',
+                  headers: { Authorization: `Bearer ${token}` },
+                  keepalive: true,
+                },
+              ).catch(() => {});
+              sessionIdRef.current = null;
+            }
+            setState('expired');
+          }
+          return current;
+        });
+      }, 500);
+
       pollTimerRef.current = setInterval(async () => {
         try {
           const pollRes = await fetch(
@@ -237,7 +272,7 @@ export default function QrCodeLoginDialog({
           const { status, error, ...rest } = pollJson.data;
 
           if (status === 'success') {
-            sessionIdRef.current = null; // backend already cleaned up
+            sessionIdRef.current = null;
             cleanup();
             setState('success');
             setTimeout(() => {
@@ -249,9 +284,14 @@ export default function QrCodeLoginDialog({
             cleanup();
             setState('error');
             setErrorMessage(error || tRef.current(cfg.failedKey));
+          } else if (status === 'expired') {
+            sessionIdRef.current = null;
+            cleanup();
+            setExpireIn(0);
+            setState('expired');
           }
         } catch {
-          // ignore poll errors, will retry next interval
+          // ignore poll errors
         }
       }, POLL_INTERVAL_MS);
     } catch (err: unknown) {
@@ -323,6 +363,31 @@ export default function QrCodeLoginDialog({
             </div>
           )}
 
+          {/* QR code expired — click overlay to refresh */}
+          {state === 'expired' && qrDataUrl && (
+            <div className="flex flex-col items-center space-y-3">
+              <p className="text-sm text-muted-foreground text-center">
+                {t(platformConfig.scanQRCodeKey)}
+              </p>
+              <button
+                type="button"
+                className="relative border rounded-lg p-2 bg-white cursor-pointer group"
+                onClick={() => startLogin()}
+              >
+                <img
+                  src={qrDataUrl}
+                  alt="QR Code"
+                  className="w-56 h-56 opacity-40"
+                />
+                <div className="absolute inset-0 flex items-center justify-center bg-white/60 rounded-lg group-hover:bg-white/70 transition-colors">
+                  <div className="flex items-center justify-center w-16 h-16 rounded-full bg-black/5 group-hover:bg-black/10 transition-colors">
+                    <RotateCw className="h-8 w-8 text-muted-foreground" />
+                  </div>
+                </div>
+              </button>
+            </div>
+          )}
+
           {/* Success */}
           {state === 'success' && (
             <div className="flex flex-col items-center space-y-3 py-8">
@@ -350,7 +415,7 @@ export default function QrCodeLoginDialog({
         </div>
 
         {state === 'error' && (
-          <DialogFooter>
+          <div className="flex justify-end gap-2">
             <Button variant="outline" onClick={() => handleOpenChange(false)}>
               {t('common.cancel')}
             </Button>
@@ -358,7 +423,7 @@ export default function QrCodeLoginDialog({
               <RefreshCw className="h-4 w-4 mr-1.5" />
               {t(platformConfig.retryKey)}
             </Button>
-          </DialogFooter>
+          </div>
         )}
       </DialogContent>
     </Dialog>

web/src/app/home/mcp/components/mcp-form/MCPForm.tsx

@@ -71,7 +71,13 @@ function StatusDisplay({
     );
   }
 
-  if (runtimeInfo.status === MCPSessionStatus.CONNECTING) {
+  // CONNECTING, or any not-yet-resolved status (initial/null while the box is
+  // still bringing the session up) — show "connecting" rather than failing.
+  if (
+    runtimeInfo.status === MCPSessionStatus.CONNECTING ||
+    (runtimeInfo.status !== MCPSessionStatus.ERROR &&
+      runtimeInfo.error_phase !== 'box_unavailable')
+  ) {
     return (
       <div className="flex items-center gap-2 text-blue-600">
         <Loader2 className="size-5 animate-spin" />
@@ -258,6 +264,13 @@ function RuntimePanel({
 
   const isConnected =
     !mcpTesting && runtimeInfo.status === MCPSessionStatus.CONNECTED;
+  // Only treat an explicit error (or box-unavailable) as failed; while testing,
+  // connecting, or in an initial/unresolved state, show "connecting" so we
+  // don't flash "connection failed" during a normal connection attempt.
+  const isFailed =
+    !mcpTesting &&
+    (runtimeInfo.status === MCPSessionStatus.ERROR ||
+      runtimeInfo.error_phase === 'box_unavailable');
   const tools = runtimeInfo.tools || [];
 
   return (
@@ -268,7 +281,9 @@ function RuntimePanel({
           <p className="text-sm text-muted-foreground">
             {isConnected
               ? t('mcp.toolCount', { count: tools.length })
-              : t('mcp.connectionFailedStatus')}
+              : isFailed
+                ? t('mcp.connectionFailedStatus')
+                : t('mcp.connecting')}
           </p>
         </div>
         {isConnected && (

web/src/app/home/plugins/components/plugin-install-task/PluginInstallProgressDialog.tsx

@@ -10,6 +10,8 @@ import { Button } from '@/components/ui/button';
 import {
   Download,
   Package,
+  Server,
+  Sparkles,
   CheckCircle2,
   XCircle,
   Loader2,
@@ -171,6 +173,15 @@ function TaskProgressContent({ task }: { task: PluginInstallTask }) {
   const isDone = task.stage === InstallStage.DONE;
   const isError = task.stage === InstallStage.ERROR;
 
+  // MCP / Skill don't have the plugin's download + dependency-install stages;
+  // show a single "installing → done/failed" row instead of plugin steps.
+  const isPlugin = task.extensionType === 'plugin';
+  const simpleIcon = task.extensionType === 'mcp' ? Server : Sparkles;
+  const simpleInstallingLabel =
+    task.extensionType === 'mcp'
+      ? t('addExtension.installStage.mcpInstalling')
+      : t('addExtension.installStage.skillInstalling');
+
   /** Build detail node for a stage */
   const getStageDetail = (
     stageKey: InstallStage,
@@ -307,42 +318,60 @@ function TaskProgressContent({ task }: { task: PluginInstallTask }) {
 
       {/* Stage display */}
       <div className="space-y-1.5">
-        {isDone
-          ? /* When done: show all stages with completed style */
-            STAGES.map((stageConfig) => (
-              <StageRow
-                key={stageConfig.key}
-                icon={stageConfig.icon}
-                label={t(stageConfig.i18nKey)}
-                isActive={false}
-                isCompleted={true}
-                isError={false}
-                detail={getStageDetail(stageConfig.key, true)}
-              />
-            ))
-          : isError
-            ? /* Error: show the failed stage */
-              currentStageIndex >= 0 && (
-                <StageRow
-                  icon={STAGES[currentStageIndex].icon}
-                  label={t(STAGES[currentStageIndex].i18nKey)}
-                  isActive={true}
-                  isCompleted={false}
-                  isError={true}
-                  detail={task.error}
-                />
-              )
-            : /* In progress: only show the current active stage */
-              currentStageIndex >= 0 && (
-                <StageRow
-                  icon={STAGES[currentStageIndex].icon}
-                  label={t(STAGES[currentStageIndex].i18nKey)}
-                  isActive={true}
-                  isCompleted={false}
-                  isError={false}
-                  detail={getStageDetail(STAGES[currentStageIndex].key, false)}
-                />
-              )}
+        {!isPlugin ? (
+          /* MCP / Skill: single installing → done/failed row */
+          <StageRow
+            icon={simpleIcon}
+            label={
+              isDone
+                ? t('addExtension.installStage.installed')
+                : isError
+                  ? t('plugins.installProgress.failed')
+                  : simpleInstallingLabel
+            }
+            isActive={!isDone}
+            isCompleted={isDone}
+            isError={isError}
+            detail={isError ? task.error : undefined}
+          />
+        ) : isDone ? (
+          /* When done: show all stages with completed style */
+          STAGES.map((stageConfig) => (
+            <StageRow
+              key={stageConfig.key}
+              icon={stageConfig.icon}
+              label={t(stageConfig.i18nKey)}
+              isActive={false}
+              isCompleted={true}
+              isError={false}
+              detail={getStageDetail(stageConfig.key, true)}
+            />
+          ))
+        ) : isError ? (
+          /* Error: show the failed stage */
+          currentStageIndex >= 0 && (
+            <StageRow
+              icon={STAGES[currentStageIndex].icon}
+              label={t(STAGES[currentStageIndex].i18nKey)}
+              isActive={true}
+              isCompleted={false}
+              isError={true}
+              detail={task.error}
+            />
+          )
+        ) : (
+          /* In progress: only show the current active stage */
+          currentStageIndex >= 0 && (
+            <StageRow
+              icon={STAGES[currentStageIndex].icon}
+              label={t(STAGES[currentStageIndex].i18nKey)}
+              isActive={true}
+              isCompleted={false}
+              isError={false}
+              detail={getStageDetail(STAGES[currentStageIndex].key, false)}
+            />
+          )
+        )}
       </div>
 
       {/* Done banner */}

web/src/app/home/plugins/components/plugin-install-task/PluginInstallTaskQueue.tsx

@@ -9,9 +9,9 @@ import {
   Loader2,
   X,
   ListTodo,
-  Wrench,
-  AudioWaveform,
-  Book,
+  Puzzle,
+  Server,
+  Sparkles,
 } from 'lucide-react';
 import { Button } from '@/components/ui/button';
 import {
@@ -35,9 +35,9 @@ const STAGE_ICONS: Record<string, React.ElementType> = {
 };
 
 const EXTENSION_TYPE_ICONS: Record<string, React.ElementType> = {
-  plugin: Wrench,
-  mcp: AudioWaveform,
-  skill: Book,
+  plugin: Puzzle,
+  mcp: Server,
+  skill: Sparkles,
 };
 
 function TaskQueueItem({
@@ -54,7 +54,7 @@ function TaskQueueItem({
   const isError = task.stage === InstallStage.ERROR;
   const isRunning = !isDone && !isError;
   const StageIcon = STAGE_ICONS[task.stage] || Download;
-  const TypeIcon = EXTENSION_TYPE_ICONS[task.extensionType] || Wrench;
+  const TypeIcon = EXTENSION_TYPE_ICONS[task.extensionType] || Puzzle;
 
   const getTypeBadgeClass = () => {
     switch (task.extensionType) {

web/src/app/home/plugins/components/plugin-installed/PluginInstalledComponent.tsx

@@ -21,8 +21,7 @@ import { extractI18nObject } from '@/i18n/I18nProvider';
 import { toast } from 'sonner';
 import { useAsyncTask, AsyncTaskStatus } from '@/hooks/useAsyncTask';
 import { useSidebarData } from '@/app/home/components/home-sidebar/SidebarDataContext';
-import { Loader2, Puzzle } from 'lucide-react';
-import { Wrench, AudioWaveform, Book } from 'lucide-react';
+import { Loader2, Puzzle, Server, Sparkles } from 'lucide-react';
 
 export interface PluginInstalledComponentRef {
   refreshPluginList: () => void;
@@ -44,14 +43,18 @@ export const FilterOptions = [
   {
     value: 'plugin' as FilterType,
     labelKey: 'market.typePlugin',
-    icon: Wrench,
+    icon: Puzzle,
   },
   {
     value: 'mcp' as FilterType,
     labelKey: 'market.typeMCP',
-    icon: AudioWaveform,
+    icon: Server,
+  },
+  {
+    value: 'skill' as FilterType,
+    labelKey: 'market.typeSkill',
+    icon: Sparkles,
   },
-  { value: 'skill' as FilterType, labelKey: 'market.typeSkill', icon: Book },
 ];
 
 interface PluginInstalledComponentProps {

web/src/app/home/plugins/components/plugin-market/PluginMarketComponent.tsx

@@ -17,17 +17,32 @@ import { Separator } from '@/components/ui/separator';
 import { ToggleGroup, ToggleGroupItem } from '@/components/ui/toggle-group';
 import {
   Search,
+  Puzzle,
+  Server,
+  Sparkles,
   Wrench,
   AudioWaveform,
   Hash,
   Book,
   FileText,
+  AppWindow,
   SlidersHorizontal,
   X,
+  Info,
 } from 'lucide-react';
+import {
+  Tooltip,
+  TooltipContent,
+  TooltipTrigger,
+} from '@/components/ui/tooltip';
 import PluginMarketCardComponent from './plugin-market-card/PluginMarketCardComponent';
 import { PluginMarketCardVO } from './plugin-market-card/PluginMarketCardVO';
-import { getCloudServiceClientSync } from '@/app/infra/http';
+import { RecommendationLists } from './RecommendationLists';
+import type { RecommendationList } from './RecommendationLists';
+import {
+  getCloudServiceClient,
+  getCloudServiceClientSync,
+} from '@/app/infra/http';
 import { useTranslation } from 'react-i18next';
 import { PluginV4, PluginV4Status } from '@/app/infra/entities/plugin';
 import { extractI18nObject } from '@/i18n/I18nProvider';
@@ -44,6 +59,23 @@ interface SortOption {
   sortOrder: string;
 }
 
+// Persist the market filter conditions (type / component / tags / sort) across
+// visits via localStorage.
+const MARKET_FILTERS_KEY = 'langbot_market_filters';
+interface MarketFilters {
+  typeFilter?: string;
+  componentFilter?: string;
+  selectedTags?: string[];
+  sortOption?: string;
+}
+function loadMarketFilters(): MarketFilters {
+  try {
+    return JSON.parse(localStorage.getItem(MARKET_FILTERS_KEY) || '{}');
+  } catch {
+    return {};
+  }
+}
+
 // 内部组件，用于处理搜索参数
 function MarketPageContent({
   installPlugin,
@@ -59,34 +91,61 @@ function MarketPageContent({
 
   const extensionTypeOptions = [
     { value: 'all', label: t('market.filters.allFormats'), icon: null },
-    { value: 'plugin', label: t('market.typePlugin'), icon: Wrench },
-    { value: 'mcp', label: t('market.typeMCP'), icon: AudioWaveform },
-    { value: 'skill', label: t('market.typeSkill'), icon: Book },
+    { value: 'plugin', label: t('market.typePlugin'), icon: Puzzle },
+    { value: 'mcp', label: t('market.typeMCP'), icon: Server },
+    { value: 'skill', label: t('market.typeSkill'), icon: Sparkles },
   ];
 
   const [searchQuery, setSearchQuery] = useState('');
-  const [componentFilter, setComponentFilter] = useState('all');
+  const [componentFilter, setComponentFilter] = useState<string>(
+    () => loadMarketFilters().componentFilter ?? 'all',
+  );
   const [typeFilter, setTypeFilter] = useState<string>(() => {
     const type = searchParams.get('type');
     if (type && validTypes.includes(type)) {
       return type;
     }
-    return 'all';
+    const saved = loadMarketFilters().typeFilter;
+    return saved && validTypes.includes(saved) ? saved : 'all';
   });
   const activeAdvancedFilters =
     (typeFilter === 'all' ? 0 : 1) + (componentFilter === 'all' ? 0 : 1);
-  const [selectedTags, setSelectedTags] = useState<string[]>([]);
+  const [selectedTags, setSelectedTags] = useState<string[]>(
+    () => loadMarketFilters().selectedTags ?? [],
+  );
   const [availableTags, setAvailableTags] = useState<PluginTag[]>([]);
   const [tagNames, setTagNames] = useState<Record<string, string>>({});
+  const [recommendationLists, setRecommendationLists] = useState<
+    RecommendationList[]
+  >([]);
   const [plugins, setPlugins] = useState<PluginMarketCardVO[]>([]);
   const [isLoading, setIsLoading] = useState(false);
   const [isLoadingMore, setIsLoadingMore] = useState(false);
   const [hasMore, setHasMore] = useState(true);
   const [currentPage, setCurrentPage] = useState(1);
   const [total, setTotal] = useState(0);
-  const [sortOption, setSortOption] = useState('install_count_desc');
+  const [sortOption, setSortOption] = useState<string>(
+    () => loadMarketFilters().sortOption ?? 'install_count_desc',
+  );
 
-  const pageSize = 12; // 每页12个
+  // Persist filter conditions so they survive navigation / reload.
+  useEffect(() => {
+    try {
+      localStorage.setItem(
+        MARKET_FILTERS_KEY,
+        JSON.stringify({
+          typeFilter,
+          componentFilter,
+          selectedTags,
+          sortOption,
+        }),
+      );
+    } catch {
+      // ignore storage errors
+    }
+  }, [typeFilter, componentFilter, selectedTags, sortOption]);
+
+  const pageSize = 24; // 每页24个
   const searchTimeoutRef = useRef<NodeJS.Timeout | null>(null);
   const scrollContainerRef = useRef<HTMLDivElement | null>(null);
   const isComposingRef = useRef(false);
@@ -138,6 +197,11 @@ function MarketPageContent({
       label: t('market.componentName.Parser'),
       icon: FileText,
     },
+    {
+      value: 'Page',
+      label: t('market.componentName.Page'),
+      icon: AppWindow,
+    },
   ];
 
   // 获取当前排序参数
@@ -248,11 +312,29 @@ function MarketPageContent({
 
   // 初始加载
   useEffect(() => {
-    fetchPlugins(1, false, true);
-    fetchAvailableTags();
+    // Resolve the cloud service base URL (from system info) before any
+    // marketplace fetch — otherwise the sync client may still hold the default
+    // URL and hit space.langbot.app instead of the configured instance.
+    (async () => {
+      await getCloudServiceClient();
+      fetchPlugins(1, false, true);
+      fetchAvailableTags();
+      fetchRecommendationLists();
+    })();
     // eslint-disable-next-line react-hooks/exhaustive-deps
   }, []);
 
+  // 获取推荐列表（精选，混合插件/MCP/Skill）
+  const fetchRecommendationLists = async () => {
+    try {
+      const client = await getCloudServiceClient();
+      const { lists } = await client.getRecommendationLists();
+      setRecommendationLists(lists || []);
+    } catch (error) {
+      console.error('Failed to fetch recommendation lists:', error);
+    }
+  };
+
   // 获取可用标签
   const fetchAvailableTags = async () => {
     try {
@@ -616,8 +698,22 @@ function MarketPageContent({
                 </div>
                 <Separator />
                 <div className="space-y-2">
-                  <div className="text-xs font-medium text-muted-foreground">
+                  <div className="flex items-center gap-1 text-xs font-medium text-muted-foreground">
                     {t('market.filterByComponent')}
+                    <Tooltip>
+                      <TooltipTrigger asChild>
+                        <button
+                          type="button"
+                          className="inline-flex text-muted-foreground/70 hover:text-foreground"
+                          aria-label={t('market.filterByComponentHint')}
+                        >
+                          <Info className="size-3.5" />
+                        </button>
+                      </TooltipTrigger>
+                      <TooltipContent side="top" className="max-w-64">
+                        {t('market.filterByComponentHint')}
+                      </TooltipContent>
+                    </Tooltip>
                   </div>
                   <ToggleGroup
                     type="single"
@@ -701,6 +797,18 @@ function MarketPageContent({
         ref={scrollContainerRef}
         className="flex-1 overflow-y-auto px-3 sm:px-4 pb-6 container mx-auto"
       >
+        {/* 推荐列表（仅在无搜索/筛选时展示，混合插件/MCP/Skill） */}
+        {!searchQuery &&
+          typeFilter === 'all' &&
+          componentFilter === 'all' &&
+          selectedTags.length === 0 && (
+            <RecommendationLists
+              lists={recommendationLists}
+              tagNames={tagNames}
+              onInstall={handleInstallPlugin}
+            />
+          )}
+
         {isLoading ? (
           <div className="flex items-center justify-center py-12">
             <LoadingSpinner text={t('market.loading')} />

web/src/app/home/plugins/components/plugin-market/RecommendationLists.tsx

@@ -22,6 +22,15 @@ function pluginToVO(
   plugin: PluginV4,
   t: (key: string) => string,
 ): PluginMarketCardVO {
+  const cloudClient = getCloudServiceClientSync();
+  // Recommendation lists are mixed-type; resolve the icon per extension type.
+  const iconURL =
+    plugin.type === 'mcp'
+      ? cloudClient.getMCPMarketplaceIconURL(plugin.author, plugin.name)
+      : plugin.type === 'skill'
+        ? cloudClient.getSkillMarketplaceIconURL(plugin.author, plugin.name)
+        : cloudClient.getPluginIconURL(plugin.author, plugin.name);
+
   return new PluginMarketCardVO({
     pluginId: plugin.author + ' / ' + plugin.name,
     author: plugin.author,
@@ -30,10 +39,7 @@ function pluginToVO(
     description:
       extractI18nObject(plugin.description) || t('market.noDescription'),
     installCount: plugin.install_count,
-    iconURL: getCloudServiceClientSync().getPluginIconURL(
-      plugin.author,
-      plugin.name,
-    ),
+    iconURL,
     githubURL: plugin.repository,
     version: plugin.latest_version,
     components: plugin.components,

web/src/app/home/plugins/components/plugin-market/TagsFilter.tsx

@@ -44,7 +44,7 @@ export function TagsFilter({
 
   return (
     <Select open={open} onOpenChange={setOpen}>
-      <SelectTrigger className="w-[140px]">
+      <SelectTrigger className="w-[140px] cursor-pointer">
         <div className="flex items-center gap-2 w-full">
           <TagIcon className="h-4 w-4 flex-shrink-0" />
           {selectedTags.length === 0 ? (

web/src/app/home/plugins/components/plugin-market/plugin-market-card/PluginMarketCardComponent.tsx

@@ -94,7 +94,7 @@ export default function PluginMarketCardComponent({
       role="button"
       tabIndex={0}
       aria-label={t('market.installCard', { name: cardVO.label })}
-      className="w-[100%] h-[10rem] cursor-pointer bg-white rounded-[10px] shadow-[0px_0px_4px_0_rgba(0,0,0,0.2)] p-3 sm:p-[1rem] hover:shadow-[0px_2px_8px_0_rgba(0,0,0,0.15)] transition-shadow duration-200 outline-none focus-visible:ring-[3px] focus-visible:ring-ring/50 dark:bg-[#1f1f22] dark:shadow-[0px_0px_4px_0_rgba(255,255,255,0.1)] dark:hover:shadow-[0px_2px_8px_0_rgba(255,255,255,0.15)] relative"
+      className="w-[100%] h-[10rem] cursor-pointer bg-white rounded-[10px] border border-border shadow-[0px_1px_2px_0_rgba(0,0,0,0.06)] p-3 sm:p-[1rem] hover:shadow-[0px_2px_5px_0_rgba(0,0,0,0.08)] transition-shadow duration-200 outline-none focus-visible:ring-[3px] focus-visible:ring-ring/50 dark:bg-[#1f1f22] dark:shadow-[0px_1px_2px_0_rgba(255,255,255,0.04)] dark:hover:shadow-[0px_2px_5px_0_rgba(255,255,255,0.07)] relative"
       onClick={handleInstallClick}
       onKeyDown={(event) => {
         if (event.key === 'Enter' || event.key === ' ') {

web/src/app/home/plugins/mcp-server/mcp-card/MCPCardComponent.tsx

@@ -129,22 +129,22 @@ export default function MCPCardComponent({
                   {t('mcp.toolCount', { count: toolsCount })}
                 </div>
               </div>
-            ) : status === MCPSessionStatus.CONNECTING ? (
-              // 连接中 - 蓝色加载
-              <div className="flex flex-row items-center gap-[0.4rem]">
-                <Loader2 className="w-4 h-4 text-blue-500 dark:text-blue-400 animate-spin" />
-                <div className="text-sm text-blue-500 dark:text-blue-400 font-medium">
-                  {t('mcp.connecting')}
-                </div>
-              </div>
-            ) : (
-              // 连接失败 - 红色
+            ) : status === MCPSessionStatus.ERROR ? (
+              // 连接失败 - 红色（仅在明确报错时）
               <div className="flex flex-row items-center gap-[0.4rem]">
                 <AlertCircle className="w-4 h-4 text-red-500 dark:text-red-400" />
                 <div className="text-sm text-red-500 dark:text-red-400 font-medium">
                   {t('mcp.connectionFailedStatus')}
                 </div>
               </div>
+            ) : (
+              // 连接中 - 蓝色加载（CONNECTING 或初始/未知状态，避免误报失败）
+              <div className="flex flex-row items-center gap-[0.4rem]">
+                <Loader2 className="w-4 h-4 text-blue-500 dark:text-blue-400 animate-spin" />
+                <div className="text-sm text-blue-500 dark:text-blue-400 font-medium">
+                  {t('mcp.connecting')}
+                </div>
+              </div>
             )}
           </div>
         </div>

web/src/i18n/locales/en-US.ts

@@ -10,6 +10,8 @@ const enUS = {
     pluginPagesTooltip: 'Visual pages provided by installed plugins',
     quickStart: 'Quick Start',
     scrollToBottom: 'Scroll to bottom',
+    editionCommunity: 'Community',
+    editionCloud: 'Cloud',
   },
   common: {
     login: 'Login',
@@ -35,6 +37,7 @@ const enUS = {
     helpDocs: 'Get Help',
     featureRequest: 'Feature Request',
     starOnGitHub: 'Star on GitHub',
+    joinDiscord: 'Join our Discord',
     create: 'Create',
     edit: 'Edit',
     delete: 'Delete',
@@ -454,7 +457,7 @@ const enUS = {
     noPluginInstalled: 'No plugins installed',
     noExtensionInstalled: 'No extensions installed',
     loadingExtensions: 'Loading extensions...',
-    groupByType: 'Group by type',
+    groupByType: 'Group by format',
     pluginConfig: 'Plugin Configuration',
     pluginSort: 'Plugin Sort',
     pluginSortDescription:
@@ -629,8 +632,8 @@ const enUS = {
   },
   market: {
     searchPlaceholder: 'Search plugins...',
-    searchResults: 'Found {{count}} plugins',
-    totalPlugins: 'Total {{count}} plugins',
+    searchResults: 'Found {{count}} extensions',
+    totalPlugins: 'Total {{count}} extensions',
     noPlugins: 'No plugins available',
     noResults: 'No relevant plugins found',
     loadingMore: 'Loading more...',
@@ -670,8 +673,18 @@ const enUS = {
     markAsRead: 'Mark as Read',
     markAsReadSuccess: 'Marked as read',
     markAsReadFailed: 'Mark as read failed',
-    filterByComponent: 'Component',
+    filterByComponent: 'Plugin Component',
+    filterByComponentHint:
+      'The capability types a plugin provides — Tool, Command, EventListener, etc. — used to extend LangBot in various ways. Filter by component to show only plugins offering that capability.',
     allComponents: 'All Components',
+    componentName: {
+      Tool: 'Tool',
+      EventListener: 'Event Listener',
+      Command: 'Command',
+      KnowledgeEngine: 'Knowledge Engine',
+      Parser: 'Parser',
+      Page: 'Page',
+    },
     filterByType: 'Type',
     allTypes: 'All Types',
     typePlugin: 'Plugin',
@@ -1531,6 +1544,17 @@ const enUS = {
     },
   },
   addExtension: {
+    installTitle: 'Install {{type}}',
+    installConfirm: 'Install {{type}} "{{name}}"?',
+    installInfoType: 'Type',
+    installInfoId: 'ID',
+    installInfoVersion: 'Version',
+    installSuccess: 'Installed successfully',
+    installStage: {
+      mcpInstalling: 'Adding and connecting the MCP server…',
+      skillInstalling: 'Installing the skill…',
+      installed: 'Done',
+    },
     manualAdd: 'Manual Add',
     uploadExtension: 'Drag & drop or click to upload',
     uploadHint: 'Supports .zip (skills) and .lbpkg (plugins) files',

web/src/i18n/locales/es-ES.ts

@@ -11,6 +11,8 @@ const esES = {
       'Páginas visuales proporcionadas por los plugins instalados',
     quickStart: 'Inicio rápido',
     scrollToBottom: 'Desplazar al final',
+    editionCommunity: 'Comunidad',
+    editionCloud: 'Cloud',
   },
   common: {
     login: 'Iniciar sesión',
@@ -38,6 +40,7 @@ const esES = {
     helpDocs: 'Obtener ayuda',
     featureRequest: 'Solicitar función',
     starOnGitHub: 'Dar estrella en GitHub',
+    joinDiscord: 'Únete a Discord',
     create: 'Crear',
     edit: 'Editar',
     delete: 'Eliminar',
@@ -466,7 +469,7 @@ const esES = {
     noPluginInstalled: 'No hay plugins instalados',
     noExtensionInstalled: 'No hay extensiones instaladas',
     loadingExtensions: 'Cargando extensiones...',
-    groupByType: 'Agrupar por tipo',
+    groupByType: 'Agrupar por formato',
     pluginConfig: 'Configuración del plugin',
     pluginSort: 'Orden de plugins',
     pluginSortDescription:
@@ -642,8 +645,8 @@ const esES = {
   },
   market: {
     searchPlaceholder: 'Buscar plugins...',
-    searchResults: 'Se encontraron {{count}} plugins',
-    totalPlugins: 'Total {{count}} plugins',
+    searchResults: 'Se encontraron {{count}} extensiones',
+    totalPlugins: 'Total {{count}} extensiones',
     noPlugins: 'No hay plugins disponibles',
     noResults: 'No se encontraron plugins relevantes',
     loadingMore: 'Cargando más...',
@@ -683,8 +686,18 @@ const esES = {
     markAsRead: 'Marcar como leído',
     markAsReadSuccess: 'Marcado como leído',
     markAsReadFailed: 'Error al marcar como leído',
-    filterByComponent: 'Componente',
+    filterByComponent: 'Componente del plugin',
+    filterByComponentHint:
+      'Los tipos de capacidad que ofrece un plugin: herramienta (Tool), comando (Command), escucha de eventos (EventListener), etc., usados para ampliar las capacidades de LangBot. Filtra por componente para ver solo los plugins que ofrecen esa capacidad.',
     allComponents: 'Todos los componentes',
+    componentName: {
+      Tool: 'Herramienta',
+      EventListener: 'Listener de eventos',
+      Command: 'Comando',
+      KnowledgeEngine: 'Motor de conocimiento',
+      Parser: 'Analizador',
+      Page: 'Página',
+    },
     filterByType: 'Tipo',
     allTypes: 'Todos los tipos',
     typePlugin: 'Plugin',
@@ -1638,6 +1651,17 @@ const esES = {
     saveFileError: 'Error al guardar el archivo: ',
   },
   addExtension: {
+    installTitle: 'Instalar {{type}}',
+    installConfirm: '¿Instalar {{type}} "{{name}}"?',
+    installInfoType: 'Tipo',
+    installInfoId: 'ID',
+    installInfoVersion: 'Versión',
+    installSuccess: 'Instalado correctamente',
+    installStage: {
+      mcpInstalling: 'Añadiendo y conectando el servidor MCP…',
+      skillInstalling: 'Instalando la skill…',
+      installed: 'Listo',
+    },
     manualAdd: 'Añadir manualmente',
     uploadExtension: 'Arrastra y suelta o haz clic para subir',
     uploadHint: 'Admite archivos .zip (skills) y .lbpkg (plugins)',

web/src/i18n/locales/ja-JP.ts

@@ -10,6 +10,8 @@ const jaJP = {
     pluginPagesTooltip: 'インストール済みプラグインが提供するビジュアルページ',
     quickStart: 'クイックスタート',
     scrollToBottom: '一番下までスクロール',
+    editionCommunity: 'コミュニティ版',
+    editionCloud: 'Cloud',
   },
   common: {
     login: 'ログイン',
@@ -36,6 +38,7 @@ const jaJP = {
     helpDocs: 'ヘルプドキュメント',
     featureRequest: '機能リクエスト',
     starOnGitHub: 'GitHubでStarする',
+    joinDiscord: 'Discord に参加',
     create: '作成',
     edit: '編集',
     delete: '削除',
@@ -459,7 +462,7 @@ const jaJP = {
     noPluginInstalled: 'プラグインがインストールされていません',
     noExtensionInstalled: '拡張機能がインストールされていません',
     loadingExtensions: '拡張機能を読み込み中...',
-    groupByType: '種類でグループ化',
+    groupByType: '形式でグループ化',
     pluginConfig: 'プラグイン設定',
     pluginSort: 'プラグインの並び替え',
     pluginSortDescription:
@@ -634,8 +637,8 @@ const jaJP = {
   },
   market: {
     searchPlaceholder: 'プラグインを検索...',
-    searchResults: '{{count}} 個のプラグインが見つかりました',
-    totalPlugins: '合計 {{count}} 個のプラグイン',
+    searchResults: '{{count}} 個の拡張機能が見つかりました',
+    totalPlugins: '合計 {{count}} 個の拡張機能',
     noPlugins: '利用可能なプラグインがありません',
     noResults: '関連するプラグインが見つかりません',
     loadingMore: 'さらに読み込み中...',
@@ -675,8 +678,18 @@ const jaJP = {
     markAsRead: '既読',
     markAsReadSuccess: '既読に設定しました',
     markAsReadFailed: '既読に設定に失敗しました',
-    filterByComponent: 'コンポーネント',
+    filterByComponent: 'プラグインコンポーネント',
+    filterByComponentHint:
+      'プラグインが提供する機能の種類です（ツール、コマンド、イベントリスナーなど）。LangBot のさまざまな機能を拡張するために使われます。コンポーネントで絞り込むと、その機能を提供するプラグインのみを表示できます。',
     allComponents: '全部コンポーネント',
+    componentName: {
+      Tool: 'ツール',
+      EventListener: 'イベント監視器',
+      Command: 'コマンド',
+      KnowledgeEngine: '知識エンジン',
+      Parser: 'パーサー',
+      Page: 'ページ',
+    },
     filterByType: 'タイプ',
     allTypes: '全部',
     typePlugin: 'プラグイン',
@@ -1445,6 +1458,17 @@ const jaJP = {
     },
   },
   addExtension: {
+    installTitle: '{{type}}をインストール',
+    installConfirm: '{{type}}「{{name}}」をインストールしますか？',
+    installInfoType: 'タイプ',
+    installInfoId: 'ID',
+    installInfoVersion: 'バージョン',
+    installSuccess: 'インストールに成功しました',
+    installStage: {
+      mcpInstalling: 'MCPサーバーを追加して接続しています…',
+      skillInstalling: 'スキルをインストールしています…',
+      installed: '完了',
+    },
     manualAdd: '手動追加',
     uploadExtension: 'ドラッグ＆ドロップまたはクリックしてアップロード',
     uploadHint: '.zip（スキル）と.lbpkg（プラグイン）ファイルに対応',

web/src/i18n/locales/ru-RU.ts

@@ -11,6 +11,8 @@ const ruRU = {
       'Визуальные страницы, предоставляемые установленными плагинами',
     quickStart: 'Быстрый старт',
     scrollToBottom: 'Прокрутить вниз',
+    editionCommunity: 'Сообщество',
+    editionCloud: 'Cloud',
   },
   common: {
     login: 'Войти',
@@ -36,6 +38,7 @@ const ruRU = {
     helpDocs: 'Помощь',
     featureRequest: 'Запрос функции',
     starOnGitHub: 'Поставить звезду на GitHub',
+    joinDiscord: 'Присоединиться к Discord',
     create: 'Создать',
     edit: 'Редактировать',
     delete: 'Удалить',
@@ -464,7 +467,7 @@ const ruRU = {
     noPluginInstalled: 'Плагины не установлены',
     noExtensionInstalled: 'Расширения не установлены',
     loadingExtensions: 'Загрузка расширений...',
-    groupByType: 'Группировать по типу',
+    groupByType: 'Группировать по формату',
     pluginConfig: 'Настройка плагина',
     pluginSort: 'Порядок плагинов',
     pluginSortDescription:
@@ -640,8 +643,8 @@ const ruRU = {
   },
   market: {
     searchPlaceholder: 'Поиск плагинов...',
-    searchResults: 'Найдено {{count}} плагинов',
-    totalPlugins: 'Всего {{count}} плагинов',
+    searchResults: 'Найдено {{count}} расширений',
+    totalPlugins: 'Всего {{count}} расширений',
     noPlugins: 'Нет доступных плагинов',
     noResults: 'Подходящие плагины не найдены',
     loadingMore: 'Загрузка ещё...',
@@ -680,8 +683,18 @@ const ruRU = {
     markAsRead: 'Отметить как прочитанное',
     markAsReadSuccess: 'Отмечено как прочитанное',
     markAsReadFailed: 'Не удалось отметить как прочитанное',
-    filterByComponent: 'Компонент',
+    filterByComponent: 'Компонент плагина',
+    filterByComponentHint:
+      'Типы возможностей, которые предоставляет плагин — инструмент (Tool), команда (Command), обработчик событий (EventListener) и т. д., — расширяющие функции LangBot. Фильтруйте по компоненту, чтобы видеть только плагины с нужной возможностью.',
     allComponents: 'Все компоненты',
+    componentName: {
+      Tool: 'Инструмент',
+      EventListener: 'Обработчик событий',
+      Command: 'Команда',
+      KnowledgeEngine: 'Движок знаний',
+      Parser: 'Парсер',
+      Page: 'Страница',
+    },
     filterByType: 'Тип',
     allTypes: 'Все типы',
     typePlugin: 'Плагин',
@@ -1606,6 +1619,17 @@ const ruRU = {
     saveFileError: 'Не удалось сохранить файл: ',
   },
   addExtension: {
+    installTitle: 'Установить {{type}}',
+    installConfirm: 'Установить {{type}} «{{name}}»?',
+    installInfoType: 'Тип',
+    installInfoId: 'ID',
+    installInfoVersion: 'Версия',
+    installSuccess: 'Успешно установлено',
+    installStage: {
+      mcpInstalling: 'Добавление и подключение сервера MCP…',
+      skillInstalling: 'Установка навыка…',
+      installed: 'Готово',
+    },
     manualAdd: 'Добавить вручную',
     uploadExtension: 'Перетащите файл сюда или нажмите для загрузки',
     uploadHint: 'Поддерживаются файлы .zip (навыки) и .lbpkg (плагины)',

web/src/i18n/locales/th-TH.ts

@@ -10,6 +10,8 @@ const thTH = {
     pluginPagesTooltip: 'หน้าเว็บที่จัดทำโดยปลั๊กอินที่ติดตั้ง',
     quickStart: 'เริ่มต้นอย่างรวดเร็ว',
     scrollToBottom: 'เลื่อนไปด้านล่าง',
+    editionCommunity: 'รุ่นชุมชน',
+    editionCloud: 'Cloud',
   },
   common: {
     login: 'เข้าสู่ระบบ',
@@ -35,6 +37,7 @@ const thTH = {
     helpDocs: 'ขอความช่วยเหลือ',
     featureRequest: 'ขอฟีเจอร์ใหม่',
     starOnGitHub: 'ให้ดาวบน GitHub',
+    joinDiscord: 'เข้าร่วม Discord',
     create: 'สร้าง',
     edit: 'แก้ไข',
     delete: 'ลบ',
@@ -450,7 +453,7 @@ const thTH = {
     noPluginInstalled: 'ยังไม่มีปลั๊กอินที่ติดตั้ง',
     noExtensionInstalled: 'ยังไม่มีส่วนขยายที่ติดตั้ง',
     loadingExtensions: 'กำลังโหลดส่วนขยาย...',
-    groupByType: 'จัดกลุ่มตามประเภท',
+    groupByType: 'จัดกลุ่มตามรูปแบบ',
     pluginConfig: 'การกำหนดค่าปลั๊กอิน',
     pluginSort: 'เรียงลำดับปลั๊กอิน',
     pluginSortDescription:
@@ -621,8 +624,8 @@ const thTH = {
   },
   market: {
     searchPlaceholder: 'ค้นหาปลั๊กอิน...',
-    searchResults: 'พบ {{count}} ปลั๊กอิน',
-    totalPlugins: 'ทั้งหมด {{count}} ปลั๊กอิน',
+    searchResults: 'พบ {{count}} ส่วนขยาย',
+    totalPlugins: 'ทั้งหมด {{count}} ส่วนขยาย',
     noPlugins: 'ไม่มีปลั๊กอินที่พร้อมใช้งาน',
     noResults: 'ไม่พบปลั๊กอินที่เกี่ยวข้อง',
     loadingMore: 'กำลังโหลดเพิ่มเติม...',
@@ -661,8 +664,18 @@ const thTH = {
     markAsRead: 'ทำเครื่องหมายว่าอ่านแล้ว',
     markAsReadSuccess: 'ทำเครื่องหมายว่าอ่านแล้ว',
     markAsReadFailed: 'ทำเครื่องหมายว่าอ่านแล้วล้มเหลว',
-    filterByComponent: 'ส่วนประกอบ',
+    filterByComponent: 'ส่วนประกอบปลั๊กอิน',
+    filterByComponentHint:
+      'ประเภทความสามารถที่ปลั๊กอินมีให้ เช่น เครื่องมือ (Tool) คำสั่ง (Command) ตัวรับฟังเหตุการณ์ (EventListener) เป็นต้น ใช้เพื่อขยายความสามารถต่าง ๆ ของ LangBot กรองตามส่วนประกอบเพื่อแสดงเฉพาะปลั๊กอินที่มีความสามารถนั้น',
     allComponents: 'ส่วนประกอบทั้งหมด',
+    componentName: {
+      Tool: 'เครื่องมือ',
+      EventListener: 'ตัวรับฟังเหตุการณ์',
+      Command: 'คำสั่ง',
+      KnowledgeEngine: 'เครื่องมือความรู้',
+      Parser: 'ตัวแยกวิเคราะห์',
+      Page: 'หน้า',
+    },
     filterByType: 'ประเภท',
     allTypes: 'ทุกประเภท',
     typePlugin: 'ปลั๊กอิน',
@@ -1569,6 +1582,17 @@ const thTH = {
     saveFileError: 'บันทึกไฟล์ไม่สำเร็จ: ',
   },
   addExtension: {
+    installTitle: 'ติดตั้ง {{type}}',
+    installConfirm: 'ติดตั้ง {{type}} "{{name}}" หรือไม่?',
+    installInfoType: 'ประเภท',
+    installInfoId: 'ID',
+    installInfoVersion: 'เวอร์ชัน',
+    installSuccess: 'ติดตั้งสำเร็จ',
+    installStage: {
+      mcpInstalling: 'กำลังเพิ่มและเชื่อมต่อเซิร์ฟเวอร์ MCP…',
+      skillInstalling: 'กำลังติดตั้งสกิล…',
+      installed: 'เสร็จสิ้น',
+    },
     manualAdd: 'เพิ่มด้วยตนเอง',
     uploadExtension: 'ลากแล้ววางหรือคลิกเพื่ออัปโหลด',
     uploadHint: 'รองรับไฟล์ .zip (สกิล) และ .lbpkg (ปลั๊กอิน)',

web/src/i18n/locales/vi-VN.ts

@@ -11,6 +11,8 @@ const viVN = {
       'Các trang trực quan được cung cấp bởi plugin đã cài đặt',
     quickStart: 'Bắt đầu nhanh',
     scrollToBottom: 'Cuộn xuống cuối',
+    editionCommunity: 'Bản cộng đồng',
+    editionCloud: 'Cloud',
   },
   common: {
     login: 'Đăng nhập',
@@ -36,6 +38,7 @@ const viVN = {
     helpDocs: 'Trợ giúp',
     featureRequest: 'Yêu cầu tính năng',
     starOnGitHub: 'Star trên GitHub',
+    joinDiscord: 'Tham gia Discord',
     create: 'Tạo',
     edit: 'Chỉnh sửa',
     delete: 'Xóa',
@@ -460,7 +463,7 @@ const viVN = {
     noPluginInstalled: 'Chưa cài đặt plugin nào',
     noExtensionInstalled: 'Chưa cài đặt tiện ích mở rộng nào',
     loadingExtensions: 'Đang tải tiện ích mở rộng...',
-    groupByType: 'Nhóm theo loại',
+    groupByType: 'Nhóm theo định dạng',
     pluginConfig: 'Cấu hình Plugin',
     pluginSort: 'Sắp xếp Plugin',
     pluginSortDescription:
@@ -635,8 +638,8 @@ const viVN = {
   },
   market: {
     searchPlaceholder: 'Tìm kiếm plugin...',
-    searchResults: 'Tìm thấy {{count}} plugin',
-    totalPlugins: 'Tổng cộng {{count}} plugin',
+    searchResults: 'Tìm thấy {{count}} tiện ích mở rộng',
+    totalPlugins: 'Tổng cộng {{count}} tiện ích mở rộng',
     noPlugins: 'Không có plugin nào',
     noResults: 'Không tìm thấy plugin liên quan',
     loadingMore: 'Đang tải thêm...',
@@ -675,8 +678,18 @@ const viVN = {
     markAsRead: 'Đánh dấu đã đọc',
     markAsReadSuccess: 'Đã đánh dấu đã đọc',
     markAsReadFailed: 'Đánh dấu đã đọc thất bại',
-    filterByComponent: 'Thành phần',
+    filterByComponent: 'Thành phần plugin',
+    filterByComponentHint:
+      'Các loại năng lực mà plugin cung cấp — Công cụ (Tool), Lệnh (Command), Trình lắng nghe sự kiện (EventListener), v.v. — dùng để mở rộng các khả năng của LangBot. Lọc theo thành phần để chỉ xem những plugin cung cấp năng lực đó.',
     allComponents: 'Tất cả thành phần',
+    componentName: {
+      Tool: 'Công cụ',
+      EventListener: 'Trình lắng nghe sự kiện',
+      Command: 'Lệnh',
+      KnowledgeEngine: 'Công cụ tri thức',
+      Parser: 'Trình phân tích',
+      Page: 'Trang',
+    },
     filterByType: 'Loại',
     allTypes: 'Tất cả loại',
     typePlugin: 'Plugin',
@@ -1598,6 +1611,17 @@ const viVN = {
     saveFileError: 'Lưu tệp thất bại: ',
   },
   addExtension: {
+    installTitle: 'Cài đặt {{type}}',
+    installConfirm: 'Cài đặt {{type}} "{{name}}"?',
+    installInfoType: 'Loại',
+    installInfoId: 'ID',
+    installInfoVersion: 'Phiên bản',
+    installSuccess: 'Cài đặt thành công',
+    installStage: {
+      mcpInstalling: 'Đang thêm và kết nối máy chủ MCP…',
+      skillInstalling: 'Đang cài đặt kỹ năng…',
+      installed: 'Hoàn tất',
+    },
     manualAdd: 'Thêm thủ công',
     uploadExtension: 'Kéo thả hoặc nhấp để tải lên',
     uploadHint: 'Hỗ trợ tệp .zip (kỹ năng) và .lbpkg (plugin)',

web/src/i18n/locales/zh-Hans.ts

@@ -10,6 +10,8 @@ const zhHans = {
     pluginPagesTooltip: '由已安装的插件提供的可视化页面',
     quickStart: '快速开始向导',
     scrollToBottom: '滚动到底部',
+    editionCommunity: '社区版',
+    editionCloud: 'Cloud',
   },
   common: {
     login: '登录',
@@ -34,6 +36,7 @@ const zhHans = {
     helpDocs: '帮助文档',
     featureRequest: '需求建议',
     starOnGitHub: '在 GitHub 上 Star',
+    joinDiscord: '加入 Discord 社区',
     create: '创建',
     edit: '编辑',
     delete: '删除',
@@ -438,7 +441,7 @@ const zhHans = {
     noPluginInstalled: '暂未安装任何插件',
     noExtensionInstalled: '暂未安装任何扩展',
     loadingExtensions: '正在加载扩展...',
-    groupByType: '按类型分组',
+    groupByType: '按格式分组',
     pluginSort: '插件排序',
     pluginSortDescription:
       '插件顺序会影响同一事件内的处理顺序，请拖动插件卡片排序',
@@ -603,8 +606,8 @@ const zhHans = {
   },
   market: {
     searchPlaceholder: '搜索插件...',
-    searchResults: '搜索到 {{count}} 个插件',
-    totalPlugins: '共 {{count}} 个插件',
+    searchResults: '搜索到 {{count}} 个扩展',
+    totalPlugins: '共 {{count}} 个扩展',
     noPlugins: '暂无插件',
     noResults: '未找到相关插件',
     loadingMore: '加载更多...',
@@ -643,8 +646,18 @@ const zhHans = {
     markAsRead: '已读',
     markAsReadSuccess: '已标记为已读',
     markAsReadFailed: '标记为已读失败',
-    filterByComponent: '组件',
+    filterByComponent: '插件组件',
+    filterByComponentHint:
+      '插件提供的能力类型，如工具（Tool）、命令（Command）、事件监听器（EventListener）等，用于扩展 LangBot 的各项能力。按组件筛选可只看提供对应能力的插件。',
     allComponents: '全部组件',
+    componentName: {
+      Tool: '工具',
+      EventListener: '事件监听器',
+      Command: '命令',
+      KnowledgeEngine: '知识引擎',
+      Parser: '解析器',
+      Page: '页面',
+    },
     filterByType: '类型',
     allTypes: '全部类型',
     typePlugin: '插件',
@@ -1467,6 +1480,17 @@ const zhHans = {
     },
   },
   addExtension: {
+    installTitle: '安装{{type}}',
+    installConfirm: '确定要安装{{type}} "{{name}}" 吗？',
+    installInfoType: '类型',
+    installInfoId: '标识',
+    installInfoVersion: '版本',
+    installSuccess: '安装成功',
+    installStage: {
+      mcpInstalling: '正在添加并连接 MCP 服务器…',
+      skillInstalling: '正在安装技能…',
+      installed: '已完成',
+    },
     manualAdd: '手动添加',
     uploadExtension: '拖拽或点击上传扩展包',
     uploadHint: '支持 .zip（技能）和 .lbpkg（插件）文件',

web/src/i18n/locales/zh-Hant.ts

@@ -10,6 +10,8 @@ const zhHant = {
     pluginPagesTooltip: '由已安裝的插件提供的視覺化頁面',
     quickStart: '快速開始',
     scrollToBottom: '捲動到底部',
+    editionCommunity: '社區版',
+    editionCloud: 'Cloud',
   },
   common: {
     login: '登入',
@@ -34,6 +36,7 @@ const zhHant = {
     helpDocs: '輔助說明',
     featureRequest: '需求建議',
     starOnGitHub: '在 GitHub 上 Star',
+    joinDiscord: '加入 Discord 社群',
     create: '建立',
     edit: '編輯',
     delete: '刪除',
@@ -439,7 +442,7 @@ const zhHant = {
     noPluginInstalled: '暫未安裝任何外掛',
     noExtensionInstalled: '暫未安裝任何擴充功能',
     loadingExtensions: '正在載入擴充功能...',
-    groupByType: '依類型分組',
+    groupByType: '依格式分組',
     pluginSort: '外掛排序',
     pluginSortDescription:
       '外掛順序會影響同一事件內的處理順序，請拖曳外掛卡片排序',
@@ -603,8 +606,8 @@ const zhHant = {
   },
   market: {
     searchPlaceholder: '搜尋插件...',
-    searchResults: '搜尋到 {{count}} 個插件',
-    totalPlugins: '共 {{count}} 個插件',
+    searchResults: '搜尋到 {{count}} 個擴展',
+    totalPlugins: '共 {{count}} 個擴展',
     noPlugins: '暫無插件',
     noResults: '未找到相關插件',
     loadingMore: '載入更多...',
@@ -643,8 +646,18 @@ const zhHant = {
     markAsRead: '已讀',
     markAsReadSuccess: '已標記為已讀',
     markAsReadFailed: '標記為已讀失敗',
-    filterByComponent: '組件',
+    filterByComponent: '插件組件',
+    filterByComponentHint:
+      '插件提供的能力類型，如工具（Tool）、命令（Command）、事件監聽器（EventListener）等，用於擴展 LangBot 的各項能力。按組件篩選可只看提供對應能力的插件。',
     allComponents: '全部組件',
+    componentName: {
+      Tool: '工具',
+      EventListener: '事件監聽器',
+      Command: '命令',
+      KnowledgeEngine: '知識引擎',
+      Parser: '解析器',
+      Page: '擴展頁',
+    },
     filterByType: '類型',
     allTypes: '全部類型',
     typePlugin: '插件',
@@ -1377,6 +1390,17 @@ const zhHant = {
     },
   },
   addExtension: {
+    installTitle: '安裝{{type}}',
+    installConfirm: '確定要安裝{{type}}「{{name}}」嗎？',
+    installInfoType: '類型',
+    installInfoId: 'ID',
+    installInfoVersion: '版本',
+    installSuccess: '安裝成功',
+    installStage: {
+      mcpInstalling: '正在新增並連接 MCP 伺服器…',
+      skillInstalling: '正在安裝技能…',
+      installed: '完成',
+    },
     manualAdd: '手動新增',
     uploadExtension: '拖拽或點擊上傳擴充套件',
     uploadHint: '支援 .zip（技能）和 .lbpkg（插件）檔案',