docs(review): refresh box docs; trim issue list to SaaS blockers only

Community self-hosted edition is release-ready, so the box review docs are
updated to current state (date 2026-06-02 + status note) and box-issues.md is
rewritten to keep only the SaaS / multi-tenant / network-exposed release
blockers (S1-S8): unauthenticated control plane, no per-pipeline exec
authorization, unbounded sessions + no reaper, no kernel-level quota, mount
validation gaps (/ + extra_mounts), missing container hardening, lock-around-
cold-start, and the lower-severity follow-ups. Resolved items (tool-call loop
cap, async quota scan, host_path mount allowlist, _is_path_under dedup) moved to
a short "resolved before community release" record; community-only and
pure-cleanup items dropped.

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

.github/workflows/run-tests.yml

@@ -15,14 +15,10 @@ on:
     branches:
       - master
       - develop
-    paths:
-      - 'src/langbot/**'
-      - 'tests/**'
-      - '.github/workflows/run-tests.yml'
-      - 'pyproject.toml'
-      - 'uv.lock'
-      - 'run_tests.sh'
-      - 'scripts/test-*.sh'
+      - 'feat/**'
+    # No path filter on push: every push to the branches above runs the
+    # full unit-test suite. feat/** branches in particular must be tested
+    # on every push (they accumulate large changes before a PR exists).
 
 jobs:
   test:

README_CN.md

@@ -25,7 +25,7 @@
 <a href="https://link.langbot.app/zh/docs/guide">文档</a> ｜
 <a href="https://link.langbot.app/zh/docs/api">API</a> ｜
 <a href="https://space.langbot.app/cloud">Cloud</a> ｜
-<a href="https://space.langbot.app">插件市场</a> ｜
+<a href="https://space.langbot.app">扩展市场</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">路线图</a>
 
 </div>

docker/docker-compose.yaml

@@ -18,6 +18,40 @@ services:
     networks:
       - langbot_network
 
+  # The Box sandbox runtime is optional. It is only started when you run
+  # ``docker compose --profile box up`` (or ``docker compose --profile all
+  # up``). With Box off, LangBot keeps the dashboard / skills list visible
+  # (read-only) but disables sandbox tools, skill add/edit and stdio MCP —
+  # set ``box.enabled: false`` in ``data/config.yaml`` (or
+  # ``BOX__ENABLED=false`` in the langbot service env below) to match.
+  langbot_box:
+    image: rockchin/langbot:latest
+    container_name: langbot_box
+    profiles: ["box", "all"]
+    volumes:
+      # Keep the source and target path identical because langbot_box uses the
+      # host Docker socket to create sandbox containers. Override
+      # LANGBOT_BOX_ROOT with an absolute path if you do not want the default.
+      - ${LANGBOT_BOX_ROOT:-${PWD}/data/box}:${LANGBOT_BOX_ROOT:-${PWD}/data/box}
+      # Mount container runtime socket for Box sandbox backend.
+      # Uncomment the one that matches your container runtime:
+      # - /var/run/podman/podman.sock:/var/run/podman/podman.sock   # Podman
+      - /var/run/docker.sock:/var/run/docker.sock                   # Docker
+    restart: on-failure
+    environment:
+      - TZ=Asia/Shanghai
+      # The Box runtime does NOT read box.local.* from config.yaml or env; it
+      # receives its configuration from LangBot via the INIT RPC action.
+      # Do not add LANGBOT_BOX_* / BOX__* here — they would be silently ignored.
+    # Launched through the same CLI entry point as the plugin runtime
+    # (`langbot_plugin.cli.__init__ <subcommand>`). WebSocket is the default
+    # control transport — mirrors `rt`, which also runs with no flag. Pass
+    # `-s` / `--stdio-control` only for the stdio mode LangBot uses outside
+    # containers.
+    command: ["uv", "run", "--no-sync", "-m", "langbot_plugin.cli.__init__", "box"]
+    networks:
+      - langbot_network
+
   langbot:
     image: rockchin/langbot:latest
     container_name: langbot
@@ -26,6 +60,13 @@ services:
     restart: on-failure
     environment:
       - TZ=Asia/Shanghai
+      # Unified env-override convention: SECTION__SUBSECTION__KEY overrides the
+      # matching config.yaml field (see LoadConfigStage). These map onto
+      # box.local.* and are forwarded to the Box runtime via INIT RPC.
+      - BOX__LOCAL__HOST_ROOT=${LANGBOT_BOX_ROOT:-${PWD}/data/box}
+      - BOX__LOCAL__DEFAULT_WORKSPACE=default
+      - BOX__LOCAL__SKILLS_ROOT=skills
+      - BOX__LOCAL__ALLOWED_MOUNT_ROOTS=${LANGBOT_BOX_ROOT:-${PWD}/data/box}
     ports:
       - 5300:5300  # For web ui and webhook callback
       - 2280-2285:2280-2285  # For platform reverse connection
@@ -34,4 +75,4 @@ services:
 
 networks:
   langbot_network:
-    driver: bridge
+    driver: bridge

docs/review/box-architecture.md

@@ -0,0 +1,595 @@
+# Box 系统架构深度分析
+
+> 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: [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)
+
+---
+
+## 1. 全局架构
+
+```
+┌──────────────────────────────────────────────────────────────────┐
+│                       LangBot 主进程                              │
+│                                                                   │
+│  LocalAgentRunner ──> ToolManager ──> NativeToolLoader            │
+│       │                    │              │                       │
+│       │                    │      exec / read / write / edit      │
+│       │                    │              glob / grep             │
+│       │                    │                                      │
+│       │                    ├──> MCPLoader ──> BoxStdioSession     │
+│       │                    │       (shared 容器, 多 process)       │
+│       │                    │                                      │
+│       │                    ├──> SkillToolLoader (activate 工具)    │
+│       │                    │                                      │
+│       │                    ├──> SkillAuthoringToolLoader          │
+│       │                    │                                      │
+│       │                    └──> PluginToolLoader                  │
+│       │                                                           │
+│  BoxService (门面)                                                 │
+│    ├─ Profile 管理 (locked 字段)                                   │
+│    ├─ Host mount 校验 (allowed_mount_roots)                        │
+│    ├─ Workspace quota 检查                                         │
+│    ├─ 输出截断 (head+tail)                                         │
+│    ├─ Session ID 模板解析 (resolve_box_session_id)                 │
+│    ├─ 技能挂载组装 (build_skill_extra_mounts)                      │
+│    ├─ 重连循环 (_reconnect_loop, 指数退避)                          │
+│    └─ BoxRuntimeConnector                                          │
+│         ├─ 心跳 loop (20s ping)                                    │
+│         └─ ActionRPCBoxClient                                      │
+│              │  Action RPC (stdio 或 WebSocket)                    │
+│                                                                    │
+│  SkillManager (skill_mgr)                                          │
+│    └─ 从 Box runtime 拉取 skills, 不可用时回落 data/skills          │
+└──────────────────────────────────────────────────────────────────┘
+               │
+               ▼
+┌──────────────────────────────────────────────────────────────────┐
+│              Box Runtime 进程 (SDK 侧)                            │
+│                                                                   │
+│  BoxServerHandler (Action RPC 处理, INIT 配置注入)                  │
+│       │                                                           │
+│  BoxRuntime (session 管理 / 进程生命周期 / TTL reaper)              │
+│       │       └─ session.managed_processes: dict[pid, _ManagedProcess]
+│       │                                                           │
+│  Backend (启动时根据 box.backend 配置选择):                          │
+│    DockerBackend ──┐                                              │
+│    PodmanBackend ──┤── CLISandboxBackend                          │
+│    NsjailBackend ──┘  (本地 CLI 或 fallback 到容器内 CLI)            │
+│    E2BBackend         (云沙箱, 需要 E2B_API_KEY)                    │
+│                                                                   │
+│  BoxSkillStore                                                    │
+│    ├─ list / get / create / update / delete                       │
+│    ├─ scan_skill_directory / read_skill_file / write_skill_file   │
+│    └─ preview_skill_zip / install_skill_zip (zip 或 GitHub)        │
+│                                                                   │
+│  aiohttp 单端口服务 (默认 :5410):                                    │
+│    /rpc/ws                                       — Action RPC      │
+│    /v1/sessions/{id}/managed-process/ws          — 默认 process     │
+│    /v1/sessions/{id}/managed-process/{pid}/ws    — 指定 process     │
+└──────────────────────────────────────────────────────────────────┘
+               │
+               ▼
+┌──────────────────────────────────────────────────────────────────┐
+│  容器 / 沙箱 (Docker/Podman 容器, nsjail sandbox, 或 E2B 远程沙箱)  │
+│  - 隔离文件系统 / 网络 / PID 命名空间                                │
+│  - 资源限制 (CPU, 内存, PID 数, 可选 workspace 配额)                 │
+│  - 主挂载 (host_path → mount_path) + 任意条 extra_mounts             │
+│      └─ Skills 通过 extra_mounts 挂在 /workspace/.skills/<name>     │
+│  - exec: 用户命令在此执行                                            │
+│  - managed process: 多个长驻进程并存 (MCP Server / 自定义服务)        │
+└──────────────────────────────────────────────────────────────────┘
+```
+
+**核心设计原则**:
+- Box Runtime 作为独立进程运行，通过 Action RPC 与 LangBot 主进程通信，两者复用 SDK 的 IO 层（Handler → Connection → Controller）
+- 一个 session_id 对应一个容器/沙箱实例。同一 session 内可并存多条 mount 与多个 managed process
+- Skill / 默认 exec / MCP Server 共享同一个 session 容器（详见 [box-session-scope.md](./box-session-scope.md)）
+
+---
+
+## 2. LangBot 侧模块
+
+### 2.1 BoxService (`pkg/box/service.py`, 722 行)
+
+应用层门面，协调 Profile、安全校验、配额、连接、Skill 挂载与 Session 模板：
+
+主要公开方法（按定义顺序）：
+
+```
+BoxService
+  ├─ initialize()                              连接 Box Runtime + 默认 workspace 准备
+  ├─ _on_runtime_disconnect(connector)         触发重连
+  ├─ _reconnect_loop(connector)                指数退避重连
+  ├─ available (property)                      连接状态
+  │
+  ├─ resolve_box_session_id(query)             从 pipeline 模板解析 session_id
+  ├─ build_skill_extra_mounts(query)           组装 pipeline-bound skill 的挂载列表
+  │
+  ├─ execute_tool(parameters, query)           Agent 调用 exec 时的入口
+  │    ├─ _apply_profile / build_spec
+  │    ├─ _validate_host_mount
+  │    ├─ _enforce_workspace_quota (phase=pre)
+  │    ├─ client.execute(spec)
+  │    ├─ _enforce_workspace_quota (phase=post)
+  │    └─ _truncate (stdout/stderr)
+  │
+  ├─ execute_spec_payload(spec_payload, ...)   内部入口（其他 loader 调用）
+  ├─ create_session(spec_payload, ...)         显式创建 session
+  ├─ start_managed_process(session_id, ...)    启动 managed process
+  ├─ get_managed_process(session_id, pid)      查询进程状态（pid 默认 'default'）
+  ├─ stop_managed_process(session_id, pid)     单独停止某个 managed process
+  ├─ get_managed_process_websocket_url(...)    返回 WS attach URL
+  │
+  ├─ list_skills() / get_skill(name)           Skill 元数据
+  ├─ create_skill / update_skill / delete_skill  Skill CRUD
+  ├─ scan_skill_directory(path)                扫描目录
+  ├─ list_skill_files / read_skill_file / write_skill_file
+  ├─ preview_skill_zip / install_skill_zip     zip / GitHub 安装
+  │
+  ├─ shutdown() / dispose()                    清理：RPC SHUTDOWN + 进程终止
+  ├─ get_status() / get_sessions() / get_recent_errors()
+  └─ get_system_guidance()                     LLM 系统提示
+```
+
+**Profile 系统**: 4 个内置 Profile（`default` / `offline_readonly` / `network_basic` / `network_extended`），`locked` frozenset 字段不可被 LLM 覆盖。参数合并顺序：Profile defaults → LLM 请求参数 → locked 强制值。
+
+**输出截断**: 默认 4000 字符上限，保留前 60% + 后 40%，中间插入 `[...truncated...]`。
+
+**Skill 挂载合并**: `execute_tool()` 调用时，`build_skill_extra_mounts(query)` 会把当前 pipeline-bound 的所有 skill 的 `package_root` 作为 `extra_mounts` 加入 BoxSpec，挂在 `/workspace/.skills/<name>`。LLM 通过 `activate` 工具显式激活某个 skill 后，工具调用才允许引用这个 skill 的虚拟路径。
+
+### 2.2 BoxRuntimeConnector (`pkg/box/connector.py`, 357 行)
+
+管理与 Box Runtime 的通信连接：
+
+- **本地 stdio**: Unix/macOS 默认路径，fork `python -m langbot_plugin.cli.__init__ box -s --ws-control-port {port}` 子进程（与 plugin runtime 统一走 `lbp` CLI 入口）
+- **本地 subprocess + WS**: Windows 本地（asyncio ProactorEventLoop 不支持 stdio pipe）
+- **远程 WebSocket**: Docker 部署 / `box.runtime.endpoint` 显式配置时，连接 `ws://{host}:{port}/rpc/ws`
+- **同步等待**: `asyncio.Event` + `wait_for(timeout=30s)` 模式确认连接
+- **心跳**: `_heartbeat_loop()` 每 20s 调用 `ping()`，失败仅 DEBUG 日志（断开检测靠 connection close）
+- **重连**: `runtime_disconnect_callback` 由 BoxService 提供，触发 `_reconnect_loop`
+- **INIT 注入**: 连接建立后立即下发当前 `box.*` 配置子树（剔除 `runtime` 私有字段），Runtime 据此初始化 backend
+
+> **历史改进**: 2026-04-16 版本本文档曾列 P0 「Box 无心跳 / 无重连」，已修复（commit `2dfd9d5d`、`c6882cf`、`5029d9c` 等）。
+
+### 2.3 BoxWorkspaceSession 工具 (`pkg/box/workspace.py`, 413 行)
+
+此文件目前提供两类能力：
+
+1. **路径与命令重写工具函数** — `normalize_host_path` / `rewrite_mounted_path` / `unwrap_venv_path` / `rewrite_venv_command` / `infer_workspace_host_path`，被 MCP loader 与 Skill 路径解析共用。
+2. **`BoxWorkspaceSession`** — 围绕 BoxService 的轻量包装，专供 MCP-in-Box 场景使用（管理一个共享 session 的 session_id、构建挂载 payload、stage host 文件到共享 workspace）。
+
+**变化点**: 早期 Skill exec 会为每个 skill 创建独立 BoxWorkspaceSession（独占 session）；当前实现已转为 `extra_mounts` 模式，Skill 不再独占容器，只追加挂载。这部分 wrapping 逻辑已从 native loader 移除。
+
+### 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 [SaaS 阻塞项 S2](./box-issues.md)。
+
+### 2.5 SkillManager (`pkg/skill/manager.py`, 186 行)
+
+```
+SkillManager
+  ├─ initialize()                  调用 reload_skills()
+  ├─ reload_skills()               先从 Box runtime list_skills()，
+  │                                 不可用则回落 data/skills/ 扫描
+  ├─ refresh_skill_from_disk()     单 skill 重新加载
+  ├─ get_skill_by_name(name)
+  └─ get_managed_skills_root()     返回 Box 视角的 skills_root 路径
+```
+
+skill 元数据通过 `parse_frontmatter` 解析 `SKILL.md` 头部（`name` / `description` / `instructions`），不再做整体扫描的代价（典型 < 50 个）。
+
+### 2.6 Skill activation (`pkg/skill/activation.py`, 33 行) + Skill loader 辅助
+
+历史上 skill 通过 LLM 在文本中输出 `[ACTIVATE_SKILL:name]` 标记激活；当前已改为 **Tool Call 机制**：
+
+- `SkillToolLoader` (`pkg/provider/tools/loaders/skill.py`, 157 行) 暴露 `activate` 工具，参数为 skill 名
+- 工具实现调用 `register_activated_skill(query, skill_data)`，将激活态写入 `query.variables['_activated_skills']`
+- 这种 KV-cache-friendly 模式对齐 Claude Code 设计；详见 [box-session-scope.md §4.3](./box-session-scope.md) 的 Tool Call 描述
+
+`activation.py` 现仅保留对外辅助函数（pipeline 层调用 loader 的 `register_activated_skill`）。
+
+---
+
+## 3. SDK 侧模块
+
+### 3.1 BoxRuntime (`box/runtime.py`, 599 行)
+
+核心编排器，管理 session 生命周期与 backend 调度：
+
+```
+Session 生命周期:
+
+  Client EXEC / CREATE_SESSION
+       │
+       ▼
+  _get_or_create_session(spec)
+    ├─ _reap_expired_sessions_locked()   清理 TTL 过期 session
+    ├─ 已存在? → _assert_session_compatible() → 复用
+    ├─ Backend session 失踪? → 重建 (commit c6882cf)
+    └─ 新建? → backend.start_session(spec) → 创建容器
+       │       └─ 应用 spec.extra_mounts （多挂载）
+       ▼
+  execute(spec)
+    ├─ 获取 session lock (每 session 独立)
+    ├─ backend.exec(session, spec)       在容器中执行命令
+    ├─ 更新 last_used_at
+    └─ 超时? → 销毁 session
+       │
+       ▼
+  Session 保持存活直到:
+    ├─ TTL 过期 (默认 300s，下次操作时清理)
+    ├─ 执行超时 (自动销毁)
+    ├─ 客户端 DELETE_SESSION
+    └─ SHUTDOWN
+```
+
+**关键设计**:
+- 每 session 有独立 `asyncio.Lock`，同一 session 内的命令串行执行
+- 每 session 维护 `managed_processes: dict[process_id, _ManagedProcess]`，支持多个长驻进程并存（MCP / 自定义）
+- 全局 `_lock` 保护 `_sessions` dict 的读写
+- 兼容性检查：比较核心 spec 字段，`image` 字段对不支持自定义镜像的 backend（nsjail/E2B）会跳过
+
+**Backend 选择 (`_select_backend`)**: 优先级
+1. 显式 `box.backend` 配置（`docker` / `nsjail` / `e2b`）
+2. `local` (默认) → Docker / Podman / nsjail CLI 顺序探测
+3. `get_status` 调用时若当前 backend 不可用，会尝试重新选择 (commit `e5617c7`)
+
+### 3.2 Backend 系统
+
+#### CLISandboxBackend (`box/backend.py`, 411 行)
+
+Docker / Podman 公共基类：
+
+```
+start_session(spec):
+  1. validate_sandbox_security(spec)
+  2. docker/podman run -d --rm --name <name>
+     --network none (可选)
+     --cpus/--memory/--pids-limit
+     --read-only + --tmpfs /tmp
+     -v <host>:<mount>:<mode>          主挂载
+     -v <extra.host>:<extra.mount>:..  额外挂载 (extra_mounts)
+     <image> sh -lc 'while true; do sleep 3600; done'
+  3. 返回 BoxSessionInfo
+
+exec(session, spec):
+  docker/podman exec -e KEY=VAL <container>
+    sh -lc 'mkdir -p <workdir> && cd <workdir> && <cmd>'
+
+start_managed_process(session, spec):
+  docker/podman exec -i <container>
+    sh -lc 'mkdir -p <cwd> && cd <cwd> && exec <command> <args>'
+  返回 asyncio.subprocess.Process (stdin/stdout PIPE)
+```
+
+容器以 idle 进程启动，实际命令通过 `docker exec` 执行。`--rm` 确保容器退出时自动清理。
+
+**Windows 支持**: backend 内对 Windows 路径处理与 subprocess 调用做了适配（commit `120817a`）。
+
+**孤儿清理**: 启动时枚举 `langbot.box=true` 标签的容器，instance_id 不匹配的强制删除。
+
+#### NsjailBackend (`box/nsjail_backend.py`, 552 行)
+
+轻量级 Linux 沙箱（无容器引擎依赖）：
+
+- 使用 namespace 隔离（user/mount/pid/ipc/uts/cgroup/net）
+- 挂载宿主 `/usr`/`/lib`/`/bin`/`/sbin` 只读 + 选定 `/etc` 条目
+- 每 session 创建独立目录（workspace/tmp/home）
+- 资源限制: cgroup v2 优先，fallback 到 rlimit
+- **CLI 兼容**: 通过 `shutil.which(self._nsjail_bin)` 检测系统安装版 nsjail；不存在时再尝试容器内 nsjail（commit `686fcc0`、`feed530`）
+- **无自定义镜像**: 使用宿主 OS，`image` 字段固定为 `'host'`，兼容性检查跳过 image
+
+#### E2BBackend (`box/e2b_backend.py`, 429 行)
+
+云沙箱后端（commit `75b547f` 引入）：
+
+- 通过 `e2b` SDK 与 E2B 平台通信
+- 配置：`box.e2b.api_key` / `api_url` / `template`
+- 支持 `extra_mounts`（commit `0fea9b1` 同步上传文件）
+- 无本地容器引擎依赖，适合无 Docker 的部署或 SaaS 多租户场景
+- 不支持自定义 image 字段，由 template 控制
+
+### 3.3 Server (`box/server.py`, 508 行)
+
+单端口 aiohttp 服务（默认 5410），通过路径区分（commit `8c71ec5` 合并端口）：
+
+1. **Action RPC** (`/rpc/ws`): `BoxServerHandler` 处理所有 action，包括 `INIT` 配置注入、skill store 操作等
+2. **WS Relay** (`/v1/sessions/{id}/managed-process/ws` 与 `/v1/sessions/{id}/managed-process/{pid}/ws`): 双向桥接 WebSocket ↔ 指定 managed process stdin/stdout
+
+stdio 模式同样会在 5410 启动 aiohttp，专门承担 managed process attach；Action RPC 走 stdin/stdout。
+
+### 3.4 Client (`box/client.py`, 377 行)
+
+`ActionRPCBoxClient` 封装 `Handler.call_action()` 调用：
+
+- 25+ 方法对应 25+ 个 RPC action（exec / session / managed-process / skill / status / shutdown）
+- 错误还原: `_translate_action_error()` 通过字符串前缀匹配还原 SDK 侧异常类型
+- `execute()` timeout = 300s，其他默认 15s
+- `BoxRuntimeClient` 是 ABC，供后续可能的非 RPC 实现复用
+
+包级别 `__init__.py` 显式导出：`BoxRuntimeClient`、`ActionRPCBoxClient`（commit `df9c722`）。
+
+### 3.5 Actions (`box/actions.py`, 34 行)
+
+`LangBotToBoxAction` 枚举共定义 **25 个** action：
+
+| 类别 | Actions |
+|------|---------|
+| 控制 | `INIT`、`HEALTH`、`STATUS`、`GET_BACKEND_INFO`、`SHUTDOWN` |
+| 执行 | `EXEC` |
+| Session | `CREATE_SESSION` / `GET_SESSION` / `GET_SESSIONS` / `DELETE_SESSION` |
+| Managed Process | `START_MANAGED_PROCESS` / `GET_MANAGED_PROCESS` / `STOP_MANAGED_PROCESS` |
+| Skill | `LIST_SKILLS` / `GET_SKILL` / `CREATE_SKILL` / `UPDATE_SKILL` / `DELETE_SKILL` / `SCAN_SKILL_DIRECTORY` / `LIST_SKILL_FILES` / `READ_SKILL_FILE` / `WRITE_SKILL_FILE` / `PREVIEW_SKILL_ZIP` / `INSTALL_SKILL_ZIP` |
+
+### 3.6 Models (`box/models.py`, 331 行)
+
+核心数据模型：
+
+| 模型 | 用途 |
+|------|------|
+| `BoxNetworkMode` | `OFF` / `ON` |
+| `BoxExecutionStatus` | `COMPLETED` / `TIMED_OUT` |
+| `BoxHostMountMode` | `NONE` / `READ_ONLY` / `READ_WRITE` |
+| `BoxManagedProcessStatus` | `RUNNING` / `EXITED` |
+| `BoxMountSpec` | 单条挂载（host_path/mount_path/mode）— **新增** |
+| `BoxSpec` | 执行请求；新增 `extra_mounts: list[BoxMountSpec]`、`persistent`、`workspace_quota_mb` |
+| `BoxProfile` | 4 个内置 Profile + `locked` frozenset |
+| `BoxSessionInfo` | Session 状态（含 backend_name/created_at/last_used_at） |
+| `BoxManagedProcessSpec` | 长驻进程参数（process_id/command/args/env/cwd） |
+| `BoxManagedProcessInfo` | 进程状态（status/exit_code/stderr_preview/attached） |
+| `BoxExecutionResult` | 执行结果（status/exit_code/stdout/stderr/duration_ms） |
+
+`BoxSpec` 校验器: `workdir` 默认继承 `mount_path`；`host_path` 支持 POSIX 和 Windows 路径；设置 `host_path` 时 `workdir` 必须在 `mount_path` 下。
+
+### 3.7 BoxSkillStore (`box/skill_store.py`, 647 行)
+
+新增模块（commit `4ab3502`），把 skill 持久化收归 Box runtime：
+
+```
+BoxSkillStore
+  ├─ list_skills() / get_skill(name)
+  ├─ create_skill(data) / update_skill(name, data) / delete_skill(name)
+  ├─ scan_skill_directory(path)            扫描目录返回候选 skill 包列表
+  ├─ list_skill_files(name, path)          浏览 skill 内文件树
+  ├─ read_skill_file(name, path) / write_skill_file(name, path, content)
+  ├─ preview_skill_zip(zip_bytes, ...)     不落盘预览 zip 内容
+  └─ install_skill_zip(zip_bytes, ...)     解压、校验、复制到 skills_root
+     └─ 支持 source_subdir / target_suffix（commit 1aa043f）
+```
+
+GitHub 安装路径：HTTP 层（`api/http/service/skill.py`）先 `git clone` 拉取，再走 `install_skill_zip` 或 directory 路径。Skill 文件存放于 `box.local.skills_root`（默认 `skills`，相对 `host_root`），容器内对应 `/workspace/.skills/`。
+
+### 3.8 Security (`box/security.py`, 52 行)
+
+`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 [SaaS 阻塞项 S5](./box-issues.md)。
+
+### 3.9 Errors (`box/errors.py`, 33 行)
+
+| 异常类型 | 含义 |
+|----------|------|
+| `BoxError` | 基类 |
+| `BoxValidationError` | spec/参数校验失败 |
+| `BoxBackendUnavailableError` | 无可用 backend |
+| `BoxRuntimeUnavailableError` | Runtime 服务不可用 |
+| `BoxSessionConflictError` | session 已存在但 spec 不兼容 |
+| `BoxSessionNotFoundError` | session 不存在 |
+| `BoxManagedProcessConflictError` | session 已有同名 process |
+| `BoxManagedProcessNotFoundError` | process 不存在 |
+
+---
+
+## 4. 工具系统集成
+
+### 4.1 ToolManager 编排 (`toolmgr.py`)
+
+```
+ToolManager.initialize()
+  ├─ NativeToolLoader      (exec / read / write / edit / glob / grep)
+  ├─ PluginToolLoader      (插件工具)
+  ├─ MCPLoader             (MCP Server 工具)
+  ├─ SkillToolLoader       (activate 工具 — Tool Call 激活)
+  └─ SkillAuthoringToolLoader  (Skill CRUD)
+
+工具调用优先级: native → plugin → mcp → skill → skill_authoring
+```
+
+### 4.2 Native Tools (`native.py`, 846 行)
+
+| 工具 | 是否在 Box 中执行 | 是否访问宿主文件系统 |
+|------|:---:|:---:|
+| `exec`  | 是 | 否 |
+| `read`  | **否** | **是** — 直接 `open()` 宿主文件 |
+| `write` | **否** | **是** — 直接 `open()` 宿主文件 |
+| `edit`  | **否** | **是** — 直接 `open()` 宿主文件 |
+| `glob`  | **否** | **是** — 直接遍历宿主目录 |
+| `grep`  | **否** | **是** — 直接读宿主文件 |
+
+**沙箱边界不对称**: 这是刻意的设计权衡 — `read`/`write`/`edit`/`glob`/`grep` 绕过沙箱以获得性能（避免容器 I/O 开销与跨进程拷贝），但意味着 LLM 可以直接读写 `allowed_mount_roots` 下任何文件。Skill 路径经 `_resolve_host_path()` 重写，禁止穿越 `package_root`。
+
+**exec 的 Skill 分支**: 命令中引用 `/workspace/.skills/<name>` 的 skill 时：
+1. 验证 skill 已激活
+2. 单次 exec 只能引用一个 skill 包
+3. 若 skill 是 Python 项目（有 `requirements.txt` 或 `pyproject.toml`），命令会被 venv bootstrap 包裹（在 skill 挂载点内创建 `.venv`）
+4. 调用 `box_service.execute_tool()` → 走默认 session_id 与已组装好的 `extra_mounts`，**不再为每 skill 起独立 session**
+
+### 4.3 MCP-in-Box (`mcp_stdio.py`, 354 行)
+
+`BoxStdioSessionRuntime` 让 MCP stdio 服务器在 Box 容器中运行，**共享 session、多 process**模式（commit `529088e`）：
+
+```
+initialize()
+  1. 复用/创建共享 session (session_id = _build_box_session_id())
+     - persistent=True，长期保持
+  2. workspace.execute_raw(install_cmd) 安装依赖 (可选)
+  3. 将每个 MCP server 文件 stage 到 /workspace/.mcp/<process_id>/
+  4. workspace.start_managed_process(process_id=<server>)
+  5. websocket_client(ws_url) 通过 WS relay 连接
+  6. ClientSession.initialize() MCP 协议握手
+```
+
+配置 (`MCPServerBoxConfig`): `network='on'` (MCP 服务器通常需要网络)，`host_path_mode='ro'` (默认只读)，`startup_timeout_sec=120` (留时间给 pip install)。
+
+每条 MCP server 是同一 session 中的一个 managed process，独立的 `process_id`、独立 attach URL，互不阻塞。
+
+---
+
+## 5. 启动与生命周期
+
+### 5.1 启动顺序 (`build_app.py`)
+
+```
+BuildAppStage.run(ap)
+  ├─ ... (persistence, models, sessions) ...
+  │
+  ├─ BoxService(ap)
+  ├─ box_service.initialize()
+  │    └─ connector.initialize()
+  │         ├─ [stdio] fork box subprocess
+  │         ├─ [subprocess+WS] Windows 本地
+  │         └─ [remote WS] connect URL
+  │    └─ 启动心跳 _heartbeat_task
+  ├─ ap.box_service = box_service
+  │
+  ├─ ToolManager(ap)
+  ├─ tool_mgr.initialize()
+  │    ├─ NativeToolLoader   (检查 box_service.available)
+  │    ├─ PluginToolLoader
+  │    ├─ MCPLoader          (Box 可用时，stdio MCP 走沙箱)
+  │    └─ SkillAuthoringToolLoader
+  ├─ ap.tool_mgr = tool_mgr
+  │
+  ├─ ... (platform, pipeline) ...
+  ├─ SkillManager.initialize()    (从 Box runtime 加载 skill 列表)
+  └─ ... (RAG, HTTP, plugins) ...
+```
+
+BoxService 在 ToolManager **之前**初始化。ToolManager 创建 loader 时检查 `box_service.available`。
+
+### 5.2 初始化失败处理
+
+```python
+try:
+    await self._runtime_connector.initialize()
+    self._available = True
+except Exception as e:
+    self._available = False
+    logger.warning(f"Box runtime unavailable: {e}")
+```
+
+**静默降级**: Box 初始化失败不会阻止应用启动，仅导致 6 个 native tool、所有 Skill 工具和 MCP-in-Box 工具不暴露给 LLM。与 Plugin 的行为不同（Plugin 失败会抛异常）。
+
+### 5.3 销毁流程
+
+```
+app.dispose()
+  └─ box_service.dispose()
+       ├─ connector.dispose()
+       │    ├─ cancel _heartbeat_task
+       │    ├─ cancel _handler_task / _ctrl_task
+       │    └─ terminate subprocess (SIGTERM)
+       └─ loop.create_task(client.shutdown())
+            └─ RPC SHUTDOWN → Box Runtime 清理所有容器
+```
+
+Box 额外做了 RPC SHUTDOWN 通知 Runtime 主动清理容器，比 Plugin 的直接杀进程更安全。
+
+---
+
+## 6. 配置
+
+### config.yaml (重构后)
+
+```yaml
+box:
+    enabled: true         # 整个 Box 子系统的总开关。设为 false 时：
+                          #  - 不连接远程 Box runtime，不 fork 本地 stdio 子进程
+                          #  - sandbox 工具 (exec/read/write/edit/glob/grep) 不暴露给 LLM
+                          #  - skill 添加/编辑 / GitHub 安装 / 文件写入全部拒绝
+                          #  - stdio 模式的 MCP server 启动时报错（http/sse 模式不受影响）
+                          #  - 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'
+                          # 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
+    local:
+        profile: 'default'
+        image: ''                       # 覆盖 profile 默认 image
+        host_root: './data/box'         # 工作区挂载根，Docker 部署需绝对路径
+        default_workspace: ''           # 默认 '<host_root>/default'
+        skills_root: 'skills'           # Box 管理的 skill 包目录（相对 host_root）
+        allowed_mount_roots:            # 默认 ['<host_root>']
+            - './data/box'
+            - '/tmp'
+        workspace_quota_mb: null        # 配额覆盖，null = 走 profile
+    e2b:
+        api_key: ''                     # 也可走 E2B_API_KEY 环境变量
+        api_url: ''                     # 自托管 E2B 时填写
+        template: ''                    # 默认 template ID
+```
+
+> **重大变更**: 较 2026-04-16 文档，配置结构完全重组（commit `eefdea4`）。原字段 `box.profile` / `box.runtime_url` / `box.shared_host_root` / `box.allowed_host_mount_roots` 全部迁入 `box.local.*` 子表，新增 `box.backend` 与 `box.e2b.*` 配置组。
+
+### docker-compose.yaml
+
+`langbot_box` 服务受 compose profile 控制,默认 `docker compose up` **不会**启动它。需要 sandbox 时:
+
+```bash
+docker compose --profile box up        # 启动 langbot + langbot_box + plugin runtime
+docker compose --profile all up        # 同上
+docker compose up                       # 只起 langbot + plugin runtime (box 关闭)
+```
+
+若不起 `langbot_box`,需要同步在 `data/config.yaml` 中设 `box.enabled: false`(或 langbot 容器 env 加 `BOX__ENABLED=false`),否则 LangBot 会一直尝试连接不存在的 Box runtime 并报错。
+
+```yaml
+# langbot_box 的关键 volume
+volumes:
+  - ${LANGBOT_BOX_ROOT}:${LANGBOT_BOX_ROOT}         # 工作区挂载(源/目标同路径)
+  - /var/run/docker.sock:/var/run/docker.sock       # Docker backend 复用宿主 docker
+```
+
+### 关闭/连接失败时的行为矩阵
+
+`box.enabled = false` 与"启用但连接失败"在用户可观察行为上**完全一致**——都通过 `BoxService.available = False` 表达,只是 `get_status` 多返回 `enabled` 字段供前端区分文案。
+
+| 消费方 | Box 可用 | Box 不可用(disabled 或 failed) |
+|---|---|---|
+| native exec/read/write/edit/glob/grep 工具 | 暴露给 LLM | **不暴露** |
+| `activate` / `register_skill` 工具 | 暴露给 LLM | **不暴露** |
+| stdio MCP server | 在 Box 内启动 | **`_init_stdio_python_server` 抛 RuntimeError** 拒绝;不退化到宿主 stdio |
+| http/sse MCP server | 正常 | 正常(不依赖 Box) |
+| Skill 列表/读取 (`list_skills`/`get_skill`/`read_skill_file`) | 走 Box runtime | 走 LangBot 本地 `data/skills/` 只读 fallback |
+| Skill 创建/编辑/安装/写文件 | 走 Box runtime | **HTTP 400** + 明确错误信息(`_require_box_for_write`) |
+| Pipeline AI 配置中 `box-session-id-template` | 正常生效 | **前端 banner** 提示字段无效 |
+| Pipeline 扩展页 `enable_all_skills` / 绑定 skill | 可编辑 | **前端禁用** + banner |
+| 仪表盘 Box 状态卡片 | 绿点 / "已连接" | 灰点 / "已禁用"(disabled) 或 红点 / "已断开"(failed) |
+
+> 后端拒写的边界条件:如果 `ap.box_service` **完全没装**(老式 dev mode,没经过 BuildAppStage),`_require_box_for_write` 视作 no-op,保留 `data/skills/` 本地路径——以兼容历史测试与最小化设置。生产环境总会装 `ap.box_service`,因此该 fallback 不会被触发。
+
+### Pipeline 配置 (templates/metadata/pipeline/ai.yaml)
+
+`local-agent.config.box-session-id-template` 控制 session 作用域，预设：
+
+- `{launcher_type}_{launcher_id}` — 每个会话 (推荐，默认)
+- `{launcher_type}_{launcher_id}_{sender_id}` — 群聊每个用户
+- `{launcher_type}_{launcher_id}_{conversation_id}` — 每个对话上下文
+- `{query_id}` — 每条消息（完全隔离）
+
+详见 [box-session-scope.md](./box-session-scope.md)。
+
+### REST API
+
+| 端点 | 方法 | 说明 | 前端 |
+|------|------|------|:---:|
+| `/api/v1/box/status` | GET | 可用性、Profile、后端信息 | ✅ 监控页 |
+| `/api/v1/box/sessions` | GET | 活跃 session 列表 | ❌ |
+| `/api/v1/box/errors` | GET | 最近 50 条错误 | ❌ |
+| `/api/v1/skills` 等 | GET/POST/PUT/DELETE | Skill CRUD、文件浏览、zip/GitHub 安装、preview | ✅ Skill 管理页 |
+
+前端 `web/src/app/home/monitoring/components/overview-cards/SystemStatusCards.tsx` 已接入 `/api/v1/box/status`，展示 backend 名称、profile 与活跃 session 数。Sessions 与 errors API 仍未接入。

docs/review/box-issues.md

@@ -0,0 +1,76 @@
+# Box 系统 — SaaS 发布前阻塞项
+
+> 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 |
+
+---
+
+## SaaS 阻塞项
+
+### S1. Box 控制面无认证 — Critical
+
+- **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
+
+- **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。
+
+### S3. 会话资源无界（DoS） — High
+
+- **#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）。
+
+### S4. 工作区配额无内核级限制（TOCTOU） — Med-High
+
+- **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。
+
+### S5. 挂载校验缺口 — Med-High
+
+- **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。
+
+### S6. 容器加固缺失 — Med
+
+- **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
+
+- **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。
+
+### S8. 其他硬化 / 跟进 — Low
+
+- **#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

@@ -0,0 +1,402 @@
+# Box Session Scope Design
+
+> 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)
+
+---
+
+## 0. Implementation Status (2026-05-19)
+
+This document was authored as a design proposal. The current `feat/sandbox` branch
+has shipped the design largely as written:
+
+| Item | Status | Notes |
+|------|--------|-------|
+| `BoxMountSpec` + `BoxSpec.extra_mounts` | ✅ Shipped | SDK `box/models.py` |
+| Docker / nsjail / E2B backends apply extra mounts | ✅ Shipped | Last gap closed by SDK commit `0fea9b1` (E2B) |
+| `box-session-id-template` in `local-agent` pipeline config | ✅ Shipped | `templates/metadata/pipeline/ai.yaml`, default `{launcher_type}_{launcher_id}` |
+| `BoxService.resolve_box_session_id(query)` | ✅ Shipped | `pkg/box/service.py:166` |
+| `BoxService.build_skill_extra_mounts(query)` | ✅ Shipped | `pkg/box/service.py:189` |
+| Skill exec uses unified container + extra mounts | ✅ Shipped | `pkg/provider/tools/loaders/native.py` skill branch |
+| MCP-in-Box uses shared persistent session, multi-process | ✅ Shipped (earlier than originally scoped) | SDK commit `529088e`, LangBot `mcp_stdio.py:_build_box_session_id` |
+| `BoxManagedProcessSpec.process_id` + multi-process per session | ✅ Shipped | `BoxRuntime` keeps `managed_processes: dict[pid, _ManagedProcess]` |
+| Per-tenant / quota integration with templates | ❌ Not started | See [box-tob-analysis.md](./box-tob-analysis.md) |
+
+The "Phase 2 deferred" note in §10 is **out of date** — MCP unification went in on
+the same line. Pipeline-scoped (not user-scoped) MCP container is the realized
+behavior: each pipeline's MCP servers share one `mcp-<pipeline>` session, and
+user exec sessions use the template-derived id.
+
+The remaining open work is multi-tenant overlays (tenant_id in session_id,
+quota counters keyed by tenant), tracked in the toB analysis doc rather than here.
+
+---
+
+## 1. Problems
+
+### 1.1 Default exec: per-message containers
+
+Currently, `BoxService.execute_tool()` sets `session_id = str(query.query_id)` — an
+auto-incrementing integer per incoming message. Every user message creates a new sandbox
+container. Dependencies installed and in-container state are lost between messages.
+
+### 1.2 Three isolated container pools
+
+Default exec, skills, and MCP servers each manage their own containers with
+independent session IDs:
+
+| Path         | Session ID                                    | Container   |
+|--------------|-----------------------------------------------|-------------|
+| Default exec | `str(query_id)` (per message)                 | Ephemeral   |
+| Skill exec   | `skill-{launcher}_{id}-{skill_name}`          | Per skill   |
+| MCP stdio    | `mcp-{server_uuid}`                           | Per server  |
+
+This means a single logical user interaction can spawn 3+ containers that cannot
+share state, see each other's files, or reuse installed dependencies.
+
+### 1.3 Single bind mount limitation
+
+`BoxSpec` currently supports only **one** `host_path` → `mount_path` bind mount.
+This prevents mounting both a default workspace and skill directories into the
+same container.
+
+---
+
+## 2. Concept Model
+
+```
+Platform Message
+  → Query (query_id: int, auto-increment, per message)
+    → Session (launcher_type + launcher_id, per chat window)
+      → Conversation (uuid, per dialogue context within a Session)
+```
+
+| Concept       | Key                                 | Example                    | Scope                        |
+|---------------|-------------------------------------|----------------------------|------------------------------|
+| Query         | `query_id`                          | `42`                       | Single message               |
+| Session       | `launcher_type` + `launcher_id`     | `group_123456`             | Chat window (group or PM)    |
+| Conversation  | `conversation_id` (UUID)            | `a1b2c3d4-...`             | Dialogue context within a Session |
+| Sender        | `sender_id`                         | `789`                      | Individual user              |
+
+Note: in a **group chat**, all users share the same Session (keyed by `group_id`). The
+individual sender is tracked as `sender_id` but does not affect Session/Conversation routing.
+
+---
+
+## 3. Target Scenarios
+
+| #  | Scenario                       | Box Granularity                          | Desired `session_id`                                   |
+|----|--------------------------------|------------------------------------------|---------------------------------------------------------|
+| 1  | Personal assistant             | 1 Box per user, long-lived               | `{launcher_type}_{launcher_id}`                          |
+| 2  | Customer service               | 1 Box per customer, cross-pipeline       | `{launcher_type}_{launcher_id}`                          |
+| 3  | Internal employee tool         | 1 Box per employee                       | `{launcher_type}_{launcher_id}`                          |
+| 4  | Group chat shared assistant    | 1 Box per group                          | `{launcher_type}_{launcher_id}`                          |
+| 5  | Group chat isolated per user   | 1 Box per user within a group            | `{launcher_type}_{launcher_id}_{sender_id}`              |
+| 6  | Teaching (cross-channel)       | 1 Box per student across groups/PMs      | `{sender_id}`                                           |
+| 7  | One-off execution              | 1 Box per message (current behavior)     | `{query_id}`                                            |
+| 8  | Multi-project development      | 1 Box per conversation context           | `{launcher_type}_{launcher_id}_{conversation_id}`        |
+
+No single fixed granularity covers all scenarios. A template-based approach is needed.
+
+---
+
+## 4. Design Overview
+
+Two key changes:
+
+1. **Unified container**: exec, skills, and MCP all share the same container per
+   session scope. No more separate container pools.
+2. **Configurable session scope**: `session_id` is generated from a template with
+   pipeline variables, configurable per pipeline.
+
+### 4.1 Unified Container with Multiple Mounts
+
+A single container per session scope is created on first use. It has:
+
+- **Primary mount**: default workspace at `/workspace` (from `default_host_workspace`)
+- **Skill mounts**: each pipeline-bound skill's `package_root` mounted at
+  `/workspace/.skills/{skill_name}/`
+- **MCP servers**: run as managed processes inside the same container
+
+```
+Container (session_id = "group_123456")
+  /workspace/                          ← default workspace (bind mount, rw)
+  /workspace/.skills/web-search/       ← skill package (bind mount, rw)
+  /workspace/.skills/data-analysis/    ← skill package (bind mount, rw)
+  [managed process: mcp-server-a]      ← MCP server running inside
+  [managed process: mcp-server-b]      ← MCP server running inside
+```
+
+This requires extending `BoxSpec` to support multiple mounts (see §5).
+
+### 4.2 Session ID Template
+
+A new field `box-session-id-template` in the `local-agent` pipeline runner config
+controls the session scope:
+
+```yaml
+# templates/metadata/pipeline/ai.yaml (under local-agent.config)
+- name: box-session-id-template
+  label:
+    en_US: Sandbox Scope
+    zh_Hans: 沙箱作用域
+  description:
+    en_US: >-
+      Determines how sandbox environments are shared. Use variables to
+      control isolation granularity.
+    zh_Hans: >-
+      决定沙箱环境的共享方式。使用变量控制隔离粒度。
+  type: select
+  required: false
+  default: "{launcher_type}_{launcher_id}"
+  options:
+    - value: "{launcher_type}_{launcher_id}"
+      label:
+        en_US: Per chat (Recommended)
+        zh_Hans: 每个会话（推荐）
+    - value: "{launcher_type}_{launcher_id}_{sender_id}"
+      label:
+        en_US: Per user in chat
+        zh_Hans: 会话中每个用户
+    - value: "{launcher_type}_{launcher_id}_{conversation_id}"
+      label:
+        en_US: Per conversation context
+        zh_Hans: 每个对话上下文
+    - value: "{query_id}"
+      label:
+        en_US: Per message (isolated)
+        zh_Hans: 每条消息（完全隔离）
+```
+
+Available template variables (populated by PreProcessor in `query.variables`):
+
+| Variable            | Source                          | Example              |
+|---------------------|---------------------------------|----------------------|
+| `{launcher_type}`   | `query.session.launcher_type`   | `person` / `group`   |
+| `{launcher_id}`     | `query.session.launcher_id`     | `123456`             |
+| `{sender_id}`       | `query.sender_id`               | `789`                |
+| `{conversation_id}` | `conversation.uuid`             | `a1b2c3d4-...`       |
+| `{query_id}`        | `query.query_id`                | `42`                 |
+
+Default `{launcher_type}_{launcher_id}` covers scenarios 1–4 out of the box.
+
+---
+
+## 5. SDK Changes: Multi-Mount BoxSpec
+
+### 5.1 Model Extension
+
+```python
+# box/models.py
+
+class BoxMountSpec(pydantic.BaseModel):
+    """A single bind mount specification."""
+    host_path: str
+    mount_path: str
+    mode: BoxHostMountMode = BoxHostMountMode.READ_WRITE
+
+class BoxSpec(pydantic.BaseModel):
+    # ... existing fields ...
+    host_path: str | None = None              # Primary mount (backward compat)
+    host_path_mode: BoxHostMountMode = BoxHostMountMode.READ_WRITE
+    mount_path: str = DEFAULT_BOX_MOUNT_PATH
+    extra_mounts: list[BoxMountSpec] = []     # NEW: additional mounts
+```
+
+`extra_mounts` is additive — the existing `host_path` / `mount_path` pair remains
+the primary mount for backward compatibility.
+
+### 5.2 Backend: Apply Extra Mounts
+
+```python
+# box/backend.py — CLISandboxBackend.start_session()
+
+# Primary mount (unchanged)
+if spec.host_path is not None and spec.host_path_mode != BoxHostMountMode.NONE:
+    args.extend(['-v', f'{spec.host_path}:{spec.mount_path}:{spec.host_path_mode.value}'])
+
+# Extra mounts (NEW)
+for mount in spec.extra_mounts:
+    if mount.mode != BoxHostMountMode.NONE:
+        args.extend(['-v', f'{mount.host_path}:{mount.mount_path}:{mount.mode.value}'])
+```
+
+Same pattern for nsjail backend.
+
+---
+
+## 6. LangBot Changes
+
+### 6.1 Session ID Resolution
+
+In `BoxService.execute_tool()`:
+
+```python
+# Before:
+spec_payload.setdefault('session_id', str(query.query_id))
+
+# After:
+template = (query.pipeline_config or {}).get('ai', {}) \
+    .get('local-agent', {}).get('box-session-id-template',
+         '{launcher_type}_{launcher_id}')
+variables = query.variables or {}
+session_id = template.format_map(collections.defaultdict(
+    lambda: 'unknown', variables
+))
+spec_payload.setdefault('session_id', session_id)
+```
+
+### 6.2 Skill Exec: Use Same Container
+
+Currently `native.py:_invoke_exec` creates a separate `BoxWorkspaceSession` per
+skill with `host_path=package_root`. Instead:
+
+1. Use the **same session_id** as default exec (from the template).
+2. Pass the skill's `package_root` as an **extra mount** at
+   `/workspace/.skills/{skill_name}/` instead of replacing `/workspace`.
+3. The container already has the default workspace at `/workspace`.
+
+```python
+# native.py — _invoke_exec, skill branch (REVISED)
+
+# Same session_id as default exec
+session_id = resolve_box_session_id(query)
+
+spec_payload = {
+    'cmd': rewritten_command,
+    'workdir': rewritten_workdir,
+    'session_id': session_id,
+    'extra_mounts': [{
+        'host_path': package_root,
+        'mount_path': f'/workspace/.skills/{selected_skill_name}',
+        'mode': 'rw',
+    }],
+}
+result = await self.ap.box_service.execute_spec_payload(spec_payload, query)
+```
+
+The virtual path `/workspace/.skills/{name}` no longer needs rewriting at the
+command level — it maps directly to the bind mount path inside the container.
+
+### 6.3 MCP: Use Same Container
+
+MCP servers should run inside the same container as exec and skills. Changes:
+
+1. `BoxStdioSessionRuntime` uses the pipeline's session_id template instead of
+   `mcp-{server_uuid}`.
+2. MCP server's working directory is a subdirectory (e.g. `/workspace/.mcp/{name}/`).
+3. MCP server's dependencies are mounted or installed into that subdirectory.
+4. The MCP server runs as a managed process inside the shared container.
+
+Since MCP servers start at LangBot boot (not per-query), the session must be
+created eagerly. The container will be kept alive by the managed process
+exemption in TTL reaping (`runtime.py:259`).
+
+**Note**: MCP sessions are pipeline-scoped (not per-launcher), so their session_id
+should be a **fixed identifier per pipeline** rather than the user-facing template.
+This means one shared MCP container per pipeline, with user exec sessions separate.
+
+Alternatively, in a future iteration, MCP managed processes could be launched
+lazily into the user's container on first MCP tool call. This is more complex
+but maximizes sharing. For V1, keeping MCP containers at pipeline scope is
+simpler and more predictable.
+
+---
+
+## 7. Mount Layout Summary
+
+### Default exec (no skills activated)
+
+```
+Container (session_id from template)
+  /workspace/          ← default_host_workspace (rw)
+```
+
+### Exec with activated skills
+
+```
+Container (same session_id)
+  /workspace/                          ← default_host_workspace (rw)
+  /workspace/.skills/web-search/       ← skill package_root (rw)
+  /workspace/.skills/data-analysis/    ← skill package_root (rw)
+```
+
+Extra mounts are **additive** — they are added when the container is first
+created (or on the first exec that references a skill). Since Docker bind
+mounts are specified at container creation time, skills must be known at
+creation time.
+
+**Resolution**: When creating a container, inject `extra_mounts` for **all
+pipeline-bound skills** (from `extensions_preferences`), not just the
+currently activated one. This way any skill can be activated later without
+recreating the container.
+
+### MCP servers (V1: pipeline-scoped)
+
+```
+Container (session_id = "mcp-pipeline-{pipeline_uuid}")
+  /workspace/                    ← MCP shared workspace
+  /workspace/.mcp/server-a/      ← MCP server A files
+  /workspace/.mcp/server-b/      ← MCP server B files
+  [managed process: server-a]
+  [managed process: server-b]
+```
+
+---
+
+## 8. Data Migration
+
+Existing pipelines do not have `box-session-id-template`. The backend uses
+`.get(..., default)` so missing keys fall back to `{launcher_type}_{launcher_id}`.
+This changes behavior from per-message to per-launcher for existing pipelines.
+
+Recommendation: **accept the behavior change** — per-launcher is the more
+intuitive default, and the old per-message behavior was rarely desired.
+
+---
+
+## 9. Cloud Quota Implications
+
+| Scope                                         | Typical concurrent containers |
+|-----------------------------------------------|-------------------------------|
+| `{query_id}` (per message)                    | Many, short-lived             |
+| `{launcher_type}_{launcher_id}` (per chat)    | = active chat count           |
+| `{sender_id}` (per user)                      | = active user count           |
+| `{conversation_id}` (per conversation)        | Between per-chat and per-msg  |
+
+With the unified container model, each scope value maps to exactly **one**
+container (instead of potentially 3+ per-message). This significantly reduces
+resource usage.
+
+Quota enforcement point: `BoxRuntime._get_or_create_session()` in the SDK.
+
+---
+
+## 10. Implementation Phases
+
+### Phase 1: Session scope + skill unification (this PR)
+
+1. **SDK**: Extend `BoxSpec` with `extra_mounts: list[BoxMountSpec]`.
+2. **SDK**: Update Docker/nsjail backends to apply extra mounts.
+3. **LangBot**: Add `box-session-id-template` to `local-agent` YAML metadata
+   and default pipeline config JSON.
+4. **LangBot**: Update `BoxService.execute_tool()` to use template interpolation.
+5. **LangBot**: Update `native.py:_invoke_exec` skill branch to use same
+   session_id + extra mounts instead of separate `BoxWorkspaceSession`.
+6. **LangBot**: On container creation, inject extra mounts for all
+   pipeline-bound skills.
+7. **Frontend**: No code change — `DynamicFormComponent` renders `select` fields.
+8. **Tests**: Unit tests for template interpolation and multi-mount specs.
+
+### Phase 2: MCP unification (future)
+
+1. Refactor `BoxStdioSessionRuntime` to use pipeline-scoped shared container.
+2. MCP servers become managed processes in the shared container.
+3. Support multiple concurrent managed processes per container.
+
+MCP unification is deferred because it requires changes to the managed process
+model (currently 1 managed process per session) and has startup ordering
+concerns (MCP servers start at boot, before any user query determines
+a session_id).

docs/review/box-test-coverage.md

@@ -0,0 +1,122 @@
+# Box 系统测试覆盖分析
+
+> 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)
+
+---
+
+## 1. 测试文件清单
+
+### LangBot 仓库
+
+| 文件 | 行数 | CI 运行 | 覆盖范围 |
+|------|------|---------|---------|
+| `tests/unit_tests/box/test_box_connector.py` | 106 | 是 | Connector 传输决策、WS relay URL、dispose、心跳/重连 |
+| `tests/unit_tests/box/test_box_service.py` | 1224 | 是 | Service 核心逻辑（最全面） |
+| `tests/unit_tests/box/test_workspace.py` | 147 | 是 | WorkspaceSession 路径重写、payload 构建 |
+| `tests/unit_tests/provider/test_mcp_box_integration.py` | 707 | 是 | MCP Box 配置、路径重写、payload、shared-session/multi-process、runtime info |
+| `tests/unit_tests/provider/test_localagent_sandbox_exec.py` | 444 | 是 | LocalAgent exec 流程、流式、Skill 激活 (Tool Call) |
+| `tests/unit_tests/provider/test_tool_manager_native.py` | 249 | 是 | ToolManager 路由、native tool CRUD、路径穿越、6 工具暴露 |
+| `tests/unit_tests/provider/test_skill_tools.py` | 582 | 是 | Skill 管理、Tool Call 激活、路径、authoring CRUD |
+| `tests/unit_tests/test_skill_service.py` | 396 | 是 | HTTP service：skill CRUD、zip/GitHub install、文件浏览 |
+| `tests/unit_tests/test_paths.py` | 23 | 是 | paths 工具 |
+| `tests/unit_tests/test_preproc.py` | 134 | 是 | PreProcessor 注入 session 变量、bound skill 解析 |
+| `tests/unit_tests/pipeline/test_chat_handler_logging.py` | 78 | 是 | Chat handler 日志相关回归 |
+| `tests/integration_tests/box/test_box_integration.py` | 329 | **否** | 真实容器执行、超时、网络隔离 |
+| `tests/integration_tests/box/test_box_mcp_integration.py` | 368 | **否** | Managed process、WS attach、shared-session 清理 |
+
+### SDK 仓库
+
+| 文件 | 行数 | CI 运行 | 覆盖范围 |
+|------|------|---------|---------|
+| `tests/box/test_backend_selection.py` | 255 | 是 | 显式 backend / local 模式探测顺序 / 配置变更触发 reselect |
+| `tests/box/test_nsjail_backend.py` | 452 | 是 | nsjail 可用性、安装版 CLI vs 容器内 CLI、session、arg 构建、资源限制 |
+| `tests/box/test_e2b_backend.py` | 482 | 是 | E2B SDK mock、session 生命周期、extra_mounts 同步 |
+| `tests/box/test_skill_store.py` | 88 | 是 | zip preview/install、基础 file CRUD |
+
+**总计**: 17 个测试文件, ~6,500 行测试代码; 其中 2 个集成测试（约 700 行）在 CI 中不运行。
+
+> 较 2026-04-16 版增加：`test_skill_service.py`、`test_paths.py`、`test_preproc.py`、`test_chat_handler_logging.py` (LangBot)，`test_backend_selection.py`、`test_e2b_backend.py`、`test_skill_store.py` (SDK)。`test_nsjail_backend.py` 增加 CLI 兼容性 case (commit `feed530`)。
+
+---
+
+## 2. 覆盖良好的区域
+
+| 区域 | 质量 | 说明 |
+|------|------|------|
+| BoxRuntime session 管理 | 优秀 | session 复用、冲突检测、TTL 配置、消失 session 重建 |
+| BoxService Profile 系统 | 优秀 | 4 个内置 Profile、locked/unlocked 字段、timeout clamp |
+| BoxService host mount 安全 | 优秀 | allowed_mount_roots、disallowed_roots、shared host root |
+| BoxService workspace quota | 优秀 | 前置/后置配额检查、超额清理 |
+| BoxService 输出截断 | 优秀 | 短/精确边界/长输出、独立 stderr |
+| BoxService 可观测性 | 优秀 | 状态报告、error ring buffer、buffer 上限 |
+| BoxService session 模板 | 良好 | `resolve_box_session_id` + `build_skill_extra_mounts` 在 service / native / mcp 三处都有覆盖 |
+| RPC client/server 协议 | 优秀 | execute/get_sessions/delete/create/conflict error |
+| BoxRuntimeConnector | 良好 | local/remote 模式、Docker 平台、relay URL、心跳与重连回调 |
+| BoxWorkspaceSession | 良好 | payload 构建、managed process 路径重写、stage host file |
+| BoxHostMountMode.NONE | 良好 | 枚举校验、workdir 约束 |
+| NsjailBackend | 良好 | 可用性、安装版 vs 容器内、session 生命周期、arg 构建、资源限制 |
+| E2BBackend | 良好 | mock SDK、session/extra_mounts 同步 |
+| Backend selection | 良好 | 显式 backend 优先级、local 探测顺序、配置变更触发 reselect |
+| MCP Box 集成 | 良好 | config model、路径重写、payload、shared-session 多 process |
+| Native tool loader | 良好 | 6 工具（exec/read/write/edit/glob/grep）、路径穿越拦截 |
+| LocalAgent exec 流程 | 良好 | 完整 tool call 循环、流式、system prompt 注入、Tool Call 激活 |
+| Skill 系统 | 良好 | 加载、Tool Call 激活、marker、路径解析、authoring CRUD、HTTP service |
+
+---
+
+## 3. 覆盖缺失的区域
+
+### 3.1 零测试 / 严重不足
+
+| 区域 | 源文件 | 影响 |
+|------|--------|------|
+| **`security.py`** | SDK `box/security.py` (52 行) | `validate_sandbox_security()` 无任何测试。阻止 `/etc`/`/proc`/Docker socket 等危险挂载的安全函数从未被验证 |
+| **`policy.py`** | `pkg/box/policy.py` (98 行) | 三层安全策略无测试（也是死代码） |
+| **`skill_store.py` 边缘场景** | SDK `box/skill_store.py` (647 行) vs 测试 88 行 | GitHub 安装路径、`source_subdir` / `target_suffix` 组合、损坏 zip、文件冲突等场景未覆盖 |
+
+### 3.2 未测试的关键路径
+
+| 区域 | 说明 |
+|------|------|
+| **Session TTL 过期** | 测试配置了 `session_ttl_sec` 但从未推进时间验证过期清理 |
+| **并发 session 访问** | 无并发 exec / 并发创建 / race condition 测试 |
+| **Container backend (Docker)** | 仅通过集成测试覆盖（CI 不运行），单元测试全用 FakeBackend |
+| **E2B 真实 sandbox** | 单测全是 mock，未对接真实 E2B API |
+| **BoxRuntime shutdown()** | 在 test cleanup 中调用但未验证行为 |
+| **BoxServerHandler 错误路径** | 畸形请求、未知 action 类型 |
+| **WS relay** | 仅在集成测试中覆盖（CI 不运行） |
+| **NsjailBackend managed process** | 完全未测试 |
+| **MCP stdio 完整生命周期** | 依赖安装 → 进程启动 → 健康检查 → 多 process 并发 → 重试 |
+| **BoxService start/stop_managed_process** | 单 process 流转有单测，多 process 互不阻塞主要靠集成测试 |
+| **重连指数退避** | connector 单测覆盖回调接线，未实际跑完整重连周期 |
+
+### 3.3 边缘情况缺失
+
+| 区域 | 说明 |
+|------|------|
+| BoxSpec 校验 | 无效 session_id 格式、超长命令、env 特殊字符 |
+| BoxSpec.extra_mounts | 重复 mount_path、与 host_path 冲突、绝对 vs 相对路径 |
+| BoxExecutionResult | 仅 COMPLETED 和 TIMED_OUT，无 ERROR 状态测试 |
+| 多后端 fallback | local 模式探测顺序仅靠 mock，无真实 Docker 不可用 → nsjail 真机 fallback 测试 |
+| Profile YAML 加载 | 测试用硬编码字符串，未从真实 config.yaml 加载 |
+| INIT 配置变更触发 backend 重建 | 单测仅在初始化场景验证 |
+
+---
+
+## 4. 集成测试 vs CI 的差距
+
+CI 仅运行 `tests/unit_tests/`，以下场景**从未在自动化中验证**:
+
+- 真实容器的创建/执行/销毁
+- 容器网络隔离（`--network none`）
+- 容器资源限制生效（cpus/memory/pids_limit）
+- Managed process 的 WS 双向 I/O
+- 多 process 同 session 并发 I/O
+- 孤儿容器清理
+- Session 删除清理容器
+- 进程退出检测
+- E2B 真实 sandbox 行为
+
+**建议**: 在 CI 中加一个可选的 Docker-in-Docker 集成测试 stage，至少覆盖核心执行路径（exec / MCP attach / session 销毁）。

docs/review/box-tob-analysis.md

@@ -0,0 +1,167 @@
+# Box 系统 toB 商业化分析
+
+> 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)
+
+---
+
+## 1. 现有优势
+
+| 能力 | toB 价值 | 代码位置 |
+|------|---------|---------|
+| **沙箱隔离执行** | 企业安全运行不受信代码的基础能力 | SDK `box/backend.py` |
+| **多后端支持** | 适配不同企业容器基础设施 (Podman/Docker/nsjail/E2B) | SDK `box/runtime.py` `_select_backend()` |
+| **E2B 云沙箱** | SaaS / 无 Docker 部署的兜底执行环境 | SDK `box/e2b_backend.py` |
+| **连接自愈** | 心跳 + 自动重连，单点 Box runtime 故障可恢复 | `pkg/box/connector.py` `_heartbeat_loop`, `pkg/box/service.py` `_reconnect_loop` |
+| **Profile + locked 字段** | 运维锁定安全边界，LLM/用户无法绕过 | `pkg/box/service.py`, SDK `box/models.py` |
+| **资源限制** | CPU/内存/PID 数限制防止资源滥用 | SDK `backend.py` `--cpus/--memory/--pids-limit` |
+| **Workspace quota** | 磁盘用量控制 | `pkg/box/service.py` `_enforce_workspace_quota` |
+| **静默降级** | Box 不可用不影响其他功能，降低部署门槛 | `pkg/box/service.py:78` `_available=False` |
+| **孤儿容器清理** | 防止泄漏的容器持续占用资源 | SDK `backend.py` `cleanup_orphaned_containers` |
+| **网络隔离** | `--network none` 防止数据外泄 | SDK `backend.py` start_session |
+| **只读根文件系统** | `--read-only` 防止容器被持久篡改 | SDK `backend.py` start_session |
+| **Host path 白名单** | `allowed_host_mount_roots` 限制可挂载目录 | `pkg/box/service.py` `_validate_host_mount` |
+
+---
+
+## 2. toB 差距分析
+
+### 2.1 安全与合规
+
+| 维度 | 现状 | toB 要求 | 优先级 |
+|------|------|---------|--------|
+| **WS relay 认证** | 无认证，任何人可 attach | 至少 token 认证 | **P0** |
+| **安全策略** | policy.py 是死代码，实际无细粒度控制 | 工具级 allow/deny、沙箱模式控制 | **P0** |
+| **审计日志** | 仅内存中 50 条 `_recent_errors` | 持久化审计：谁何时执行了什么、结果如何 | **P0** |
+| **Host path 校验** | 黑名单策略，`/` 未拦截 | 白名单策略，默认拒绝 | **P1** |
+| **数据驻留** | 无控制 | GDPR / 等保要求的数据隔离 | **P2** |
+
+### 2.2 多租户
+
+| 维度 | 现状 | toB 要求 | 优先级 |
+|------|------|---------|--------|
+| **租户隔离** | 无租户概念 | BoxSpec/Profile 绑定 tenant_id | **P0** |
+| **RBAC** | 仅 token 认证 | admin/operator/viewer 角色权限 | **P0** |
+| **资源配额** | 单一 workspace quota | 每租户 CPU 时间/内存/并发/执行次数配额 | **P1** |
+| **Session 隔离** | 所有 session 共享 dict | 按租户分区，互不可见 | **P1** |
+
+### 2.3 可靠性
+
+| 维度 | 现状 | toB 要求 | 优先级 |
+|------|------|---------|--------|
+| **连接恢复** | 已实现：20s 心跳 + `_reconnect_loop` 指数退避 | 已满足基本要求 | 已有 |
+| **Session 清理** | 机会性（仅新建时触发） | 定时清理 + 独立 reaper | **P1** |
+| **水平扩展** | 单 Box Runtime 实例 | 多实例负载均衡（按 tenant 路由） | **P1** |
+| **优雅降级** | 已有（_available=False） | 已满足基本要求 | 已有 |
+| **Backend 自愈** | 已实现：`get_status` 时若 backend 不可用会重新选择 | 已满足基本要求 | 已有 |
+
+### 2.4 可观测性
+
+| 维度 | 现状 | toB 要求 | 优先级 |
+|------|------|---------|--------|
+| **监控指标** | 无 Prometheus metrics | session 数/执行延迟/资源用量/错误率 | **P1** |
+| **结构化日志** | Python logging, 无结构化 | JSON 格式日志，含 trace_id/tenant_id | **P1** |
+| **前端面板** | 监控页接入 `/api/v1/box/status`（backend 名 + 活跃 session 数）；`sessions` / `errors` 仍未接入 | 完整状态面板 + 历史错误/审计列表 | **P2** |
+
+---
+
+## 3. SaaS 部署架构建议
+
+### 3.1 方案 A: 共享 Box Runtime Pool (快速上线)
+
+```
+LangBot Instance ──> Box Runtime (共享)
+                       ├─ tenant_id 标签隔离
+                       ├─ Redis 配额计数器
+                       └─ Container labels: langbot.tenant_id=xxx
+```
+
+- **优点**: 改动最小，加 tenant_id 到 BoxSpec/labels 即可
+- **缺点**: 容器引擎共享，安全隔离弱
+
+### 3.2 方案 B: 每租户 K8s Namespace + gVisor (推荐中期)
+
+```
+LangBot ──> K8s API
+              ├─ namespace: tenant-xxx
+              │    ├─ RuntimeClass: gVisor (runsc)
+              │    ├─ ResourceQuota
+              │    └─ NetworkPolicy
+              └─ namespace: tenant-yyy
+                   └─ ...
+```
+
+- **优点**: 强隔离（namespace + gVisor），原生 K8s 配额
+- **缺点**: 需要重写 backend 为 K8s Job，部署复杂度高
+
+### 3.3 方案 C: K8s Job 直接编排 (长期)
+
+```
+LangBot ──> K8s Job per execution
+              ├─ 每次执行创建 Job
+              ├─ Pod Security Standards
+              ├─ 自动调度和资源分配
+              └─ Job TTL Controller 自动清理
+```
+
+- **优点**: 最强隔离，天然水平扩展
+- **缺点**: 冷启动延迟，架构重写
+
+**推荐演进路径**: A → B → C
+
+---
+
+## 4. 配额体系建议
+
+### 三层配额
+
+| 层 | 实现 | 作用 |
+|----|------|------|
+| **内核层** | Docker `--cpus`/`--memory`/`--storage-opt` | 硬性资源上限，不可绕过 |
+| **应用层** | Redis 原子计数器 | 并发 session 数/执行次数/CPU 时间预算 |
+| **计费层** | 月度聚合 | 按租户计费（session-hours/execution-count） |
+
+### Profile 与套餐映射
+
+| 套餐 | Profile | locked 字段 | 配额 |
+|------|---------|------------|------|
+| Free | `offline_readonly` | network, host_path_mode, rootfs | 10 exec/天, 0.5 CPU, 256MB |
+| Pro | `default` | (无) | 100 exec/天, 1 CPU, 512MB |
+| Enterprise | `network_extended` | (按需) | 无限, 2 CPU, 1GB, 自定义镜像 |
+
+### TOCTOU 配额修复
+
+当前 `_enforce_workspace_quota` 的 TOCTOU 问题可通过两种方式解决:
+
+1. **预留式配额** (应用层): Redis `INCRBY` 预扣额度 → 执行 → 成功则扣减，失败则回滚
+2. **内核级限制** (Docker): `--storage-opt size=500m` 直接限制容器可写层大小
+
+---
+
+## 5. 优先实施路线
+
+### Phase 1 (2-4 周): 安全基线
+
+- [ ] WS relay 加 token 认证
+- [ ] 接入或删除 policy.py
+- [x] ~~Box 加重连和心跳~~（已完成，见 [box-issues.md 已解决](./box-issues.md)）
+- [ ] 审计日志持久化（至少写文件/数据库）
+- [ ] `security.py` 加 `/` 拦截，考虑白名单
+- [ ] INIT 与 backend 初始化顺序整理（避免 backend 在配置到达前实例化）
+
+### Phase 2 (4-8 周): 多租户基础
+
+- [ ] BoxSpec 加 `tenant_id` 字段
+- [ ] 容器 labels 加 tenant 标识
+- [ ] Redis 配额计数器（并发/执行次数/时间）
+- [ ] RBAC 基础框架
+- [ ] 定时 session reaper
+
+### Phase 3 (8-16 周): 生产就绪
+
+- [ ] Prometheus metrics exporter
+- [ ] 前端 Box 状态面板
+- [ ] K8s backend 支持 (方案 B)
+- [ ] 结构化日志 (JSON, trace_id)
+- [ ] 水平扩展支持

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

@@ -0,0 +1,222 @@
+# Box Runtime vs Plugin Runtime: 连接架构对比
+
+> 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)
+
+---
+
+## 1. 总体差异
+
+| 维度 | Plugin Runtime | Box Runtime |
+|------|---------------|-------------|
+| **继承关系** | `PluginRuntimeConnector(ManagedRuntimeConnector)` | `BoxRuntimeConnector`（独立类） |
+| **传输分支** | 3 条 (Docker/WS, Win32/subprocess+WS, Unix/stdio) | 3 条 (本地 stdio, Win32/subprocess+WS, 远程 WS) |
+| **心跳** | 20s ping loop | 20s ping loop（`_heartbeat_loop`） |
+| **重连** | WS 模式: sleep 3s → re-initialize | 由 BoxService `_reconnect_loop` 处理，指数退避 |
+| **Handler 类型** | `RuntimeConnectionHandler` (1132 行, 25+ action) | 基础 `Handler` + `BoxServerHandler`（SDK 端 25 action） |
+| **Client 抽象** | Handler 即 API | 独立 `ActionRPCBoxClient` 封装 Handler |
+| **启用/禁用** | `is_enable_plugin` 开关 | 无开关（可用/不可用由初始化结果决定） |
+| **初始化失败** | 异常上抛 | 静默降级 `_available=False` |
+| **Shutdown** | 直接杀进程 | RPC SHUTDOWN → 清理容器 → 再杀进程 |
+
+---
+
+## 2. 传输决策
+
+### Plugin: 3-路决策
+
+```python
+# pkg/plugin/connector.py:106-165
+if get_platform() == 'docker' or use_websocket_to_connect_plugin_runtime():
+    # Docker/WS → ws://langbot_plugin_runtime:5400/control/ws
+elif get_platform() == 'win32':
+    # Windows → 起子进程(无 pipe) + ws://localhost:5400/control/ws
+else:
+    # Unix/Mac → StdioClientController(python -m langbot_plugin.cli rt -s)
+```
+
+### Box: 3-路决策
+
+```python
+# pkg/box/connector.py
+if self._uses_websocket():
+    if platform.get_platform() == 'win32' and not self.configured_runtime_url:
+        await self._start_subprocess_then_ws()  # subprocess + ws://localhost:5410/rpc/ws
+    else:
+        await self._connect_remote_ws()         # ws://{host}:5410/rpc/ws
+else:
+    await self._start_local_stdio()             # StdioClientController
+```
+
+> 历史：2026-04-16 版本本文档曾把 Box 描述为 2 路决策（缺 Windows 分支）。现已对齐 Plugin 的 3 路设计。
+
+### 决策矩阵
+
+| 环境 | Plugin | Box |
+|------|--------|-----|
+| Docker | WS → `:5400` | WS → `:5410/rpc/ws` |
+| `--standalone-box` | N/A | WS → `localhost:5410/rpc/ws` |
+| Windows 非 Docker | subprocess + WS (`:5400`) | subprocess + WS (`localhost:5410/rpc/ws`) |
+| Unix/Mac 非 Docker | stdio | stdio |
+| 手动配置 URL | 通过配置项 | WS → 用户配置的 URL |
+
+---
+
+## 3. 连接建立
+
+### 同步模式差异
+
+**Plugin**: `new_connection_callback` 内直接 ping + await handler_task，`initialize()` 通过 `create_task()` 异步启动，不阻塞等待连接。
+
+**Box**: 使用 `asyncio.Event` + `wait_for(timeout=30s)` 模式，`initialize()` 同步等待连接成功或超时。
+
+### Box stdio 路径
+
+```
+connector._start_local_stdio()
+  ├─ connected = asyncio.Event()
+  ├─ ctrl = StdioClientController(python, ['-m', 'langbot_plugin.cli.__init__', 'box', '-s', '--ws-control-port', N])
+  ├─ _ctrl_task = create_task(ctrl.run(callback))
+  │    callback:
+  │      handler = Handler(connection)          ← 基础 Handler, 无 disconnect_callback
+  │      client.set_handler(handler)
+  │      _handler_task = create_task(handler.run())
+  │      call_action(PING, {})                  ← 握手, timeout=15s
+  │      connected.set()                        ← 通知外层
+  │      await _handler_task                    ← 阻塞直到断开
+  └─ await wait_for(connected.wait(), 30s)      ← 同步等待
+```
+
+### Plugin stdio 路径
+
+```
+connector.initialize()
+  ├─ ctrl = StdioClientController(python, ['-m', 'langbot_plugin.cli', 'rt', '-s'])
+  ├─ task = ctrl.run(callback)
+  │    callback:
+  │      disconnect_callback:
+  │        [WS] → runtime_disconnect_callback → 重连
+  │        [stdio] → 仅日志, 不重连
+  │      handler = RuntimeConnectionHandler(conn, disconnect_cb, ap)
+  │      create_task(handler.run())
+  │      handler.ping()                         ← 握手, timeout=10s
+  │      await handler_task                     ← 阻塞直到断开
+  ├─ create_task(heartbeat_loop())              ← 20s ping loop
+  └─ create_task(task)                          ← 不等待连接
+```
+
+---
+
+## 4. 心跳与重连
+
+### 心跳
+
+| 维度 | Plugin | Box |
+|------|--------|-----|
+| 有心跳? | 是 | 是（`connector.py` `_heartbeat_loop`） |
+| 间隔 | 20s | 20s |
+| 失败处理 | 仅 DEBUG 日志，不触发重连 | 仅 DEBUG 日志，依赖 connection close 触发重连 |
+| 生命周期 | 整个应用生命周期 | 连接建立后启动；`dispose()` 时 cancel |
+
+### 重连
+
+| 维度 | Plugin | Box |
+|------|--------|-----|
+| Docker/WS 断开 | `runtime_disconnect_callback` → sleep 3s → re-initialize | `runtime_disconnect_callback` → `BoxService._reconnect_loop()`（指数退避） |
+| WS 连接失败 | 同上 | 同上；初次失败时 `_available=False`，重连成功后恢复 |
+| stdio 断开 | 仅日志，不重连 | 接同样回调；stdio 重连需重新 fork 子进程 |
+| 重连退避 | 固定 3s，无 backoff | 指数退避 |
+
+> 历史：2026-04-16 版本本文档曾把心跳与重连标记为 Box 缺失。这两项已在 commit `2dfd9d5d` / `c6882cf` / `5029d9c` 等修复（详见 [box-issues.md 已解决](./box-issues.md)）。
+
+---
+
+## 5. 共享 IO 层
+
+两者复用同一套 SDK IO 基础设施：
+
+```
+Handler ← ABC                              (runtime/io/handler.py)
+  ├── RuntimeConnectionHandler              (Plugin 用, LangBot 侧)
+  ├── ControlConnectionHandler              (Plugin 用, SDK 侧)
+  ├── BoxServerHandler                      (Box 用, SDK 侧)
+  └── 匿名 Handler 实例                     (Box 用, LangBot 侧)
+
+Connection ← ABC
+  ├── StdioConnection    (stdio: 16KB chunks, 应用层分帧协议)
+  └── WebSocketConnection (WS: 64KB chunks, 原生 WS 分帧)
+
+Controller ← ABC
+  ├── StdioClientController    (fork 子进程, pipe stdin/stdout)
+  ├── StdioServerController    (接管当前进程 stdin/stdout)
+  ├── WebSocketClientController (连接 WS 服务端)
+  └── WebSocketServerController (监听 WS 端口)
+```
+
+共享的核心机制：
+- `call_action()` / `call_action_generator()` — RPC 调用/流式调用
+- `ActionRequest` / `ActionResponse` — 请求/响应协议
+- `seq_id` 关联 — 并发请求复用单连接
+- `CommonAction.PING` — 两者都用于初始握手
+- 文件传输 (`send_file`) — Plugin 用，Box 不用
+
+---
+
+## 6. 端口方案
+
+| 服务 | Plugin | Box |
+|------|--------|-----|
+| Action RPC (stdio) | stdin/stdout | stdin/stdout |
+| Action RPC (WS) | `:5400` | `:5410/rpc/ws` |
+| 辅助服务 | debug WS `:5401` | managed process WS relay `:5410/v1/sessions/{id}/managed-process/ws` |
+
+**Box 特点**: 单端口 aiohttp 服务（默认 5410），通过路径区分 Action RPC 和 managed process relay。即使在 stdio 模式，也在 `:5410` 启动 aiohttp 用于 managed process attach。Plugin 在 stdio 模式不开额外端口。
+
+---
+
+## 7. 销毁对比
+
+### Plugin
+
+```python
+dispose():
+  if stdio: ctrl.process.terminate()
+  _dispose_subprocess()         # Windows 子进程
+  heartbeat_task.cancel()
+```
+
+### Box
+
+```python
+connector.dispose():
+  _handler_task.cancel()
+  _ctrl_task.cancel()
+  _subprocess.terminate()
+
+service.dispose():
+  connector.dispose()
+  loop.create_task(client.shutdown())   # RPC SHUTDOWN → 清理所有容器
+```
+
+Box 的 RPC SHUTDOWN 确保容器被正确停止，不会成为孤儿。Plugin 直接杀进程。
+
+---
+
+## 8. 改进建议
+
+### P0
+
+1. **两者都加 WS 认证**: 至少 token 认证（INIT 时下发，连接时校验）
+
+### P1
+
+2. **考虑 Box 继承 ManagedRuntimeConnector**: 复用 `_start_runtime_subprocess` / `_wait_until_ready` / `_dispose_subprocess`，减少重复代码
+3. **Plugin 重连加退避**: 固定 3s 无 backoff 可能造成日志洪水，建议向 Box 的指数退避看齐
+4. **统一连接管理模式**: Event-based (Box) vs direct-await (Plugin)，考虑收敛为一种
+
+### 已完成（自上一轮）
+
+- ~~Box 加重连~~（commit `2dfd9d5d`）
+- ~~Box 加心跳~~（20s loop 与 Plugin 一致）
+- ~~Box 加 Windows 支持~~（commit `120817a` / `fafb7a4`）

pyproject.toml

@@ -1,6 +1,6 @@
 [project]
 name = "langbot"
-version = "4.9.7"
+version = "4.10.0-beta.1"
 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==0.3.11",
+    "langbot-plugin==0.4.0b1",
     "asyncpg>=0.30.0",
     "line-bot-sdk>=3.19.0",
     "matrix-nio>=0.25.2",
@@ -223,4 +223,3 @@ skip-magic-trailing-comma = false
 
 # Like Black, automatically detect the appropriate line ending.
 line-ending = "auto"
-

src/langbot/__init__.py

@@ -1,3 +1,3 @@
 """LangBot - Production-grade platform for building agentic IM bots"""
 
-__version__ = '4.9.7'
+__version__ = '4.10.0-beta.1'

src/langbot/__main__.py

@@ -5,6 +5,8 @@ import argparse
 import sys
 import os
 
+from langbot.pkg.utils import paths
+
 # ASCII art banner
 asciiart = r"""
  _                   ___      _   
@@ -27,6 +29,12 @@ async def main_entry(loop: asyncio.AbstractEventLoop):
         help='Use standalone plugin runtime / 使用独立插件运行时',
         default=False,
     )
+    parser.add_argument(
+        '--standalone-box',
+        action='store_true',
+        help='Use standalone box runtime / 使用独立 Box 运行时',
+        default=False,
+    )
     parser.add_argument('--debug', action='store_true', help='Debug mode / 调试模式', default=False)
     args = parser.parse_args()
 
@@ -35,6 +43,11 @@ async def main_entry(loop: asyncio.AbstractEventLoop):
 
         platform.standalone_runtime = True
 
+    if args.standalone_box:
+        from langbot.pkg.utils import platform
+
+        platform.standalone_box = True
+
     if args.debug:
         from langbot.pkg.utils import constants
 
@@ -87,7 +100,7 @@ def main():
     # Set up the working directory
     # When installed as a package, we need to handle the working directory differently
     # We'll create data directory in current working directory if not exists
-    os.makedirs('data', exist_ok=True)
+    os.makedirs(paths.get_data_root(), exist_ok=True)
 
     loop = asyncio.new_event_loop()
 

src/langbot/pkg/api/http/controller/groups/box.py

@@ -0,0 +1,22 @@
+from __future__ import annotations
+
+from .. import group
+
+
+@group.group_class('box', '/api/v1/box')
+class BoxRouterGroup(group.RouterGroup):
+    async def initialize(self) -> None:
+        @self.route('/status', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            status = await self.ap.box_service.get_status()
+            return self.success(data=status)
+
+        @self.route('/sessions', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            sessions = await self.ap.box_service.get_sessions()
+            return self.success(data=sessions)
+
+        @self.route('/errors', methods=['GET'], auth_type=group.AuthType.USER_TOKEN)
+        async def _() -> str:
+            errors = self.ap.box_service.get_recent_errors()
+            return self.success(data=errors)

src/langbot/pkg/api/http/controller/groups/extensions.py

@@ -0,0 +1,52 @@
+from __future__ import annotations
+
+import asyncio
+import quart
+
+from .. import group
+
+
+@group.group_class('extensions', '/api/v1/extensions')
+class ExtensionsRouterGroup(group.RouterGroup):
+    """Unified API for installed extensions (plugins, MCP servers, skills)."""
+
+    async def initialize(self) -> None:
+        @self.route('', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _() -> quart.Response:
+            plugins, mcp_servers, skills = await asyncio.gather(
+                self.ap.plugin_connector.list_plugins(),
+                self.ap.mcp_service.get_mcp_servers(contain_runtime_info=True),
+                self.ap.skill_service.list_skills(),
+                return_exceptions=True,
+            )
+
+            def _sort_key(item: dict) -> str:
+                if item['type'] == 'plugin':
+                    return (
+                        item['plugin']
+                        .get('manifest', {})
+                        .get('manifest', {})
+                        .get('metadata', {})
+                        .get('name', '')
+                        .lower()
+                    )
+                if item['type'] == 'mcp':
+                    return (item['server'].get('name') or '').lower()
+                if item['type'] == 'skill':
+                    return (item['skill'].get('display_name') or item['skill'].get('name') or '').lower()
+                return ''
+
+            extensions: list[dict] = []
+            if isinstance(plugins, list):
+                for plugin in plugins:
+                    extensions.append({'type': 'plugin', 'plugin': plugin})
+            if isinstance(mcp_servers, list):
+                for server in mcp_servers:
+                    extensions.append({'type': 'mcp', 'server': server})
+            if isinstance(skills, list):
+                for skill in skills:
+                    extensions.append({'type': 'skill', 'skill': skill})
+
+            extensions.sort(key=_sort_key)
+
+            return self.success(data={'extensions': extensions})

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

@@ -73,15 +73,21 @@ class PipelinesRouterGroup(group.RouterGroup):
                 plugins = await self.ap.plugin_connector.list_plugins(component_kinds=pipeline_component_kinds)
                 mcp_servers = await self.ap.mcp_service.get_mcp_servers(contain_runtime_info=True)
 
+                # Get available skills
+                available_skills = await self.ap.skill_service.list_skills()
+
                 extensions_prefs = pipeline.get('extensions_preferences', {})
                 return self.success(
                     data={
                         'enable_all_plugins': extensions_prefs.get('enable_all_plugins', True),
                         'enable_all_mcp_servers': extensions_prefs.get('enable_all_mcp_servers', True),
+                        'enable_all_skills': extensions_prefs.get('enable_all_skills', True),
                         'bound_plugins': extensions_prefs.get('plugins', []),
                         'available_plugins': plugins,
                         'bound_mcp_servers': extensions_prefs.get('mcp_servers', []),
                         'available_mcp_servers': mcp_servers,
+                        'bound_skills': extensions_prefs.get('skills', []),
+                        'available_skills': available_skills,
                     }
                 )
             elif quart.request.method == 'PUT':
@@ -89,11 +95,19 @@ class PipelinesRouterGroup(group.RouterGroup):
                 json_data = await quart.request.json
                 enable_all_plugins = json_data.get('enable_all_plugins', True)
                 enable_all_mcp_servers = json_data.get('enable_all_mcp_servers', True)
+                enable_all_skills = json_data.get('enable_all_skills', True)
                 bound_plugins = json_data.get('bound_plugins', [])
                 bound_mcp_servers = json_data.get('bound_mcp_servers', [])
+                bound_skills = json_data.get('bound_skills', [])
 
                 await self.ap.pipeline_service.update_pipeline_extensions(
-                    pipeline_uuid, bound_plugins, bound_mcp_servers, enable_all_plugins, enable_all_mcp_servers
+                    pipeline_uuid,
+                    bound_plugins,
+                    bound_mcp_servers,
+                    enable_all_plugins,
+                    enable_all_mcp_servers,
+                    bound_skills=bound_skills,
+                    enable_all_skills=enable_all_skills,
                 )
 
                 return self.success()

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/plugins.py

@@ -1,11 +1,15 @@
 from __future__ import annotations
 
 import base64
+import io
 import quart
 import re
 import httpx
 import uuid
 import os
+import zipfile
+import yaml
+from urllib.parse import urlparse
 import posixpath
 import sqlalchemy
 
@@ -53,6 +57,97 @@ def _get_request_origin() -> str:
 
 @group.group_class('plugins', '/api/v1/plugins')
 class PluginsRouterGroup(group.RouterGroup):
+    @staticmethod
+    def _normalize_archive_path(path: str) -> str:
+        normalized = str(path or '').replace('\\', '/').strip('/')
+        return posixpath.normpath(normalized) if normalized else ''
+
+    @classmethod
+    def _component_source_path(cls, entry) -> str:
+        if isinstance(entry, dict):
+            return cls._normalize_archive_path(entry.get('path') or '')
+        return cls._normalize_archive_path(str(entry or ''))
+
+    @classmethod
+    def _count_component_configs(cls, component_config, archive_names: list[str]) -> int:
+        normalized_names = [cls._normalize_archive_path(name) for name in archive_names]
+        component_files: set[str] = set()
+
+        if isinstance(component_config, list):
+            return len(component_config)
+        if not isinstance(component_config, dict):
+            return 1 if component_config else 0
+
+        for entry in component_config.get('fromFiles') or []:
+            source_path = cls._component_source_path(entry)
+            if source_path and source_path in normalized_names:
+                component_files.add(source_path)
+
+        for entry in component_config.get('fromDirs') or []:
+            source_dir = cls._component_source_path(entry).rstrip('/')
+            if not source_dir:
+                continue
+            prefix = f'{source_dir}/'
+            for archive_name in normalized_names:
+                if not archive_name.startswith(prefix):
+                    continue
+                if archive_name.lower().endswith(('.yaml', '.yml')):
+                    component_files.add(archive_name)
+
+        if component_files:
+            return len(component_files)
+
+        return 1 if any(key in component_config for key in ('path', 'name', 'kind')) else 0
+
+    @classmethod
+    def _count_plugin_components(cls, components, archive_names: list[str]) -> dict[str, int]:
+        if not isinstance(components, dict):
+            return {}
+
+        component_counts: dict[str, int] = {}
+        for kind, component_config in components.items():
+            count = cls._count_component_configs(component_config, archive_names)
+            if count > 0:
+                component_counts[str(kind)] = count
+        return component_counts
+
+    @staticmethod
+    def _parse_github_repo_url(repo_url: str) -> dict | None:
+        raw_url = str(repo_url or '').strip()
+        if not raw_url:
+            return None
+
+        if not re.match(r'^[a-zA-Z][a-zA-Z0-9+.-]*://', raw_url):
+            raw_url = f'https://{raw_url}'
+
+        parsed = urlparse(raw_url)
+        if parsed.netloc.lower() not in ('github.com', 'www.github.com'):
+            return None
+
+        parts = [part for part in parsed.path.strip('/').split('/') if part]
+        if len(parts) < 2:
+            return None
+
+        owner = parts[0]
+        repo = parts[1]
+        if repo.endswith('.git'):
+            repo = repo[:-4]
+        if not owner or not repo:
+            return None
+
+        ref = ''
+        subdir = ''
+        if len(parts) >= 4 and parts[2] in ('tree', 'blob'):
+            ref = parts[3]
+            subdir = '/'.join(parts[4:]).strip('/')
+
+        return {
+            'owner': owner,
+            'repo': repo,
+            'ref': ref,
+            'subdir': subdir,
+        }
+
     async def _check_extensions_limit(self) -> str | None:
         """Check if extensions limit is reached. Returns error response if limit exceeded, None otherwise."""
         limitation = self.ap.instance_config.data.get('system', {}).get('limitation', {})
@@ -254,17 +349,37 @@ class PluginsRouterGroup(group.RouterGroup):
             data = await quart.request.json
             repo_url = data.get('repo_url', '')
 
-            # Parse GitHub repository URL to extract owner and repo
-            # Supports: https://github.com/owner/repo or github.com/owner/repo
-            pattern = r'github\.com/([^/]+)/([^/]+?)(?:\.git)?(?:/.*)?$'
-            match = re.search(pattern, repo_url)
-
-            if not match:
+            parsed_repo = self._parse_github_repo_url(repo_url)
+            if not parsed_repo:
                 return self.http_status(400, -1, 'Invalid GitHub repository URL')
 
-            owner, repo = match.groups()
+            owner = parsed_repo['owner']
+            repo = parsed_repo['repo']
+            requested_ref = parsed_repo['ref']
+            requested_subdir = parsed_repo['subdir']
 
             try:
+                if requested_ref:
+                    return self.success(
+                        data={
+                            'releases': [
+                                {
+                                    'id': 0,
+                                    'tag_name': requested_ref,
+                                    'name': requested_ref,
+                                    'published_at': '',
+                                    'prerelease': False,
+                                    'draft': False,
+                                    'source_type': 'branch',
+                                    'archive_url': f'https://api.github.com/repos/{owner}/{repo}/zipball/{requested_ref}',
+                                }
+                            ],
+                            'owner': owner,
+                            'repo': repo,
+                            'source_subdir': requested_subdir,
+                        }
+                    )
+
                 # Fetch releases from GitHub API
                 url = f'https://api.github.com/repos/{owner}/{repo}/releases'
                 async with httpx.AsyncClient(
@@ -290,7 +405,14 @@ class PluginsRouterGroup(group.RouterGroup):
                         }
                     )
 
-                return self.success(data={'releases': formatted_releases, 'owner': owner, 'repo': repo})
+                return self.success(
+                    data={
+                        'releases': formatted_releases,
+                        'owner': owner,
+                        'repo': repo,
+                        'source_subdir': requested_subdir,
+                    }
+                )
             except httpx.RequestError as e:
                 return self.http_status(500, -1, f'Failed to fetch releases: {str(e)}')
 
@@ -445,6 +567,62 @@ class PluginsRouterGroup(group.RouterGroup):
 
             return self.success(data={'task_id': wrapper.id})
 
+        @self.route('/install/local/preview', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def _() -> str:
+            file = (await quart.request.files).get('file')
+            if file is None:
+                return self.http_status(400, -1, 'file is required')
+
+            file_bytes = file.read()
+            try:
+                with zipfile.ZipFile(io.BytesIO(file_bytes)) as zf:
+                    names = [name for name in zf.namelist() if not name.endswith('/')]
+                    manifest_name = next(
+                        (
+                            name
+                            for name in names
+                            if name.replace('\\', '/').strip('/').lower() in ('manifest.yaml', 'manifest.yml')
+                        ),
+                        None,
+                    )
+                    if manifest_name is None:
+                        return self.http_status(400, -1, 'manifest.yaml is required')
+
+                    manifest = yaml.safe_load(zf.read(manifest_name).decode('utf-8')) or {}
+                    requirements: list[str] = []
+                    requirements_name = next(
+                        (name for name in names if name.replace('\\', '/').strip('/').lower() == 'requirements.txt'),
+                        None,
+                    )
+                    if requirements_name is not None:
+                        requirements = [
+                            line.strip()
+                            for line in zf.read(requirements_name).decode('utf-8', errors='ignore').splitlines()
+                            if line.strip() and not line.strip().startswith('#')
+                        ]
+
+                    spec = manifest.get('spec') or {}
+                    components = spec.get('components') or {}
+                    component_counts = self._count_plugin_components(components, names)
+                    component_types = list(component_counts.keys())
+
+                    return self.success(
+                        data={
+                            'filename': file.filename or 'local plugin',
+                            'size': len(file_bytes),
+                            'manifest': manifest,
+                            'metadata': manifest.get('metadata') or {},
+                            'component_types': component_types,
+                            'component_counts': component_counts,
+                            'requirements': requirements,
+                            'file_count': len(names),
+                        }
+                    )
+            except zipfile.BadZipFile:
+                return self.http_status(400, -1, 'invalid .lbpkg file')
+            except Exception as exc:
+                return self.http_status(500, -1, f'Failed to preview plugin package: {exc}')
+
         @self.route('/config-files', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
         async def _() -> str:
             """Upload a file for plugin configuration"""

src/langbot/pkg/api/http/controller/groups/resources/mcp.py

@@ -31,6 +31,9 @@ class MCPRouterGroup(group.RouterGroup):
         @self.route('/servers/<server_name>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN)
         async def _(server_name: str) -> str:
             """获取、更新或删除MCP服务器配置"""
+            from urllib.parse import unquote
+
+            server_name = unquote(server_name)
 
             server_data = await self.ap.mcp_service.get_mcp_server_by_name(server_name)
             if server_data is None:
@@ -57,6 +60,9 @@ class MCPRouterGroup(group.RouterGroup):
         @self.route('/servers/<server_name>/test', methods=['POST'], auth_type=group.AuthType.USER_TOKEN)
         async def _(server_name: str) -> str:
             """测试MCP服务器连接"""
+            from urllib.parse import unquote
+
+            server_name = unquote(server_name)
             server_data = await quart.request.json
             task_id = await self.ap.mcp_service.test_mcp_server(server_name=server_name, server_data=server_data)
             return self.success(data={'task_id': task_id})

src/langbot/pkg/api/http/controller/groups/skills.py

@@ -0,0 +1,190 @@
+from __future__ import annotations
+
+import quart
+
+from langbot_plugin.box.errors import BoxError
+
+from .. import group
+
+
+@group.group_class('skills', '/api/v1/skills')
+class SkillsRouterGroup(group.RouterGroup):
+    """Skills management API endpoints."""
+
+    async def initialize(self) -> None:
+        @self.route('', methods=['GET', 'POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def list_or_create_skills() -> quart.Response:
+            if quart.request.method == 'GET':
+                try:
+                    skills = await self.ap.skill_service.list_skills()
+                except (ValueError, BoxError) as exc:
+                    return self.http_status(400, -1, str(exc))
+                return self.success(data={'skills': skills})
+
+            data = await quart.request.json
+            if 'name' not in data or not data['name']:
+                return self.http_status(400, -1, 'Missing required field: name')
+
+            try:
+                skill = await self.ap.skill_service.create_skill(data)
+                return self.success(data={'skill': skill})
+            except (ValueError, BoxError) as exc:
+                return self.http_status(400, -1, str(exc))
+
+        @self.route('/<skill_name>', methods=['GET', 'PUT', 'DELETE'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def get_update_delete_skill(skill_name: str) -> quart.Response:
+            if quart.request.method == 'GET':
+                try:
+                    skill = await self.ap.skill_service.get_skill(skill_name)
+                except (ValueError, BoxError) as exc:
+                    return self.http_status(400, -1, str(exc))
+                if not skill:
+                    return self.http_status(404, -1, 'Skill not found')
+                return self.success(data={'skill': skill})
+
+            if quart.request.method == 'PUT':
+                data = await quart.request.json
+                try:
+                    skill = await self.ap.skill_service.update_skill(skill_name, data)
+                    return self.success(data={'skill': skill})
+                except (ValueError, BoxError) as exc:
+                    return self.http_status(400, -1, str(exc))
+
+            try:
+                await self.ap.skill_service.delete_skill(skill_name)
+                return self.success()
+            except (ValueError, BoxError) as exc:
+                return self.http_status(400, -1, str(exc))
+
+        @self.route('/<skill_name>/files', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def list_skill_files(skill_name: str) -> quart.Response:
+            """List files in skill package directory."""
+            path = quart.request.args.get('path', '.').strip()
+            include_hidden = quart.request.args.get('include_hidden', 'false').lower() == 'true'
+
+            try:
+                result = await self.ap.skill_service.list_skill_files(
+                    skill_name,
+                    path=path,
+                    include_hidden=include_hidden,
+                )
+                return self.success(data=result)
+            except (ValueError, BoxError) as exc:
+                return self.http_status(400, -1, str(exc))
+
+        @self.route(
+            '/<skill_name>/files/<path:path>', methods=['GET', 'PUT'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY
+        )
+        async def read_or_write_skill_file(skill_name: str, path: str) -> quart.Response:
+            """Read or write a file in skill package."""
+            if quart.request.method == 'GET':
+                try:
+                    result = await self.ap.skill_service.read_skill_file(skill_name, path)
+                    return self.success(data=result)
+                except (ValueError, BoxError) as exc:
+                    return self.http_status(400, -1, str(exc))
+
+            # PUT - write file
+            data = await quart.request.json
+            content = data.get('content', '')
+            if content is None:
+                return self.http_status(400, -1, 'Missing required field: content')
+
+            try:
+                result = await self.ap.skill_service.write_skill_file(skill_name, path, content)
+                return self.success(data=result)
+            except (ValueError, BoxError) as exc:
+                return self.http_status(400, -1, str(exc))
+
+        @self.route('/<skill_name>/preview', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def preview_skill(skill_name: str) -> quart.Response:
+            skill = self.ap.skill_mgr.get_skill_by_name(skill_name)
+            if not skill:
+                return self.http_status(404, -1, 'Skill not found')
+            return self.success(data={'instructions': skill.get('instructions', '')})
+
+        @self.route('/install/github', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def install_skill_from_github() -> quart.Response:
+            data = await quart.request.json
+            required_fields = ['asset_url', 'owner', 'repo']
+            for field in required_fields:
+                if field not in data or not data[field]:
+                    return self.http_status(400, -1, f'Missing required field: {field}')
+            asset_url = str(data['asset_url']).strip().lower().split('?', 1)[0].split('#', 1)[0]
+            if not asset_url.endswith('skill.md') and not data.get('release_tag'):
+                return self.http_status(400, -1, 'Missing required field: release_tag')
+
+            try:
+                skill = await self.ap.skill_service.install_from_github(data)
+                return self.success(data={'skills': skill})
+            except (ValueError, BoxError) as exc:
+                return self.http_status(400, -1, str(exc))
+            except Exception as exc:
+                return self.http_status(500, -1, f'Failed to install skill: {exc}')
+
+        @self.route('/install/github/preview', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def preview_skill_from_github() -> quart.Response:
+            data = await quart.request.json
+            required_fields = ['asset_url', 'owner', 'repo']
+            for field in required_fields:
+                if field not in data or not data[field]:
+                    return self.http_status(400, -1, f'Missing required field: {field}')
+            asset_url = str(data['asset_url']).strip().lower().split('?', 1)[0].split('#', 1)[0]
+            if not asset_url.endswith('skill.md') and not data.get('release_tag'):
+                return self.http_status(400, -1, 'Missing required field: release_tag')
+
+            try:
+                preview = await self.ap.skill_service.preview_install_from_github(data)
+                return self.success(data={'skills': preview})
+            except (ValueError, BoxError) as exc:
+                return self.http_status(400, -1, str(exc))
+            except Exception as exc:
+                return self.http_status(500, -1, f'Failed to preview skill: {exc}')
+
+        @self.route('/install/upload', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def install_skill_from_upload() -> quart.Response:
+            file = (await quart.request.files).get('file')
+            if file is None:
+                return self.http_status(400, -1, 'file is required')
+            form = await quart.request.form
+
+            try:
+                skill = await self.ap.skill_service.install_from_zip_upload(
+                    file_bytes=file.read(),
+                    filename=file.filename or '',
+                    source_paths=form.getlist('source_paths'),
+                )
+                return self.success(data={'skills': skill})
+            except (ValueError, BoxError) as exc:
+                return self.http_status(400, -1, str(exc))
+            except Exception as exc:
+                return self.http_status(500, -1, f'Failed to install skill: {exc}')
+
+        @self.route('/install/upload/preview', methods=['POST'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def preview_skill_from_upload() -> quart.Response:
+            file = (await quart.request.files).get('file')
+            if file is None:
+                return self.http_status(400, -1, 'file is required')
+
+            try:
+                preview = await self.ap.skill_service.preview_install_from_zip_upload(
+                    file_bytes=file.read(),
+                    filename=file.filename or '',
+                )
+                return self.success(data={'skills': preview})
+            except (ValueError, BoxError) as exc:
+                return self.http_status(400, -1, str(exc))
+            except Exception as exc:
+                return self.http_status(500, -1, f'Failed to preview skill: {exc}')
+
+        @self.route('/scan', methods=['GET'], auth_type=group.AuthType.USER_TOKEN_OR_API_KEY)
+        async def scan_skill_directory() -> quart.Response:
+            path = quart.request.args.get('path', '').strip()
+            if not path:
+                return self.http_status(400, -1, 'Missing required parameter: path')
+
+            try:
+                result = await self.ap.skill_service.scan_directory_async(path)
+                return self.success(data=result)
+            except (ValueError, BoxError) as exc:
+                return self.http_status(400, -1, str(exc))

src/langbot/pkg/api/http/service/pipeline.py

@@ -215,6 +215,8 @@ class PipelineService:
         bound_mcp_servers: list[str] = None,
         enable_all_plugins: bool = True,
         enable_all_mcp_servers: bool = True,
+        bound_skills: list[str] = None,
+        enable_all_skills: bool = True,
     ) -> None:
         """Update the bound plugins and MCP servers for a pipeline"""
         # Get current pipeline
@@ -232,9 +234,12 @@ class PipelineService:
         extensions_preferences = pipeline.extensions_preferences or {}
         extensions_preferences['enable_all_plugins'] = enable_all_plugins
         extensions_preferences['enable_all_mcp_servers'] = enable_all_mcp_servers
+        extensions_preferences['enable_all_skills'] = enable_all_skills
         extensions_preferences['plugins'] = bound_plugins
         if bound_mcp_servers is not None:
             extensions_preferences['mcp_servers'] = bound_mcp_servers
+        if bound_skills is not None:
+            extensions_preferences['skills'] = bound_skills
 
         await self.ap.persistence_mgr.execute_async(
             sqlalchemy.update(persistence_pipeline.LegacyPipeline)

src/langbot/pkg/api/http/service/skill.py

@@ -0,0 +1,428 @@
+from __future__ import annotations
+
+import io
+import inspect
+import os
+import posixpath
+import zipfile
+from typing import Optional
+from urllib.parse import quote, unquote, urlparse
+
+import httpx
+
+from ....core import app
+from ....skill.utils import parse_frontmatter
+
+
+_PUBLIC_SKILL_FIELDS = (
+    'name',
+    'display_name',
+    'description',
+    'instructions',
+    'package_root',
+    'created_at',
+    'updated_at',
+)
+
+_GITHUB_ASSET_HOSTS = {
+    'github.com',
+    'api.github.com',
+    'objects.githubusercontent.com',
+    'githubusercontent.com',
+    'raw.githubusercontent.com',
+    'codeload.github.com',
+}
+
+
+class SkillService:
+    """Filesystem-backed skill management service."""
+
+    ap: app.Application
+
+    def __init__(self, ap: app.Application) -> None:
+        self.ap = ap
+
+    def _box_service(self):
+        box_service = getattr(self.ap, 'box_service', None)
+        if box_service is not None and getattr(box_service, 'available', False):
+            return box_service
+        return None
+
+    def _require_box(self, action: str):
+        """Return the Box service or raise if it is not available.
+
+        Box is the only source of truth for skills. Every read and write
+        operation goes through it — there is no local-filesystem fallback.
+        """
+        box_service = self._box_service()
+        if box_service is not None:
+            return box_service
+        ap_box = getattr(self.ap, 'box_service', None)
+        if ap_box is None:
+            reason = 'not initialised'
+        elif not getattr(ap_box, 'enabled', True):
+            reason = 'disabled in config (box.enabled = false)'
+        else:
+            connector_error = getattr(ap_box, '_connector_error', '') or 'currently unavailable'
+            reason = f'unavailable: {connector_error}'
+        raise ValueError(
+            f'{action} requires the Box runtime, which is {reason}. '
+            f'Enable Box in config.yaml (box.enabled = true) and ensure the '
+            f'runtime is reachable before retrying.'
+        )
+
+    def _require_box_for_write(self, action: str) -> None:
+        """Backwards-compatible alias preserved for clarity at call sites."""
+        self._require_box(action)
+
+    @staticmethod
+    def _serialize_skill(skill: dict) -> dict:
+        return {field: skill.get(field) for field in _PUBLIC_SKILL_FIELDS if field in skill}
+
+    async def list_skills(self) -> list[dict]:
+        # When Box is unavailable, surface an empty list rather than raising —
+        # the skills page should render cleanly, and the UI separately renders
+        # a "Box disabled / unavailable" banner via useBoxStatus.
+        box_service = self._box_service()
+        if box_service is None:
+            return []
+        return [self._serialize_skill(skill) for skill in await box_service.list_skills()]
+
+    async def get_skill(self, skill_name: str) -> Optional[dict]:
+        box_service = self._box_service()
+        if box_service is None:
+            return None
+        skill = await box_service.get_skill(skill_name)
+        return self._serialize_skill(skill) if skill else None
+
+    async def get_skill_by_name(self, name: str) -> Optional[dict]:
+        return await self.get_skill(name)
+
+    async def create_skill(self, data: dict) -> dict:
+        box_service = self._require_box('Creating a skill')
+        created = await box_service.create_skill(data)
+        await self._reload_skills()
+        return self._serialize_skill(created)
+
+    async def update_skill(self, skill_name: str, data: dict) -> dict:
+        box_service = self._require_box('Editing a skill')
+        updated = await box_service.update_skill(skill_name, data)
+        await self._reload_skills()
+        return self._serialize_skill(updated)
+
+    async def delete_skill(self, skill_name: str) -> bool:
+        box_service = self._require_box('Deleting a skill')
+        await box_service.delete_skill(skill_name)
+        await self._reload_skills()
+        return True
+
+    async def list_skill_files(
+        self,
+        skill_name: str,
+        path: str = '.',
+        include_hidden: bool = False,
+        max_entries: int = 200,
+    ) -> dict:
+        box_service = self._require_box('Browsing skill files')
+        return await box_service.list_skill_files(skill_name, path, include_hidden, max_entries)
+
+    async def read_skill_file(self, skill_name: str, path: str) -> dict:
+        box_service = self._require_box('Reading a skill file')
+        return await box_service.read_skill_file(skill_name, path)
+
+    async def write_skill_file(self, skill_name: str, path: str, content: str) -> dict:
+        box_service = self._require_box('Editing skill files')
+        result = await box_service.write_skill_file(skill_name, path, content)
+        await self._reload_skills()
+        return result
+
+    async def install_from_github(self, data: dict) -> list[dict]:
+        box_service = self._require_box('Installing a skill from GitHub')
+        owner = str(data['owner']).strip()
+        repo = str(data['repo']).strip()
+        release_tag = str(data.get('release_tag', '')).strip()
+        raw_asset_url = str(data['asset_url']).strip()
+        if self._is_github_skill_md_url(raw_asset_url):
+            return await self._install_github_skill_md(raw_asset_url, owner=owner, repo=repo, data=data)
+
+        asset_url = self._validate_github_asset_url(raw_asset_url, owner=owner, repo=repo, release_tag=release_tag)
+        source_subdir = str(data.get('source_subdir', '') or '').strip()
+
+        zip_bytes = await self._download_github_asset(asset_url)
+        filename = f'{repo}-{release_tag.lstrip("v").replace("/", "-") or "source"}.zip'
+        installed = await box_service.install_skill_zip(
+            zip_bytes,
+            filename,
+            source_paths=data.get('source_paths') or [],
+            source_path=str(data.get('source_path', '') or ''),
+            source_subdir=source_subdir,
+        )
+        await self._reload_skills()
+        return [self._serialize_skill(skill) for skill in installed]
+
+    async def preview_install_from_github(self, data: dict) -> list[dict]:
+        box_service = self._require_box('Previewing a skill from GitHub')
+        owner = str(data['owner']).strip()
+        repo = str(data['repo']).strip()
+        release_tag = str(data.get('release_tag', '')).strip()
+        raw_asset_url = str(data['asset_url']).strip()
+        if self._is_github_skill_md_url(raw_asset_url):
+            return await self._preview_github_skill_md(raw_asset_url, owner=owner, repo=repo)
+
+        asset_url = self._validate_github_asset_url(raw_asset_url, owner=owner, repo=repo, release_tag=release_tag)
+        source_subdir = str(data.get('source_subdir', '') or '').strip()
+
+        zip_bytes = await self._download_github_asset(asset_url)
+        return await box_service.preview_skill_zip(
+            zip_bytes,
+            f'{repo}-{release_tag.lstrip("v").replace("/", "-") or "source"}.zip',
+            source_subdir=source_subdir,
+        )
+
+    async def install_from_zip_upload(
+        self,
+        *,
+        file_bytes: bytes,
+        filename: str,
+        source_paths: list[str] | None = None,
+        source_path: str = '',
+    ) -> list[dict]:
+        box_service = self._require_box('Installing a skill from upload')
+        installed = await box_service.install_skill_zip(
+            file_bytes,
+            filename,
+            source_paths=source_paths or [],
+            source_path=source_path,
+        )
+        await self._reload_skills()
+        return [self._serialize_skill(skill) for skill in installed]
+
+    async def preview_install_from_zip_upload(self, *, file_bytes: bytes, filename: str) -> list[dict]:
+        box_service = self._require_box('Previewing a skill upload')
+        return await box_service.preview_skill_zip(file_bytes, filename)
+
+    async def _install_github_skill_md(self, asset_url: str, *, owner: str, repo: str, data: dict) -> list[dict]:
+        box_service = self._require_box('Installing a skill from GitHub')
+        zip_bytes, filename, _package_name = await self._download_github_skill_directory_as_zip(
+            asset_url,
+            owner=owner,
+            repo=repo,
+        )
+
+        installed = await box_service.install_skill_zip(
+            zip_bytes,
+            filename,
+            source_paths=data.get('source_paths') or [],
+            source_path=str(data.get('source_path', '') or ''),
+            target_suffix='',
+        )
+        await self._reload_skills()
+        return [self._serialize_skill(skill) for skill in installed]
+
+    async def _preview_github_skill_md(self, asset_url: str, *, owner: str, repo: str) -> list[dict]:
+        box_service = self._require_box('Previewing a skill from GitHub')
+        zip_bytes, _filename, package_name = await self._download_github_skill_directory_as_zip(
+            asset_url,
+            owner=owner,
+            repo=repo,
+        )
+        return await box_service.preview_skill_zip(zip_bytes, f'{package_name}.zip', target_suffix='')
+
+    async def reload_skills(self) -> list[dict]:
+        await self._reload_skills()
+        return await self.list_skills()
+
+    async def scan_directory_async(self, path: str) -> dict:
+        box_service = self._require_box('Scanning a skill directory')
+        return await box_service.scan_skill_directory(path)
+
+    async def _reload_skills(self) -> None:
+        skill_mgr = getattr(self.ap, 'skill_mgr', None)
+        reload_skills = getattr(skill_mgr, 'reload_skills', None)
+        if not callable(reload_skills):
+            return
+        result = reload_skills()
+        if inspect.isawaitable(result):
+            await result
+
+    async def _download_github_asset(self, asset_url: str) -> bytes:
+        async with httpx.AsyncClient(follow_redirects=True, timeout=120) as client:
+            resp = await client.get(asset_url)
+            resp.raise_for_status()
+            return resp.content
+
+    async def _download_github_skill_directory_as_zip(
+        self, asset_url: str, *, owner: str, repo: str
+    ) -> tuple[bytes, str, str]:
+        info = self._parse_github_skill_md_url(asset_url, owner=owner, repo=repo)
+        archive_url = f'https://codeload.github.com/{owner}/{repo}/zip/{quote(info["ref"], safe="/")}'
+        archive_bytes = await self._download_github_asset(archive_url)
+
+        try:
+            source_archive = zipfile.ZipFile(io.BytesIO(archive_bytes), 'r')
+        except zipfile.BadZipFile as exc:
+            raise ValueError('GitHub repository archive must be a valid .zip archive') from exc
+
+        with source_archive as source_zip:
+            skill_entry = self._find_github_skill_archive_entry(source_zip, info['file_path'])
+            try:
+                skill_md_content = source_zip.read(skill_entry).decode('utf-8')
+            except UnicodeDecodeError as exc:
+                raise ValueError('GitHub SKILL.md must be valid UTF-8 text') from exc
+
+            package_name = self._resolve_github_skill_md_package_name(skill_md_content, info['package_name'])
+            source_skill_dir = posixpath.dirname(posixpath.normpath(skill_entry.filename))
+
+            buffer = io.BytesIO()
+            with zipfile.ZipFile(buffer, 'w', zipfile.ZIP_DEFLATED) as target_zip:
+                self._copy_github_skill_directory_to_zip(source_zip, target_zip, source_skill_dir, package_name)
+        return buffer.getvalue(), f'{package_name}.zip', package_name
+
+    def _find_github_skill_archive_entry(self, archive: zipfile.ZipFile, file_path: str) -> zipfile.ZipInfo:
+        normalized_file_path = posixpath.normpath(file_path).lower()
+        for member in archive.infolist():
+            if member.is_dir():
+                continue
+            normalized_member = posixpath.normpath(member.filename)
+            path_parts = normalized_member.split('/', 1)
+            if len(path_parts) != 2:
+                continue
+            archive_relative_path = path_parts[1].lower()
+            if archive_relative_path == normalized_file_path:
+                return member
+        raise ValueError(f'GitHub archive does not contain requested SKILL.md: {file_path}')
+
+    def _copy_github_skill_directory_to_zip(
+        self,
+        source_zip: zipfile.ZipFile,
+        target_zip: zipfile.ZipFile,
+        source_skill_dir: str,
+        package_name: str,
+    ) -> None:
+        normalized_source_dir = posixpath.normpath(source_skill_dir)
+        source_prefix = f'{normalized_source_dir}/'
+        copied_files = 0
+
+        for member in source_zip.infolist():
+            normalized_member = posixpath.normpath(member.filename)
+            if normalized_member != normalized_source_dir and not normalized_member.startswith(source_prefix):
+                continue
+
+            relative_path = posixpath.relpath(normalized_member, normalized_source_dir)
+            if relative_path in ('', '.'):
+                continue
+            if relative_path.startswith('../') or relative_path == '..' or posixpath.isabs(relative_path):
+                raise ValueError(f'GitHub archive contains an unsafe skill path: {member.filename}')
+
+            target_name = f'{package_name}/{relative_path}'
+            if member.is_dir() and not target_name.endswith('/'):
+                target_name = f'{target_name}/'
+            target_info = zipfile.ZipInfo(target_name, date_time=member.date_time)
+            target_info.external_attr = member.external_attr
+            target_info.compress_type = zipfile.ZIP_DEFLATED
+
+            if member.is_dir():
+                target_zip.writestr(target_info, b'')
+                continue
+
+            target_zip.writestr(target_info, source_zip.read(member))
+            copied_files += 1
+
+        if copied_files == 0:
+            raise ValueError('GitHub skill directory is empty')
+
+    def _uploaded_skill_target_stem(self, filename: str) -> str:
+        stem = os.path.splitext(os.path.basename(str(filename or '').strip()))[0]
+        safe_stem = ''.join(ch if ch.isalnum() or ch in ('-', '_') else '-' for ch in stem).strip('-_')
+        if not safe_stem:
+            safe_stem = 'uploaded-skill'
+        return safe_stem
+
+    @staticmethod
+    def _is_github_skill_md_url(asset_url: str) -> bool:
+        parsed = urlparse(str(asset_url or '').strip())
+        normalized_path = posixpath.normpath(parsed.path or '/')
+        return normalized_path.lower().endswith('/skill.md')
+
+    def _parse_github_skill_md_url(self, asset_url: str, *, owner: str, repo: str) -> dict:
+        parsed = urlparse(str(asset_url or '').strip())
+        if parsed.scheme != 'https' or not parsed.netloc:
+            raise ValueError('asset_url must be a valid HTTPS GitHub SKILL.md URL')
+
+        host = parsed.netloc.lower()
+        path_parts = [unquote(part) for part in (parsed.path or '').split('/') if part]
+        if host == 'github.com':
+            if (
+                len(path_parts) < 5
+                or path_parts[0] != owner
+                or path_parts[1] != repo
+                or path_parts[2]
+                not in (
+                    'blob',
+                    'raw',
+                )
+            ):
+                raise ValueError('GitHub SKILL.md URL must point to the requested owner/repo blob path')
+            ref = path_parts[3]
+            file_path = '/'.join(path_parts[4:])
+        elif host == 'raw.githubusercontent.com':
+            if len(path_parts) < 4 or path_parts[0] != owner or path_parts[1] != repo:
+                raise ValueError('GitHub SKILL.md URL must point to the requested owner/repo raw path')
+            ref = path_parts[2]
+            file_path = '/'.join(path_parts[3:])
+        else:
+            raise ValueError('asset_url must point to a GitHub SKILL.md file')
+
+        normalized_file_path = posixpath.normpath(file_path)
+        normalized_file_path_lower = normalized_file_path.lower()
+        if normalized_file_path_lower != 'skill.md' and not normalized_file_path_lower.endswith('/skill.md'):
+            raise ValueError('GitHub skill import requires a URL ending with SKILL.md')
+
+        parent_dir = posixpath.basename(posixpath.dirname(normalized_file_path)) or repo
+        return {
+            'ref': ref,
+            'file_path': normalized_file_path,
+            'package_name': self._uploaded_skill_target_stem(parent_dir),
+        }
+
+    def _resolve_github_skill_md_package_name(self, content: str, fallback: str) -> str:
+        metadata, _instructions = parse_frontmatter(content)
+        candidate = str(metadata.get('name') or fallback or '').strip()
+        try:
+            return self._validate_skill_name(candidate)
+        except ValueError:
+            return self._validate_skill_name(fallback)
+
+    @staticmethod
+    def _validate_github_asset_url(asset_url: str, *, owner: str, repo: str, release_tag: str) -> str:
+        parsed = urlparse(str(asset_url).strip())
+        if parsed.scheme != 'https' or not parsed.netloc:
+            raise ValueError('asset_url must be a valid HTTPS GitHub asset URL')
+
+        host = parsed.netloc.lower()
+        if host not in _GITHUB_ASSET_HOSTS:
+            raise ValueError('asset_url must point to a GitHub-hosted release asset or archive')
+
+        normalized_path = posixpath.normpath(parsed.path or '/')
+        allowed_prefixes = [
+            f'/repos/{owner}/{repo}/',
+            f'/{owner}/{repo}/',
+        ]
+        if not any(normalized_path.startswith(prefix) for prefix in allowed_prefixes):
+            raise ValueError('asset_url does not match the requested owner/repo')
+
+        if release_tag and release_tag not in parsed.path and release_tag not in parsed.query:
+            raise ValueError('asset_url does not match the requested release_tag')
+
+        return parsed.geturl()
+
+    @staticmethod
+    def _validate_skill_name(name: str) -> str:
+        name = str(name or '').strip()
+        if not name:
+            raise ValueError('Skill name is required')
+        if not name.replace('-', '').replace('_', '').isalnum():
+            raise ValueError('Skill name can only contain letters, numbers, hyphens and underscores')
+        if len(name) > 64:
+            raise ValueError('Skill name cannot exceed 64 characters')
+        return name

src/langbot/pkg/box/__init__.py

@@ -0,0 +1,5 @@
+"""LangBot Box runtime package."""
+
+from .workspace import BoxWorkspaceSession
+
+__all__ = ['BoxWorkspaceSession']

src/langbot/pkg/box/connector.py

@@ -0,0 +1,354 @@
+from __future__ import annotations
+
+import asyncio
+import json
+import os
+import sys
+import typing
+from typing import TYPE_CHECKING
+from urllib.parse import urlparse
+
+from langbot_plugin.entities.io.actions.enums import CommonAction
+from langbot_plugin.runtime.io.handler import Handler
+from langbot_plugin.runtime.io.connection import Connection
+
+from langbot_plugin.box.client import ActionRPCBoxClient
+from langbot_plugin.box.errors import BoxRuntimeUnavailableError
+from langbot_plugin.box.actions import LangBotToBoxAction
+
+from ..utils import platform
+from ..utils.managed_runtime import ManagedRuntimeConnector
+
+if TYPE_CHECKING:
+    from ..core import app as core_app
+
+
+# Default Docker Compose service name for the standalone Box container.
+_DOCKER_BOX_HOST = 'langbot_box'
+_DEFAULT_PORT = 5410
+
+_HEARTBEAT_INTERVAL_SEC = 20
+
+# Top-level keys under ``box`` that are LangBot-internal and should not be
+# forwarded to the Box runtime.
+_INTERNAL_BOX_CONFIG_KEYS = frozenset({'runtime'})
+
+
+def _get_box_config(ap) -> dict:
+    """Return the 'box' section from instance config.
+
+    Environment-variable overrides are handled uniformly by
+    ``LoadConfigStage._apply_env_overrides_to_config`` using the
+    ``SECTION__SUBSECTION__KEY`` convention (e.g. ``BOX__LOCAL__HOST_ROOT``,
+    ``BOX__LOCAL__ALLOWED_MOUNT_ROOTS="/a,/b"``) before this is read, so no
+    box-specific env parsing is needed here.
+    """
+    instance_config = getattr(ap, 'instance_config', None)
+    config_data = getattr(instance_config, 'data', {}) if instance_config is not None else {}
+    return dict(config_data.get('box', {}) or {})
+
+
+def _get_runtime_endpoint(box_cfg: dict) -> str:
+    runtime_cfg = box_cfg.get('runtime') or {}
+    return str(runtime_cfg.get('endpoint', '')).strip()
+
+
+def _filter_config_for_runtime(box_cfg: dict) -> dict:
+    return {k: v for k, v in box_cfg.items() if k not in _INTERNAL_BOX_CONFIG_KEYS}
+
+
+def resolve_box_ws_relay_url(ap: core_app.Application) -> str:
+    """Derive the WS relay base URL used for managed-process attach.
+
+    The WS relay serves the ``/v1/sessions/{id}/managed-process/ws`` endpoint
+    on the *relay* port (default 5410).
+    """
+    box_cfg = _get_box_config(ap)
+
+    # Explicit runtime endpoint takes precedence. The config value is a base
+    # URL; endpoint-specific paths are appended by the SDK client.
+    endpoint = _get_runtime_endpoint(box_cfg)
+    if endpoint:
+        parsed = urlparse(endpoint)
+        scheme = parsed.scheme or 'ws'
+        if scheme == 'ws':
+            scheme = 'http'
+        elif scheme == 'wss':
+            scheme = 'https'
+        host = parsed.hostname or '127.0.0.1'
+        port = parsed.port or _DEFAULT_PORT
+        return f'{scheme}://{host}:{port}'
+
+    # In Docker, relay lives on the box runtime container.
+    if platform.get_platform() == 'docker':
+        return f'http://{_DOCKER_BOX_HOST}:{_DEFAULT_PORT}'
+
+    return f'http://127.0.0.1:{_DEFAULT_PORT}'
+
+
+class BoxRuntimeConnector(ManagedRuntimeConnector):
+    """Connect to the Box runtime via action RPC.
+
+    Transport decision (mirrors Plugin runtime logic):
+      1. Docker / --standalone-box / explicit runtime.endpoint -> WebSocket to external Box process
+      2. Windows (non-Docker)                              -> subprocess + WebSocket (Windows lacks async stdio pipe)
+      3. Unix / macOS                                      -> subprocess + stdio pipe
+    """
+
+    def __init__(
+        self,
+        ap: core_app.Application,
+        runtime_disconnect_callback: typing.Callable[
+            ['BoxRuntimeConnector'], typing.Coroutine[typing.Any, typing.Any, None]
+        ]
+        | None = None,
+    ):
+        super().__init__(ap)
+        self.runtime_disconnect_callback = runtime_disconnect_callback
+        self.configured_runtime_endpoint = self._load_configured_runtime_endpoint()
+        self.ws_relay_base_url = resolve_box_ws_relay_url(ap)
+        self.client = ActionRPCBoxClient(logger=ap.logger)
+
+        self._handler: Handler | None = None
+        self._handler_task: asyncio.Task | None = None
+        self._ctrl_task: asyncio.Task | None = None
+        self._heartbeat_task: asyncio.Task | None = None
+
+        # Parse the relay URL once for reuse.
+        parsed = urlparse(self.ws_relay_base_url)
+        self._relay_host = parsed.hostname or '127.0.0.1'
+        self._relay_port = parsed.port or _DEFAULT_PORT
+        self._filtered_box_config = _filter_config_for_runtime(_get_box_config(ap))
+
+    def _uses_websocket(self) -> bool:
+        """Whether the connector should use WebSocket to reach the Box runtime.
+
+        True when:
+          - Running inside Docker (Box runtime is a separate container)
+          - The ``--standalone-box`` CLI flag was passed
+          - An explicit ``runtime.endpoint`` was configured
+        """
+        return bool(
+            self.configured_runtime_endpoint
+            or platform.get_platform() == 'docker'
+            or platform.use_websocket_to_connect_box_runtime()
+        )
+
+    async def initialize(self) -> None:
+        if self._uses_websocket():
+            if platform.get_platform() == 'win32' and not self.configured_runtime_endpoint:
+                await self._start_subprocess_then_ws()
+            else:
+                await self._connect_remote_ws()
+        else:
+            await self._start_local_stdio()
+
+        # Start heartbeat after successful connection
+        if self._heartbeat_task is None:
+            self._heartbeat_task = asyncio.create_task(self._heartbeat_loop())
+
+    # -- heartbeat -----------------------------------------------------------
+
+    async def _heartbeat_loop(self) -> None:
+        """Periodically ping the Box runtime to detect silent disconnections."""
+        while True:
+            await asyncio.sleep(_HEARTBEAT_INTERVAL_SEC)
+            try:
+                await self.ping()
+                self.ap.logger.debug('Heartbeat to Box runtime success.')
+            except Exception as e:
+                self.ap.logger.debug(f'Failed to heartbeat to Box runtime: {e}')
+
+    async def ping(self) -> None:
+        if self._handler is None:
+            raise BoxRuntimeUnavailableError('Box runtime is not connected')
+        await self._handler.call_action(CommonAction.PING, {})
+
+    # -- transport paths -----------------------------------------------------
+
+    async def _start_local_stdio(self) -> None:
+        """Launch box server as subprocess and connect via stdio (Unix/macOS)."""
+        from langbot_plugin.runtime.io.controllers.stdio.client import StdioClientController
+
+        self.ap.logger.info('Use stdio to connect to box runtime')
+        python_path = sys.executable
+        env = os.environ.copy()
+        if self._filtered_box_config:
+            env['LANGBOT_BOX_CONFIG'] = json.dumps(self._filtered_box_config)
+
+        connected = asyncio.Event()
+        connect_error: list[Exception] = []
+
+        ctrl = StdioClientController(
+            command=python_path,
+            # Launched through the same CLI entry point as the plugin runtime
+            # (cli.__init__ <subcommand>); `-s` selects the stdio transport,
+            # mirroring `rt -s`.
+            args=['-m', 'langbot_plugin.cli.__init__', 'box', '-s', '--ws-control-port', str(self._relay_port)],
+            env=env,
+        )
+        self._ctrl_task = asyncio.create_task(
+            ctrl.run(self._make_connection_callback('stdio', connected, connect_error))
+        )
+
+        try:
+            await asyncio.wait_for(connected.wait(), timeout=30.0)
+        except asyncio.TimeoutError:
+            raise BoxRuntimeUnavailableError('box runtime subprocess did not connect in time')
+
+        if connect_error:
+            raise BoxRuntimeUnavailableError(f'box runtime connection failed: {connect_error[0]}')
+
+        self._subprocess = ctrl.process
+
+    async def _start_subprocess_then_ws(self) -> None:
+        """Launch box server as detached subprocess, then connect via WS (Windows)."""
+        self.ap.logger.info('(windows) Use cmd to launch box runtime and communicate via ws')
+
+        env = os.environ.copy()
+        if self._filtered_box_config:
+            env['LANGBOT_BOX_CONFIG'] = json.dumps(self._filtered_box_config)
+
+        python_path = sys.executable
+        # Launched through the same CLI entry point as the plugin runtime
+        # (cli.__init__ <subcommand>); no flag => WebSocket transport.
+        self.runtime_subprocess = await asyncio.create_subprocess_exec(
+            python_path,
+            '-m',
+            'langbot_plugin.cli.__init__',
+            'box',
+            '--ws-control-port',
+            str(self._relay_port),
+            env=env,
+        )
+        self.runtime_subprocess_task = asyncio.create_task(self.runtime_subprocess.wait())
+
+        ws_url = f'ws://localhost:{self._relay_port}/rpc/ws'
+        await self._connect_ws(ws_url, '(windows) WebSocket')
+
+    async def _connect_remote_ws(self) -> None:
+        """Connect to a remote (or Docker) box server via WebSocket."""
+        ws_url = self._resolve_rpc_ws_url()
+        self.ap.logger.info(f'Use WebSocket to connect to box runtime ({ws_url})')
+        await self._connect_ws(ws_url, 'WebSocket')
+
+    # -- helpers -------------------------------------------------------------
+
+    def _resolve_rpc_ws_url(self) -> str:
+        """Determine the action-RPC WebSocket URL.
+
+        All endpoints share a single port; action RPC is at ``/rpc/ws``.
+        """
+        if self.configured_runtime_endpoint:
+            base = self.configured_runtime_endpoint.rstrip('/')
+            parsed = urlparse(base)
+            scheme = parsed.scheme or 'ws'
+            if scheme in ('http', 'https'):
+                scheme = 'wss' if scheme == 'https' else 'ws'
+            host = parsed.hostname or '127.0.0.1'
+            port = parsed.port or _DEFAULT_PORT
+            return f'{scheme}://{host}:{port}/rpc/ws'
+
+        if platform.get_platform() == 'docker':
+            return f'ws://{_DOCKER_BOX_HOST}:{_DEFAULT_PORT}/rpc/ws'
+
+        return f'ws://localhost:{self._relay_port}/rpc/ws'
+
+    async def _connect_ws(self, ws_url: str, transport_name: str) -> None:
+        """Shared WebSocket connection procedure."""
+        from langbot_plugin.runtime.io.controllers.ws.client import WebSocketClientController
+
+        connected = asyncio.Event()
+        connect_error: list[Exception] = []
+
+        async def on_connect_failed(ctrl, exc):
+            if exc is not None:
+                self.ap.logger.error(f'Failed to connect to Box runtime ({ws_url}): {exc}')
+            else:
+                self.ap.logger.error(f'Failed to connect to Box runtime ({ws_url}), trying to reconnect...')
+            connect_error.append(exc or BoxRuntimeUnavailableError('ws connection failed'))
+            connected.set()
+            if self.runtime_disconnect_callback is not None:
+                await self.runtime_disconnect_callback(self)
+
+        ctrl = WebSocketClientController(ws_url=ws_url, make_connection_failed_callback=on_connect_failed)
+        self._ctrl_task = asyncio.create_task(
+            ctrl.run(self._make_connection_callback(transport_name, connected, connect_error))
+        )
+
+        try:
+            await asyncio.wait_for(connected.wait(), timeout=30.0)
+        except asyncio.TimeoutError:
+            raise BoxRuntimeUnavailableError(f'box runtime ws connection timed out ({ws_url})')
+
+        if connect_error:
+            raise BoxRuntimeUnavailableError(f'box runtime connection failed: {connect_error[0]}')
+
+    def _make_connection_callback(
+        self,
+        transport_name: str,
+        connected: asyncio.Event,
+        connect_error: list[Exception],
+    ):
+        async def new_connection_callback(connection: Connection) -> None:
+            handler = Handler(connection)
+            self._handler = handler
+            self.client.set_handler(handler)
+            self._handler_task = asyncio.create_task(handler.run())
+            try:
+                await handler.call_action(CommonAction.PING, {})
+                if self._filtered_box_config:
+                    await handler.call_action(LangBotToBoxAction.INIT, self._filtered_box_config)
+                    self.ap.logger.debug('Sent box configuration to Box runtime via INIT.')
+                self.ap.logger.info(f'Connected to Box runtime via {transport_name}.')
+                connected.set()
+                await self._handler_task
+            except Exception as exc:
+                if not connected.is_set():
+                    connect_error.append(exc)
+                    connected.set()
+                    return
+
+            # If we reach here, handler.run() returned normally (connection
+            # closed) or raised after the initial handshake succeeded.
+            # Either way, treat it as a disconnect.
+            if connected.is_set():
+                if self._uses_websocket():
+                    self.ap.logger.error('Disconnected from Box runtime, trying to reconnect...')
+                    if self.runtime_disconnect_callback is not None:
+                        await self.runtime_disconnect_callback(self)
+                else:
+                    self.ap.logger.error(
+                        'Disconnected from Box runtime via stdio. '
+                        'Cannot automatically reconnect — please restart LangBot.'
+                    )
+
+        return new_connection_callback
+
+    # -- lifecycle -----------------------------------------------------------
+
+    def dispose(self) -> None:
+        if self._heartbeat_task is not None:
+            self._heartbeat_task.cancel()
+            self._heartbeat_task = None
+
+        if self._handler_task is not None:
+            self._handler_task.cancel()
+            self._handler_task = None
+
+        if self._ctrl_task is not None:
+            self._ctrl_task.cancel()
+            self._ctrl_task = None
+
+        # stdio-managed subprocess (stored as self._subprocess by _start_local_stdio)
+        if hasattr(self, '_subprocess') and self._subprocess is not None and self._subprocess.returncode is None:
+            self.ap.logger.info('Terminating managed box runtime process...')
+            self._subprocess.terminate()
+
+        # Subprocess launched by ManagedRuntimeConnector._start_runtime_subprocess (Windows path)
+        self._dispose_subprocess()
+
+    # -- config helpers ------------------------------------------------------
+
+    def _load_configured_runtime_endpoint(self) -> str:
+        return _get_runtime_endpoint(_get_box_config(self.ap))

src/langbot/pkg/box/policy.py

@@ -0,0 +1,98 @@
+"""Three-layer security policy for LangBot Box.
+
+The design separates concerns into three independent layers, aligned with
+OpenCode / OpenClaw patterns:
+
+1. **SandboxPolicy** – *where* tools run (host vs sandbox).
+2. **ToolPolicy** – *which* tools are allowed (allow/deny lists).
+3. **ElevatedPolicy** – *whether* a single exec call may temporarily
+   escape the default sandbox boundary.
+
+These three layers are orthogonal:
+- ToolPolicy is a hard boundary; ``elevated`` cannot bypass a denied tool.
+- SandboxPolicy decides the default execution location.
+- ElevatedPolicy only affects ``exec`` and only when the framework allows it.
+"""
+
+from __future__ import annotations
+
+import enum
+from typing import Sequence
+
+
+# ── Layer 1: Sandbox Policy ──────────────────────────────────────────
+
+
+class SandboxMode(str, enum.Enum):
+    """Determines when agent execution is routed through the sandbox."""
+
+    OFF = 'off'
+    """Sandbox disabled; all exec runs on the host."""
+
+    NON_DEFAULT = 'non_default'
+    """Only non-default sessions are sandboxed (e.g. sub-agents, MCP)."""
+
+    ALL = 'all'
+    """Every agent exec call is routed through the sandbox."""
+
+
+class SandboxPolicy:
+    """Decides whether a given execution context should use the sandbox."""
+
+    def __init__(self, mode: SandboxMode = SandboxMode.ALL):
+        self.mode = mode
+
+    def should_sandbox(self, *, is_default_session: bool = True) -> bool:
+        if self.mode == SandboxMode.OFF:
+            return False
+        if self.mode == SandboxMode.ALL:
+            return True
+        # NON_DEFAULT: sandbox everything except the default session
+        return not is_default_session
+
+
+# ── Layer 2: Tool Policy ─────────────────────────────────────────────
+
+
+class ToolPolicy:
+    """Controls which tools are available to the current agent/session.
+
+    Rules:
+    - ``deny`` always takes precedence over ``allow``.
+    - An empty ``allow`` list means "all tools allowed" (no allowlist filter).
+    - ``elevated`` cannot bypass a denied tool.
+    """
+
+    def __init__(
+        self,
+        allow: Sequence[str] = (),
+        deny: Sequence[str] = (),
+    ):
+        self._allow: frozenset[str] = frozenset(allow)
+        self._deny: frozenset[str] = frozenset(deny)
+
+    def is_tool_allowed(self, tool_name: str) -> bool:
+        if tool_name in self._deny:
+            return False
+        if self._allow and tool_name not in self._allow:
+            return False
+        return True
+
+
+# ── Layer 3: Elevated Policy ─────────────────────────────────────────
+
+
+class ElevatedPolicy:
+    """Controls whether ``exec`` may request temporary privilege escalation.
+
+    ``elevated`` only applies to the ``exec`` tool.  It means "run this
+    command outside the default sandbox boundary" (e.g. with network, or
+    on the host).  The framework decides whether to honor the request.
+    """
+
+    def __init__(self, *, allow_elevated: bool = False, require_approval: bool = True):
+        self.allow_elevated = allow_elevated
+        self.require_approval = require_approval
+
+    def is_elevation_permitted(self) -> bool:
+        return self.allow_elevated

src/langbot/pkg/box/service.py

@@ -0,0 +1,797 @@
+from __future__ import annotations
+
+import asyncio
+import collections
+import datetime as _dt
+import enum
+import json
+import os
+from typing import TYPE_CHECKING
+
+import pydantic
+
+from langbot_plugin.box.client import BoxRuntimeClient
+from .connector import BoxRuntimeConnector, _get_box_config
+from langbot_plugin.box.errors import BoxError, BoxValidationError
+from langbot_plugin.box.models import (
+    BUILTIN_PROFILES,
+    BoxExecutionResult,
+    BoxManagedProcessInfo,
+    BoxManagedProcessSpec,
+    BoxProfile,
+    BoxSpec,
+)
+
+_INT_ADAPTER = pydantic.TypeAdapter(int)
+_UTC = _dt.timezone.utc
+_MAX_RECENT_ERRORS = 50
+_MIB = 1024 * 1024
+
+
+def _is_path_under(path: str, root: str) -> bool:
+    """Check whether *path* equals *root* or is a child of *root*."""
+    return path == root or path.startswith(f'{root}{os.sep}')
+
+
+if TYPE_CHECKING:
+    from ..core import app as core_app
+    import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+
+
+class BoxService:
+    def __init__(
+        self,
+        ap: core_app.Application,
+        client: BoxRuntimeClient | None = None,
+        output_limit_chars: int = 4000,
+    ):
+        self.ap = ap
+        self._enabled = self._load_enabled()
+        self._runtime_connector: BoxRuntimeConnector | None = None
+        if client is None:
+            # Always construct a connector — its __init__ is side-effect free
+            # (no I/O, no subprocess). When ``box.enabled = false`` we simply
+            # skip ``connector.initialize()`` so no connection is attempted.
+            self._runtime_connector = BoxRuntimeConnector(ap, runtime_disconnect_callback=self._on_runtime_disconnect)
+            client = self._runtime_connector.client
+        self.client = client
+        self.output_limit_chars = output_limit_chars
+        self.host_root = self._load_host_root()
+        self.allowed_mount_roots = self._load_allowed_mount_roots()
+        self.default_workspace = self._load_default_workspace()
+        self.profile = self._load_profile()
+        self.custom_image = self._load_custom_image()
+        self.workspace_quota_mb = self._load_workspace_quota_mb()
+        self._recent_errors: collections.deque[dict] = collections.deque(maxlen=_MAX_RECENT_ERRORS)
+        self._shutdown_task = None
+        self._available = False
+        self._connector_error: str = ''
+        self._reconnecting = False
+
+    @property
+    def enabled(self) -> bool:
+        """Whether Box is enabled in config. False means the operator has
+        deliberately turned the sandbox off via ``box.enabled = false``.
+        Disabled and "enabled but unavailable" are reported as the same
+        ``available = False`` to consumers, but distinguished in get_status."""
+        return self._enabled
+
+    async def initialize(self):
+        self._ensure_default_workspace()
+        if not self._enabled:
+            # Disabled by config: do NOT connect to a remote runtime, do NOT
+            # fork a stdio subprocess. Every consumer of box_service should
+            # gate on ``available`` and degrade gracefully.
+            self._available = False
+            self._connector_error = 'Box runtime is disabled in config (box.enabled = false)'
+            self.ap.logger.info(
+                'Box runtime disabled by config; sandbox features (exec/read/write/edit, '
+                'skill add/edit, stdio MCP) will be unavailable.'
+            )
+            return
+        try:
+            if self._runtime_connector is not None:
+                await self._runtime_connector.initialize()
+            else:
+                await self.client.initialize()
+            self._available = True
+            self._connector_error = ''
+            self.ap.logger.info(
+                f'LangBot Box runtime initialized: profile={self.profile.name} '
+                f'default_workspace={self.default_workspace or "(none)"}'
+            )
+        except Exception as exc:
+            self.ap.logger.warning(f'LangBot Box runtime unavailable, sandbox features disabled: {exc}')
+            self._available = False
+            self._connector_error = str(exc)
+
+    async def _on_runtime_disconnect(self, connector: BoxRuntimeConnector) -> None:
+        """Called by the connector when the Box runtime connection drops.
+
+        Spawns a background reconnection loop so the caller is not blocked.
+        Skipped entirely when Box is disabled by config — that path should
+        never have connected in the first place.
+        """
+        if not self._enabled:
+            return
+        if self._reconnecting:
+            return  # Another reconnect loop is already running
+        self._reconnecting = True
+        self._available = False
+        self._connector_error = 'Disconnected from Box runtime'
+        self.ap.logger.warning('Box runtime disconnected, sandbox features temporarily disabled.')
+        asyncio.create_task(self._reconnect_loop(connector))
+
+    async def _reconnect_loop(self, connector: BoxRuntimeConnector) -> None:
+        """Retry reconnection with exponential backoff (3s → 60s max)."""
+        delay = 3
+        max_delay = 60
+        try:
+            while True:
+                self.ap.logger.info(f'Attempting to reconnect to Box runtime in {delay}s...')
+                await asyncio.sleep(delay)
+                try:
+                    connector.dispose()
+                    await connector.initialize()
+                    self._available = True
+                    self._connector_error = ''
+                    self.ap.logger.info('Box runtime reconnected, sandbox features restored.')
+                    return
+                except Exception as exc:
+                    self._connector_error = str(exc)
+                    self.ap.logger.warning(f'Box runtime reconnection failed: {exc}')
+                    delay = min(delay * 2, max_delay)
+        finally:
+            self._reconnecting = False
+
+    @property
+    def available(self) -> bool:
+        return self._available
+
+    async def execute_spec_payload(
+        self,
+        spec_payload: dict,
+        query: pipeline_query.Query,
+        *,
+        skip_host_mount_validation: bool = False,
+    ) -> dict:
+        if not self._available:
+            raise BoxError('Box runtime is not available. Install and start Docker to use sandbox features.')
+        try:
+            spec = self.build_spec(spec_payload, skip_host_mount_validation=skip_host_mount_validation)
+        except BoxError as exc:
+            self._record_error(exc, query)
+            raise
+        self.ap.logger.info(
+            'LangBot Box request: '
+            f'query_id={query.query_id} '
+            f'spec={json.dumps(self._summarize_spec(spec), ensure_ascii=False)}'
+        )
+        try:
+            await self._enforce_workspace_quota(spec, phase='before execution')
+        except BoxError as exc:
+            self._record_error(exc, query)
+            raise
+        try:
+            result = await self.client.execute(spec)
+        except BoxError as exc:
+            self._record_error(exc, query)
+            raise
+        try:
+            await self._enforce_workspace_quota(spec, phase='after execution')
+        except BoxError as exc:
+            await self._cleanup_exceeded_session(spec)
+            self._record_error(exc, query)
+            raise
+        self.ap.logger.info(
+            'LangBot Box result: '
+            f'query_id={query.query_id} '
+            f'summary={json.dumps(self._summarize_result(result), ensure_ascii=False)}'
+        )
+        return self._serialize_result(result)
+
+    def resolve_box_session_id(self, query: pipeline_query.Query) -> str:
+        """Resolve the Box session_id from the pipeline's template and query variables."""
+        template = (
+            (query.pipeline_config or {})
+            .get('ai', {})
+            .get('local-agent', {})
+            .get('box-session-id-template', '{launcher_type}_{launcher_id}')
+        )
+        variables = dict(query.variables or {})
+        launcher_type = getattr(query, 'launcher_type', None)
+        if hasattr(launcher_type, 'value'):
+            launcher_type = launcher_type.value
+        launcher_id = getattr(query, 'launcher_id', None)
+        sender_id = getattr(query, 'sender_id', None)
+        query_id = getattr(query, 'query_id', None)
+
+        variables.setdefault('query_id', str(query_id or 'unknown'))
+        variables.setdefault('launcher_type', str(launcher_type or 'query'))
+        variables.setdefault('launcher_id', str(launcher_id or query_id or 'unknown'))
+        variables.setdefault('sender_id', str(sender_id or launcher_id or query_id or 'unknown'))
+        variables.setdefault('global', 'global')
+        return template.format_map(collections.defaultdict(lambda: 'unknown', variables))
+
+    def build_skill_extra_mounts(self, query: pipeline_query.Query) -> list[dict]:
+        """Build extra_mounts entries for all pipeline-bound skills.
+
+        This ensures that when a container is first created it already has
+        all skill packages mounted, regardless of which skill is currently
+        activated.
+
+        Skills whose ``package_root`` is missing or no longer a directory on
+        the LangBot-visible filesystem are skipped with a warning instead of
+        being passed through to the backend. Without this guard the three
+        backends behave inconsistently on a stale mount: nsjail refuses to
+        start the sandbox (failing every exec in the session), Docker
+        silently auto-creates a root-owned empty directory on the host, and
+        E2B silently skips the upload — none of which surfaces an
+        actionable error to the agent or operator.
+        """
+        skill_mgr = getattr(self.ap, 'skill_mgr', None)
+        if skill_mgr is None:
+            return []
+
+        from ..provider.tools.loaders import skill as skill_loader
+
+        visible_skills = skill_loader.get_visible_skills(self.ap, query)
+        mounts: list[dict] = []
+        for skill_name, skill_data in visible_skills.items():
+            package_root = str(skill_data.get('package_root', '') or '').strip()
+            if not package_root:
+                continue
+            if not os.path.isdir(package_root):
+                self.ap.logger.warning(
+                    f'Skill "{skill_name}" package_root missing on filesystem '
+                    f'({package_root}); skipping mount to prevent sandbox failures. '
+                    f'The skill cache may be stale — consider reloading skills.'
+                )
+                continue
+            mounts.append(
+                {
+                    'host_path': package_root,
+                    'mount_path': f'/workspace/.skills/{skill_name}',
+                    'mode': 'rw',
+                }
+            )
+        return mounts
+
+    async def execute_tool(self, parameters: dict, query: pipeline_query.Query) -> dict:
+        """Execute an agent-facing ``exec`` tool call.
+
+        Translates the agent-facing ``command`` field to the internal
+        ``BoxSpec.cmd`` field and injects the session id from the query.
+        """
+        spec_payload: dict = {'cmd': parameters['command']}
+
+        # Pass through allowed agent-facing fields
+        for key in ('workdir', 'timeout_sec', 'env'):
+            if key in parameters:
+                spec_payload[key] = parameters[key]
+
+        # Inject context the agent must not control
+        spec_payload.setdefault('session_id', self.resolve_box_session_id(query))
+
+        # Mount all pipeline-bound skills so they are available in the container
+        if 'extra_mounts' not in spec_payload:
+            spec_payload['extra_mounts'] = self.build_skill_extra_mounts(query)
+
+        return await self.execute_spec_payload(spec_payload, query)
+
+    async def shutdown(self):
+        await self.client.shutdown()
+
+    def dispose(self):
+        if self._runtime_connector is not None:
+            self._runtime_connector.dispose()
+        loop = getattr(self.ap, 'event_loop', None)
+        if loop is not None and not loop.is_closed() and (self._shutdown_task is None or self._shutdown_task.done()):
+            self._shutdown_task = loop.create_task(self.shutdown())
+
+    async def get_sessions(self) -> list[dict]:
+        if not self._available:
+            return []
+        try:
+            return await self.client.get_sessions()
+        except Exception:
+            return []
+
+    def build_spec(self, spec_payload: dict, skip_host_mount_validation: bool = False) -> BoxSpec:
+        spec_payload = dict(spec_payload)
+        spec_payload.setdefault('env', {})
+        if spec_payload.get('host_path') in (None, '') and self.default_workspace is not None:
+            spec_payload['host_path'] = self.default_workspace
+        if spec_payload.get('workspace_quota_mb') in (None, '') and self.workspace_quota_mb is not None:
+            spec_payload['workspace_quota_mb'] = self.workspace_quota_mb
+
+        # Global custom image overrides profile default (but not caller-specified image)
+        if self.custom_image and 'image' not in spec_payload:
+            spec_payload['image'] = self.custom_image
+
+        self._apply_profile(spec_payload)
+
+        try:
+            spec = BoxSpec.model_validate(spec_payload)
+        except pydantic.ValidationError as exc:
+            first_error = exc.errors()[0]
+            raise BoxValidationError(first_error.get('msg', 'invalid box arguments')) from exc
+
+        if not skip_host_mount_validation:
+            self._validate_host_mount(spec)
+        return spec
+
+    async def create_session(self, spec_payload: dict, *, skip_host_mount_validation: bool = False) -> dict:
+        spec = self.build_spec(spec_payload, skip_host_mount_validation=skip_host_mount_validation)
+        return await self.client.create_session(spec)
+
+    async def start_managed_process(self, session_id: str, process_payload: dict) -> BoxManagedProcessInfo:
+        process_spec = BoxManagedProcessSpec.model_validate(process_payload)
+        return await self.client.start_managed_process(session_id, process_spec)
+
+    async def get_managed_process(self, session_id: str, process_id: str = 'default') -> BoxManagedProcessInfo:
+        return await self.client.get_managed_process(session_id, process_id)
+
+    async def stop_managed_process(self, session_id: str, process_id: str = 'default') -> None:
+        return await self.client.stop_managed_process(session_id, process_id)
+
+    def get_managed_process_websocket_url(self, session_id: str, process_id: str = 'default') -> str:
+        getter = getattr(self.client, 'get_managed_process_websocket_url', None)
+        if getter is None:
+            raise BoxValidationError('box runtime client does not support managed process websocket attach')
+        ws_relay_base_url = (
+            self._runtime_connector.ws_relay_base_url
+            if self._runtime_connector is not None
+            else 'http://127.0.0.1:5410'
+        )
+        return getter(session_id, ws_relay_base_url, process_id)
+
+    async def list_skills(self) -> list[dict]:
+        return await self.client.list_skills()
+
+    async def get_skill(self, name: str) -> dict | None:
+        return await self.client.get_skill(name)
+
+    async def create_skill(self, skill: dict) -> dict:
+        return await self.client.create_skill(skill)
+
+    async def update_skill(self, name: str, skill: dict) -> dict:
+        return await self.client.update_skill(name, skill)
+
+    async def delete_skill(self, name: str) -> None:
+        await self.client.delete_skill(name)
+
+    async def scan_skill_directory(self, path: str) -> dict:
+        return await self.client.scan_skill_directory(path)
+
+    async def list_skill_files(
+        self,
+        name: str,
+        path: str = '.',
+        include_hidden: bool = False,
+        max_entries: int = 200,
+    ) -> dict:
+        return await self.client.list_skill_files(name, path, include_hidden, max_entries)
+
+    async def read_skill_file(self, name: str, path: str) -> dict:
+        return await self.client.read_skill_file(name, path)
+
+    async def write_skill_file(self, name: str, path: str, content: str) -> dict:
+        return await self.client.write_skill_file(name, path, content)
+
+    async def preview_skill_zip(
+        self,
+        file_bytes: bytes,
+        filename: str,
+        source_subdir: str = '',
+        target_suffix: str = 'upload',
+    ) -> list[dict]:
+        return await self.client.preview_skill_zip(file_bytes, filename, source_subdir, target_suffix)
+
+    async def install_skill_zip(
+        self,
+        file_bytes: bytes,
+        filename: str,
+        source_paths: list[str] | None = None,
+        source_path: str = '',
+        source_subdir: str = '',
+        target_suffix: str = 'upload',
+    ) -> list[dict]:
+        return await self.client.install_skill_zip(
+            file_bytes,
+            filename,
+            source_paths,
+            source_path,
+            source_subdir,
+            target_suffix,
+        )
+
+    def _serialize_result(self, result: BoxExecutionResult) -> dict:
+        stdout, stdout_truncated = self._truncate(result.stdout)
+        stderr, stderr_truncated = self._truncate(result.stderr)
+
+        return {
+            'session_id': result.session_id,
+            'backend': result.backend_name,
+            'status': result.status.value,
+            'ok': result.ok,
+            'exit_code': result.exit_code,
+            'stdout': stdout,
+            'stderr': stderr,
+            'stdout_truncated': stdout_truncated,
+            'stderr_truncated': stderr_truncated,
+            'duration_ms': result.duration_ms,
+        }
+
+    def _truncate(self, text: str) -> tuple[str, bool]:
+        if len(text) <= self.output_limit_chars:
+            return text, False
+        if self.output_limit_chars <= 0:
+            return '', True
+
+        head_size = 0
+        tail_size = 0
+        notice = ''
+        # Recompute once the omitted count is known so the final payload
+        # stays within output_limit_chars even after adding the notice.
+        for _ in range(4):
+            omitted = max(len(text) - head_size - tail_size, 0)
+            notice = f'\n\n... [{omitted} characters truncated] ...\n\n'
+            available = self.output_limit_chars - len(notice)
+            if available <= 0:
+                return notice[: self.output_limit_chars], True
+
+            new_head_size = int(available * 0.6)
+            new_tail_size = available - new_head_size
+            if new_head_size == head_size and new_tail_size == tail_size:
+                break
+            head_size = new_head_size
+            tail_size = new_tail_size
+
+        head = text[:head_size]
+        tail = text[-tail_size:] if tail_size else ''
+        truncated = f'{head}{notice}{tail}'
+        return truncated[: self.output_limit_chars], True
+
+    def _summarize_spec(self, spec: BoxSpec) -> dict:
+        cmd = spec.cmd.strip()
+        if len(cmd) > 400:
+            cmd = f'{cmd[:397]}...'
+
+        return {
+            'session_id': spec.session_id,
+            'workdir': spec.workdir,
+            'mount_path': spec.mount_path,
+            'timeout_sec': spec.timeout_sec,
+            'network': spec.network.value,
+            'image': spec.image,
+            'host_path': spec.host_path,
+            'host_path_mode': spec.host_path_mode.value,
+            'cpus': spec.cpus,
+            'memory_mb': spec.memory_mb,
+            'pids_limit': spec.pids_limit,
+            'read_only_rootfs': spec.read_only_rootfs,
+            'workspace_quota_mb': spec.workspace_quota_mb,
+            'env_keys': sorted(spec.env.keys()),
+            'cmd': cmd,
+        }
+
+    def _summarize_result(self, result: BoxExecutionResult) -> dict:
+        stdout_preview = result.stdout[:200]
+        stderr_preview = result.stderr[:200]
+        if len(result.stdout) > 200:
+            stdout_preview = f'{stdout_preview}...'
+        if len(result.stderr) > 200:
+            stderr_preview = f'{stderr_preview}...'
+
+        return {
+            'session_id': result.session_id,
+            'backend': result.backend_name,
+            'status': result.status.value,
+            'exit_code': result.exit_code,
+            'duration_ms': result.duration_ms,
+            'stdout_preview': stdout_preview,
+            'stderr_preview': stderr_preview,
+        }
+
+    def _local_config(self) -> dict:
+        """Return ``box.local`` from instance config.
+
+        Environment overrides are applied uniformly by
+        ``LoadConfigStage._apply_env_overrides_to_config`` (e.g.
+        ``BOX__LOCAL__HOST_ROOT``) before this is read, so no box-specific
+        env parsing happens here.
+        """
+        return dict(_get_box_config(self.ap).get('local') or {})
+
+    def _load_allowed_mount_roots(self) -> list[str]:
+        configured_roots = self._local_config().get('allowed_mount_roots', [])
+        # The unified env-override mechanism stores a brand-new key as a raw
+        # string when the key is absent from config.yaml. Accept a
+        # comma-separated string as well as a list so that
+        # ``BOX__LOCAL__ALLOWED_MOUNT_ROOTS="/a,/b"`` keeps working even when
+        # the config file has no ``box.local.allowed_mount_roots`` entry.
+        if isinstance(configured_roots, str):
+            configured_roots = [item.strip() for item in configured_roots.split(',') if item.strip()]
+
+        normalized_roots: list[str] = []
+        for root in configured_roots:
+            root_value = str(root).strip()
+            if not root_value:
+                continue
+            normalized_roots.append(os.path.realpath(os.path.abspath(root_value)))
+
+        if not normalized_roots and self.host_root is not None:
+            normalized_roots.append(self.host_root)
+
+        return normalized_roots
+
+    def _load_host_root(self) -> str | None:
+        host_root = str(self._local_config().get('host_root', '')).strip()
+        if not host_root:
+            return None
+        return os.path.realpath(os.path.abspath(host_root))
+
+    def _load_default_workspace(self) -> str | None:
+        default_workspace = str(self._local_config().get('default_workspace', '')).strip()
+        if not default_workspace:
+            if self.host_root is None:
+                return None
+            default_workspace = os.path.join(self.host_root, 'default')
+        elif not os.path.isabs(default_workspace) and self.host_root is not None:
+            default_workspace = os.path.join(self.host_root, default_workspace)
+        return os.path.realpath(os.path.abspath(default_workspace))
+
+    def get_skills_root(self) -> str | None:
+        skills_root = str(self._local_config().get('skills_root', '') or 'skills').strip()
+        if not skills_root:
+            skills_root = 'skills'
+        if not os.path.isabs(skills_root) and self.host_root is not None:
+            skills_root = os.path.join(self.host_root, skills_root)
+        return os.path.realpath(os.path.abspath(skills_root))
+
+    def _load_enabled(self) -> bool:
+        """Read ``box.enabled`` (top-level, not ``box.local.*``). Default True
+        — disabling is opt-in. Accepts bool, ``'true'``/``'false'`` strings,
+        and the standard env-overridden truthy values that
+        ``LoadConfigStage._apply_env_overrides_to_config`` produces."""
+        raw = _get_box_config(self.ap).get('enabled', True)
+        if isinstance(raw, bool):
+            return raw
+        return str(raw).strip().lower() not in ('false', '0', 'no', 'off', '')
+
+    def _load_custom_image(self) -> str | None:
+        raw = str(self._local_config().get('image', '') or '').strip()
+        return raw or None
+
+    def _load_workspace_quota_mb(self) -> int | None:
+        raw_value = self._local_config().get('workspace_quota_mb')
+        if raw_value in (None, ''):
+            return None
+        try:
+            value = _INT_ADAPTER.validate_python(raw_value)
+        except pydantic.ValidationError as exc:
+            raise BoxValidationError('workspace_quota_mb must be an integer greater than or equal to 0') from exc
+        if value < 0:
+            raise BoxValidationError('workspace_quota_mb must be greater than or equal to 0')
+        return value
+
+    def _ensure_default_workspace(self):
+        if self.default_workspace is None:
+            return
+
+        if os.path.isdir(self.default_workspace):
+            return
+
+        if os.path.exists(self.default_workspace):
+            raise BoxValidationError('box.local.default_workspace must point to a directory on the host')
+
+        if not self.allowed_mount_roots:
+            raise BoxValidationError(
+                'box.local.default_workspace cannot be created because no allowed_mount_roots are configured'
+            )
+
+        for allowed_root in self.allowed_mount_roots:
+            if _is_path_under(self.default_workspace, allowed_root):
+                os.makedirs(self.default_workspace, exist_ok=True)
+                return
+
+        allowed_roots = ', '.join(self.allowed_mount_roots)
+        raise BoxValidationError(f'box.local.default_workspace is outside allowed_mount_roots: {allowed_roots}')
+
+    def _validate_host_mount(self, spec: BoxSpec):
+        if spec.host_path is None:
+            return
+
+        host_path = os.path.realpath(spec.host_path)
+        if not os.path.isdir(host_path):
+            raise BoxValidationError('host_path must point to an existing directory on the host')
+
+        if not self.allowed_mount_roots:
+            raise BoxValidationError('host_path mounting is disabled because no allowed_mount_roots are configured')
+
+        for allowed_root in self.allowed_mount_roots:
+            if _is_path_under(host_path, allowed_root):
+                return
+
+        allowed_roots = ', '.join(self.allowed_mount_roots)
+        raise BoxValidationError(f'host_path is outside allowed_mount_roots: {allowed_roots}')
+
+    def _load_profile(self) -> BoxProfile:
+        profile_name = str(self._local_config().get('profile', 'default')).strip() or 'default'
+
+        profile = BUILTIN_PROFILES.get(profile_name)
+        if profile is None:
+            available = ', '.join(sorted(BUILTIN_PROFILES))
+            raise BoxValidationError(f"unknown box profile '{profile_name}', available profiles: {available}")
+        return profile
+
+    def _apply_profile(self, params: dict):
+        """Merge profile defaults into *params* in-place, enforce locked fields and clamp timeout."""
+        profile = self.profile
+        _PROFILE_FIELDS = (
+            'image',
+            'network',
+            'timeout_sec',
+            'host_path_mode',
+            'cpus',
+            'memory_mb',
+            'pids_limit',
+            'read_only_rootfs',
+            'workspace_quota_mb',
+        )
+
+        for field in _PROFILE_FIELDS:
+            profile_value = getattr(profile, field)
+            raw_value = profile_value.value if isinstance(profile_value, enum.Enum) else profile_value
+
+            if field in profile.locked:
+                params[field] = raw_value
+            elif field not in params:
+                params[field] = raw_value
+
+        timeout = params.get('timeout_sec')
+        try:
+            normalized_timeout = _INT_ADAPTER.validate_python(timeout)
+        except pydantic.ValidationError:
+            return
+
+        if normalized_timeout > profile.max_timeout_sec:
+            params['timeout_sec'] = profile.max_timeout_sec
+
+    def _get_workspace_size_bytes(self, root: str) -> int:
+        total = 0
+
+        def _walk(path: str):
+            nonlocal total
+            try:
+                with os.scandir(path) as entries:
+                    for entry in entries:
+                        try:
+                            if entry.is_symlink():
+                                total += entry.stat(follow_symlinks=False).st_size
+                                continue
+                            if entry.is_dir(follow_symlinks=False):
+                                _walk(entry.path)
+                                continue
+                            total += entry.stat(follow_symlinks=False).st_size
+                        except FileNotFoundError:
+                            continue
+            except FileNotFoundError:
+                return
+
+        _walk(root)
+        return total
+
+    async def _enforce_workspace_quota(self, spec: BoxSpec, *, phase: str) -> None:
+        if spec.host_path is None or spec.workspace_quota_mb <= 0:
+            return
+
+        host_path = os.path.realpath(spec.host_path)
+        if not os.path.isdir(host_path):
+            return
+
+        # 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
+
+        raise BoxValidationError(
+            f'workspace quota exceeded {phase}: '
+            f'used={used_bytes} bytes limit={limit_bytes} bytes '
+            f'host_path={host_path} session_id={spec.session_id}'
+        )
+
+    async def _cleanup_exceeded_session(self, spec: BoxSpec) -> None:
+        try:
+            await self.client.delete_session(spec.session_id)
+        except Exception as exc:
+            self.ap.logger.warning(
+                'Failed to clean up Box session after workspace quota was exceeded: '
+                f'session_id={spec.session_id} error={exc}'
+            )
+
+    # ── Observability ─────────────────────────────────────────────────
+
+    def _record_error(self, exc: Exception, query: pipeline_query.Query):
+        self._recent_errors.append(
+            {
+                'timestamp': _dt.datetime.now(_UTC).isoformat(),
+                'type': type(exc).__name__,
+                'message': str(exc),
+                'query_id': str(query.query_id),
+            }
+        )
+
+    def get_recent_errors(self) -> list[dict]:
+        return list(self._recent_errors)
+
+    def get_system_guidance(self) -> str:
+        """Return LLM system-prompt guidance for the exec tool.
+
+        All execution-specific prompt text is kept here so that callers
+        (e.g. LocalAgentRunner) stay free of box domain knowledge.
+        """
+        guidance = (
+            'When the exec tool is available, use it for exact calculations, statistics, structured data parsing, '
+            'and code execution instead of estimating mentally. If the user provides numbers, tables, CSV-like text, '
+            'JSON, or other data and asks for a computed answer, prefer running a short Python script via exec '
+            'and then answer from the tool result. Unless the user explicitly asks for the script, code, or implementation '
+            'details, do not include the generated script in the final answer; return the result and a brief explanation only.'
+        )
+        if self.default_workspace:
+            guidance += (
+                ' A default workspace is mounted at /workspace for file tasks. When the user asks to read, create, or '
+                'modify local files in the working directory, use exec with /workspace paths directly; do not ask the '
+                'user for directory parameters unless they explicitly need a different directory.'
+            )
+        return guidance
+
+    async def get_status(self) -> dict:
+        if not self._available:
+            return {
+                'available': False,
+                'enabled': self._enabled,
+                'profile': self.profile.name,
+                'recent_error_count': len(self._recent_errors),
+                'connector_error': self._connector_error,
+            }
+        try:
+            runtime_status = await self.client.get_status()
+        except Exception as exc:
+            # RPC failed — the runtime likely just disconnected and the
+            # heartbeat hasn't flipped _available yet.
+            return {
+                'available': False,
+                'enabled': self._enabled,
+                'profile': self.profile.name,
+                'recent_error_count': len(self._recent_errors),
+                'connector_error': str(exc),
+            }
+        # Backend state can be unavailable even when the connector is healthy
+        # (operator selected nsjail but the binary is missing, Docker daemon
+        # went down after the runtime started, E2B credentials wrong, ...).
+        # Report the combined state in the top-level ``available`` so the
+        # frontend banner / ``useBoxStatus`` hook / native-tool gate all
+        # agree on "actually usable" rather than "connector alive". The
+        # detailed ``backend`` object stays in the payload so the dialog
+        # can still show which backend was tried.
+        backend_info = runtime_status.get('backend') if isinstance(runtime_status, dict) else None
+        backend_ok = bool(backend_info and backend_info.get('available', False))
+        payload = {
+            **runtime_status,
+            'available': backend_ok,
+            'enabled': self._enabled,
+            'profile': self.profile.name,
+            'recent_error_count': len(self._recent_errors),
+        }
+        if not backend_ok and 'connector_error' not in payload:
+            backend_name = backend_info.get('name') if backend_info else None
+            if backend_name:
+                payload['connector_error'] = f'Configured sandbox backend "{backend_name}" is unavailable'
+            else:
+                payload['connector_error'] = 'No supported sandbox backend (Docker / nsjail / E2B) is available'
+        return payload

src/langbot/pkg/box/workspace.py

@@ -0,0 +1,413 @@
+"""Reusable workspace/session helpers built on top of Box.
+
+This module is the middle layer between the raw Box runtime primitives and
+application-specific flows such as skills or MCP stdio.
+
+It intentionally stays generic:
+- path and virtualenv rewriting are workspace concerns
+- Python project detection/bootstrap are workspace concerns
+- session exec / managed-process helpers are workspace concerns
+
+Higher layers add their own semantics on top, for example:
+- skills choose a stable per-skill session id and use repeated exec
+- MCP stdio chooses how to prepare dependencies and attaches to a managed process
+"""
+
+from __future__ import annotations
+
+import os
+import textwrap
+from typing import Any
+
+PYTHON_MANIFEST_FILES = (
+    'requirements.txt',
+    'pyproject.toml',
+    'setup.py',
+    'setup.cfg',
+)
+_VENV_DIRS = frozenset({'.venv', 'venv', 'env', '.env'})
+_VENV_BIN_DIRS = frozenset({'bin', 'Scripts'})
+
+
+def normalize_host_path(path: str | None) -> str:
+    if path is None:
+        return ''
+    stripped = str(path).strip()
+    if not stripped:
+        return ''
+    return os.path.realpath(os.path.abspath(stripped))
+
+
+def rewrite_mounted_path(path: str, host_path: str | None, *, mount_path: str = '/workspace') -> str:
+    """Translate a host path into the path visible inside the sandbox mount."""
+    if not host_path or not path:
+        return path
+    normalized_host = os.path.realpath(host_path)
+    normalized_path = os.path.realpath(path)
+    if normalized_path.startswith(normalized_host + '/'):
+        return mount_path + normalized_path[len(normalized_host) :]
+    if normalized_path == normalized_host:
+        return mount_path
+    return path
+
+
+def unwrap_venv_path(directory: str) -> str:
+    """Collapse ``.../.venv/bin`` style paths back to the project root."""
+    parts = directory.replace('\\', '/').split('/')
+    for i in range(len(parts) - 1, 0, -1):
+        if parts[i] in _VENV_BIN_DIRS and i >= 1:
+            venv_dir = parts[i - 1]
+            if venv_dir in _VENV_DIRS:
+                project_root = '/'.join(parts[: i - 1])
+                return project_root if project_root else '/'
+    return directory
+
+
+def infer_workspace_host_path(command: str, args: list[str] | None = None) -> str | None:
+    """Infer the project/workspace root from absolute command/arg paths."""
+    candidates: list[str] = []
+    for part in [command, *(args or [])]:
+        if not os.path.isabs(part):
+            continue
+        if os.path.exists(part):
+            directory = os.path.dirname(part)
+            candidates.append(os.path.realpath(unwrap_venv_path(directory)))
+    if not candidates:
+        return None
+    common = os.path.commonpath(candidates)
+    return common if common != '/' else None
+
+
+def rewrite_venv_command(command: str, host_path: str | None, *, mount_path: str = '/workspace') -> str:
+    """Rewrite host venv interpreters to plain ``python`` inside the sandbox.
+
+    Once a project is mounted into the sandbox, host virtualenv paths are no
+    longer valid. For those paths we intentionally drop down to ``python`` and
+    let the sandbox-side environment/bootstrap decide what interpreter to use.
+    """
+    if not host_path or not command:
+        return command
+    normalized_host = os.path.realpath(host_path)
+    normalized_command = os.path.realpath(command)
+    if not normalized_command.startswith(normalized_host + '/'):
+        return command
+    rel = normalized_command[len(normalized_host) + 1 :]
+    parts = rel.replace('\\', '/').split('/')
+    if len(parts) >= 3 and parts[0] in _VENV_DIRS and parts[1] in _VENV_BIN_DIRS and parts[2].startswith('python'):
+        return 'python'
+    return rewrite_mounted_path(normalized_command, host_path, mount_path=mount_path)
+
+
+def list_python_manifest_files(host_path: str | None) -> list[str]:
+    normalized_root = normalize_host_path(host_path)
+    if not normalized_root:
+        return []
+    return [filename for filename in PYTHON_MANIFEST_FILES if os.path.isfile(os.path.join(normalized_root, filename))]
+
+
+def classify_python_workspace(host_path: str | None) -> str | None:
+    """Return the generic Python workspace shape, without app-specific policy."""
+    manifest_files = set(list_python_manifest_files(host_path))
+    if not manifest_files:
+        return None
+    if {'pyproject.toml', 'setup.py', 'setup.cfg'} & manifest_files:
+        return 'package'
+    if 'requirements.txt' in manifest_files:
+        return 'requirements'
+    return None
+
+
+def should_prepare_python_env(host_path: str | None) -> bool:
+    normalized_root = normalize_host_path(host_path)
+    if not normalized_root:
+        return False
+    if os.path.isdir(os.path.join(normalized_root, '.venv')):
+        return True
+    return bool(list_python_manifest_files(normalized_root))
+
+
+def wrap_python_command_with_env(command: str, *, mount_path: str = '/workspace') -> str:
+    """Wrap a command with a reusable sandbox-local Python env bootstrap.
+
+    This is the generic "workspace is a Python project" path used by mutable
+    workspaces such as skills. Read-only installation strategies stay in the
+    higher-level caller because they are application policy, not workspace
+    semantics.
+    """
+    bootstrap = textwrap.dedent(
+        f"""
+        set -e
+
+        _LB_VENV_DIR="{mount_path}/.venv"
+        _LB_META_DIR="{mount_path}/.langbot"
+        _LB_META_FILE="$_LB_META_DIR/python-env.json"
+        _LB_LOCK_DIR="$_LB_META_DIR/python-env.lock"
+        _LB_TMP_DIR="{mount_path}/.tmp"
+        _LB_PIP_CACHE_DIR="{mount_path}/.cache/pip"
+
+        mkdir -p "$_LB_META_DIR" "$_LB_TMP_DIR" "$_LB_PIP_CACHE_DIR"
+        export TMPDIR="$_LB_TMP_DIR"
+        export TEMP="$_LB_TMP_DIR"
+        export TMP="$_LB_TMP_DIR"
+        export PIP_CACHE_DIR="$_LB_PIP_CACHE_DIR"
+
+        _lb_python_meta() {{
+          python - <<'PY'
+        import hashlib
+        import json
+        import os
+        import sys
+
+        root = "{mount_path}"
+        digest = hashlib.sha256()
+        manifest_files = []
+        for rel in ("requirements.txt", "pyproject.toml", "setup.py", "setup.cfg"):
+            path = os.path.join(root, rel)
+            if not os.path.isfile(path):
+                continue
+            manifest_files.append(rel)
+            with open(path, "rb") as handle:
+                digest.update(rel.encode("utf-8"))
+                digest.update(b"\\0")
+                digest.update(handle.read())
+                digest.update(b"\\0")
+
+        print(
+            json.dumps(
+                {{
+                    "python_executable": sys.executable,
+                    "python_version": list(sys.version_info[:3]),
+                    "manifest_files": manifest_files,
+                    "manifest_sha256": digest.hexdigest(),
+                }},
+                sort_keys=True,
+            )
+        )
+        PY
+        }}
+
+        _LB_CURRENT_META="$(_lb_python_meta)"
+        _LB_NEEDS_BOOTSTRAP=0
+
+        if [ ! -x "$_LB_VENV_DIR/bin/python" ]; then
+          _LB_NEEDS_BOOTSTRAP=1
+        elif [ ! -f "$_LB_META_FILE" ]; then
+          _LB_NEEDS_BOOTSTRAP=1
+        elif [ "$(cat "$_LB_META_FILE")" != "$_LB_CURRENT_META" ]; then
+          _LB_NEEDS_BOOTSTRAP=1
+        fi
+
+        if [ "$_LB_NEEDS_BOOTSTRAP" -eq 1 ]; then
+          _LB_LOCK_WAIT=0
+          while ! mkdir "$_LB_LOCK_DIR" 2>/dev/null; do
+            if [ "$_LB_LOCK_WAIT" -ge 120 ]; then
+              echo "Timed out waiting for Python environment lock: $_LB_LOCK_DIR" >&2
+              exit 1
+            fi
+            sleep 1
+            _LB_LOCK_WAIT=$((_LB_LOCK_WAIT + 1))
+          done
+
+          _lb_cleanup_lock() {{
+            rmdir "$_LB_LOCK_DIR" >/dev/null 2>&1 || true
+          }}
+          trap _lb_cleanup_lock EXIT INT TERM
+
+          _LB_CURRENT_META="$(_lb_python_meta)"
+          _LB_NEEDS_BOOTSTRAP=0
+          if [ ! -x "$_LB_VENV_DIR/bin/python" ]; then
+            _LB_NEEDS_BOOTSTRAP=1
+          elif [ ! -f "$_LB_META_FILE" ]; then
+            _LB_NEEDS_BOOTSTRAP=1
+          elif [ "$(cat "$_LB_META_FILE")" != "$_LB_CURRENT_META" ]; then
+            _LB_NEEDS_BOOTSTRAP=1
+          fi
+
+          if [ "$_LB_NEEDS_BOOTSTRAP" -eq 1 ]; then
+            rm -rf "$_LB_VENV_DIR"
+            python -m venv "$_LB_VENV_DIR"
+            . "$_LB_VENV_DIR/bin/activate"
+            python -m pip install --upgrade pip setuptools wheel
+            if [ -f "{mount_path}/requirements.txt" ]; then
+              python -m pip install -r "{mount_path}/requirements.txt"
+            elif [ -f "{mount_path}/pyproject.toml" ] || [ -f "{mount_path}/setup.py" ] || [ -f "{mount_path}/setup.cfg" ]; then
+              python -m pip install "{mount_path}"
+            fi
+            printf '%s' "$_LB_CURRENT_META" > "$_LB_META_FILE"
+          fi
+        fi
+
+        export VIRTUAL_ENV="$_LB_VENV_DIR"
+        export PATH="$_LB_VENV_DIR/bin:$PATH"
+        {command}
+        """
+    ).strip()
+    return bootstrap + '\n'
+
+
+class BoxWorkspaceSession:
+    """High-level handle for one reusable workspace-backed Box session.
+
+    The Box runtime already understands sessions and managed processes. This
+    wrapper adds LangBot's workspace-centric view on top: a mounted host path,
+    a stable ``session_id``, optional environment defaults, and convenience
+    helpers for exec or long-running processes inside that workspace.
+    """
+
+    def __init__(
+        self,
+        box_service,
+        session_id: str,
+        *,
+        host_path: str | None = None,
+        host_path_mode: str = 'rw',
+        workdir: str = '/workspace',
+        env: dict[str, str] | None = None,
+        mount_path: str = '/workspace',
+        network: str | None = None,
+        read_only_rootfs: bool | None = None,
+        image: str | None = None,
+        cpus: float | None = None,
+        memory_mb: int | None = None,
+        pids_limit: int | None = None,
+        persistent: bool = False,
+    ):
+        self.box_service = box_service
+        self.session_id = session_id
+        self.host_path = host_path
+        self.host_path_mode = host_path_mode
+        self.workdir = workdir
+        self.env = dict(env or {})
+        self.mount_path = mount_path
+        self.network = network
+        self.read_only_rootfs = read_only_rootfs
+        self.image = image
+        self.cpus = cpus
+        self.memory_mb = memory_mb
+        self.pids_limit = pids_limit
+        self.persistent = persistent
+
+    def rewrite_path(self, path: str) -> str:
+        return rewrite_mounted_path(path, self.host_path, mount_path=self.mount_path)
+
+    def rewrite_venv_command(self, command: str) -> str:
+        return rewrite_venv_command(command, self.host_path, mount_path=self.mount_path)
+
+    def build_session_payload(self) -> dict[str, Any]:
+        # Keep this payload generic so callers can reuse the same workspace
+        # handle for plain exec, file-producing tasks, or managed processes.
+        payload: dict[str, Any] = {
+            'session_id': self.session_id,
+            'workdir': self.workdir,
+            'env': self.env,
+            'persistent': self.persistent,
+        }
+        if self.network is not None:
+            payload['network'] = self.network
+        if self.read_only_rootfs is not None:
+            payload['read_only_rootfs'] = self.read_only_rootfs
+        if self.host_path:
+            payload['host_path'] = self.host_path
+            payload['host_path_mode'] = self.host_path_mode
+        for key in ('image', 'cpus', 'memory_mb', 'pids_limit'):
+            value = getattr(self, key)
+            if value is not None:
+                payload[key] = value
+        return payload
+
+    def build_exec_payload(
+        self,
+        cmd: str,
+        *,
+        workdir: str | None = None,
+        env: dict[str, str] | None = None,
+        timeout_sec: int | None = None,
+    ) -> dict[str, Any]:
+        # Exec payloads inherit the session-level workspace config, then layer
+        # per-call command/workdir/env overrides on top.
+        payload = self.build_session_payload()
+        payload['cmd'] = cmd
+        payload['workdir'] = workdir or self.workdir
+        if timeout_sec is not None:
+            payload['timeout_sec'] = timeout_sec
+        resolved_env = self.env if env is None else env
+        if resolved_env:
+            payload['env'] = resolved_env
+        elif 'env' in payload and not payload['env']:
+            payload.pop('env')
+        return payload
+
+    async def execute_raw(
+        self,
+        cmd: str,
+        *,
+        workdir: str | None = None,
+        env: dict[str, str] | None = None,
+        timeout_sec: int | None = None,
+    ):
+        payload = self.build_exec_payload(cmd, workdir=workdir, env=env, timeout_sec=timeout_sec)
+        return await self.box_service.client.execute(self.box_service.build_spec(payload))
+
+    async def execute_for_query(
+        self,
+        query,
+        cmd: str,
+        *,
+        workdir: str | None = None,
+        env: dict[str, str] | None = None,
+        timeout_sec: int | None = None,
+    ) -> dict:
+        payload = self.build_exec_payload(cmd, workdir=workdir, env=env, timeout_sec=timeout_sec)
+        return await self.box_service.execute_spec_payload(payload, query)
+
+    async def create_session(self):
+        return await self.box_service.create_session(self.build_session_payload())
+
+    def build_process_payload(
+        self,
+        command: str,
+        args: list[str] | None = None,
+        *,
+        env: dict[str, str] | None = None,
+        cwd: str = '/workspace',
+    ) -> dict[str, Any]:
+        # Managed processes run inside the same workspace model as one-shot
+        # execs, so path/venv rewriting is shared here.
+        normalized_command = command
+        normalized_args = list(args or [])
+        normalized_cwd = cwd
+        if self.host_path:
+            normalized_command = self.rewrite_venv_command(command)
+            normalized_args = [self.rewrite_path(arg) for arg in normalized_args]
+            normalized_cwd = self.rewrite_path(cwd)
+        return {
+            'command': normalized_command,
+            'args': normalized_args,
+            'env': dict(env or {}),
+            'cwd': normalized_cwd,
+        }
+
+    async def start_managed_process(
+        self,
+        command: str,
+        args: list[str] | None = None,
+        *,
+        process_id: str = 'default',
+        env: dict[str, str] | None = None,
+        cwd: str = '/workspace',
+    ):
+        payload = self.build_process_payload(command, args, env=env, cwd=cwd)
+        payload['process_id'] = process_id
+        return await self.box_service.start_managed_process(self.session_id, payload)
+
+    async def get_managed_process(self, process_id: str = 'default'):
+        return await self.box_service.get_managed_process(self.session_id, process_id)
+
+    async def stop_managed_process(self, process_id: str = 'default') -> None:
+        await self.box_service.stop_managed_process(self.session_id, process_id)
+
+    def get_managed_process_websocket_url(self, process_id: str = 'default') -> str:
+        return self.box_service.get_managed_process_websocket_url(self.session_id, process_id)
+
+    async def cleanup(self) -> None:
+        await self.box_service.client.delete_session(self.session_id)

src/langbot/pkg/core/app.py

@@ -9,6 +9,7 @@ from ..platform import botmgr as im_mgr
 from ..platform.webhook_pusher import WebhookPusher
 from ..provider.session import sessionmgr as llm_session_mgr
 from ..provider.modelmgr import modelmgr as llm_model_mgr
+from ..box import service as box_service_module
 
 from langbot.pkg.provider.tools import toolmgr as llm_tool_mgr
 from ..config import manager as config_mgr
@@ -31,8 +32,8 @@ from ..api.http.service import mcp as mcp_service
 from ..api.http.service import apikey as apikey_service
 from ..api.http.service import webhook as webhook_service
 from ..api.http.service import monitoring as monitoring_service
+from ..api.http.service import skill as skill_service
 from ..api.http.service import maintenance as maintenance_service
-
 from ..discover import engine as discover_engine
 from ..storage import mgr as storagemgr
 from ..utils import logcache
@@ -43,6 +44,7 @@ from ..rag.service import RAGRuntimeService
 from ..vector import mgr as vectordb_mgr
 from ..telemetry import telemetry as telemetry_module
 from ..survey import manager as survey_module
+from ..skill import manager as skill_mgr
 
 
 class Application:
@@ -70,6 +72,7 @@ class Application:
 
     # TODO move to pipeline
     tool_mgr: llm_tool_mgr.ToolManager = None
+    box_service: box_service_module.BoxService = None
 
     # ======= Config manager =======
 
@@ -156,6 +159,10 @@ class Application:
 
     monitoring_service: monitoring_service.MonitoringService = None
 
+    skill_service: skill_service.SkillService = None
+
+    skill_mgr: skill_mgr.SkillManager = None
+
     maintenance_service: maintenance_service.MaintenanceService = None
 
     def __init__(self):
@@ -301,7 +308,10 @@ class Application:
         return parsed
 
     def dispose(self):
-        self.plugin_connector.dispose()
+        if self.plugin_connector is not None:
+            self.plugin_connector.dispose()
+        if self.box_service is not None:
+            self.box_service.dispose()
 
     async def print_web_access_info(self):
         """Print access webui tips"""

src/langbot/pkg/core/boot.py

@@ -62,4 +62,6 @@ async def main(loop: asyncio.AbstractEventLoop):
         app_inst = await make_app(loop)
         await app_inst.run()
     except Exception:
+        if app_inst is not None:
+            app_inst.dispose()
         traceback.print_exc()

src/langbot/pkg/core/stages/build_app.py

@@ -6,6 +6,7 @@ from .. import stage, app
 from ...utils import version, proxy
 from ...pipeline import pool, controller, pipelinemgr
 from ...pipeline import aggregator as message_aggregator
+from ...box import service as box_service
 from ...plugin import connector as plugin_connector
 from ...command import cmdmgr
 from ...provider.session import sessionmgr as llm_session_mgr
@@ -28,6 +29,8 @@ from ...api.http.service import mcp as mcp_service
 from ...api.http.service import apikey as apikey_service
 from ...api.http.service import webhook as webhook_service
 from ...api.http.service import monitoring as monitoring_service
+from ...api.http.service import skill as skill_service
+from ...skill import manager as skill_mgr
 from ...api.http.service import maintenance as maintenance_service
 from ...discover import engine as discover_engine
 from ...storage import mgr as storagemgr
@@ -86,6 +89,9 @@ class BuildAppStage(stage.BootingStage):
         webhook_service_inst = webhook_service.WebhookService(ap)
         ap.webhook_service = webhook_service_inst
 
+        skill_service_inst = skill_service.SkillService(ap)
+        ap.skill_service = skill_service_inst
+
         proxy_mgr = proxy.ProxyManager(ap)
         await proxy_mgr.initialize()
         ap.proxy_mgr = proxy_mgr
@@ -129,6 +135,10 @@ class BuildAppStage(stage.BootingStage):
         await llm_session_mgr_inst.initialize()
         ap.sess_mgr = llm_session_mgr_inst
 
+        box_service_inst = box_service.BoxService(ap)
+        await box_service_inst.initialize()
+        ap.box_service = box_service_inst
+
         llm_tool_mgr_inst = llm_tool_mgr.ToolManager(ap)
         await llm_tool_mgr_inst.initialize()
         ap.tool_mgr = llm_tool_mgr_inst
@@ -149,6 +159,11 @@ class BuildAppStage(stage.BootingStage):
         msg_aggregator_inst = message_aggregator.MessageAggregator(ap)
         ap.msg_aggregator = msg_aggregator_inst
 
+        # Initialize skill manager
+        skill_mgr_inst = skill_mgr.SkillManager(ap)
+        await skill_mgr_inst.initialize()
+        ap.skill_mgr = skill_mgr_inst
+
         rag_mgr_inst = rag_mgr.RAGManager(ap)
         await rag_mgr_inst.initialize()
         ap.rag_mgr = rag_mgr_inst

src/langbot/pkg/pipeline/preproc/preproc.py

@@ -32,6 +32,9 @@ class PreProcessor(stage.PipelineStage):
     ) -> entities.StageProcessResult:
         """Process"""
         selected_runner = query.pipeline_config['ai']['runner']['runner']
+        include_skill_authoring = (
+            selected_runner == 'local-agent' and getattr(self.ap, 'skill_service', None) is not None
+        )
 
         session = await self.ap.sess_mgr.get_session(query)
 
@@ -110,7 +113,11 @@ class PreProcessor(stage.PipelineStage):
                     # Get bound plugins and MCP servers for filtering tools
                     bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
                     bound_mcp_servers = query.variables.get('_pipeline_bound_mcp_servers', None)
-                    query.use_funcs = await self.ap.tool_mgr.get_all_tools(bound_plugins, bound_mcp_servers)
+                    query.use_funcs = await self.ap.tool_mgr.get_all_tools(
+                        bound_plugins,
+                        bound_mcp_servers,
+                        include_skill_authoring=include_skill_authoring,
+                    )
 
                     self.ap.logger.debug(f'Bound plugins: {bound_plugins}')
                     self.ap.logger.debug(f'Bound MCP servers: {bound_mcp_servers}')
@@ -121,7 +128,11 @@ class PreProcessor(stage.PipelineStage):
             if not query.use_funcs and query.variables.get('_fallback_model_uuids'):
                 bound_plugins = query.variables.get('_pipeline_bound_plugins', None)
                 bound_mcp_servers = query.variables.get('_pipeline_bound_mcp_servers', None)
-                query.use_funcs = await self.ap.tool_mgr.get_all_tools(bound_plugins, bound_mcp_servers)
+                query.use_funcs = await self.ap.tool_mgr.get_all_tools(
+                    bound_plugins,
+                    bound_mcp_servers,
+                    include_skill_authoring=include_skill_authoring,
+                )
 
         sender_name = ''
 
@@ -237,4 +248,67 @@ class PreProcessor(stage.PipelineStage):
         query.prompt.messages = event_ctx.event.default_prompt
         query.messages = event_ctx.event.prompt
 
+        # =========== Skill awareness for the local-agent runner ===========
+        # The actual activation goes through the ``activate`` Tool Call so the
+        # LLM doesn't see full SKILL.md instructions until it commits to a
+        # skill (Claude Code's progressive disclosure). But the LLM still has
+        # to KNOW which skills exist to make that choice, so we:
+        #   1. resolve the pipeline's bound skills and stash them in
+        #      ``query.variables['_pipeline_bound_skills']`` for downstream
+        #      visibility checks (skill loader, native exec workdir);
+        #   2. inject a short ``Available Skills`` index (name + description
+        #      only) into the system prompt. The contributor's original PR
+        #      relied on this injection; without it the LLM never discovers
+        #      the skills are there and just calls native tools instead.
+        if selected_runner == 'local-agent' and self.ap.skill_mgr:
+            pipeline_data = await self.ap.pipeline_service.get_pipeline(query.pipeline_uuid)
+            extensions_prefs = (pipeline_data or {}).get('extensions_preferences', {})
+            enable_all_skills = extensions_prefs.get('enable_all_skills', True)
+
+            if enable_all_skills:
+                bound_skills = None  # None = all loaded skills are visible
+            else:
+                bound_skills = extensions_prefs.get('skills', [])
+
+            query.variables['_pipeline_bound_skills'] = bound_skills
+
+            skill_addition = self.ap.skill_mgr.build_skill_aware_prompt_addition(
+                bound_skills=bound_skills,
+            )
+            if skill_addition:
+                # Append to the first system message; create one if the
+                # prompt has none. Handles both plain-string and
+                # content-element (list) message bodies.
+                if query.prompt.messages and query.prompt.messages[0].role == 'system':
+                    head = query.prompt.messages[0]
+                    if isinstance(head.content, str):
+                        head.content = head.content + skill_addition
+                    elif isinstance(head.content, list):
+                        appended = False
+                        for ce in head.content:
+                            if getattr(ce, 'type', None) == 'text':
+                                ce.text = (ce.text or '') + skill_addition
+                                appended = True
+                                break
+                        if not appended:
+                            head.content.append(provider_message.ContentElement(type='text', text=skill_addition))
+                else:
+                    query.prompt.messages.insert(
+                        0,
+                        provider_message.Message(role='system', content=skill_addition.strip()),
+                    )
+                self.ap.logger.debug(
+                    f'Skill index injected into system prompt: '
+                    f'pipeline={query.pipeline_uuid} '
+                    f'bound_skills={bound_skills or "all"} '
+                    f'loaded_skills={len(self.ap.skill_mgr.skills)}'
+                )
+            else:
+                self.ap.logger.debug(
+                    f'No skills available for prompt injection: '
+                    f'pipeline={query.pipeline_uuid} '
+                    f'loaded_skills={len(self.ap.skill_mgr.skills)} '
+                    f'bound_skills={bound_skills}'
+                )
+
         return entities.StageProcessResult(result_type=entities.ResultType.CONTINUE, new_query=query)

src/langbot/pkg/pipeline/process/handler.py

@@ -5,6 +5,7 @@ import abc
 from ...core import app
 from .. import entities
 import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+import langbot_plugin.api.entities.builtin.provider.message as provider_message
 
 
 class MessageHandler(metaclass=abc.ABCMeta):
@@ -31,3 +32,29 @@ class MessageHandler(metaclass=abc.ABCMeta):
         if len(s0) > 20 or '\n' in s:
             s0 = s0[:20] + '...'
         return s0
+
+    def format_result_log(
+        self,
+        result: provider_message.Message | provider_message.MessageChunk,
+    ) -> str | None:
+        if result.tool_calls:
+            tool_names = [tc.function.name for tc in result.tool_calls if tc.function and tc.function.name]
+            if tool_names:
+                return f'{result.role}: requested tools: {", ".join(tool_names)}'
+            return f'{result.role}: requested tool calls'
+
+        content = result.content
+        if isinstance(content, str):
+            if not content.strip():
+                return None
+
+            if result.role == 'tool':
+                if content.startswith('err:'):
+                    return f'tool error: {self.cut_str(content)}'
+
+            return self.cut_str(result.readable_str())
+
+        if isinstance(content, list) and len(content) == 0:
+            return None
+
+        return self.cut_str(result.readable_str())

src/langbot/pkg/pipeline/process/handlers/chat.py

@@ -113,9 +113,11 @@ class ChatMessageHandler(handler.MessageHandler):
                         # This prevents memory overflow from thousands of log entries per conversation
                         # First chunk uses INFO level to confirm connection establishment
                         if chunk_count == 1:
-                            self.ap.logger.info(
-                                f'Conversation({query.query_id}) Streaming started: {self.cut_str(result.readable_str())}'
-                            )
+                            summary = self.format_result_log(result)
+                            if summary is not None:
+                                self.ap.logger.info(f'Conversation({query.query_id}) Streaming started: {summary}')
+                            else:
+                                self.ap.logger.info(f'Conversation({query.query_id}) Streaming started')
                         elif chunk_count % 10 == 0:
                             self.ap.logger.debug(
                                 f'Conversation({query.query_id}) Streaming chunk {chunk_count}: {self.cut_str(result.readable_str())}'
@@ -135,9 +137,9 @@ class ChatMessageHandler(handler.MessageHandler):
                     async for result in runner.run(query):
                         query.resp_messages.append(result)
 
-                        self.ap.logger.info(
-                            f'Conversation({query.query_id}) Response: {self.cut_str(result.readable_str())}'
-                        )
+                        summary = self.format_result_log(result)
+                        if summary is not None:
+                            self.ap.logger.info(f'Conversation({query.query_id}) Response: {summary}')
 
                         if result.content is not None:
                             text_length += len(result.content)

src/langbot/pkg/plugin/connector.py

@@ -18,6 +18,7 @@ from langbot_plugin.api.entities.builtin.pipeline.query import provider_session
 from ..core import app
 from . import handler
 from ..utils import platform
+from ..utils.managed_runtime import ManagedRuntimeConnector
 from langbot_plugin.runtime.io.controllers.stdio import (
     client as stdio_client_controller,
 )
@@ -39,11 +40,9 @@ class PluginRuntimeNotConnectedError(RuntimeError):
     """Raised when plugin runtime operations are requested before connection."""
 
 
-class PluginRuntimeConnector:
+class PluginRuntimeConnector(ManagedRuntimeConnector):
     """Plugin runtime connector"""
 
-    ap: app.Application
-
     handler: handler.RuntimeConnectionHandler
 
     handler_task: asyncio.Task
@@ -54,10 +53,6 @@ class PluginRuntimeConnector:
 
     ctrl: stdio_client_controller.StdioClientController | ws_client_controller.WebSocketClientController
 
-    runtime_subprocess_on_windows: asyncio.subprocess.Process | None = None
-
-    runtime_subprocess_on_windows_task: asyncio.Task | None = None
-
     runtime_disconnect_callback: typing.Callable[
         [PluginRuntimeConnector], typing.Coroutine[typing.Any, typing.Any, None]
     ]
@@ -72,7 +67,7 @@ class PluginRuntimeConnector:
             [PluginRuntimeConnector], typing.Coroutine[typing.Any, typing.Any, None]
         ],
     ):
-        self.ap = ap
+        super().__init__(ap)
         self.runtime_disconnect_callback = runtime_disconnect_callback
         self.is_enable_plugin = self.ap.instance_config.data.get('plugin', {}).get('enable', True)
 
@@ -108,6 +103,16 @@ class PluginRuntimeConnector:
 
             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
 
@@ -140,19 +145,7 @@ class PluginRuntimeConnector:
             # We have to launch runtime via cmd but communicate via ws.
             self.ap.logger.info('(windows) use cmd to launch plugin runtime and communicate via ws')
 
-            if self.runtime_subprocess_on_windows is None:  # only launch once
-                python_path = sys.executable
-                env = os.environ.copy()
-                self.runtime_subprocess_on_windows = await asyncio.create_subprocess_exec(
-                    python_path,
-                    '-m',
-                    'langbot_plugin.cli.__init__',
-                    'rt',
-                    env=env,
-                )
-
-                # hold the process
-                self.runtime_subprocess_on_windows_task = asyncio.create_task(self.runtime_subprocess_on_windows.wait())
+            await self._start_runtime_subprocess('-m', 'langbot_plugin.cli.__init__', 'rt')
 
             ws_url = 'ws://localhost:5400/control/ws'
 
@@ -236,6 +229,81 @@ class PluginRuntimeConnector:
 
         return plugin_author, plugin_name
 
+    async def _install_mcp_from_marketplace(
+        self,
+        mcp_data: dict[str, Any],
+        task_context: taskmgr.TaskContext | None = None,
+    ):
+        """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
+
+        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", "")}'
+
+        # 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)
+        )
+        if existing.scalar_one_or_none():
+            self.ap.logger.info(f'MCP server {name} already exists, skipping installation')
+            return
+
+        # Create MCP server record
+        server_uuid = str(uuid.uuid4())
+        server_data = {
+            'uuid': server_uuid,
+            'name': name,
+            'enable': True,
+            'mode': mode,
+            'extra_args': extra_args,
+        }
+
+        await self.ap.persistence_mgr.execute_async(sqlalchemy.insert(persistence_mcp.MCPServer).values(server_data))
+
+        # Start the MCP server
+        result = await self.ap.persistence_mgr.execute_async(
+            sqlalchemy.select(persistence_mcp.MCPServer).where(persistence_mcp.MCPServer.uuid == server_uuid)
+        )
+        server_entity = result.first()
+        if server_entity:
+            server_config = self.ap.persistence_mgr.serialize_model(persistence_mcp.MCPServer, server_entity)
+            if self.ap.tool_mgr.mcp_tool_loader:
+                mcp_task = asyncio.create_task(self.ap.tool_mgr.mcp_tool_loader.host_mcp_server(server_config))
+                self.ap.tool_mgr.mcp_tool_loader._hosted_mcp_tasks.append(mcp_task)
+
+        self.ap.logger.info(f'Installed MCP server {name} from marketplace')
+
+    async def _install_skill_from_zip(
+        self,
+        file_bytes: bytes,
+        filename: str,
+        task_context: taskmgr.TaskContext | None = None,
+    ):
+        """Install a skill from marketplace ZIP data."""
+        from ..api.http.service.skill import SkillService
+
+        skill_service = SkillService(self.ap)
+
+        self.ap.logger.info(f'Installing skill from marketplace ZIP ({len(file_bytes)} bytes)')
+
+        # Install from ZIP using skill service
+        result = await skill_service.install_from_zip_upload(
+            file_bytes=file_bytes,
+            filename=filename + '.zip',
+        )
+        self.ap.logger.info(f'Skill installed successfully: {result}')
+
     def _build_plugin_startup_failure_message(
         self,
         plugin_author: str,
@@ -298,6 +366,117 @@ class PluginRuntimeConnector:
         plugin_author = install_info.get('plugin_author')
         plugin_name = install_info.get('plugin_name')
 
+        if install_source == PluginInstallSource.MARKETPLACE:
+            # Handle marketplace plugin/mcp/skill installation
+            plugin_author = install_info.get('plugin_author', '')
+            plugin_name = install_info.get('plugin_name', '')
+            space_url = (
+                self.ap.instance_config.data.get('space', {}).get('url', 'https://space.langbot.app').rstrip('/')
+            )
+
+            # Try MCP endpoint first
+            async with httpx.AsyncClient(trust_env=True, timeout=15) as client:
+                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('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 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}')
+                    if task_context:
+                        task_context.set_current_action('checking skill marketplace')
+
+                    # Get skill detail to find version
+                    skill_resp = await client.get(
+                        f'{space_url}/api/v1/marketplace/skills/{plugin_author}/{plugin_name}'
+                    )
+                    if skill_resp.status_code == 200:
+                        self.ap.logger.info(f'Installing skill from marketplace: {plugin_author}/{plugin_name}')
+                        if task_context:
+                            task_context.set_current_action('installing skill from marketplace')
+
+                        # Download the skill ZIP (no version needed - uses latest)
+                        if task_context:
+                            task_context.set_current_action('downloading skill package')
+
+                        download_resp = await client.get(
+                            f'{space_url}/api/v1/marketplace/skills/download/{plugin_author}/{plugin_name}'
+                        )
+                        if download_resp.status_code != 200:
+                            raise Exception(
+                                f'Failed to download skill {plugin_author}/{plugin_name}: {download_resp.status_code}'
+                            )
+
+                        file_bytes = download_resp.content
+                        file_size = len(file_bytes)
+                        self.ap.logger.info(f'Downloaded skill ZIP ({file_size} bytes)')
+
+                        # Install skill from ZIP using skill service
+                        await self._install_skill_from_zip(file_bytes, f'{plugin_author}-{plugin_name}', task_context)
+                        return
+                    elif skill_resp.status_code == 404:
+                        # Try plugin endpoint - get versions and download
+                        self.ap.logger.info(f'Trying plugin endpoint for: {plugin_author}/{plugin_name}')
+                        if task_context:
+                            task_context.set_current_action('checking plugin marketplace')
+
+                        # Get plugin versions to find latest
+                        versions_resp = await client.get(
+                            f'{space_url}/api/v1/marketplace/plugins/{plugin_author}/{plugin_name}/versions'
+                        )
+                        if versions_resp.status_code == 200:
+                            versions_data = versions_resp.json().get('data', {}).get('versions', [])
+                            if versions_data:
+                                latest_version = versions_data[0].get('version', '')
+                                if latest_version:
+                                    self.ap.logger.info(
+                                        f'Installing plugin from marketplace: {plugin_author}/{plugin_name} v{latest_version}'
+                                    )
+                                    if task_context:
+                                        task_context.set_current_action('downloading plugin package')
+
+                                    download_resp = await client.get(
+                                        f'{space_url}/api/v1/marketplace/plugins/download/{plugin_author}/{plugin_name}/{latest_version}'
+                                    )
+                                    if download_resp.status_code != 200:
+                                        raise Exception(
+                                            f'Failed to download plugin {plugin_author}/{plugin_name}: {download_resp.status_code}'
+                                        )
+
+                                    file_bytes = download_resp.content
+                                    self._extract_deps_metadata(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')
+                                    # Continue to install via runtime
+                                else:
+                                    raise Exception(f'No version found for plugin {plugin_author}/{plugin_name}')
+                            else:
+                                raise Exception(f'Plugin {plugin_author}/{plugin_name} has no versions')
+                        else:
+                            raise Exception(f'Plugin {plugin_author}/{plugin_name} not found in marketplace')
+                    else:
+                        skill_resp.raise_for_status()
+                        raise Exception(f'Failed to get skill {plugin_author}/{plugin_name}')
+                else:
+                    mcp_resp.raise_for_status()
+                    raise Exception(f'Failed to get MCP {plugin_author}/{plugin_name}')
+
         if install_source == PluginInstallSource.LOCAL:
             # transfer file before install
             file_bytes = install_info['plugin_file']
@@ -613,13 +792,18 @@ class PluginRuntimeConnector:
         return await self.handler.retrieve_knowledge(plugin_author, plugin_name, retriever_name, retrieval_context)
 
     def dispose(self):
-        # No need to consider the shutdown on Windows
-        # for Windows can kill processes and subprocesses chainly
-
-        if self.is_enable_plugin and isinstance(self.ctrl, stdio_client_controller.StdioClientController):
+        # On non-Windows stdio mode, terminate via the controller's process handle.
+        # On Windows, the managed subprocess is cleaned up by the base class.
+        if (
+            self.is_enable_plugin
+            and hasattr(self, 'ctrl')
+            and isinstance(self.ctrl, stdio_client_controller.StdioClientController)
+        ):
             self.ap.logger.info('Terminating plugin runtime process...')
             self.ctrl.process.terminate()
 
+        self._dispose_subprocess()
+
         if self.heartbeat_task is not None:
             self.heartbeat_task.cancel()
             self.heartbeat_task = None

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/runner.py

@@ -2,8 +2,12 @@ from __future__ import annotations
 
 import abc
 import typing
+from typing import TYPE_CHECKING
 
-from ..core import app
+if TYPE_CHECKING:
+    from ..core import app
+    import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+    import langbot_plugin.api.entities.builtin.provider.message as provider_message
 
 
 preregistered_runners: list[typing.Type[RequestRunner]] = []
@@ -35,7 +39,7 @@ class RequestRunner(abc.ABC):
 
     @abc.abstractmethod
     async def run(
-        self, query: core_entities.Query
-    ) -> typing.AsyncGenerator[llm_entities.Message | llm_entities.MessageChunk, None]:
+        self, query: pipeline_query.Query
+    ) -> typing.AsyncGenerator[provider_message.Message | provider_message.MessageChunk, None]:
         """运行请求"""
         pass

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

@@ -5,6 +5,7 @@ import copy
 import typing
 from .. import runner
 from ..modelmgr import requester as modelmgr_requester
+from ..tools.loaders.native import EXEC_TOOL_NAME
 import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 import langbot_plugin.api.entities.builtin.provider.message as provider_message
 import langbot_plugin.api.entities.builtin.rag.context as rag_context
@@ -24,11 +25,44 @@ Respond in the same language as the user's input.
 </user_message>
 """
 
+SANDBOX_EXEC_TOOL_NAME = 'sandbox_exec'
+SANDBOX_EXEC_SYSTEM_GUIDANCE = (
+    'When sandbox_exec is available, use it for exact calculations, statistics, structured data parsing, '
+    'and code execution instead of estimating mentally. If the user provides numbers, tables, CSV-like text, '
+    'JSON, or other data and asks for a computed answer, prefer running a short Python script in sandbox_exec '
+    'and then answer from the tool result.'
+)
+
+
+# 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"""
 
+    def _build_request_messages(
+        self,
+        query: pipeline_query.Query,
+        user_message: provider_message.Message,
+    ) -> list[provider_message.Message]:
+        req_messages = query.prompt.messages.copy() + query.messages.copy()
+
+        if any(getattr(tool, 'name', None) == EXEC_TOOL_NAME for tool in query.use_funcs or []):
+            req_messages.append(
+                provider_message.Message(
+                    role='system',
+                    content=self.ap.box_service.get_system_guidance(),
+                )
+            )
+
+        req_messages.append(user_message)
+        return req_messages
+
     async def _get_model_candidates(
         self,
         query: pipeline_query.Query,
@@ -131,6 +165,7 @@ class LocalAgentRunner(runner.RequestRunner):
     ) -> typing.AsyncGenerator[provider_message.Message | provider_message.MessageChunk, None]:
         """Run request"""
         pending_tool_calls = []
+        initial_response_emitted = False
 
         # Get knowledge bases list from query variables (set by PreProcessor,
         # may have been modified by plugins during PromptPreProcessing)
@@ -236,7 +271,7 @@ class LocalAgentRunner(runner.RequestRunner):
                     ce.text = final_user_message_text
                     break
 
-        req_messages = query.prompt.messages.copy() + query.messages.copy() + [user_message]
+        req_messages = self._build_request_messages(query, user_message)
 
         try:
             is_stream = await query.adapter.is_stream_output_supported()
@@ -264,7 +299,6 @@ class LocalAgentRunner(runner.RequestRunner):
                 query.use_funcs,
                 remove_think,
             )
-            yield msg
             final_msg = msg
         else:
             # Streaming: invoke with fallback
@@ -312,6 +346,7 @@ class LocalAgentRunner(runner.RequestRunner):
                         is_final=msg.is_final,
                         msg_sequence=msg_sequence,
                     )
+                    initial_response_emitted = True
 
             final_msg = provider_message.MessageChunk(
                 role=last_role,
@@ -325,11 +360,25 @@ class LocalAgentRunner(runner.RequestRunner):
         if isinstance(final_msg, provider_message.MessageChunk):
             first_end_sequence = final_msg.msg_sequence
 
+        if not is_stream:
+            yield final_msg
+        elif not initial_response_emitted:
+            yield final_msg
+            initial_response_emitted = True
+
         req_messages.append(final_msg)
 
         # 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
@@ -369,7 +418,15 @@ class LocalAgentRunner(runner.RequestRunner):
 
                     req_messages.append(msg)
                 except Exception as e:
-                    err_msg = provider_message.Message(role='tool', content=f'err: {e}', tool_call_id=tool_call.id)
+                    if is_stream:
+                        err_msg = provider_message.MessageChunk(
+                            role='tool',
+                            content=f'err: {e}',
+                            tool_call_id=tool_call.id,
+                            is_final=True,
+                        )
+                    else:
+                        err_msg = provider_message.Message(role='tool', content=f'err: {e}', tool_call_id=tool_call.id)
 
                     yield err_msg
 

src/langbot/pkg/provider/tools/loader.py

@@ -2,12 +2,14 @@ from __future__ import annotations
 
 import abc
 import typing
+from typing import TYPE_CHECKING
 
 from langbot_plugin.api.entities.events import pipeline_query
-
-from ...core import app
 import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
 
+if TYPE_CHECKING:
+    from ...core import app
+
 
 preregistered_loaders: list[typing.Type[ToolLoader]] = []
 

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

@@ -20,6 +20,7 @@ from ....core import app
 import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
 import langbot_plugin.api.entities.builtin.provider.message as provider_message
 from ....entity.persistence import mcp as persistence_mcp
+from .mcp_stdio import BoxStdioSessionRuntime, MCPServerBoxConfig, MCPSessionErrorPhase  # noqa: F401
 
 
 class MCPSessionStatus(enum.Enum):
@@ -58,6 +59,12 @@ class RuntimeMCPSession:
 
     error_message: str | None = None
 
+    error_phase: MCPSessionErrorPhase | None = None
+
+    retry_count: int = 0
+
+    _box_stdio_runtime: BoxStdioSessionRuntime
+
     def __init__(self, server_name: str, server_config: dict, enable: bool, ap: app.Application):
         self.server_name = server_name
         self.server_uuid = server_config.get('uuid', '')
@@ -75,7 +82,33 @@ class RuntimeMCPSession:
         self._shutdown_event = asyncio.Event()
         self._ready_event = asyncio.Event()
 
+        self._box_stdio_runtime = BoxStdioSessionRuntime(self)
+        self.box_config = self._box_stdio_runtime.config
+
     async def _init_stdio_python_server(self):
+        if self._uses_box_stdio():
+            await self._box_stdio_runtime.initialize()
+            return
+
+        # Box is configured (ap.box_service exists) but currently unavailable
+        # (disabled by config or connection failed). Refuse stdio MCP rather
+        # than silently falling through to host-stdio — the operator asked
+        # for the sandbox and the failure mode should be visible.
+        #
+        # Set ``error_phase = BOX_UNAVAILABLE`` BEFORE raising so the retry
+        # wrapper can short-circuit (retrying is pointless when Box is
+        # deliberately off) and the frontend can render a localized,
+        # actionable message instead of this raw RuntimeError. Keep the
+        # message itself short — the frontend ignores it for this phase.
+        box_service = getattr(self.ap, 'box_service', None)
+        if box_service is not None and not getattr(box_service, 'available', False):
+            self.error_phase = MCPSessionErrorPhase.BOX_UNAVAILABLE
+            if not getattr(box_service, 'enabled', True):
+                raise RuntimeError('box_disabled_in_config')
+            raise RuntimeError('box_unavailable')
+
+        # Legacy: no box_service installed at all (pre-Box dev mode). Fall
+        # through to host-stdio for backward compatibility.
         server_params = StdioServerParameters(
             command=self.server_config['command'],
             args=self.server_config['args'],
@@ -90,6 +123,9 @@ class RuntimeMCPSession:
 
         await self.session.initialize()
 
+    async def _init_box_stdio_server(self):
+        await self._box_stdio_runtime.initialize()
+
     async def _init_sse_server(self):
         sse_transport = await self.exit_stack.enter_async_context(
             sse_client(
@@ -124,8 +160,11 @@ class RuntimeMCPSession:
 
         await self.session.initialize()
 
+    _MAX_RETRIES = 3
+    _RETRY_DELAYS = [2, 4, 8]
+
     async def _lifecycle_loop(self):
-        """在后台任务中管理整个MCP会话的生命周期"""
+        """Manage the full MCP session lifecycle in a background task."""
         try:
             if self.server_config['mode'] == 'stdio':
                 await self._init_stdio_python_server()
@@ -134,49 +173,109 @@ class RuntimeMCPSession:
             elif self.server_config['mode'] == 'http':
                 await self._init_streamable_http_server()
             else:
-                raise ValueError(f'无法识别 MCP 服务器类型: {self.server_name}: {self.server_config}')
+                raise ValueError(f'Unknown MCP server mode: {self.server_name}: {self.server_config}')
 
             await self.refresh()
 
             self.status = MCPSessionStatus.CONNECTED
 
-            # 通知start()方法连接已建立
+            # Notify start() that connection is established
             self._ready_event.set()
 
-            # 等待shutdown信号
-            await self._shutdown_event.wait()
+            # Wait for shutdown signal, with optional health monitoring for Box stdio
+            if self._uses_box_stdio():
+                monitor_task = asyncio.create_task(self._box_stdio_runtime.monitor_process_health())
+                shutdown_task = asyncio.create_task(self._shutdown_event.wait())
+                done, pending = await asyncio.wait(
+                    [shutdown_task, monitor_task],
+                    return_when=asyncio.FIRST_COMPLETED,
+                )
+                for task in pending:
+                    task.cancel()
+                for task in done:
+                    if task is monitor_task and not self._shutdown_event.is_set():
+                        self.error_phase = MCPSessionErrorPhase.RUNTIME
+                        raise Exception('Box managed process exited unexpectedly')
+            else:
+                await self._shutdown_event.wait()
 
         except Exception as e:
             self.status = MCPSessionStatus.ERROR
             self.error_message = str(e)
             self.ap.logger.error(f'Error in MCP session lifecycle {self.server_name}: {e}\n{traceback.format_exc()}')
-            # 即使出错也要设置ready事件，让start()方法知道初始化已完成
-            self._ready_event.set()
+            # Do NOT set _ready_event here — let _lifecycle_loop_with_retry
+            # handle retries first. It will set the event when all retries
+            # are exhausted or on success.
+            raise  # Re-raise so _lifecycle_loop_with_retry can catch it
         finally:
-            # 在同一个任务中清理所有资源
+            # Clean up all resources in the same task
             try:
                 if self.exit_stack:
                     await self.exit_stack.aclose()
+                    self.exit_stack = AsyncExitStack()
                 self.functions.clear()
                 self.session = None
             except Exception as e:
                 self.ap.logger.error(f'Error cleaning up MCP session {self.server_name}: {e}\n{traceback.format_exc()}')
+            finally:
+                await self._cleanup_box_stdio_session()
+
+    async def _lifecycle_loop_with_retry(self):
+        """Wrap _lifecycle_loop with retry and exponential backoff."""
+        for attempt in range(self._MAX_RETRIES + 1):
+            try:
+                await self._lifecycle_loop()
+                return  # Normal shutdown, don't retry
+            except Exception as e:
+                self.retry_count = attempt + 1
+                if self._shutdown_event.is_set():
+                    return  # Shutdown requested, don't retry
+                # BOX_UNAVAILABLE is a deliberate refusal, not a transient
+                # failure — retrying produces log spam and a misleading
+                # "Failed after N attempts" message. Surface it immediately.
+                if self.error_phase == MCPSessionErrorPhase.BOX_UNAVAILABLE:
+                    self.status = MCPSessionStatus.ERROR
+                    self.error_message = str(e)
+                    self._ready_event.set()
+                    return
+                if attempt >= self._MAX_RETRIES:
+                    self.status = MCPSessionStatus.ERROR
+                    self.error_message = f'Failed after {self._MAX_RETRIES + 1} attempts: {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}'
+                )
+                await self._cleanup_box_stdio_session()
+                # Reset status for retry
+                self.status = MCPSessionStatus.CONNECTING
+                self.error_message = None
+                self.error_phase = None
+                await asyncio.sleep(delay)
+
+    _MONITOR_POLL_INTERVAL = 5
+    _MONITOR_MAX_CONSECUTIVE_ERRORS = 3
+
+    async def _monitor_box_process_health(self):
+        await self._box_stdio_runtime.monitor_process_health()
 
     async def start(self):
         if not self.enable:
             return
 
-        # 创建后台任务来管理生命周期
-        self._lifecycle_task = asyncio.create_task(self._lifecycle_loop())
+        # Create background task for lifecycle management with retry
+        self._lifecycle_task = asyncio.create_task(self._lifecycle_loop_with_retry())
 
-        # 等待连接建立或失败（带超时）
+        # Wait for connection or failure (with timeout)
+        startup_timeout = (self.box_config.startup_timeout_sec + 30) if self._uses_box_stdio() else 30.0
         try:
-            await asyncio.wait_for(self._ready_event.wait(), timeout=30.0)
+            await asyncio.wait_for(self._ready_event.wait(), timeout=startup_timeout)
         except asyncio.TimeoutError:
             self.status = MCPSessionStatus.ERROR
-            raise Exception('Connection timeout after 30 seconds')
+            raise Exception(f'Connection timeout after {startup_timeout} seconds')
 
-        # 检查是否有错误
+        # Check for errors
         if self.status == MCPSessionStatus.ERROR:
             raise Exception('Connection failed, please check URL')
 
@@ -232,18 +331,25 @@ class RuntimeMCPSession:
         return self.functions
 
     def get_runtime_info_dict(self) -> dict:
-        return {
+        info = {
             'status': self.status.value,
             'error_message': self.error_message,
+            'error_phase': self.error_phase.value if self.error_phase else None,
+            'retry_count': self.retry_count,
             'tool_count': len(self.get_tools()),
             'tools': [
                 {
                     'name': tool.name,
                     'description': tool.description,
+                    'parameters': tool.parameters,
                 }
                 for tool in self.get_tools()
             ],
         }
+        if self._uses_box_stdio():
+            info['box_session_id'] = self._build_box_session_id()
+            info['box_enabled'] = True
+        return info
 
     async def shutdown(self):
         """关闭会话并清理资源"""
@@ -267,6 +373,41 @@ class RuntimeMCPSession:
         except Exception as e:
             self.ap.logger.error(f'Error shutting down MCP session {self.server_name}: {e}\n{traceback.format_exc()}')
 
+    def _uses_box_stdio(self) -> bool:
+        return self._box_stdio_runtime.uses_box_stdio()
+
+    def _build_box_session_id(self) -> str:
+        return 'mcp-shared'
+
+    def _rewrite_path(self, path: str, host_path: str | None) -> str:
+        return self._box_stdio_runtime.rewrite_path(path, host_path)
+
+    def _infer_host_path(self) -> str | None:
+        return self._box_stdio_runtime.infer_host_path()
+
+    @staticmethod
+    def _unwrap_venv_path(directory: str) -> str:
+        return BoxStdioSessionRuntime.unwrap_venv_path(directory)
+
+    def _resolve_host_path(self) -> str | None:
+        return self._box_stdio_runtime.resolve_host_path()
+
+    @staticmethod
+    def _detect_install_command(host_path: str) -> str | None:
+        return BoxStdioSessionRuntime.detect_install_command(host_path)
+
+    def _build_box_session_payload(self, session_id: str, host_path: str | None = None) -> dict:
+        return self._box_stdio_runtime.build_box_session_payload(session_id, host_path)
+
+    def _build_box_process_payload(self, host_path: str | None = None) -> dict:
+        return self._box_stdio_runtime.build_box_process_payload(host_path)
+
+    def _rewrite_venv_command(self, command: str, host_path: str) -> str:
+        return self._box_stdio_runtime.rewrite_venv_command(command, host_path)
+
+    async def _cleanup_box_stdio_session(self) -> None:
+        await self._box_stdio_runtime.cleanup_session()
+
 
 # @loader.loader_class('mcp')
 class MCPLoader(loader.ToolLoader):
@@ -332,7 +473,7 @@ class MCPLoader(loader.ToolLoader):
         Args:
             server_config: 服务器配置字典，必须包含:
                 - name: 服务器名称
-                - mode: 连接模式 (stdio/sse)
+                - mode: 连接模式 (stdio/sse/http)
                 - enable: 是否启用
                 - extra_args: 额外的配置参数 (可选)
         """
@@ -431,12 +572,13 @@ class MCPLoader(loader.ToolLoader):
         """获取所有服务器的信息"""
         info = {}
         for server_name, session in self.sessions.items():
+            tools = session.get_tools()
             info[server_name] = {
                 'name': server_name,
                 'mode': session.server_config.get('mode'),
                 'enable': session.enable,
-                'tools_count': len(session.get_tools()),
-                'tool_names': [f.name for f in session.get_tools()],
+                'tools_count': len(tools),
+                'tool_names': [f.name for f in tools],
             }
         return info
 

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

@@ -0,0 +1,366 @@
+from __future__ import annotations
+
+import enum
+import asyncio
+import os
+import shutil
+import shlex
+from typing import TYPE_CHECKING, Any
+
+import pydantic
+from mcp import ClientSession
+from mcp.client.websocket import websocket_client
+from ....box.workspace import (
+    BoxWorkspaceSession,
+    classify_python_workspace,
+    infer_workspace_host_path,
+    normalize_host_path,
+    rewrite_mounted_path,
+    rewrite_venv_command,
+    unwrap_venv_path,
+)
+
+if TYPE_CHECKING:
+    from .mcp import RuntimeMCPSession
+
+
+class MCPSessionErrorPhase(enum.Enum):
+    """Which phase of the MCP lifecycle failed."""
+
+    SESSION_CREATE = 'session_create'
+    DEP_INSTALL = 'dep_install'
+    PROCESS_START = 'process_start'
+    RELAY_CONNECT = 'relay_connect'
+    MCP_INIT = 'mcp_init'
+    RUNTIME = 'runtime'
+    TOOL_CALL = 'tool_call'
+    # Stdio MCP refused because Box is disabled in config or currently
+    # unavailable. Not transient — retries would be pointless. The frontend
+    # uses this phase to render a localized actionable message instead of
+    # the raw RuntimeError text.
+    BOX_UNAVAILABLE = 'box_unavailable'
+
+
+class MCPServerBoxConfig(pydantic.BaseModel):
+    """Structured configuration for running an MCP server inside a Box container."""
+
+    image: str | None = None
+    network: str = 'on'  # MCP servers need network for dependency installation
+    host_path: str | None = None
+    host_path_mode: str = 'ro'  # MCP servers default to read-write mount only when explicitly requested
+    env: dict[str, str] = pydantic.Field(default_factory=dict)
+    startup_timeout_sec: int = 120  # Longer default to allow dependency bootstrap
+    cpus: float | None = None
+    memory_mb: int | None = None
+    pids_limit: int | None = None
+    read_only_rootfs: bool | None = None
+
+    model_config = pydantic.ConfigDict(extra='ignore')
+
+
+class BoxStdioSessionRuntime:
+    """Encapsulate Box-backed stdio MCP session orchestration."""
+
+    def __init__(self, owner: RuntimeMCPSession):
+        self.owner = owner
+        self.config = MCPServerBoxConfig.model_validate(owner.server_config.get('box', {}))
+
+    @property
+    def ap(self):
+        return self.owner.ap
+
+    @property
+    def server_name(self) -> str:
+        return self.owner.server_name
+
+    @property
+    def server_config(self) -> dict:
+        return self.owner.server_config
+
+    def _build_workspace(
+        self,
+        *,
+        host_path: str | None | object = ...,
+        workdir: str = '/workspace',
+        mount_path: str = '/workspace',
+    ) -> BoxWorkspaceSession:
+        resolved_host_path = self.resolve_host_path() if host_path is ... else host_path
+        return BoxWorkspaceSession(
+            self.ap.box_service,
+            self.owner._build_box_session_id(),
+            host_path=resolved_host_path,
+            host_path_mode=self.config.host_path_mode,
+            workdir=workdir,
+            env=self.config.env,
+            mount_path=mount_path,
+            network=self.config.network,
+            read_only_rootfs=self.config.read_only_rootfs if self.config.read_only_rootfs is not None else False,
+            image=self.config.image,
+            cpus=self.config.cpus,
+            memory_mb=self.config.memory_mb,
+            pids_limit=self.config.pids_limit,
+            persistent=True,
+        )
+
+    @property
+    def process_id(self) -> str:
+        """Each MCP server gets a unique process_id within the shared session."""
+        return self.owner.server_uuid
+
+    def uses_box_stdio(self) -> bool:
+        if self.server_config.get('mode') != 'stdio':
+            return False
+        box_service = getattr(self.ap, 'box_service', None)
+        if box_service is None:
+            return False
+        # When Box is configured but currently unavailable (disabled or
+        # connection failed), do NOT silently fall through to host-stdio —
+        # that would bypass the sandbox the operator asked for. The caller
+        # is expected to refuse the stdio MCP server with a clear error.
+        return bool(getattr(box_service, 'available', False))
+
+    async def initialize(self) -> None:
+        await self._wait_for_box_runtime()
+
+        # All stdio MCP servers share one Box session. Per-server host paths
+        # are staged into the shared workspace instead of becoming session
+        # mounts, because an existing Docker container cannot add bind mounts.
+        workspace = self._build_workspace(host_path=None)
+        host_path = self.resolve_host_path()
+        process_cwd = '/workspace'
+
+        try:
+            await workspace.create_session()
+        except Exception:
+            self.owner.error_phase = MCPSessionErrorPhase.SESSION_CREATE
+            raise
+
+        if host_path:
+            process_cwd = await self._stage_host_path_to_shared_workspace(host_path)
+            install_cmd = self.detect_install_command(host_path, process_cwd)
+            if install_cmd:
+                self.ap.logger.info(
+                    f'MCP server {self.server_name}: installing dependencies in Box with: {install_cmd}'
+                )
+                try:
+                    result = await workspace.execute_raw(
+                        install_cmd,
+                        workdir=process_cwd,
+                        timeout_sec=self.config.startup_timeout_sec or 120,
+                    )
+                except Exception:
+                    self.owner.error_phase = MCPSessionErrorPhase.DEP_INSTALL
+                    raise
+                if not result.ok:
+                    self.owner.error_phase = MCPSessionErrorPhase.DEP_INSTALL
+                    stderr_preview = (result.stderr or '')[:500]
+                    raise Exception(f'Dependency install failed (exit code {result.exit_code}): {stderr_preview}')
+
+        try:
+            process_workspace = (
+                self._build_workspace(host_path=host_path, workdir=process_cwd, mount_path=process_cwd)
+                if host_path
+                else workspace
+            )
+            payload = process_workspace.build_process_payload(
+                self.server_config['command'],
+                self.server_config.get('args', []),
+                env=self.server_config.get('env', {}),
+                cwd=process_cwd,
+            )
+            payload['process_id'] = self.process_id
+            await workspace.box_service.start_managed_process(workspace.session_id, payload)
+        except Exception:
+            self.owner.error_phase = MCPSessionErrorPhase.PROCESS_START
+            raise
+
+        try:
+            websocket_url = workspace.get_managed_process_websocket_url(self.process_id)
+            transport = await self.owner.exit_stack.enter_async_context(websocket_client(websocket_url))
+            read_stream, write_stream = transport
+            self.owner.session = await self.owner.exit_stack.enter_async_context(
+                ClientSession(read_stream, write_stream)
+            )
+        except Exception:
+            self.owner.error_phase = MCPSessionErrorPhase.RELAY_CONNECT
+            raise
+
+        try:
+            await self.owner.session.initialize()
+        except Exception:
+            self.owner.error_phase = MCPSessionErrorPhase.MCP_INIT
+            raise
+
+    async def monitor_process_health(self) -> None:
+        from langbot_plugin.box.models import BoxManagedProcessStatus
+
+        workspace = self._build_workspace()
+        consecutive_errors = 0
+        while not self.owner._shutdown_event.is_set():
+            try:
+                info = await workspace.get_managed_process(self.process_id)
+                if isinstance(info, dict):
+                    status = info.get('status', '')
+                else:
+                    status = getattr(info, 'status', '')
+                if status == BoxManagedProcessStatus.EXITED.value or status == BoxManagedProcessStatus.EXITED:
+                    return
+                consecutive_errors = 0
+            except Exception as exc:
+                consecutive_errors += 1
+                self.ap.logger.warning(
+                    f'MCP monitor for {self.server_name}: get_managed_process failed '
+                    f'({consecutive_errors}/{self.owner._MONITOR_MAX_CONSECUTIVE_ERRORS}): '
+                    f'{type(exc).__name__}: {exc}'
+                )
+                if consecutive_errors >= self.owner._MONITOR_MAX_CONSECUTIVE_ERRORS:
+                    return
+            await asyncio.sleep(self.owner._MONITOR_POLL_INTERVAL)
+
+    async def _stage_host_path_to_shared_workspace(self, host_path: str) -> str:
+        source_path = normalize_host_path(host_path)
+        if not source_path:
+            return '/workspace'
+        if not os.path.isdir(source_path):
+            raise FileNotFoundError(f'MCP host_path does not exist or is not a directory: {host_path}')
+
+        self._validate_host_path(source_path)
+
+        shared_host_path = self._shared_workspace_host_path()
+        process_host_root = os.path.join(shared_host_path, '.mcp', self.process_id)
+        process_host_workspace = os.path.join(process_host_root, 'workspace')
+        await asyncio.to_thread(self._copy_workspace_tree, source_path, process_host_root, process_host_workspace)
+        return f'/workspace/.mcp/{self.process_id}/workspace'
+
+    def _validate_host_path(self, host_path: str) -> None:
+        self.ap.box_service.build_spec(
+            {
+                'session_id': f'mcp-validate-{self.process_id}',
+                'host_path': host_path,
+                'host_path_mode': self.config.host_path_mode,
+                'network': self.config.network,
+                'read_only_rootfs': self.config.read_only_rootfs if self.config.read_only_rootfs is not None else False,
+            }
+        )
+
+    def _shared_workspace_host_path(self) -> str:
+        default_workspace = getattr(self.ap.box_service, 'default_workspace', None)
+        if not default_workspace:
+            raise RuntimeError('Box default workspace is required for shared MCP host_path staging')
+        shared_host_path = normalize_host_path(default_workspace)
+        os.makedirs(shared_host_path, exist_ok=True)
+        return shared_host_path
+
+    @staticmethod
+    def _copy_workspace_tree(source_path: str, process_host_root: str, process_host_workspace: str) -> None:
+        shutil.rmtree(process_host_root, ignore_errors=True)
+        os.makedirs(process_host_root, exist_ok=True)
+        shutil.copytree(
+            source_path,
+            process_host_workspace,
+            symlinks=True,
+            ignore=shutil.ignore_patterns('.git', '__pycache__', '.pytest_cache', '.mypy_cache', '.ruff_cache'),
+        )
+
+    async def _cleanup_staged_workspace(self) -> None:
+        if not self.resolve_host_path():
+            return
+        try:
+            process_host_root = os.path.join(self._shared_workspace_host_path(), '.mcp', self.process_id)
+            await asyncio.to_thread(shutil.rmtree, process_host_root, True)
+        except Exception as exc:
+            self.ap.logger.warning(
+                f'MCP server {self.server_name}: failed to clean staged workspace '
+                f'process_id={self.process_id}: {type(exc).__name__}: {exc}'
+            )
+
+    async def _wait_for_box_runtime(self) -> None:
+        timeout_sec = max(float(self.config.startup_timeout_sec or 120), 1.0)
+        deadline = asyncio.get_running_loop().time() + timeout_sec
+        warned = False
+        while not getattr(self.ap.box_service, 'available', False):
+            if not warned:
+                self.ap.logger.warning(
+                    f'MCP server {self.server_name}: waiting for Box runtime before starting stdio process'
+                )
+                warned = True
+            if asyncio.get_running_loop().time() >= deadline:
+                self.owner.error_phase = MCPSessionErrorPhase.SESSION_CREATE
+                raise Exception(f'Box runtime is not available after {int(timeout_sec)} seconds')
+            await asyncio.sleep(1)
+
+    async def cleanup_session(self) -> None:
+        if not self.uses_box_stdio():
+            return
+
+        # In the shared-session model, we do not delete the session itself.
+        # Stop only this MCP server's managed process; deleting the session
+        # would kill other MCP servers sharing the same container.
+        workspace = self._build_workspace(host_path=None)
+        try:
+            await workspace.stop_managed_process(self.process_id)
+        except Exception as exc:
+            self.ap.logger.warning(
+                f'MCP server {self.server_name}: failed to stop managed process '
+                f'process_id={self.process_id}: {type(exc).__name__}: {exc}'
+            )
+            await self._cleanup_staged_workspace()
+            return
+        await self._cleanup_staged_workspace()
+        self.ap.logger.info(
+            f'MCP server {self.server_name}: stopped process_id={self.process_id} '
+            f'(shared session {self.owner._build_box_session_id()} kept alive)'
+        )
+
+    def rewrite_path(self, path: str, host_path: str | None) -> str:
+        return rewrite_mounted_path(path, host_path)
+
+    def infer_host_path(self) -> str | None:
+        return infer_workspace_host_path(self.server_config.get('command', ''), self.server_config.get('args', []))
+
+    @staticmethod
+    def unwrap_venv_path(directory: str) -> str:
+        return unwrap_venv_path(directory)
+
+    def resolve_host_path(self) -> str | None:
+        return self.config.host_path or self.infer_host_path()
+
+    @staticmethod
+    def detect_install_command(host_path: str, workspace_path: str = '/workspace') -> str | None:
+        workspace_kind = classify_python_workspace(host_path)
+        quoted_workspace_path = shlex.quote(workspace_path)
+        if workspace_kind == 'package':
+            return (
+                'mkdir -p /opt/_lb_src'
+                f' && tar -C {quoted_workspace_path}'
+                ' --exclude=.venv --exclude=.git --exclude=__pycache__'
+                ' --exclude=node_modules --exclude=.tox --exclude=.nox'
+                ' --exclude="*.egg-info" --exclude=.uv-cache'
+                ' -cf - .'
+                ' | tar -C /opt/_lb_src -xf -'
+                ' && pip install --no-cache-dir /opt/_lb_src'
+                ' && rm -rf /opt/_lb_src'
+            )
+        if workspace_kind == 'requirements':
+            return f'pip install --no-cache-dir -r {quoted_workspace_path}/requirements.txt'
+        return None
+
+    def build_box_session_payload(self, session_id: str, host_path: str | None = None) -> dict[str, Any]:
+        workspace = self._build_workspace()
+        workspace.session_id = session_id
+        if host_path is not None:
+            workspace.host_path = host_path
+        return workspace.build_session_payload()
+
+    def build_box_process_payload(self, host_path: str | None = None) -> dict[str, Any]:
+        workspace = self._build_workspace()
+        if host_path is not None:
+            workspace.host_path = host_path
+        return workspace.build_process_payload(
+            self.server_config['command'],
+            self.server_config.get('args', []),
+            env=self.server_config.get('env', {}),
+        )
+
+    def rewrite_venv_command(self, command: str, host_path: str) -> str:
+        return rewrite_venv_command(command, host_path)

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

@@ -0,0 +1,846 @@
+from __future__ import annotations
+
+import json
+import os
+
+import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
+from langbot_plugin.api.entities.events import pipeline_query
+
+from .. import loader
+from . import skill as skill_loader
+
+EXEC_TOOL_NAME = 'exec'
+READ_TOOL_NAME = 'read'
+WRITE_TOOL_NAME = 'write'
+EDIT_TOOL_NAME = 'edit'
+GLOB_TOOL_NAME = 'glob'
+GREP_TOOL_NAME = 'grep'
+
+_ALL_TOOL_NAMES = {EXEC_TOOL_NAME, READ_TOOL_NAME, WRITE_TOOL_NAME, EDIT_TOOL_NAME, GLOB_TOOL_NAME, GREP_TOOL_NAME}
+
+# Skip these dirs during grep walk to avoid noise
+_SKIP_DIRS = {'.git', 'node_modules', '__pycache__', '.venv', 'venv', '.tox', 'dist', 'build'}
+
+
+class NativeToolLoader(loader.ToolLoader):
+    def __init__(self, ap):
+        super().__init__(ap)
+        self._tools: list[resource_tool.LLMTool] | None = None
+        self._backend_available: bool | None = None
+
+    async def initialize(self):
+        """Check if backend is truly available at startup."""
+        self._backend_available = await self._check_backend_available()
+        if self._backend_available:
+            self.ap.logger.info('Native sandbox tools (exec/read/write/edit/glob/grep) are available.')
+        else:
+            self.ap.logger.warning(
+                'Native sandbox tools (exec/read/write/edit/glob/grep) are NOT available. '
+                'No sandbox backend (Docker/nsjail/E2B) is ready. '
+                'The LLM will not have access to code execution or file operation tools.'
+            )
+
+    async def _check_backend_available(self) -> bool:
+        """Check if the box backend is truly available (not just the runtime)."""
+        box_service = getattr(self.ap, 'box_service', None)
+        if box_service is None:
+            return False
+        if not getattr(box_service, 'available', False):
+            return False
+        # Check if backend is truly available via get_status
+        try:
+            status = await box_service.get_status()
+            backend_info = status.get('backend', {})
+            return backend_info.get('available', False)
+        except Exception:
+            return False
+
+    async def get_tools(self, bound_plugins: list[str] | None = None) -> list[resource_tool.LLMTool]:
+        if not self._is_sandbox_available():
+            return []
+        if self._tools is None:
+            self._tools = [
+                self._build_exec_tool(),
+                self._build_read_tool(),
+                self._build_write_tool(),
+                self._build_edit_tool(),
+                self._build_glob_tool(),
+                self._build_grep_tool(),
+            ]
+        return list(self._tools)
+
+    async def has_tool(self, name: str) -> bool:
+        return name in _ALL_TOOL_NAMES and self._is_sandbox_available()
+
+    async def invoke_tool(self, name: str, parameters: dict, query: pipeline_query.Query):
+        if name == EXEC_TOOL_NAME:
+            self.ap.logger.info(
+                'exec tool invoked: '
+                f'query_id={query.query_id} '
+                f'parameters={json.dumps(self._summarize_parameters(parameters), ensure_ascii=False)}'
+            )
+            return await self._invoke_exec(parameters, query)
+        if name == READ_TOOL_NAME:
+            return await self._invoke_read(parameters, query)
+        if name == WRITE_TOOL_NAME:
+            return await self._invoke_write(parameters, query)
+        if name == EDIT_TOOL_NAME:
+            return await self._invoke_edit(parameters, query)
+        if name == GLOB_TOOL_NAME:
+            return await self._invoke_glob(parameters, query)
+        if name == GREP_TOOL_NAME:
+            return await self._invoke_grep(parameters, query)
+        raise ValueError(f'未找到工具: {name}')
+
+    async def shutdown(self):
+        pass
+
+    async def _invoke_exec(self, parameters: dict, query: pipeline_query.Query) -> dict:
+        command = str(parameters['command'])
+        workdir = str(parameters.get('workdir', '/workspace') or '/workspace')
+
+        # Validate that skill references target activated skills.
+        selected_skill, _ = skill_loader.resolve_virtual_skill_path(
+            self.ap,
+            query,
+            workdir,
+            include_visible=False,
+            include_activated=True,
+        )
+        referenced_skill_names = skill_loader.find_referenced_skill_names(command)
+
+        if selected_skill is None and referenced_skill_names:
+            if len(referenced_skill_names) > 1:
+                raise ValueError('exec can target at most one activated skill package per call.')
+            selected_skill = skill_loader.get_activated_skill(query, referenced_skill_names[0])
+            if selected_skill is None:
+                raise ValueError(
+                    f'Skill "{referenced_skill_names[0]}" must be activated before exec can run in its package.'
+                )
+
+        if selected_skill is not None:
+            selected_skill_name = str(selected_skill.get('name', '') or '')
+            if referenced_skill_names and any(name != selected_skill_name for name in referenced_skill_names):
+                raise ValueError('exec can reference files from only one activated skill package per call.')
+
+            package_root = str(selected_skill.get('package_root', '') or '').strip()
+            if not package_root:
+                raise ValueError(f'Activated skill "{selected_skill_name}" has no package_root.')
+
+            # Wrap command with Python venv bootstrap if the skill has a Python project.
+            # The venv is created inside the skill's mount path.
+            skill_mount = f'/workspace/.skills/{selected_skill_name}'
+            if skill_loader.should_prepare_skill_python_env(package_root):
+                parameters = dict(parameters)
+                parameters['command'] = skill_loader.wrap_skill_command_with_python_env(command, mount_path=skill_mount)
+
+        # All exec calls (with or without skills) go through the same container
+        # via execute_tool. Skills are mounted at /workspace/.skills/{name}/
+        # via extra_mounts built by BoxService.
+        result = await self.ap.box_service.execute_tool(parameters, query)
+
+        if selected_skill is not None:
+            self._refresh_skill_from_disk(selected_skill)
+        return result
+
+    def _resolve_host_path(
+        self,
+        query: pipeline_query.Query,
+        sandbox_path: str,
+        *,
+        include_visible: bool,
+        include_activated: bool,
+    ) -> tuple[str, dict | None]:
+        selected_skill, rewritten_path = skill_loader.resolve_virtual_skill_path(
+            self.ap,
+            query,
+            sandbox_path,
+            include_visible=include_visible,
+            include_activated=include_activated,
+        )
+
+        box_service = self.ap.box_service
+        host_root = selected_skill.get('package_root') if selected_skill is not None else box_service.default_workspace
+        if not host_root:
+            raise ValueError('No host workspace configured for file operations.')
+
+        mount_path = '/workspace'
+        if not rewritten_path.startswith(mount_path):
+            raise ValueError(f'Path must be under {mount_path}.')
+
+        relative = rewritten_path[len(mount_path) :].lstrip('/')
+        host_path = os.path.realpath(os.path.join(host_root, relative))
+        host_root = os.path.realpath(host_root)
+
+        if not (host_path == host_root or host_path.startswith(host_root + os.sep)):
+            raise ValueError('Path escapes the workspace boundary.')
+
+        return host_path, selected_skill
+
+    def _resolve_skill_relative_path(
+        self,
+        query: pipeline_query.Query,
+        sandbox_path: str,
+        *,
+        include_visible: bool,
+        include_activated: bool,
+    ) -> tuple[dict, str] | None:
+        selected_skill, rewritten_path = skill_loader.resolve_virtual_skill_path(
+            self.ap,
+            query,
+            sandbox_path,
+            include_visible=include_visible,
+            include_activated=include_activated,
+        )
+        if selected_skill is None:
+            return None
+
+        mount_path = '/workspace'
+        if not rewritten_path.startswith(mount_path):
+            raise ValueError(f'Path must be under {mount_path}.')
+        relative = rewritten_path[len(mount_path) :].lstrip('/') or '.'
+        return selected_skill, relative
+
+    def _should_use_box_workspace_files(self, selected_skill: dict | None) -> bool:
+        if selected_skill is not None:
+            return False
+        box_service = getattr(self.ap, 'box_service', None)
+        if box_service is None or not hasattr(box_service, 'execute_tool'):
+            return False
+        default_workspace = getattr(box_service, 'default_workspace', None)
+        return bool(default_workspace and not os.path.isdir(os.path.realpath(default_workspace)))
+
+    async def _run_workspace_file_script(self, script: str, query: pipeline_query.Query) -> dict:
+        result = await self.ap.box_service.execute_tool(
+            {
+                'command': f"python - <<'PY'\n{script}\nPY",
+                'timeout_sec': 30,
+            },
+            query,
+        )
+        if not result.get('ok'):
+            return {'ok': False, 'error': result.get('stderr') or result.get('stdout') or 'Box execution failed'}
+        stdout = str(result.get('stdout') or '').strip()
+        try:
+            return json.loads(stdout.splitlines()[-1])
+        except Exception:
+            return {'ok': False, 'error': stdout or 'Box file operation returned no result'}
+
+    async def _read_workspace_via_box(self, path: str, query: pipeline_query.Query) -> dict:
+        script = f"""
+import json, os
+path = {json.dumps(path)}
+if not path.startswith('/workspace'):
+    print(json.dumps({{'ok': False, 'error': 'Path must be under /workspace.'}}))
+elif not os.path.exists(path):
+    print(json.dumps({{'ok': False, 'error': f'File not found: {{path}}'}}))
+elif os.path.isdir(path):
+    print(json.dumps({{'ok': True, 'content': '\\n'.join(sorted(os.listdir(path))), 'is_directory': True}}))
+else:
+    with open(path, 'r', encoding='utf-8', errors='replace') as f:
+        print(json.dumps({{'ok': True, 'content': f.read()}}))
+""".strip()
+        return await self._run_workspace_file_script(script, query)
+
+    async def _write_workspace_via_box(self, path: str, content: str, query: pipeline_query.Query) -> dict:
+        script = f"""
+import json, os
+path = {json.dumps(path)}
+content = {json.dumps(content)}
+if not path.startswith('/workspace'):
+    print(json.dumps({{'ok': False, 'error': 'Path must be under /workspace.'}}))
+else:
+    os.makedirs(os.path.dirname(path) or '/workspace', exist_ok=True)
+    with open(path, 'w', encoding='utf-8') as f:
+        f.write(content)
+    print(json.dumps({{'ok': True, 'path': path}}))
+""".strip()
+        return await self._run_workspace_file_script(script, query)
+
+    async def _edit_workspace_via_box(
+        self,
+        path: str,
+        old_string: str,
+        new_string: str,
+        query: pipeline_query.Query,
+    ) -> dict:
+        script = f"""
+import json, os
+path = {json.dumps(path)}
+old_string = {json.dumps(old_string)}
+new_string = {json.dumps(new_string)}
+if not path.startswith('/workspace'):
+    print(json.dumps({{'ok': False, 'error': 'Path must be under /workspace.'}}))
+elif not os.path.isfile(path):
+    print(json.dumps({{'ok': False, 'error': f'File not found: {{path}}'}}))
+else:
+    with open(path, 'r', encoding='utf-8', errors='replace') as f:
+        content = f.read()
+    count = content.count(old_string)
+    if count == 0:
+        print(json.dumps({{'ok': False, 'error': 'old_string not found in file.'}}))
+    elif count > 1:
+        print(json.dumps({{'ok': False, 'error': f'old_string matches {{count}} locations; provide a more unique string.'}}))
+    else:
+        with open(path, 'w', encoding='utf-8') as f:
+            f.write(content.replace(old_string, new_string, 1))
+        print(json.dumps({{'ok': True, 'path': path}}))
+""".strip()
+        return await self._run_workspace_file_script(script, query)
+
+    async def _glob_workspace_via_box(self, path: str, pattern: str, query: pipeline_query.Query) -> dict:
+        script = f"""
+import json, os
+from pathlib import Path
+path = {json.dumps(path)}
+pattern = {json.dumps(pattern)}
+skip_dirs = {json.dumps(sorted(_SKIP_DIRS))}
+if not path.startswith('/workspace'):
+    print(json.dumps({{'ok': False, 'error': 'Path must be under /workspace.'}}))
+elif not os.path.isdir(path):
+    print(json.dumps({{'ok': False, 'error': f'Path is not a directory: {{path}}'}}))
+else:
+    base = Path(path)
+    hits = [
+        item for item in base.rglob(pattern)
+        if not any(part in skip_dirs for part in item.parts)
+    ]
+    hits.sort(key=lambda item: item.stat().st_mtime if item.exists() else 0, reverse=True)
+    shown = hits[:100]
+    matches = []
+    for item in shown:
+        rel = os.path.relpath(str(item), path)
+        matches.append(os.path.join(path, rel).replace(os.sep, '/'))
+    print(json.dumps({{'ok': True, 'matches': matches, 'total': len(hits), 'truncated': len(hits) > 100}}))
+""".strip()
+        return await self._run_workspace_file_script(script, query)
+
+    async def _grep_workspace_via_box(
+        self,
+        path: str,
+        pattern: str,
+        include: str | None,
+        query: pipeline_query.Query,
+    ) -> dict:
+        script = f"""
+import json, os, re
+from pathlib import Path
+path = {json.dumps(path)}
+pattern = {json.dumps(pattern)}
+include = {json.dumps(include)}
+skip_dirs = {json.dumps(sorted(_SKIP_DIRS))}
+try:
+    regex = re.compile(pattern)
+except re.error as exc:
+    print(json.dumps({{'ok': False, 'error': f'Invalid regex: {{exc}}'}}))
+else:
+    if not path.startswith('/workspace'):
+        print(json.dumps({{'ok': False, 'error': 'Path must be under /workspace.'}}))
+    elif not os.path.exists(path):
+        print(json.dumps({{'ok': False, 'error': f'Path not found: {{path}}'}}))
+    else:
+        base = Path(path)
+        if base.is_file():
+            files = [base]
+        else:
+            files = []
+            for item in base.rglob(include or '*'):
+                if any(part in skip_dirs for part in item.parts):
+                    continue
+                if item.is_file():
+                    files.append(item)
+                if len(files) >= 5000:
+                    break
+
+        matches = []
+        for fp in files:
+            try:
+                text = fp.read_text(errors='ignore')
+            except OSError:
+                continue
+            for lineno, line in enumerate(text.splitlines(), 1):
+                if regex.search(line):
+                    if base.is_file():
+                        file_path = path
+                    else:
+                        rel = os.path.relpath(str(fp), path)
+                        file_path = os.path.join(path, rel).replace(os.sep, '/')
+                    matches.append({{'file': file_path, 'line': lineno, 'content': line.rstrip()}})
+                    if len(matches) >= 200:
+                        break
+            if len(matches) >= 200:
+                break
+
+        print(json.dumps({{'ok': True, 'matches': matches, 'total': len(matches), 'truncated': len(matches) >= 200}}))
+""".strip()
+        return await self._run_workspace_file_script(script, query)
+
+    async def _invoke_read(self, parameters: dict, query: pipeline_query.Query) -> dict:
+        path = parameters['path']
+        self.ap.logger.info(f'read tool invoked: query_id={query.query_id} path={path}')
+        skill_request = self._resolve_skill_relative_path(
+            query,
+            path,
+            include_visible=True,
+            include_activated=True,
+        )
+        if skill_request is not None and hasattr(self.ap.box_service, 'read_skill_file'):
+            selected_skill, relative = skill_request
+            try:
+                result = await self.ap.box_service.read_skill_file(selected_skill['name'], relative)
+                return {'ok': True, 'content': result.get('content', '')}
+            except Exception:
+                try:
+                    result = await self.ap.box_service.list_skill_files(selected_skill['name'], relative)
+                    entries = [entry['name'] for entry in result.get('entries', [])]
+                    return {'ok': True, 'content': '\n'.join(sorted(entries)), 'is_directory': True}
+                except Exception as exc:
+                    return {'ok': False, 'error': str(exc)}
+
+        host_path, selected_skill = self._resolve_host_path(
+            query,
+            path,
+            include_visible=True,
+            include_activated=True,
+        )
+        if self._should_use_box_workspace_files(selected_skill):
+            return await self._read_workspace_via_box(path, query)
+        if not os.path.exists(host_path):
+            return {'ok': False, 'error': f'File not found: {path}'}
+        if os.path.isdir(host_path):
+            entries = os.listdir(host_path)
+            return {'ok': True, 'content': '\n'.join(sorted(entries)), 'is_directory': True}
+        with open(host_path, 'r', errors='replace') as f:
+            content = f.read()
+        return {'ok': True, 'content': content}
+
+    async def _invoke_write(self, parameters: dict, query: pipeline_query.Query) -> dict:
+        path = parameters['path']
+        content = parameters['content']
+        self.ap.logger.info(f'write tool invoked: query_id={query.query_id} path={path} length={len(content)}')
+        skill_request = self._resolve_skill_relative_path(
+            query,
+            path,
+            include_visible=False,
+            include_activated=True,
+        )
+        if skill_request is not None and hasattr(self.ap.box_service, 'write_skill_file'):
+            selected_skill, relative = skill_request
+            await self.ap.box_service.write_skill_file(selected_skill['name'], relative, content)
+            await self.ap.skill_mgr.reload_skills()
+            return {'ok': True, 'path': path}
+
+        host_path, selected_skill = self._resolve_host_path(
+            query,
+            path,
+            include_visible=False,
+            include_activated=True,
+        )
+        if self._should_use_box_workspace_files(selected_skill):
+            return await self._write_workspace_via_box(path, content, query)
+        os.makedirs(os.path.dirname(host_path), exist_ok=True)
+        with open(host_path, 'w', encoding='utf-8') as f:
+            f.write(content)
+        self._refresh_skill_from_disk(selected_skill)
+        return {'ok': True, 'path': path}
+
+    async def _invoke_edit(self, parameters: dict, query: pipeline_query.Query) -> dict:
+        path = parameters['path']
+        old_string = parameters['old_string']
+        new_string = parameters['new_string']
+        self.ap.logger.info(
+            f'edit tool invoked: query_id={query.query_id} path={path} '
+            f'old_len={len(old_string)} new_len={len(new_string)}'
+        )
+        skill_request = self._resolve_skill_relative_path(
+            query,
+            path,
+            include_visible=False,
+            include_activated=True,
+        )
+        if (
+            skill_request is not None
+            and hasattr(self.ap.box_service, 'read_skill_file')
+            and hasattr(self.ap.box_service, 'write_skill_file')
+        ):
+            selected_skill, relative = skill_request
+            try:
+                result = await self.ap.box_service.read_skill_file(selected_skill['name'], relative)
+            except Exception:
+                return {'ok': False, 'error': f'File not found: {path}'}
+            content = result.get('content', '')
+            count = content.count(old_string)
+            if count == 0:
+                return {'ok': False, 'error': 'old_string not found in file.'}
+            if count > 1:
+                return {'ok': False, 'error': f'old_string matches {count} locations; provide a more unique string.'}
+            new_content = content.replace(old_string, new_string, 1)
+            await self.ap.box_service.write_skill_file(selected_skill['name'], relative, new_content)
+            await self.ap.skill_mgr.reload_skills()
+            return {'ok': True, 'path': path}
+
+        host_path, selected_skill = self._resolve_host_path(
+            query,
+            path,
+            include_visible=False,
+            include_activated=True,
+        )
+        if self._should_use_box_workspace_files(selected_skill):
+            return await self._edit_workspace_via_box(path, old_string, new_string, query)
+        if not os.path.isfile(host_path):
+            return {'ok': False, 'error': f'File not found: {path}'}
+        with open(host_path, 'r', encoding='utf-8', errors='replace') as f:
+            content = f.read()
+        count = content.count(old_string)
+        if count == 0:
+            return {'ok': False, 'error': 'old_string not found in file.'}
+        if count > 1:
+            return {'ok': False, 'error': f'old_string matches {count} locations; provide a more unique string.'}
+        new_content = content.replace(old_string, new_string, 1)
+        with open(host_path, 'w', encoding='utf-8') as f:
+            f.write(new_content)
+        self._refresh_skill_from_disk(selected_skill)
+        return {'ok': True, 'path': path}
+
+    def _refresh_skill_from_disk(self, selected_skill: dict | None) -> None:
+        if selected_skill is None:
+            return
+
+        skill_mgr = getattr(self.ap, 'skill_mgr', None)
+        if skill_mgr is None:
+            return
+
+        refresh_skill = getattr(skill_mgr, 'refresh_skill_from_disk', None)
+        if callable(refresh_skill):
+            refresh_skill(selected_skill.get('name', ''))
+
+    def _is_sandbox_available(self) -> bool:
+        """Check if sandbox backend is available.
+
+        This checks the cached backend availability from initialization,
+        not just whether the box_service process is running.
+        """
+        return bool(self._backend_available)
+
+    def _build_exec_tool(self) -> resource_tool.LLMTool:
+        return resource_tool.LLMTool(
+            name=EXEC_TOOL_NAME,
+            human_desc='Execute a command in an isolated environment',
+            description=(
+                'Run shell commands in an isolated execution environment. '
+                'Use this tool for bash commands, Python execution, and exact calculations over '
+                'user-provided data. Activated skill packages are addressable under '
+                '/workspace/.skills/<skill-name>; when running inside one, set workdir to that path. '
+                'To create a new skill package, prepare it under /workspace first, then use register_skill.'
+            ),
+            parameters={
+                'type': 'object',
+                'properties': {
+                    'command': {
+                        'type': 'string',
+                        'description': 'Shell command to execute.',
+                    },
+                    'workdir': {
+                        'type': 'string',
+                        'description': 'Working directory for the command. Defaults to /workspace.',
+                        'default': '/workspace',
+                    },
+                    'timeout_sec': {
+                        'type': 'integer',
+                        'description': 'Execution timeout in seconds. Defaults to 30.',
+                        'default': 30,
+                        'minimum': 1,
+                    },
+                    'env': {
+                        'type': 'object',
+                        'description': 'Optional environment variables for the execution.',
+                        'additionalProperties': {'type': 'string'},
+                        'default': {},
+                    },
+                    'description': {
+                        'type': 'string',
+                        'description': 'Brief description of what this command does, for logging and audit.',
+                    },
+                },
+                'required': ['command'],
+                'additionalProperties': False,
+            },
+            func=lambda parameters: parameters,
+        )
+
+    def _build_read_tool(self) -> resource_tool.LLMTool:
+        return resource_tool.LLMTool(
+            name=READ_TOOL_NAME,
+            human_desc='Read a file from the workspace',
+            description=(
+                'Read the contents of a file at the given path under /workspace. '
+                'Visible skill packages can be inspected through /workspace/.skills/<skill-name>/... .'
+            ),
+            parameters={
+                'type': 'object',
+                'properties': {
+                    'path': {
+                        'type': 'string',
+                        'description': 'Absolute path to the file (must be under /workspace).',
+                    },
+                },
+                'required': ['path'],
+                'additionalProperties': False,
+            },
+            func=lambda parameters: parameters,
+        )
+
+    def _build_write_tool(self) -> resource_tool.LLMTool:
+        return resource_tool.LLMTool(
+            name=WRITE_TOOL_NAME,
+            human_desc='Write a file to the workspace',
+            description=(
+                'Create or overwrite a file at the given path under /workspace with the provided content. '
+                'Activated skill packages can be modified through /workspace/.skills/<skill-name>/... . '
+                'For new skills, write files under /workspace and then call register_skill.'
+            ),
+            parameters={
+                'type': 'object',
+                'properties': {
+                    'path': {
+                        'type': 'string',
+                        'description': 'Absolute path to the file (must be under /workspace).',
+                    },
+                    'content': {
+                        'type': 'string',
+                        'description': 'Content to write to the file.',
+                    },
+                },
+                'required': ['path', 'content'],
+                'additionalProperties': False,
+            },
+            func=lambda parameters: parameters,
+        )
+
+    def _build_edit_tool(self) -> resource_tool.LLMTool:
+        return resource_tool.LLMTool(
+            name=EDIT_TOOL_NAME,
+            human_desc='Edit a file in the workspace',
+            description=(
+                'Perform an exact string replacement in a file under /workspace. '
+                'The old_string must appear exactly once in the file. Activated skill packages '
+                'can be edited through /workspace/.skills/<skill-name>/... . '
+                'For new skills, edit files under /workspace and then call register_skill.'
+            ),
+            parameters={
+                'type': 'object',
+                'properties': {
+                    'path': {
+                        'type': 'string',
+                        'description': 'Absolute path to the file (must be under /workspace).',
+                    },
+                    'old_string': {
+                        'type': 'string',
+                        'description': 'The exact string to find and replace.',
+                    },
+                    'new_string': {
+                        'type': 'string',
+                        'description': 'The replacement string.',
+                    },
+                },
+                'required': ['path', 'old_string', 'new_string'],
+                'additionalProperties': False,
+            },
+            func=lambda parameters: parameters,
+        )
+
+    def _build_glob_tool(self) -> resource_tool.LLMTool:
+        return resource_tool.LLMTool(
+            name=GLOB_TOOL_NAME,
+            human_desc='Find files matching a glob pattern',
+            description=(
+                'Find files matching a glob pattern under /workspace. '
+                'Supports ** for recursive matching (e.g. **/*.py). '
+                'Results are sorted by modification time (newest first). '
+                'Visible and activated skill packages can be searched through /workspace/.skills/<skill-name>/...'
+            ),
+            parameters={
+                'type': 'object',
+                'properties': {
+                    'pattern': {
+                        'type': 'string',
+                        'description': 'Glob pattern, e.g. **/*.py or src/**/*.ts',
+                    },
+                    'path': {
+                        'type': 'string',
+                        'description': 'Directory to search in (must be under /workspace, default: /workspace)',
+                        'default': '/workspace',
+                    },
+                },
+                'required': ['pattern'],
+                'additionalProperties': False,
+            },
+            func=lambda parameters: parameters,
+        )
+
+    def _build_grep_tool(self) -> resource_tool.LLMTool:
+        return resource_tool.LLMTool(
+            name=GREP_TOOL_NAME,
+            human_desc='Search file contents with regex',
+            description=(
+                'Search file contents with regex pattern under /workspace. '
+                'Returns matching lines with file path and line number. '
+                'Visible and activated skill packages can be searched through /workspace/.skills/<skill-name>/...'
+            ),
+            parameters={
+                'type': 'object',
+                'properties': {
+                    'pattern': {
+                        'type': 'string',
+                        'description': 'Regex pattern to search for',
+                    },
+                    'path': {
+                        'type': 'string',
+                        'description': 'File or directory to search (must be under /workspace, default: /workspace)',
+                        'default': '/workspace',
+                    },
+                    'include': {
+                        'type': 'string',
+                        'description': 'Only search files matching this glob (e.g. *.py)',
+                    },
+                },
+                'required': ['pattern'],
+                'additionalProperties': False,
+            },
+            func=lambda parameters: parameters,
+        )
+
+    async def _invoke_glob(self, parameters: dict, query: pipeline_query.Query) -> dict:
+        pattern = parameters['pattern']
+        path = str(parameters.get('path', '/workspace') or '/workspace')
+        self.ap.logger.info(f'glob tool invoked: query_id={query.query_id} pattern={pattern} path={path}')
+
+        host_path, selected_skill = self._resolve_host_path(
+            query,
+            path,
+            include_visible=True,
+            include_activated=True,
+        )
+        if self._should_use_box_workspace_files(selected_skill):
+            return await self._glob_workspace_via_box(path, pattern, query)
+
+        if not os.path.isdir(host_path):
+            return {'ok': False, 'error': f'Path is not a directory: {path}'}
+
+        from pathlib import Path
+
+        base = Path(host_path)
+        hits = list(base.rglob(pattern))
+
+        # Filter out skipped directories
+        hits = [h for h in hits if not any(skip in h.parts for skip in _SKIP_DIRS)]
+
+        # Sort by mtime, newest first
+        hits.sort(key=lambda p: p.stat().st_mtime if p.exists() else 0, reverse=True)
+
+        total = len(hits)
+        shown = hits[:100]
+
+        # Convert back to sandbox paths
+        sandbox_paths = []
+        for h in shown:
+            rel = os.path.relpath(str(h), host_path)
+            sandbox_path = os.path.join(path, rel)
+            sandbox_paths.append(sandbox_path)
+
+        result_lines = sandbox_paths
+        result = '\n'.join(result_lines)
+
+        if total > 100:
+            result += f'\n... ({total} matches, showing first 100)'
+
+        return {'ok': True, 'matches': result_lines, 'total': total, 'truncated': total > 100}
+
+    async def _invoke_grep(self, parameters: dict, query: pipeline_query.Query) -> dict:
+        pattern = parameters['pattern']
+        path = str(parameters.get('path', '/workspace') or '/workspace')
+        include = parameters.get('include')
+        self.ap.logger.info(f'grep tool invoked: query_id={query.query_id} pattern={pattern} path={path}')
+
+        import re
+        from pathlib import Path
+
+        try:
+            regex = re.compile(pattern)
+        except re.error as e:
+            return {'ok': False, 'error': f'Invalid regex: {e}'}
+
+        host_path, selected_skill = self._resolve_host_path(
+            query,
+            path,
+            include_visible=True,
+            include_activated=True,
+        )
+        if self._should_use_box_workspace_files(selected_skill):
+            return await self._grep_workspace_via_box(path, pattern, include, query)
+
+        if not os.path.exists(host_path):
+            return {'ok': False, 'error': f'Path not found: {path}'}
+
+        base = Path(host_path)
+
+        if base.is_file():
+            files = [base]
+        else:
+            files = self._grep_walk(base, include)
+
+        matches = []
+        for fp in files:
+            try:
+                text = fp.read_text(errors='ignore')
+            except OSError:
+                continue
+            for lineno, line in enumerate(text.splitlines(), 1):
+                if regex.search(line):
+                    rel = os.path.relpath(str(fp), host_path)
+                    sandbox_path = os.path.join(path, rel)
+                    matches.append(
+                        {
+                            'file': sandbox_path,
+                            'line': lineno,
+                            'content': line.rstrip(),
+                        }
+                    )
+                    if len(matches) >= 200:
+                        break
+            if len(matches) >= 200:
+                break
+
+        return {
+            'ok': True,
+            'matches': matches,
+            'total': len(matches),
+            'truncated': len(matches) >= 200,
+        }
+
+    @staticmethod
+    def _grep_walk(root, include: str | None) -> list:
+        """Walk dir tree for grep, skipping junk dirs."""
+        results = []
+        for item in root.rglob(include or '*'):
+            if any(skip in item.parts for skip in _SKIP_DIRS):
+                continue
+            if item.is_file():
+                results.append(item)
+            if len(results) >= 5000:
+                break
+        return results
+
+    def _summarize_parameters(self, parameters: dict) -> dict:
+        summary = dict(parameters)
+        cmd = str(summary.get('command', '')).strip()
+        if len(cmd) > 400:
+            cmd = f'{cmd[:397]}...'
+        summary['command'] = cmd
+
+        env = summary.get('env')
+        if isinstance(env, dict):
+            summary['env_keys'] = sorted(str(key) for key in env.keys())
+            del summary['env']
+
+        return summary

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

@@ -0,0 +1,157 @@
+from __future__ import annotations
+
+import re
+import typing
+
+from ....box import workspace as box_workspace
+
+if typing.TYPE_CHECKING:
+    from ....core import app
+    from langbot_plugin.api.entities.events import pipeline_query
+
+ACTIVATED_SKILLS_KEY = '_activated_skills'
+PIPELINE_BOUND_SKILLS_KEY = '_pipeline_bound_skills'
+SKILL_MOUNT_PREFIX = '/workspace/.skills'
+_SKILL_MOUNT_PATTERN = re.compile(r'/workspace/\.skills/([A-Za-z0-9_-]+)')
+
+
+def get_virtual_skill_mount_path(skill_name: str) -> str:
+    return f'{SKILL_MOUNT_PREFIX}/{skill_name}'
+
+
+def get_bound_skill_names(query: pipeline_query.Query) -> list[str] | None:
+    if query.variables is None:
+        return None
+
+    bound_skills = query.variables.get(PIPELINE_BOUND_SKILLS_KEY)
+    if bound_skills is None:
+        return None
+    if isinstance(bound_skills, list):
+        return [str(item) for item in bound_skills]
+    return None
+
+
+def get_visible_skills(ap: app.Application, query: pipeline_query.Query) -> dict[str, dict]:
+    skill_mgr = getattr(ap, 'skill_mgr', None)
+    if skill_mgr is None:
+        return {}
+
+    visible_skills = getattr(skill_mgr, 'skills', {})
+    bound_skills = get_bound_skill_names(query)
+    if bound_skills is None:
+        return visible_skills
+
+    return {skill_name: skill_data for skill_name, skill_data in visible_skills.items() if skill_name in bound_skills}
+
+
+def get_visible_skill(ap: app.Application, query: pipeline_query.Query, skill_name: str) -> dict | None:
+    return get_visible_skills(ap, query).get(skill_name)
+
+
+def get_activated_skills(query: pipeline_query.Query) -> dict[str, dict]:
+    if query.variables is None:
+        return {}
+
+    activated = query.variables.get(ACTIVATED_SKILLS_KEY, {})
+    if not isinstance(activated, dict):
+        return {}
+    return activated
+
+
+def get_activated_skill(query: pipeline_query.Query, skill_name: str) -> dict | None:
+    return get_activated_skills(query).get(skill_name)
+
+
+def register_activated_skill(query: pipeline_query.Query, skill_data: dict) -> None:
+    if query.variables is None:
+        query.variables = {}
+
+    activated = query.variables.setdefault(ACTIVATED_SKILLS_KEY, {})
+    skill_name = str(skill_data.get('name', '') or '').strip()
+    if skill_name and skill_name not in activated:
+        activated[skill_name] = skill_data
+
+
+def parse_skill_mount_path(sandbox_path: str) -> tuple[str | None, str]:
+    normalized_path = str(sandbox_path or '/workspace').strip() or '/workspace'
+    if normalized_path == SKILL_MOUNT_PREFIX:
+        raise ValueError(f'Path must include a skill name under {SKILL_MOUNT_PREFIX}/<skill-name>.')
+    prefix = f'{SKILL_MOUNT_PREFIX}/'
+    if not normalized_path.startswith(prefix):
+        return None, normalized_path
+
+    remainder = normalized_path[len(prefix) :]
+    skill_name, separator, tail = remainder.partition('/')
+    if not skill_name:
+        raise ValueError(f'Path must include a skill name under {SKILL_MOUNT_PREFIX}/<skill-name>.')
+
+    rewritten_path = '/workspace'
+    if separator:
+        rewritten_path = f'/workspace/{tail}'
+    return skill_name, rewritten_path
+
+
+def resolve_virtual_skill_path(
+    ap: app.Application,
+    query: pipeline_query.Query,
+    sandbox_path: str,
+    *,
+    include_visible: bool,
+    include_activated: bool,
+) -> tuple[dict | None, str]:
+    skill_name, rewritten_path = parse_skill_mount_path(sandbox_path)
+    if skill_name is None:
+        return None, rewritten_path
+
+    if include_activated:
+        activated_skill = get_activated_skill(query, skill_name)
+        if activated_skill is not None:
+            return activated_skill, rewritten_path
+
+    if include_visible:
+        visible_skill = get_visible_skill(ap, query, skill_name)
+        if visible_skill is not None:
+            return visible_skill, rewritten_path
+
+    activated_names = ', '.join(sorted(get_activated_skills(query).keys())) or 'none'
+    visible_names = ', '.join(sorted(get_visible_skills(ap, query).keys())) or 'none'
+    raise ValueError(
+        f'Skill "{skill_name}" is not available at this path. '
+        f'Activated skills: {activated_names}. Visible skills: {visible_names}.'
+    )
+
+
+def find_referenced_skill_names(text: str) -> list[str]:
+    if not text:
+        return []
+
+    seen: list[str] = []
+    for match in _SKILL_MOUNT_PATTERN.findall(text):
+        if match not in seen:
+            seen.append(match)
+    return seen
+
+
+def rewrite_command_for_skill_mount(command: str, skill_name: str) -> str:
+    virtual_root = get_virtual_skill_mount_path(skill_name)
+    rewritten = command.replace(f'{virtual_root}/', '/workspace/')
+    return rewritten.replace(virtual_root, '/workspace')
+
+
+def build_skill_session_id(skill_data: dict, query: pipeline_query.Query) -> str:
+    skill_identifier = str(skill_data.get('name', 'unknown') or 'unknown')
+    launcher_type = getattr(query, 'launcher_type', None)
+    launcher_id = getattr(query, 'launcher_id', None)
+    query_id = getattr(query, 'query_id', 'unknown')
+
+    if launcher_type is not None and launcher_id is not None:
+        return f'skill-{launcher_type}_{launcher_id}-{skill_identifier}'
+    return f'skill-{query_id}-{skill_identifier}'
+
+
+def should_prepare_skill_python_env(package_root: str | None) -> bool:
+    return box_workspace.should_prepare_python_env(package_root)
+
+
+def wrap_skill_command_with_python_env(command: str, *, mount_path: str = '/workspace') -> str:
+    return box_workspace.wrap_python_command_with_env(command, mount_path=mount_path).rstrip()

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

@@ -0,0 +1,304 @@
+from __future__ import annotations
+
+import os
+import typing
+
+import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
+
+from .. import loader
+
+# Align with Claude Code's Skill tool design:
+# - activate: Activate a skill via Tool Call, returns SKILL.md content
+# - register_skill: Register a skill from sandbox directory to data/skills/
+# - This protects KV Cache and follows industry standard
+
+ACTIVATE_SKILL_TOOL_NAME = 'activate'
+REGISTER_SKILL_TOOL_NAME = 'register_skill'
+
+SKILL_TOOL_NAMES = {
+    ACTIVATE_SKILL_TOOL_NAME,
+    REGISTER_SKILL_TOOL_NAME,
+}
+
+
+class SkillToolLoader(loader.ToolLoader):
+    """Skill tools aligned with Claude Code's design."""
+
+    def __init__(self, ap):
+        super().__init__(ap)
+        self._tools: list[resource_tool.LLMTool] = []
+        self._sandbox_available: bool = False
+
+    async def initialize(self):
+        # Check if sandbox backend is available (same check as native tools)
+        self._sandbox_available = await self._check_sandbox_available()
+        if self._sandbox_available:
+            self._tools = [
+                self._build_activate_skill_tool(),
+                self._build_register_skill_tool(),
+            ]
+        else:
+            self.ap.logger.info(
+                'Skill tools (activate/register_skill) are NOT available. '
+                'No sandbox backend (Docker/nsjail/E2B) is ready.'
+            )
+
+    async def _check_sandbox_available(self) -> bool:
+        """Check if the box backend is truly available (not just the runtime)."""
+        box_service = getattr(self.ap, 'box_service', None)
+        if box_service is None:
+            return False
+        if not getattr(box_service, 'available', False):
+            return False
+        # Check if backend is truly available via get_status
+        try:
+            status = await box_service.get_status()
+            backend_info = status.get('backend', {})
+            return backend_info.get('available', False)
+        except Exception:
+            return False
+
+    async def get_tools(self, bound_plugins: list[str] | None = None) -> list[resource_tool.LLMTool]:
+        if not self._is_available():
+            return []
+        return list(self._tools)
+
+    async def has_tool(self, name: str) -> bool:
+        return self._is_available() and name in SKILL_TOOL_NAMES
+
+    def _is_available(self) -> bool:
+        """Check if skill tools should be available.
+
+        Skill tools require both a skill manager and a sandbox backend.
+        """
+        return self._has_skill_manager() and self._sandbox_available
+
+    async def invoke_tool(self, name: str, parameters: dict, query) -> typing.Any:
+        if name == ACTIVATE_SKILL_TOOL_NAME:
+            return await self._invoke_activate_skill(parameters, query)
+        if name == REGISTER_SKILL_TOOL_NAME:
+            return await self._invoke_register_skill(parameters)
+        raise ValueError(f'Unknown skill tool: {name}')
+
+    async def shutdown(self):
+        pass
+
+    def _has_skill_manager(self) -> bool:
+        return getattr(self.ap, 'skill_mgr', None) is not None
+
+    async def _invoke_activate_skill(self, parameters: dict, query) -> typing.Any:
+        """Activate a skill and return SKILL.md content via Tool Result."""
+        skill_name = str(parameters.get('skill_name', '') or '').strip()
+        if not skill_name:
+            raise ValueError('skill_name is required')
+
+        skill_mgr = self.ap.skill_mgr
+        skill_data = skill_mgr.get_skill_by_name(skill_name)
+        if skill_data is None:
+            visible_skills = getattr(skill_mgr, 'skills', {})
+            available_names = ', '.join(sorted(visible_skills.keys())) or 'none'
+            raise ValueError(f'Skill "{skill_name}" not found. Available skills: {available_names}')
+
+        # Register activated skill for sandbox mount path resolution
+        from . import skill as skill_loader
+
+        skill_loader.register_activated_skill(query, skill_data)
+
+        # Return SKILL.md content as Tool Result (injects into context)
+        instructions = skill_data.get('instructions', '')
+        package_root = skill_data.get('package_root', '')
+        mount_path = skill_loader.get_virtual_skill_mount_path(skill_name)
+
+        # Build Tool Result content
+        result_content = f'<command-message>The "{skill_name}" skill is activated</command-message>\n'
+        result_content += '<skill-activation>\n'
+        result_content += f'<skill-name>{skill_name}</skill-name>\n'
+        result_content += f'<mount-path>{mount_path}</mount-path>\n'
+        result_content += f'<package-root>{package_root}</package-root>\n'
+        result_content += f'\n## Instructions\n{instructions}\n'
+        result_content += '\n## Runtime Context\n'
+        result_content += f'The skill package is mounted at {mount_path}. Use the standard tools to interact with it:\n'
+        result_content += f'- Use `read` to inspect files under {mount_path}\n'
+        result_content += f'- Use `exec` with workdir set to {mount_path} to run commands in that package\n'
+        result_content += '- Use `write` and `edit` on that path when the instructions require updating files\n'
+        result_content += '</skill-activation>\n'
+
+        return {
+            'activated': True,
+            'skill_name': skill_name,
+            'mount_path': mount_path,
+            'content': result_content,
+        }
+
+    async def _invoke_register_skill(self, parameters: dict) -> typing.Any:
+        """Register a skill from sandbox directory to data/skills/."""
+        sandbox_path = str(parameters.get('path', '') or '').strip()
+        if not sandbox_path:
+            raise ValueError('path is required')
+
+        # Resolve sandbox path to host path
+        host_path = self._resolve_workspace_directory(sandbox_path)
+
+        # Get or create skill service
+        skill_service = getattr(self.ap, 'skill_service', None)
+        if skill_service is None:
+            raise ValueError('Skill service not available')
+
+        # Scan and register the skill
+        scanned = await skill_service.scan_directory_async(host_path)
+
+        # Override name if provided
+        skill_name = str(parameters.get('name') or scanned['name']).strip()
+        if not skill_name:
+            raise ValueError('skill name is required')
+
+        # Create the skill
+        created = await skill_service.create_skill(
+            {
+                'name': skill_name,
+                'display_name': str(parameters.get('display_name') or scanned.get('display_name', '')).strip(),
+                'description': str(parameters.get('description') or scanned.get('description', '')).strip(),
+                'instructions': str(parameters.get('instructions') or scanned.get('instructions', '')),
+                'package_root': host_path,
+            }
+        )
+
+        return {
+            'registered': True,
+            'skill_name': skill_name,
+            'source_path': sandbox_path,
+            'skill': created,
+        }
+
+    def _resolve_workspace_directory(self, sandbox_path: str) -> str:
+        """Resolve sandbox path to host filesystem path."""
+        box_service = getattr(self.ap, 'box_service', None)
+        workspace_root = getattr(box_service, 'default_workspace', None)
+        if not workspace_root:
+            raise ValueError('No default workspace configured')
+
+        normalized_path = str(sandbox_path).strip() or '/workspace'
+        if not normalized_path.startswith('/workspace'):
+            raise ValueError('path must be under /workspace')
+
+        relative = normalized_path[len('/workspace') :].lstrip('/')
+        host_root = os.path.realpath(workspace_root)
+        host_path = os.path.realpath(os.path.join(host_root, relative))
+
+        # Security check: ensure path doesn't escape workspace
+        if not (host_path == host_root or host_path.startswith(host_root + os.sep)):
+            raise ValueError('path escapes the workspace boundary')
+
+        if getattr(box_service, 'available', False):
+            return host_path
+
+        if not os.path.isdir(host_path):
+            raise ValueError(f'Directory does not exist: {sandbox_path}')
+
+        return host_path
+
+    def _build_activate_skill_tool(self) -> resource_tool.LLMTool:
+        return resource_tool.LLMTool(
+            name=ACTIVATE_SKILL_TOOL_NAME,
+            human_desc='Activate a skill',
+            description=self._build_activate_tool_description(),
+            parameters={
+                'type': 'object',
+                'properties': {
+                    'skill_name': {
+                        'type': 'string',
+                        'description': 'The skill name to activate (no arguments). E.g., "pdf" or "data-analysis"',
+                    },
+                },
+                'required': ['skill_name'],
+                'additionalProperties': False,
+            },
+            func=lambda parameters: parameters,
+        )
+
+    def _build_register_skill_tool(self) -> resource_tool.LLMTool:
+        return resource_tool.LLMTool(
+            name=REGISTER_SKILL_TOOL_NAME,
+            human_desc='Register a skill from sandbox',
+            description=(
+                "Register a skill package from a directory under /workspace into LangBot's skill store. "
+                'Use this after creating or preparing a skill in the sandbox with exec/read/write/edit. '
+                'The directory must contain a SKILL.md file. '
+                'After registration, the skill can be activated with the activate tool.'
+            ),
+            parameters={
+                'type': 'object',
+                'properties': {
+                    'path': {
+                        'type': 'string',
+                        'description': 'Directory path under /workspace containing the skill package (must have SKILL.md)',
+                    },
+                    'name': {
+                        'type': 'string',
+                        'description': 'Optional skill name override. Defaults to the name in SKILL.md or directory name.',
+                    },
+                    'display_name': {
+                        'type': 'string',
+                        'description': 'Optional display name override.',
+                    },
+                    'description': {
+                        'type': 'string',
+                        'description': 'Optional description override.',
+                    },
+                    'instructions': {
+                        'type': 'string',
+                        'description': 'Optional instructions override.',
+                    },
+                },
+                'required': ['path'],
+                'additionalProperties': False,
+            },
+            func=lambda parameters: parameters,
+        )
+
+    def _build_activate_tool_description(self) -> str:
+        """Build tool description with embedded available_skills list."""
+        skill_mgr = getattr(self.ap, 'skill_mgr', None)
+        if skill_mgr is None:
+            return 'Activate a skill. No skills are currently available.'
+
+        skills = getattr(skill_mgr, 'skills', {})
+        if not skills:
+            return 'Activate a skill. No skills are currently available.'
+
+        # Build <available_skills> section
+        available_skills_lines = ['<available_skills>']
+        for skill_name, skill_data in sorted(skills.items()):
+            description = skill_data.get('description', '')
+            available_skills_lines.append('<skill>')
+            available_skills_lines.append(f'<name>{skill_name}</name>')
+            available_skills_lines.append(f'<description>{description}</description>')
+            available_skills_lines.append('</skill>')
+        available_skills_lines.append('</available_skills>')
+
+        available_skills_block = '\n'.join(available_skills_lines)
+
+        return f"""Activate a skill within the main conversation.
+
+<skills_instructions>
+When users ask you to perform tasks, check if any of the available skills
+below can help complete the task more effectively. Skills provide specialized
+capabilities and domain knowledge.
+
+How to use skills:
+- Invoke skills using this tool with the skill name only (no arguments)
+- When you invoke a skill, you will see <command-message>
+The skill is activated
+</command-message>
+- The skill's instructions will be provided in the tool result
+- Examples:
+  - skill_name: "pdf" - invoke the pdf skill
+  - skill_name: "data-analysis" - invoke the data-analysis skill
+
+Important:
+- Only use skills listed in <available_skills> below
+- Do not invoke a skill that is already running
+- To create a new skill: prepare it in /workspace, then use register_skill tool
+</skills_instructions>
+
+{available_skills_block}"""

src/langbot/pkg/provider/tools/toolmgr.py

@@ -1,15 +1,19 @@
 from __future__ import annotations
 
 import typing
+from typing import TYPE_CHECKING
 
-from ...core import app
-from langbot.pkg.utils import importutil
-from langbot.pkg.provider.tools import loaders
-from langbot.pkg.provider.tools.loaders import mcp as mcp_loader, plugin as plugin_loader
 import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
 from langbot_plugin.api.entities.events import pipeline_query
 
-importutil.import_modules_in_pkg(loaders)
+if TYPE_CHECKING:
+    from ...core import app
+    from langbot.pkg.provider.tools.loaders import (
+        mcp as mcp_loader,
+        native as native_loader,
+        plugin as plugin_loader,
+        skill_authoring as skill_authoring_loader,
+    )
 
 
 class ToolManager:
@@ -17,31 +21,53 @@ class ToolManager:
 
     ap: app.Application
 
+    native_tool_loader: native_loader.NativeToolLoader
     plugin_tool_loader: plugin_loader.PluginToolLoader
     mcp_tool_loader: mcp_loader.MCPLoader
+    skill_tool_loader: skill_authoring_loader.SkillToolLoader
 
     def __init__(self, ap: app.Application):
         self.ap = ap
 
     async def initialize(self):
+        from langbot.pkg.utils import importutil
+        from langbot.pkg.provider.tools import loaders
+        from langbot.pkg.provider.tools.loaders import (
+            mcp as mcp_loader,
+            native as native_loader,
+            plugin as plugin_loader,
+            skill_authoring as skill_authoring_loader,
+        )
+
+        importutil.import_modules_in_pkg(loaders)
+
+        self.native_tool_loader = native_loader.NativeToolLoader(self.ap)
+        await self.native_tool_loader.initialize()
+
         self.plugin_tool_loader = plugin_loader.PluginToolLoader(self.ap)
         await self.plugin_tool_loader.initialize()
         self.mcp_tool_loader = mcp_loader.MCPLoader(self.ap)
         await self.mcp_tool_loader.initialize()
+        self.skill_tool_loader = skill_authoring_loader.SkillToolLoader(self.ap)
+        await self.skill_tool_loader.initialize()
 
     async def get_all_tools(
-        self, bound_plugins: list[str] | None = None, bound_mcp_servers: list[str] | None = None
+        self,
+        bound_plugins: list[str] | None = None,
+        bound_mcp_servers: list[str] | None = None,
+        include_skill_authoring: bool = False,
     ) -> list[resource_tool.LLMTool]:
-        """获取所有函数"""
         all_functions: list[resource_tool.LLMTool] = []
 
+        all_functions.extend(await self.native_tool_loader.get_tools())
+        if include_skill_authoring:
+            all_functions.extend(await self.skill_tool_loader.get_tools())
         all_functions.extend(await self.plugin_tool_loader.get_tools(bound_plugins))
         all_functions.extend(await self.mcp_tool_loader.get_tools(bound_mcp_servers))
 
         return all_functions
 
     async def generate_tools_for_openai(self, use_funcs: list[resource_tool.LLMTool]) -> list:
-        """生成函数列表"""
         tools = []
 
         for function in use_funcs:
@@ -58,28 +84,6 @@ class ToolManager:
         return tools
 
     async def generate_tools_for_anthropic(self, use_funcs: list[resource_tool.LLMTool]) -> list:
-        """为anthropic生成函数列表
-
-        e.g.
-
-        [
-          {
-            "name": "get_stock_price",
-            "description": "Get the current stock price for a given ticker symbol.",
-            "input_schema": {
-              "type": "object",
-              "properties": {
-                "ticker": {
-                  "type": "string",
-                  "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
-                }
-              },
-              "required": ["ticker"]
-            }
-          }
-        ]
-        """
-
         tools = []
 
         for function in use_funcs:
@@ -93,16 +97,18 @@ class ToolManager:
         return tools
 
     async def execute_func_call(self, name: str, parameters: dict, query: pipeline_query.Query) -> typing.Any:
-        """执行函数调用"""
-
+        if await self.native_tool_loader.has_tool(name):
+            return await self.native_tool_loader.invoke_tool(name, parameters, query)
         if await self.plugin_tool_loader.has_tool(name):
             return await self.plugin_tool_loader.invoke_tool(name, parameters, query)
-        elif await self.mcp_tool_loader.has_tool(name):
+        if await self.mcp_tool_loader.has_tool(name):
             return await self.mcp_tool_loader.invoke_tool(name, parameters, query)
-        else:
-            raise ValueError(f'未找到工具: {name}')
+        if await self.skill_tool_loader.has_tool(name):
+            return await self.skill_tool_loader.invoke_tool(name, parameters, query)
+        raise ValueError(f'未找到工具: {name}')
 
     async def shutdown(self):
-        """关闭所有工具"""
+        await self.native_tool_loader.shutdown()
         await self.plugin_tool_loader.shutdown()
         await self.mcp_tool_loader.shutdown()
+        await self.skill_tool_loader.shutdown()

src/langbot/pkg/skill/__init__.py

@@ -0,0 +1,3 @@
+from .manager import SkillManager
+
+__all__ = ['SkillManager']

src/langbot/pkg/skill/activation.py

@@ -0,0 +1,35 @@
+from __future__ import annotations
+
+import typing
+
+from ..provider.tools.loaders import skill as skill_loader
+
+if typing.TYPE_CHECKING:
+    from ..core import app
+    import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+
+
+# Skill activation is now handled through Tool Call mechanism (activate tool).
+# This file is kept for potential future extensions but the text marker
+# detection mechanism has been removed.
+
+
+def register_activated_skill(
+    ap: app.Application,
+    query: pipeline_query.Query,
+    skill_name: str,
+) -> bool:
+    """Register an activated skill for sandbox mount path resolution.
+
+    This is called by the activate tool when a skill is activated via Tool Call.
+    """
+    skill_mgr = getattr(ap, 'skill_mgr', None)
+    if skill_mgr is None:
+        return False
+
+    skill_data = skill_mgr.get_skill_by_name(skill_name)
+    if skill_data is None:
+        return False
+
+    skill_loader.register_activated_skill(query, skill_data)
+    return True

src/langbot/pkg/skill/manager.py

@@ -0,0 +1,135 @@
+from __future__ import annotations
+
+import os
+import typing
+
+from ..core import app
+
+if typing.TYPE_CHECKING:
+    pass
+
+
+class SkillManager:
+    """Skill manager backed by Box-managed or local filesystem packages.
+
+    In sandbox deployments, skills are loaded from the Box runtime. Local
+    data/skills remains as the fallback for non-Box development.
+
+    Skills are activated through the `activate` tool (Tool Call mechanism),
+    aligned with Claude Code's design. This protects KV Cache and follows
+    industry standard.
+    """
+
+    ap: app.Application
+    skills: dict[str, dict]
+
+    def __init__(self, ap: app.Application):
+        self.ap = ap
+        self.skills = {}
+
+    async def initialize(self):
+        await self.reload_skills()
+
+    async def reload_skills(self):
+        """Reload all skills from the Box runtime.
+
+        Box is the only source of truth for skills. When Box is unavailable
+        (disabled in config or unreachable) the cache is emptied — there is
+        no local filesystem fallback. Skills whose ``package_root`` is no
+        longer visible on the LangBot-side filesystem are dropped so they
+        don't surface as stale ``extra_mounts``.
+        """
+        self.skills = {}
+
+        box_service = getattr(self.ap, 'box_service', None)
+        if box_service is None or not getattr(box_service, 'available', False):
+            self.ap.logger.info('Box runtime unavailable; skill cache is empty.')
+            return
+
+        try:
+            dropped = 0
+            for skill_data in await box_service.list_skills():
+                skill_name = skill_data.get('name')
+                if not skill_name:
+                    continue
+                package_root = str(skill_data.get('package_root', '') or '').strip()
+                if package_root and not os.path.isdir(package_root):
+                    self.ap.logger.warning(
+                        f'Skill "{skill_name}" reported by Box runtime but '
+                        f'package_root missing on LangBot filesystem '
+                        f'({package_root}); dropping from in-memory cache.'
+                    )
+                    dropped += 1
+                    continue
+                self.skills[skill_name] = skill_data
+            if dropped:
+                self.ap.logger.warning(
+                    f'Loaded {len(self.skills)} skills from Box runtime '
+                    f'({dropped} dropped due to missing package_root).'
+                )
+            else:
+                self.ap.logger.info(f'Loaded {len(self.skills)} skills from Box runtime')
+        except Exception as exc:
+            self.ap.logger.warning(f'Failed to load skills from Box runtime: {exc}')
+
+    def refresh_skill_from_disk(self, skill_name: str) -> bool:
+        """Confirm a single skill is present in the cache.
+
+        With Box as the only source of truth, the actual reload is driven by
+        SkillService callers awaiting ``reload_skills``; this method only
+        reports whether the cache still has the skill.
+        """
+        if not skill_name:
+            return False
+        return skill_name in self.skills
+
+    def get_skill_by_name(self, name: str) -> dict | None:
+        """Get skill data by name."""
+        return self.skills.get(name)
+
+    def get_skill_index(self, bound_skills: list[str] | None = None) -> str:
+        """Render the pipeline-visible skills as a short ``name: description``
+        index suitable for the system prompt.
+
+        ``bound_skills`` follows the same convention as
+        ``query.variables['_pipeline_bound_skills']``: ``None`` means every
+        loaded skill is exposed; an explicit list filters to that subset.
+        Returns an empty string when no skills are visible.
+        """
+        lines: list[str] = []
+        for skill in self.skills.values():
+            name = skill.get('name')
+            if not name:
+                continue
+            if bound_skills is not None and name not in bound_skills:
+                continue
+            display = skill.get('display_name') or name
+            description = (skill.get('description') or '').strip().replace('\n', ' ')
+            lines.append(f'- {name} ({display}): {description}')
+
+        if not lines:
+            return ''
+        return 'Available Skills:\n' + '\n'.join(lines)
+
+    def build_skill_aware_prompt_addition(self, bound_skills: list[str] | None = None) -> str:
+        """Build the system-prompt addendum that makes the LLM aware of the
+        pipeline-visible skills.
+
+        Only metadata (name + description) is injected — the full SKILL.md is
+        loaded later via the ``activate`` Tool Call, protecting KV cache and
+        matching Claude Code's progressive disclosure pattern. Returns an
+        empty string when no skills are visible (no prompt change at all).
+        """
+        skill_index = self.get_skill_index(bound_skills)
+        if not skill_index:
+            return ''
+        return (
+            '\n\n'
+            f'{skill_index}\n\n'
+            "When the user's request clearly matches one or more skills "
+            'based on their descriptions above, call the `activate` tool with '
+            'the skill name to load its full instructions. Only the name and '
+            'description are visible here; the actual instructions arrive as '
+            'the tool result. If no skill is a clear match, respond normally '
+            'without activating any skill.'
+        )

src/langbot/pkg/skill/utils.py

@@ -0,0 +1,37 @@
+"""Shared utilities for skill file parsing."""
+
+import yaml
+
+
+def parse_frontmatter(content: str) -> tuple[dict, str]:
+    """Parse YAML frontmatter from markdown content.
+
+    Expects format:
+        ---
+        name: my-skill
+        description: Does something
+        ---
+        # Actual instructions...
+
+    Returns:
+        Tuple of (metadata dict, remaining content)
+    """
+    if not content.startswith('---'):
+        return {}, content
+
+    parts = content.split('---', 2)
+    if len(parts) < 3:
+        return {}, content
+
+    frontmatter_str = parts[1].strip()
+    instructions = parts[2].strip()
+
+    try:
+        metadata = yaml.safe_load(frontmatter_str) or {}
+    except yaml.YAMLError:
+        metadata = {}
+
+    if not isinstance(metadata, dict):
+        metadata = {}
+
+    return metadata, instructions

src/langbot/pkg/utils/managed_runtime.py

@@ -0,0 +1,88 @@
+"""Base class for connectors that may manage a local runtime subprocess."""
+
+from __future__ import annotations
+
+import asyncio
+import os
+import sys
+from typing import TYPE_CHECKING, Awaitable, Callable
+
+if TYPE_CHECKING:
+    from ..core import app as core_app
+
+
+class ManagedRuntimeConnector:
+    """Base class for connectors that may manage a local runtime subprocess.
+
+    Provides shared lifecycle helpers: subprocess launch, health-check retry,
+    and graceful termination.  Concrete connectors (plugin, box, …) inherit
+    this and add their own protocol-specific logic.
+    """
+
+    ap: 'core_app.Application'
+    runtime_subprocess: asyncio.subprocess.Process | None
+    runtime_subprocess_task: asyncio.Task | None
+
+    def __init__(self, ap: 'core_app.Application'):
+        self.ap = ap
+        self.runtime_subprocess = None
+        self.runtime_subprocess_task = None
+
+    async def _start_runtime_subprocess(self, *args: str) -> None:
+        """Launch a local runtime as a subprocess of the current Python interpreter.
+
+        If a subprocess is already running (no *returncode* yet), this is a no-op.
+        """
+        if self.runtime_subprocess is not None and self.runtime_subprocess.returncode is None:
+            return
+
+        python_path = sys.executable
+        env = os.environ.copy()
+        self.runtime_subprocess = await asyncio.create_subprocess_exec(
+            python_path,
+            *args,
+            env=env,
+        )
+        self.runtime_subprocess_task = asyncio.create_task(self.runtime_subprocess.wait())
+
+    async def _wait_until_ready(
+        self,
+        check: Callable[[], Awaitable[None]],
+        retries: int = 40,
+        interval: float = 0.25,
+        runtime_name: str = 'runtime',
+    ) -> None:
+        """Repeatedly call *check* until it succeeds or retries are exhausted.
+
+        Between attempts the method sleeps for *interval* seconds.  If the
+        managed subprocess exits before readiness is confirmed, a
+        ``RuntimeError`` is raised immediately.
+        """
+        last_exc: Exception | None = None
+        for _ in range(retries):
+            # Fast-fail if the process already died.
+            if self.runtime_subprocess is not None and self.runtime_subprocess.returncode is not None:
+                raise RuntimeError(
+                    f'local {runtime_name} exited before becoming ready (code {self.runtime_subprocess.returncode})'
+                )
+
+            try:
+                await check()
+                return
+            except Exception as exc:
+                last_exc = exc
+                await asyncio.sleep(interval)
+
+        if last_exc is not None:
+            raise last_exc
+        raise RuntimeError(f'local {runtime_name} did not become ready')
+
+    def _dispose_subprocess(self) -> None:
+        """Terminate the managed subprocess and cancel its wait task."""
+        if self.runtime_subprocess is not None and self.runtime_subprocess.returncode is None:
+            self.ap.logger.info('Terminating managed runtime process...')
+            self.runtime_subprocess.terminate()
+
+        if self.runtime_subprocess_task is not None:
+            self.runtime_subprocess_task.cancel()
+            self.runtime_subprocess_task = None

src/langbot/pkg/utils/paths.py

@@ -1,37 +1,70 @@
-"""Utility functions for finding package resources"""
+"""Utility functions for finding package resources and runtime data roots."""
 
 import os
 from pathlib import Path
 
 
 _is_source_install = None
+_source_root = None
+
+
+def _find_source_root() -> Path | None:
+    """Locate the LangBot repository root when running from source."""
+    global _source_root
+
+    if _source_root is not None:
+        return _source_root
+
+    current = Path(__file__).resolve()
+    for parent in current.parents:
+        if (parent / 'pyproject.toml').exists() and (parent / 'main.py').exists():
+            _source_root = parent
+            return parent
+
+    _source_root = None
+    return None
 
 
 def _check_if_source_install() -> bool:
     """
-    Check if we're running from source directory or an installed package.
-    Cached to avoid repeated file I/O.
+    Check if we're running from the LangBot source tree.
+    Cached to avoid repeated filesystem scans.
     """
     global _is_source_install
 
     if _is_source_install is not None:
         return _is_source_install
 
-    # Check if main.py exists in current directory with LangBot marker
-    if os.path.exists('main.py'):
-        try:
-            with open('main.py', 'r', encoding='utf-8') as f:
-                # Only read first 500 chars to check for marker
-                content = f.read(500)
-                if 'LangBot/main.py' in content:
-                    _is_source_install = True
-                    return True
-        except (IOError, OSError, UnicodeDecodeError):
-            # If we can't read the file, assume not a source install
-            pass
+    _is_source_install = _find_source_root() is not None
+    return _is_source_install
 
-    _is_source_install = False
-    return False
+
+def get_data_root() -> str:
+    """
+    Get the runtime data root.
+
+    Priority:
+    1. LANGBOT_DATA_ROOT environment override
+    2. Source checkout root /data when running from source
+    3. Current working directory /data for installed-package usage
+    """
+    env_root = os.environ.get('LANGBOT_DATA_ROOT', '').strip()
+    if env_root:
+        return str(Path(env_root).expanduser().resolve())
+
+    source_root = _find_source_root()
+    if source_root is not None:
+        return str((source_root / 'data').resolve())
+
+    return str((Path.cwd() / 'data').resolve())
+
+
+def get_data_path(*parts: str) -> str:
+    """Join path segments under the resolved data root."""
+    data_root = Path(get_data_root())
+    if not parts:
+        return str(data_root)
+    return str((data_root.joinpath(*parts)).resolve())
 
 
 def get_frontend_path() -> str:
@@ -76,8 +109,11 @@ def get_resource_path(resource: str) -> str:
         Absolute path to the resource
     """
     # First, check if resource exists in current directory (source install)
-    if _check_if_source_install() and os.path.exists(resource):
-        return resource
+    source_root = _find_source_root()
+    if source_root is not None:
+        source_resource = source_root / resource
+        if source_resource.exists():
+            return str(source_resource)
 
     # Second, check current directory anyway
     if os.path.exists(resource):

src/langbot/pkg/utils/platform.py

@@ -16,7 +16,14 @@ def get_platform() -> str:
 
 standalone_runtime = False
 
+standalone_box = False
+
 
 def use_websocket_to_connect_plugin_runtime() -> bool:
     """是否使用 websocket 连接插件运行时"""
     return standalone_runtime
+
+
+def use_websocket_to_connect_box_runtime() -> bool:
+    """Whether to use WebSocket to connect to an external box runtime."""
+    return standalone_box

src/langbot/pkg/utils/version.py

@@ -1,6 +1,5 @@
 from __future__ import annotations
 
-import os
 import typing
 import logging
 
@@ -11,7 +10,7 @@ from . import constants
 
 
 class VersionManager:
-    """版本管理器"""
+    """Version manager"""
 
     ap: app.Application
 
@@ -22,190 +21,68 @@ class VersionManager:
         pass
 
     def get_current_version(self) -> str:
-        current_tag = constants.semantic_version
-
-        return current_tag
+        return constants.semantic_version
 
     async def get_release_list(self) -> list:
-        """获取发行列表"""
+        """Fetch release list from Space API (cached GitHub releases)."""
         try:
             rls_list_resp = requests.get(
-                url='https://api.github.com/repos/langbot-app/LangBot/releases',
+                url='https://space.langbot.app/api/v1/dist/info/releases',
                 proxies=self.ap.proxy_mgr.get_forward_proxies(),
-                timeout=5,
+                timeout=10,
             )
-            rls_list_resp.raise_for_status()  # 检查请求是否成功
-            rls_list = rls_list_resp.json()
-            return rls_list
+            rls_list_resp.raise_for_status()
+            resp_json = rls_list_resp.json()
+            if resp_json.get('code') == 0 and isinstance(resp_json.get('data'), list):
+                return resp_json['data']
+            self.ap.logger.warning(f'Failed to fetch release list: unexpected response: {resp_json.get("msg", "")}')
+            return []
         except Exception as e:
-            self.ap.logger.warning(f'获取发行列表失败: {e}')
-            pass
+            self.ap.logger.warning(f'Failed to fetch release list: {e}')
         return []
 
-    async def update_all(self):
-        """检查更新并下载源码"""
-
-        current_tag = self.get_current_version()
-
-        rls_list = await self.get_release_list()
-
-        latest_rls = {}
-        rls_notes = []
-        latest_tag_name = ''
-        for rls in rls_list:
-            rls_notes.append(rls['name'])  # 使用发行名称作为note
-            if latest_tag_name == '':
-                latest_tag_name = rls['tag_name']
-
-            if rls['tag_name'] == current_tag:
-                break
-
-            if latest_rls == {}:
-                latest_rls = rls
-        self.ap.logger.info('更新日志: {}'.format(rls_notes))
-
-        if latest_rls == {} and not self.is_newer(latest_tag_name, current_tag):  # 没有新版本
-            return False
-
-        # 下载最新版本的zip到temp目录
-        self.ap.logger.info('开始下载最新版本: {}'.format(latest_rls['zipball_url']))
-
-        zip_url = latest_rls['zipball_url']
-        zip_resp = requests.get(url=zip_url, proxies=self.ap.proxy_mgr.get_forward_proxies())
-        zip_data = zip_resp.content
-
-        # 检查temp/updater目录
-        if not os.path.exists('temp'):
-            os.mkdir('temp')
-        if not os.path.exists('temp/updater'):
-            os.mkdir('temp/updater')
-        with open('temp/updater/{}.zip'.format(latest_rls['tag_name']), 'wb') as f:
-            f.write(zip_data)
-
-        self.ap.logger.info('下载最新版本完成: {}'.format('temp/updater/{}.zip'.format(latest_rls['tag_name'])))
-
-        # 解压zip到temp/updater/<tag_name>/
-        import zipfile
-
-        # 检查目标文件夹
-        if os.path.exists('temp/updater/{}'.format(latest_rls['tag_name'])):
-            import shutil
-
-            shutil.rmtree('temp/updater/{}'.format(latest_rls['tag_name']))
-        os.mkdir('temp/updater/{}'.format(latest_rls['tag_name']))
-        with zipfile.ZipFile('temp/updater/{}.zip'.format(latest_rls['tag_name']), 'r') as zip_ref:
-            zip_ref.extractall('temp/updater/{}'.format(latest_rls['tag_name']))
-
-        # 覆盖源码
-        source_root = ''
-        # 找到temp/updater/<tag_name>/中的第一个子目录路径
-        for root, dirs, files in os.walk('temp/updater/{}'.format(latest_rls['tag_name'])):
-            if root != 'temp/updater/{}'.format(latest_rls['tag_name']):
-                source_root = root
-                break
-
-        # 覆盖源码
-        import shutil
-
-        for root, dirs, files in os.walk(source_root):
-            # 覆盖所有子文件子目录
-            for file in files:
-                src = os.path.join(root, file)
-                dst = src.replace(source_root, '.')
-                if os.path.exists(dst):
-                    os.remove(dst)
-
-                # 检查目标文件夹是否存在
-                if not os.path.exists(os.path.dirname(dst)):
-                    os.makedirs(os.path.dirname(dst))
-                # 检查目标文件是否存在
-                if not os.path.exists(dst):
-                    # 创建目标文件
-                    open(dst, 'w').close()
-
-                shutil.copy(src, dst)
-
-        # 把current_tag写入文件
-        current_tag = latest_rls['tag_name']
-        with open('current_tag', 'w') as f:
-            f.write(current_tag)
-
-        # TODO statistics
-
     async def is_new_version_available(self) -> bool:
-        """检查是否有新版本"""
-        # 从github获取release列表
+        """Check whether a newer version is available."""
         rls_list = await self.get_release_list()
-        if rls_list is None:
+        if not rls_list:
             return False
 
-        # 获取当前版本
         current_tag = self.get_current_version()
 
-        # 检查是否有新版本
         latest_tag_name = ''
         for rls in rls_list:
-            if latest_tag_name == '':
-                latest_tag_name = rls['tag_name']
-                break
+            latest_tag_name = rls.get('tag_name', '')
+            break
 
-        return self.is_newer(latest_tag_name, current_tag)
+        return self._is_newer(latest_tag_name, current_tag)
 
-    def is_newer(self, new_tag: str, old_tag: str):
-        """判断版本是否更新，忽略第四位版本和第一位版本"""
-        if new_tag == old_tag:
+    def _is_newer(self, new_tag: str, old_tag: str) -> bool:
+        """Check if new_tag is a newer version than old_tag.
+
+        Compares the first three segments (major.minor.patch) only.
+        Returns False if the major version differs (breaking change boundary).
+        """
+        if not new_tag or not old_tag or new_tag == old_tag:
             return False
 
-        new_tag = new_tag.split('.')
-        old_tag = old_tag.split('.')
+        new_parts = new_tag.split('.')
+        old_parts = old_tag.split('.')
 
-        # 判断主版本是否相同
-        if new_tag[0] != old_tag[0]:
+        # Different major version — not considered an upgrade
+        if new_parts[0] != old_parts[0]:
             return False
 
-        if len(new_tag) < 4:
+        if len(new_parts) < 4:
             return True
 
-        # 合成前三段，判断是否相同
-        new_tag = '.'.join(new_tag[:3])
-        old_tag = '.'.join(old_tag[:3])
-
-        return new_tag != old_tag
-
-    def compare_version_str(v0: str, v1: str) -> int:
-        """比较两个版本号"""
-
-        # 删除版本号前的v
-        if v0.startswith('v'):
-            v0 = v0[1:]
-        if v1.startswith('v'):
-            v1 = v1[1:]
-
-        v0: list = v0.split('.')
-        v1: list = v1.split('.')
-
-        # 如果两个版本号节数不同，把短的后面用0补齐
-        if len(v0) < len(v1):
-            v0.extend(['0'] * (len(v1) - len(v0)))
-        elif len(v0) > len(v1):
-            v1.extend(['0'] * (len(v0) - len(v1)))
-
-        # 从高位向低位比较
-        for i in range(len(v0)):
-            if int(v0[i]) > int(v1[i]):
-                return 1
-            elif int(v0[i]) < int(v1[i]):
-                return -1
-
-        return 0
+        return '.'.join(new_parts[:3]) != '.'.join(old_parts[:3])
 
     async def show_version_update(self) -> typing.Tuple[str, int]:
         try:
-            if await self.ap.ver_mgr.is_new_version_available():
+            if await self.is_new_version_available():
                 return (
-                    'New version available:\n有新版本可用，根据文档更新: \nhttps://link.langbot.app/zh/docs/update',
+                    'New version available. Update guide: https://link.langbot.app/en/docs/update',
                     logging.INFO,
                 )
-
         except Exception as e:
             return f'Error checking version update: {e}', logging.WARNING

src/langbot/templates/config.yaml

@@ -104,6 +104,31 @@ monitoring:
         check_interval_hours: 1
         # Number of expired rows to delete per table batch
         delete_batch_size: 1000
+box:
+    # Master switch for the Box sandbox runtime. When false, LangBot does NOT
+    # attempt to connect to a remote Box runtime nor start a local stdio Box
+    # subprocess. Disabling Box also disables every feature that depends on it:
+    # the native sandbox tools (exec/read/write/edit/glob/grep), the activate
+    # 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'. 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:
+        profile: 'default'
+        image: ''  # Custom local sandbox image. Leave empty to use the profile default.
+        host_root: './data/box'  # Base host directory for local workspace mounts. Docker deployments should override this with an absolute host path.
+        default_workspace: ''  # Defaults to '<host_root>/default'. Relative paths are resolved under host_root.
+        skills_root: 'skills'  # Box-owned skill package directory. Relative paths are resolved under host_root.
+        allowed_mount_roots:  # Defaults to ['<host_root>'] when left empty.
+            - './data/box'
+            - '/tmp'
+        workspace_quota_mb: null  # Optional disk quota override (>= 0). null = profile default.
+    e2b:
+        api_key: ''  # Can also be set via E2B_API_KEY env var.
+        api_url: ''  # Custom API URL for self-hosted deployments.
+        template: ''  # Default template ID (e.g. 'base', 'python-3.11').
 space:
     # Space service URL for OAuth and API
     url: 'https://space.langbot.app'

src/langbot/templates/default-pipeline-config.json

@@ -50,10 +50,11 @@
             "prompt": [
                 {
                     "role": "system",
-                    "content": "You are a helpful assistant."
+                    "content": "You are a helpful assistant. When tools are available, use them for exact calculations, data processing, and code execution instead of guessing. Unless the user explicitly asks for code or a script, return the result directly instead of printing the generated code."
                 }
             ],
             "knowledge-bases": [],
+            "box-session-id-template": "{launcher_type}_{launcher_id}",
             "rerank-model": "",
             "rerank-top-k": 5
         },

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

@@ -124,6 +124,99 @@ stages:
           field: __system.is_wizard
           operator: neq
           value: true
+      - name: box-session-id-template
+        label:
+          en_US: Sandbox Scope
+          zh_Hans: 沙箱作用域
+          zh_Hant: 沙箱作用域
+          ja_JP: サンドボックススコープ
+          vi_VN: Phạm vi Sandbox
+          th_TH: ขอบเขต Sandbox
+          es_ES: Alcance del Sandbox
+          ru_RU: Область песочницы
+        description:
+          en_US: Determines how sandbox environments are shared across messages.
+          zh_Hans: 决定沙箱环境在不同消息间的共享方式。
+          zh_Hant: 決定沙箱環境在不同訊息間的共享方式。
+          ja_JP: メッセージ間でサンドボックス環境を共有する方法を決定します。
+          vi_VN: Xác định cách chia sẻ môi trường sandbox giữa các tin nhắn.
+          th_TH: กำหนดวิธีแชร์สภาพแวดล้อม Sandbox ระหว่างข้อความ
+          es_ES: Determina cómo se comparten los entornos sandbox entre mensajes.
+          ru_RU: Определяет, как песочницы используются совместно между сообщениями.
+        disable_if:
+          field: __system.box_available
+          operator: eq
+          value: false
+        disabled_tooltip:
+          en_US: >-
+            Box sandbox is disabled or unavailable. Enable it in config.yaml
+            (box.enabled = true) and ensure the runtime is reachable to change
+            this setting.
+          zh_Hans: Box 沙箱已禁用或不可用。请在配置中启用（box.enabled = true）并确认运行时连接正常，才能修改此项。
+          zh_Hant: Box 沙箱已停用或無法使用。請在設定中啟用（box.enabled = true）並確認執行時連線正常，才能修改此項。
+          ja_JP: Box サンドボックスが無効または利用できません。設定で有効化（box.enabled = true）し、ランタイムが接続できることを確認してから変更してください。
+          vi_VN: Sandbox Box đã tắt hoặc không khả dụng. Hãy bật trong cấu hình (box.enabled = true) và đảm bảo runtime hoạt động để chỉnh sửa.
+          th_TH: Sandbox Box ถูกปิดใช้งานหรือไม่พร้อมใช้งาน กรุณาเปิดใช้งานในการตั้งค่า (box.enabled = true) และตรวจสอบว่ารันไทม์เชื่อมต่อปกติก่อนปรับค่า
+          es_ES: El sandbox de Box está desactivado o no disponible. Actívelo en la configuración (box.enabled = true) y asegúrese de que el runtime esté conectado para modificar este ajuste.
+          ru_RU: Песочница Box отключена или недоступна. Включите её в конфигурации (box.enabled = true) и убедитесь, что среда выполнения работает, чтобы изменить эту настройку.
+        type: select
+        required: false
+        default: "{launcher_type}_{launcher_id}"
+        options:
+          - name: "{global}"
+            label:
+              en_US: Global (shared by all)
+              zh_Hans: 全局（所有人共享）
+              zh_Hant: 全域（所有人共用）
+              ja_JP: グローバル（全員共有）
+              vi_VN: Toàn cục (chia sẻ cho tất cả)
+              th_TH: ทั่วไป (แชร์ทั้งหมด)
+              es_ES: Global (compartido por todos)
+              ru_RU: Глобальный (общий для всех)
+          - name: "{launcher_type}_{launcher_id}"
+            label:
+              en_US: Per chat (Recommended)
+              zh_Hans: 每个会话（推荐）
+              zh_Hant: 每個會話（推薦）
+              ja_JP: チャットごと（推奨）
+              vi_VN: Mỗi cuộc trò chuyện (Khuyến nghị)
+              th_TH: ต่อแชท (แนะนำ)
+              es_ES: Por chat (Recomendado)
+              ru_RU: По чату (Рекомендуется)
+          - name: "{launcher_type}_{launcher_id}_{sender_id}"
+            label:
+              en_US: Per user in chat
+              zh_Hans: 会话中每个用户
+              zh_Hant: 會話中每個用戶
+              ja_JP: チャット内のユーザーごと
+              vi_VN: Mỗi người dùng trong cuộc trò chuyện
+              th_TH: ต่อผู้ใช้ในแชท
+              es_ES: Por usuario en chat
+              ru_RU: По пользователю в чате
+          - name: "{launcher_type}_{launcher_id}_{conversation_id}"
+            label:
+              en_US: Per conversation context
+              zh_Hans: 每个对话上下文
+              zh_Hant: 每個對話上下文
+              ja_JP: 会話コンテキストごと
+              vi_VN: Mỗi ngữ cảnh hội thoại
+              th_TH: ต่อบริบทการสนทนา
+              es_ES: Por contexto de conversación
+              ru_RU: По контексту разговора
+          - name: "{query_id}"
+            label:
+              en_US: Per message (isolated)
+              zh_Hans: 每条消息（完全隔离）
+              zh_Hant: 每條訊息（完全隔離）
+              ja_JP: メッセージごと（隔離）
+              vi_VN: Mỗi tin nhắn (cách ly)
+              th_TH: ต่อข้อความ (แยกส่วน)
+              es_ES: Por mensaje (aislado)
+              ru_RU: По сообщению (изолированно)
+        show_if:
+          field: __system.is_wizard
+          operator: neq
+          value: true
       - name: rerank-model
         label:
           en_US: Rerank Model

test-embed.html

@@ -0,0 +1,21 @@
+<!DOCTYPE html>
+<html lang="zh">
+<head>
+  <meta charset="UTF-8">
+  <title>LangBot Embed Widget Test</title>
+  <style>
+    body { font-family: sans-serif; padding: 40px; background: #f5f5f5; }
+    h1 { margin-bottom: 10px; }
+    p { color: #666; }
+    code { background: #e0e0e0; padding: 2px 6px; border-radius: 3px; }
+  </style>
+</head>
+<body>
+  <h1>LangBot Embed Widget Test Page</h1>
+  <p>If the widget loaded correctly, you should see a blue chat bubble in the bottom-right corner.</p>
+  <p>Replace the <code>BOT_UUID</code> below with your actual bot UUID.</p>
+
+  <!-- Replace BOT_UUID with your real bot UUID -->
+<script data-title="LangBot" src="http://localhost:5300/api/v1/embed/a0ab80e7-742a-445f-bd0e-7d9758f1cfa7/widget.js"></script>
+</body>
+</html>

tests/factories/app.py

@@ -15,7 +15,7 @@ class FakeApp:
     def __init__(
         self,
         *,
-        command_prefix: list[str] = ["/", "!"],
+        command_prefix: list[str] = ['/', '!'],
         command_enable: bool = True,
         pipeline_concurrency: int = 10,
         admins: list[str] | None = None,
@@ -40,6 +40,8 @@ class FakeApp:
         self.telemetry = self._create_mock_telemetry()
         self.survey = None
         self.cmd_mgr = self._create_mock_cmd_mgr()
+        self.skill_mgr = self._create_mock_skill_mgr()
+        self.pipeline_service = self._create_mock_pipeline_service()
 
         # Apply any extra attributes for specific test scenarios
         for name, value in extra_attrs.items():
@@ -98,9 +100,9 @@ class FakeApp:
     ):
         instance_config = Mock()
         instance_config.data = {
-            "command": {"prefix": command_prefix, "enable": command_enable},
-            "concurrency": {"pipeline": pipeline_concurrency},
-            "admins": admins,
+            'command': {'prefix': command_prefix, 'enable': command_enable},
+            'concurrency': {'pipeline': pipeline_concurrency},
+            'admins': admins,
         }
         return instance_config
 
@@ -119,6 +121,20 @@ class FakeApp:
         cmd_mgr.execute = AsyncMock()
         return cmd_mgr
 
+    def _create_mock_skill_mgr(self):
+        """Mock SkillManager that returns no skill index addition by default."""
+        skill_mgr = Mock()
+        skill_mgr.skills = {}
+        skill_mgr.build_skill_aware_prompt_addition = Mock(return_value='')
+        skill_mgr.get_skill_index = Mock(return_value=[])
+        return skill_mgr
+
+    def _create_mock_pipeline_service(self):
+        """Mock PipelineService.get_pipeline returning empty extensions prefs."""
+        pipeline_service = AsyncMock()
+        pipeline_service.get_pipeline = AsyncMock(return_value={'extensions_preferences': {}})
+        return pipeline_service
+
     def capture_message(self, message):
         """Capture an outbound message for test assertions."""
         self._outbound_messages.append(message)
@@ -134,4 +150,4 @@ class FakeApp:
 
 def fake_app(**kwargs) -> FakeApp:
     """Create a FakeApp instance with optional overrides."""
-    return FakeApp(**kwargs)
+    return FakeApp(**kwargs)

tests/integration/api/test_pipelines.py

@@ -20,6 +20,7 @@ pytestmark = pytest.mark.integration
 
 # ============== FIXTURE FOR SYS.MODULES ISOLATION ==============
 
+
 @pytest.fixture(scope='module')
 def mock_circular_import_chain():
     """Break circular import chain for API controller."""
@@ -53,21 +54,25 @@ def mock_circular_import_chain():
     ):
         # Import groups after mocking to populate preregistered_groups
         import langbot.pkg.api.http.controller.groups.pipelines.pipelines as _pipelines  # noqa: E402, F401
+
         yield
 
 
 # ============== FAKE APPLICATION WITH PIPELINE SERVICES ==============
 
+
 @pytest.fixture(scope='module')
 def fake_pipeline_app():
     """Create FakeApp with pipeline-specific services (module scope for reuse)."""
     app = FakeApp()
 
     # Pipeline config
-    app.instance_config.data.update({
-        'api': {'port': 5300},
-        'system': {'allow_modify_login_info': True, 'limitation': {}},
-    })
+    app.instance_config.data.update(
+        {
+            'api': {'port': 5300},
+            'system': {'allow_modify_login_info': True, 'limitation': {}},
+        }
+    )
 
     # Auth services
     app.user_service = Mock()
@@ -79,25 +84,31 @@ def fake_pipeline_app():
 
     # Pipeline service
     app.pipeline_service = Mock()
-    app.pipeline_service.get_pipeline_metadata = AsyncMock(return_value=[
-        {'name': 'trigger', 'stages': []},
-        {'name': 'ai', 'stages': []},
-    ])
-    app.pipeline_service.get_pipelines = AsyncMock(return_value=[
-        {
+    app.pipeline_service.get_pipeline_metadata = AsyncMock(
+        return_value=[
+            {'name': 'trigger', 'stages': []},
+            {'name': 'ai', 'stages': []},
+        ]
+    )
+    app.pipeline_service.get_pipelines = AsyncMock(
+        return_value=[
+            {
+                'uuid': 'test-pipeline-uuid',
+                'name': 'Test Pipeline',
+                'description': 'Test description',
+                'created_at': '2024-01-01T00:00:00',
+                'updated_at': '2024-01-01T00:00:00',
+                'is_default': False,
+            }
+        ]
+    )
+    app.pipeline_service.get_pipeline = AsyncMock(
+        return_value={
             'uuid': 'test-pipeline-uuid',
             'name': 'Test Pipeline',
-            'description': 'Test description',
-            'created_at': '2024-01-01T00:00:00',
-            'updated_at': '2024-01-01T00:00:00',
-            'is_default': False,
+            'config': {},
         }
-    ])
-    app.pipeline_service.get_pipeline = AsyncMock(return_value={
-        'uuid': 'test-pipeline-uuid',
-        'name': 'Test Pipeline',
-        'config': {},
-    })
+    )
     app.pipeline_service.create_pipeline = AsyncMock(return_value={'uuid': 'new-pipeline-uuid'})
     app.pipeline_service.update_pipeline = AsyncMock(return_value={})
     app.pipeline_service.delete_pipeline = AsyncMock()
@@ -112,6 +123,10 @@ def fake_pipeline_app():
     app.mcp_service = Mock()
     app.mcp_service.get_mcp_servers = AsyncMock(return_value=[])
 
+    # Skill service (for extensions endpoint)
+    app.skill_service = Mock()
+    app.skill_service.list_skills = AsyncMock(return_value=[])
+
     # Plugin connector (for extensions endpoint)
     app.plugin_connector.list_plugins = AsyncMock(return_value=[])
 
@@ -130,6 +145,7 @@ async def quart_test_client(fake_pipeline_app, http_controller_cls):
 
 # ============== PIPELINE ENDPOINT TESTS ==============
 
+
 @pytest.mark.usefixtures('mock_circular_import_chain')
 class TestPipelineMetadataEndpoint:
     """Tests for /api/v1/pipelines/_/metadata endpoint."""
@@ -138,8 +154,7 @@ class TestPipelineMetadataEndpoint:
     async def test_get_pipeline_metadata_success(self, quart_test_client):
         """GET /api/v1/pipelines/_/metadata returns metadata list."""
         response = await quart_test_client.get(
-            '/api/v1/pipelines/_/metadata',
-            headers={'Authorization': 'Bearer test_token'}
+            '/api/v1/pipelines/_/metadata', headers={'Authorization': 'Bearer test_token'}
         )
 
         assert response.status_code == 200
@@ -162,10 +177,7 @@ class TestPipelinesListEndpoint:
     @pytest.mark.asyncio
     async def test_get_pipelines_success(self, quart_test_client):
         """GET /api/v1/pipelines returns pipeline list."""
-        response = await quart_test_client.get(
-            '/api/v1/pipelines',
-            headers={'Authorization': 'Bearer test_token'}
-        )
+        response = await quart_test_client.get('/api/v1/pipelines', headers={'Authorization': 'Bearer test_token'})
 
         assert response.status_code == 200
         data = await response.get_json()
@@ -176,8 +188,7 @@ class TestPipelinesListEndpoint:
     async def test_get_pipelines_with_sort_param(self, quart_test_client):
         """GET pipelines with sort parameter."""
         response = await quart_test_client.get(
-            '/api/v1/pipelines?sort_by=created_at&sort_order=DESC',
-            headers={'Authorization': 'Bearer test_token'}
+            '/api/v1/pipelines?sort_by=created_at&sort_order=DESC', headers={'Authorization': 'Bearer test_token'}
         )
 
         assert response.status_code == 200
@@ -193,8 +204,7 @@ class TestPipelinesCRUDEndpoints:
     async def test_get_single_pipeline_success(self, quart_test_client):
         """GET /api/v1/pipelines/{uuid} returns pipeline."""
         response = await quart_test_client.get(
-            '/api/v1/pipelines/test-pipeline-uuid',
-            headers={'Authorization': 'Bearer test_token'}
+            '/api/v1/pipelines/test-pipeline-uuid', headers={'Authorization': 'Bearer test_token'}
         )
 
         assert response.status_code == 200
@@ -208,7 +218,7 @@ class TestPipelinesCRUDEndpoints:
         response = await quart_test_client.post(
             '/api/v1/pipelines',
             headers={'Authorization': 'Bearer test_token'},
-            json={'name': 'New Pipeline', 'config': {}}
+            json={'name': 'New Pipeline', 'config': {}},
         )
 
         assert response.status_code == 200
@@ -222,7 +232,7 @@ class TestPipelinesCRUDEndpoints:
         response = await quart_test_client.put(
             '/api/v1/pipelines/test-pipeline-uuid',
             headers={'Authorization': 'Bearer test_token'},
-            json={'name': 'Updated Pipeline'}
+            json={'name': 'Updated Pipeline'},
         )
 
         assert response.status_code == 200
@@ -233,8 +243,7 @@ class TestPipelinesCRUDEndpoints:
     async def test_delete_pipeline_success(self, quart_test_client):
         """DELETE /api/v1/pipelines/{uuid} deletes pipeline."""
         response = await quart_test_client.delete(
-            '/api/v1/pipelines/test-pipeline-uuid',
-            headers={'Authorization': 'Bearer test_token'}
+            '/api/v1/pipelines/test-pipeline-uuid', headers={'Authorization': 'Bearer test_token'}
         )
 
         assert response.status_code == 200
@@ -245,8 +254,7 @@ class TestPipelinesCRUDEndpoints:
     async def test_copy_pipeline_success(self, quart_test_client):
         """POST /api/v1/pipelines/{uuid}/copy copies pipeline."""
         response = await quart_test_client.post(
-            '/api/v1/pipelines/test-pipeline-uuid/copy',
-            headers={'Authorization': 'Bearer test_token'}
+            '/api/v1/pipelines/test-pipeline-uuid/copy', headers={'Authorization': 'Bearer test_token'}
         )
 
         assert response.status_code == 200
@@ -263,8 +271,7 @@ class TestPipelineExtensionsEndpoint:
     async def test_get_extensions(self, quart_test_client):
         """GET /api/v1/pipelines/{uuid}/extensions."""
         response = await quart_test_client.get(
-            '/api/v1/pipelines/test-pipeline-uuid/extensions',
-            headers={'Authorization': 'Bearer test_token'}
+            '/api/v1/pipelines/test-pipeline-uuid/extensions', headers={'Authorization': 'Bearer test_token'}
         )
 
         # Should return 200 if pipeline found

tests/integration_tests/box/test_box_integration.py

@@ -0,0 +1,329 @@
+"""Integration tests for LangBot Box.
+
+These tests verify the end-to-end behavior of the Box sandbox execution
+system.  Tests decorated with ``requires_container`` need a real container
+runtime (Podman or Docker) and are skipped otherwise.
+
+CI only runs ``tests/unit_tests/``, so these tests never execute in the
+CI pipeline.  Run them locally with::
+
+    pytest tests/integration_tests/ -v
+"""
+
+from __future__ import annotations
+
+import asyncio
+import logging
+import shutil
+import socket
+import subprocess
+from types import SimpleNamespace
+
+import pytest
+
+from langbot.pkg.box.service import BoxService
+from langbot_plugin.box.backend import BaseSandboxBackend
+from langbot_plugin.box.client import ActionRPCBoxClient
+from langbot_plugin.box.errors import BoxBackendUnavailableError
+from langbot_plugin.box.models import BoxExecutionStatus, BoxNetworkMode, BoxSpec
+from langbot_plugin.box.runtime import BoxRuntime
+from langbot_plugin.box.server import BoxServerHandler
+
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+
+_logger = logging.getLogger('test.box.integration')
+
+# Default image for integration tests — small and fast to pull.
+_TEST_IMAGE = 'alpine:latest'
+
+
+# ── Skip helpers ──────────────────────────────────────────────────────
+
+
+def _has_container_runtime() -> bool:
+    for cmd in ('podman', 'docker'):
+        if shutil.which(cmd) is None:
+            continue
+        try:
+            result = subprocess.run(
+                [cmd, 'info'],
+                capture_output=True,
+                timeout=10,
+            )
+            if result.returncode == 0:
+                return True
+        except Exception:
+            continue
+    return False
+
+
+def _can_open_test_socket() -> bool:
+    try:
+        sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+    except OSError:
+        return False
+    sock.close()
+    return True
+
+
+requires_container = pytest.mark.skipif(
+    not _has_container_runtime(),
+    reason='no container runtime (podman/docker) available',
+)
+
+requires_socket = pytest.mark.skipif(
+    not _can_open_test_socket(),
+    reason='local test environment does not permit opening TCP sockets',
+)
+
+
+# ── Helpers ──────────────────────────────────────────────────────────
+
+
+class _QueueConnection:
+    """In-process Connection backed by asyncio Queues — no real IO."""
+
+    def __init__(self, rx: asyncio.Queue[str], tx: asyncio.Queue[str]):
+        self._rx = rx
+        self._tx = tx
+
+    async def send(self, message: str) -> None:
+        await self._tx.put(message)
+
+    async def receive(self) -> str:
+        return await self._rx.get()
+
+    async def close(self) -> None:
+        pass
+
+
+async def _make_rpc_pair(runtime: BoxRuntime):
+    """Create an in-process (ActionRPCBoxClient, server_task, client_task) connected via queues."""
+    from langbot_plugin.runtime.io.handler import Handler
+
+    c2s: asyncio.Queue[str] = asyncio.Queue()
+    s2c: asyncio.Queue[str] = asyncio.Queue()
+    client_conn = _QueueConnection(rx=s2c, tx=c2s)
+    server_conn = _QueueConnection(rx=c2s, tx=s2c)
+
+    server_handler = BoxServerHandler(server_conn, runtime)
+    server_task = asyncio.create_task(server_handler.run())
+
+    client_handler = Handler.__new__(Handler)
+    Handler.__init__(client_handler, client_conn)
+    client_task = asyncio.create_task(client_handler.run())
+
+    client = ActionRPCBoxClient(logger=_logger)
+    client.set_handler(client_handler)
+
+    return client, server_task, client_task
+
+
+# ── Fixtures ──────────────────────────────────────────────────────────
+
+
+@pytest.fixture
+async def box_client():
+    """Yield an ActionRPCBoxClient backed by a real BoxRuntime via in-process RPC."""
+    runtime = BoxRuntime(logger=_logger)
+    await runtime.initialize()
+    client, server_task, client_task = await _make_rpc_pair(runtime)
+    yield client
+    server_task.cancel()
+    client_task.cancel()
+    await runtime.shutdown()
+
+
+# ── 1. Simple command execution ───────────────────────────────────────
+
+
+@requires_container
+@requires_socket
+@pytest.mark.asyncio
+async def test_exec_simple_command(box_client: ActionRPCBoxClient):
+    """Box starts a simple command and returns stdout."""
+    spec = BoxSpec(
+        cmd='echo hello-box',
+        session_id='int-simple',
+        workdir='/tmp',
+        image=_TEST_IMAGE,
+    )
+    result = await box_client.execute(spec)
+
+    assert result.status == BoxExecutionStatus.COMPLETED
+    assert result.exit_code == 0
+    assert 'hello-box' in result.stdout
+
+
+# ── 2. Session file persistence ───────────────────────────────────────
+
+
+@requires_container
+@requires_socket
+@pytest.mark.asyncio
+async def test_session_persists_files(box_client: ActionRPCBoxClient):
+    """Write a file in one exec, read it back in a second exec on the same session."""
+    sid = 'int-persist'
+
+    write_result = await box_client.execute(
+        BoxSpec(
+            cmd='echo "hello from file" > /tmp/testfile.txt',
+            session_id=sid,
+            workdir='/tmp',
+            image=_TEST_IMAGE,
+        )
+    )
+    assert write_result.exit_code == 0
+
+    read_result = await box_client.execute(
+        BoxSpec(
+            cmd='cat /tmp/testfile.txt',
+            session_id=sid,
+            workdir='/tmp',
+            image=_TEST_IMAGE,
+        )
+    )
+    assert read_result.exit_code == 0
+    assert 'hello from file' in read_result.stdout
+
+
+# ── 3. Timeout handling ───────────────────────────────────────────────
+
+
+@requires_container
+@requires_socket
+@pytest.mark.asyncio
+async def test_timeout_kills_command(box_client: ActionRPCBoxClient):
+    """A long-running command is killed after timeout_sec."""
+    session_id = 'int-timeout'
+    spec = BoxSpec(
+        cmd='sleep 120',
+        session_id=session_id,
+        workdir='/tmp',
+        timeout_sec=3,
+        image=_TEST_IMAGE,
+    )
+    result = await box_client.execute(spec)
+
+    assert result.status == BoxExecutionStatus.TIMED_OUT
+    assert result.exit_code is None
+
+    sessions = await box_client.get_sessions()
+    assert all(session['session_id'] != session_id for session in sessions)
+
+
+# ── 4. Network isolation ─────────────────────────────────────────────
+
+
+@requires_container
+@requires_socket
+@pytest.mark.asyncio
+async def test_offline_cannot_reach_network(box_client: ActionRPCBoxClient):
+    """With network=OFF the sandbox cannot reach the internet."""
+    spec = BoxSpec(
+        cmd='wget -q -O /dev/null --timeout=3 http://1.1.1.1 2>&1; exit $?',
+        session_id='int-offline',
+        workdir='/tmp',
+        network=BoxNetworkMode.OFF,
+        image=_TEST_IMAGE,
+    )
+    result = await box_client.execute(spec)
+
+    assert result.exit_code != 0
+
+
+# ── 5. Backend unavailable ───────────────────────────────────────────
+
+
+class _UnavailableBackend(BaseSandboxBackend):
+    """A backend that always reports itself as unavailable."""
+
+    name = 'unavailable'
+
+    def __init__(self):
+        super().__init__(logging.getLogger('test'))
+
+    async def is_available(self) -> bool:
+        return False
+
+    async def start_session(self, spec):
+        raise NotImplementedError
+
+    async def exec(self, session, spec):
+        raise NotImplementedError
+
+    async def stop_session(self, session):
+        pass
+
+
+@requires_socket
+@pytest.mark.asyncio
+async def test_backend_unavailable_returns_error():
+    """When no backend is available the full RPC path returns BoxBackendUnavailableError."""
+    runtime = BoxRuntime(logger=_logger, backends=[_UnavailableBackend()])
+    await runtime.initialize()
+    client, server_task, client_task = await _make_rpc_pair(runtime)
+    try:
+        spec = BoxSpec(
+            cmd='echo hello',
+            session_id='int-no-backend',
+            workdir='/tmp',
+        )
+        with pytest.raises(BoxBackendUnavailableError):
+            await client.execute(spec)
+    finally:
+        server_task.cancel()
+        client_task.cancel()
+        await runtime.shutdown()
+
+
+# ── 6. Full service-to-runtime path ──────────────────────────────────
+
+
+@requires_container
+@requires_socket
+@pytest.mark.asyncio
+async def test_full_service_to_remote_runtime(tmp_path):
+    """BoxService -> ActionRPCBoxClient -> RPC -> BoxRuntime -> real backend."""
+    runtime = BoxRuntime(logger=_logger)
+    await runtime.initialize()
+    client, server_task, client_task = await _make_rpc_pair(runtime)
+    try:
+        host_dir = tmp_path / 'workspace'
+        host_dir.mkdir()
+
+        mock_ap = SimpleNamespace(
+            logger=_logger,
+            instance_config=SimpleNamespace(
+                data={
+                    'box': {
+                        'backend': 'local',
+                        'runtime': {'endpoint': ''},
+                        'local': {
+                            'profile': 'default',
+                            'allowed_mount_roots': [str(tmp_path)],
+                            'default_workspace': str(host_dir),
+                        },
+                        'e2b': {'api_key': '', 'api_url': '', 'template': ''},
+                    }
+                }
+            ),
+        )
+
+        service = BoxService(mock_ap, client=client)
+        await service.initialize()
+
+        query = pipeline_query.Query.model_construct(query_id=42)
+        result = await service.execute_tool(
+            {'command': 'echo service-path'},
+            query,
+        )
+
+        assert result['ok'] is True
+        assert result['status'] == 'completed'
+        assert 'service-path' in result['stdout']
+        assert result['session_id'] == 'query_42'
+    finally:
+        server_task.cancel()
+        client_task.cancel()
+        await runtime.shutdown()

tests/integration_tests/box/test_box_mcp_integration.py

@@ -0,0 +1,368 @@
+"""Integration tests for Box MCP-related features.
+
+These tests verify managed process lifecycle, WebSocket stdio attach,
+session cleanup, and the single-session query API using a real container
+runtime.
+
+CI only runs ``tests/unit_tests/``, so these tests never execute in the
+CI pipeline.  Run them locally with::
+
+    pytest tests/integration_tests/box/test_box_mcp_integration.py -v
+"""
+
+from __future__ import annotations
+
+import asyncio
+import logging
+import shutil
+import socket
+import subprocess
+
+import aiohttp
+import pytest
+from aiohttp.test_utils import TestServer
+
+from langbot_plugin.box.client import ActionRPCBoxClient
+from langbot_plugin.box.errors import BoxManagedProcessNotFoundError, BoxSessionNotFoundError
+from langbot_plugin.box.models import BoxManagedProcessSpec, BoxManagedProcessStatus, BoxSpec
+from langbot_plugin.box.runtime import BoxRuntime
+from langbot_plugin.box.server import BoxServerHandler, create_ws_relay_app
+
+_logger = logging.getLogger('test.box.mcp_integration')
+
+_TEST_IMAGE = 'alpine:latest'
+
+
+# ── Skip helpers ──────────────────────────────────────────────────────
+
+
+def _has_container_runtime() -> bool:
+    for cmd in ('podman', 'docker'):
+        if shutil.which(cmd) is None:
+            continue
+        try:
+            result = subprocess.run([cmd, 'info'], capture_output=True, timeout=10)
+            if result.returncode == 0:
+                return True
+        except Exception:
+            continue
+    return False
+
+
+def _can_open_test_socket() -> bool:
+    try:
+        sock = socket.socket(socket.AF_INET, socket.SOCK_STREAM)
+    except OSError:
+        return False
+    sock.close()
+    return True
+
+
+requires_container = pytest.mark.skipif(
+    not _has_container_runtime(),
+    reason='no container runtime (podman/docker) available',
+)
+
+requires_socket = pytest.mark.skipif(
+    not _can_open_test_socket(),
+    reason='local test environment does not permit opening TCP sockets',
+)
+
+
+# ── Helpers ──────────────────────────────────────────────────────────
+
+
+class _QueueConnection:
+    """In-process Connection backed by asyncio Queues — no real IO."""
+
+    def __init__(self, rx: asyncio.Queue[str], tx: asyncio.Queue[str]):
+        self._rx = rx
+        self._tx = tx
+
+    async def send(self, message: str) -> None:
+        await self._tx.put(message)
+
+    async def receive(self) -> str:
+        return await self._rx.get()
+
+    async def close(self) -> None:
+        pass
+
+
+async def _make_rpc_pair(runtime: BoxRuntime):
+    """Create an in-process RPC pair connected via queues."""
+    from langbot_plugin.runtime.io.handler import Handler
+
+    c2s: asyncio.Queue[str] = asyncio.Queue()
+    s2c: asyncio.Queue[str] = asyncio.Queue()
+    client_conn = _QueueConnection(rx=s2c, tx=c2s)
+    server_conn = _QueueConnection(rx=c2s, tx=s2c)
+
+    server_handler = BoxServerHandler(server_conn, runtime)
+    server_task = asyncio.create_task(server_handler.run())
+
+    client_handler = Handler.__new__(Handler)
+    Handler.__init__(client_handler, client_conn)
+    client_task = asyncio.create_task(client_handler.run())
+
+    client = ActionRPCBoxClient(logger=_logger)
+    client.set_handler(client_handler)
+
+    return client, server_task, client_task
+
+
+# ── Fixtures ──────────────────────────────────────────────────────────
+
+
+@pytest.fixture
+async def box_server():
+    """Yield a (ws_relay_url, ActionRPCBoxClient) backed by a real BoxRuntime."""
+    runtime = BoxRuntime(logger=_logger)
+    await runtime.initialize()
+
+    # Start ws relay for managed process attach
+    ws_app = create_ws_relay_app(runtime)
+    ws_server = TestServer(ws_app)
+    await ws_server.start_server()
+
+    client, server_task, client_task = await _make_rpc_pair(runtime)
+
+    ws_relay_url = str(ws_server.make_url(''))
+    yield ws_relay_url, client
+
+    server_task.cancel()
+    client_task.cancel()
+    await runtime.shutdown()
+    await ws_server.close()
+
+
+# ── 1. Managed process lifecycle ─────────────────────────────────────
+
+
+@requires_container
+@requires_socket
+@pytest.mark.asyncio
+async def test_managed_process_start_and_query(box_server):
+    """Start a managed process and query its status."""
+    ws_relay_url, client = box_server
+
+    # Create session
+    spec = BoxSpec(
+        cmd='',
+        session_id='mcp-int-lifecycle',
+        workdir='/tmp',
+        image=_TEST_IMAGE,
+    )
+    await client.create_session(spec)
+
+    # Start a managed process that stays alive
+    proc_spec = BoxManagedProcessSpec(
+        command='sh',
+        args=['-c', 'while true; do sleep 1; done'],
+        cwd='/tmp',
+    )
+    info = await client.start_managed_process('mcp-int-lifecycle', proc_spec)
+    assert info.status == BoxManagedProcessStatus.RUNNING
+
+    # Query it
+    info2 = await client.get_managed_process('mcp-int-lifecycle')
+    assert info2.status == BoxManagedProcessStatus.RUNNING
+    assert info2.command == 'sh'
+
+    # Stop only the managed process while keeping the session available
+    await client.stop_managed_process('mcp-int-lifecycle')
+    with pytest.raises(BoxManagedProcessNotFoundError):
+        await client.get_managed_process('mcp-int-lifecycle')
+    session_info = await client.get_session('mcp-int-lifecycle')
+    assert session_info['session_id'] == 'mcp-int-lifecycle'
+
+    # Cleanup
+    await client.delete_session('mcp-int-lifecycle')
+
+
+# ── 2. WebSocket stdio attach ────────────────────────────────────────
+
+
+@requires_container
+@requires_socket
+@pytest.mark.asyncio
+async def test_ws_stdio_attach_echo(box_server):
+    """Attach to a managed process via WebSocket and verify bidirectional IO."""
+    ws_relay_url, client = box_server
+
+    spec = BoxSpec(
+        cmd='',
+        session_id='mcp-int-ws',
+        workdir='/tmp',
+        image=_TEST_IMAGE,
+    )
+    await client.create_session(spec)
+
+    # Start a cat process (echoes stdin to stdout)
+    proc_spec = BoxManagedProcessSpec(
+        command='cat',
+        args=[],
+        cwd='/tmp',
+    )
+    await client.start_managed_process('mcp-int-ws', proc_spec)
+
+    # Connect via WebSocket (ws relay)
+    ws_url = client.get_managed_process_websocket_url('mcp-int-ws', ws_relay_url)
+    session = aiohttp.ClientSession()
+    try:
+        async with session.ws_connect(ws_url) as ws:
+            # Send a line
+            await ws.send_str('hello from test')
+
+            # Expect to receive it back (cat echoes)
+            msg = await asyncio.wait_for(ws.receive(), timeout=5)
+            assert msg.type == aiohttp.WSMsgType.TEXT
+            assert 'hello from test' in msg.data
+    finally:
+        await session.close()
+
+    await client.delete_session('mcp-int-ws')
+
+
+# ── 3. Session cleanup removes container ─────────────────────────────
+
+
+@requires_container
+@requires_socket
+@pytest.mark.asyncio
+async def test_delete_session_cleans_up(box_server):
+    """After deleting a session, it should no longer exist."""
+    ws_relay_url, client = box_server
+
+    spec = BoxSpec(
+        cmd='',
+        session_id='mcp-int-cleanup',
+        workdir='/tmp',
+        image=_TEST_IMAGE,
+    )
+    await client.create_session(spec)
+
+    # Start a process
+    proc_spec = BoxManagedProcessSpec(
+        command='sleep',
+        args=['3600'],
+        cwd='/tmp',
+    )
+    await client.start_managed_process('mcp-int-cleanup', proc_spec)
+
+    # Delete
+    await client.delete_session('mcp-int-cleanup')
+
+    # Session should be gone
+    with pytest.raises(BoxSessionNotFoundError):
+        await client.get_session('mcp-int-cleanup')
+
+
+# ── 4. GET session details ────────────────────────────────────────
+
+
+@requires_container
+@requires_socket
+@pytest.mark.asyncio
+async def test_get_session_returns_details(box_server):
+    """Get single session returns session details and managed process info."""
+    ws_relay_url, client = box_server
+
+    spec = BoxSpec(
+        cmd='',
+        session_id='mcp-int-get',
+        workdir='/tmp',
+        image=_TEST_IMAGE,
+    )
+    await client.create_session(spec)
+
+    # Query without managed process
+    info = await client.get_session('mcp-int-get')
+    assert info['session_id'] == 'mcp-int-get'
+    assert info['image'] == _TEST_IMAGE
+    assert 'managed_process' not in info
+
+    # Start a process and query again
+    proc_spec = BoxManagedProcessSpec(
+        command='sleep',
+        args=['3600'],
+        cwd='/tmp',
+    )
+    await client.start_managed_process('mcp-int-get', proc_spec)
+
+    info2 = await client.get_session('mcp-int-get')
+    assert info2['session_id'] == 'mcp-int-get'
+    assert 'managed_process' in info2
+    assert info2['managed_process']['status'] == BoxManagedProcessStatus.RUNNING.value
+
+    await client.delete_session('mcp-int-get')
+
+
+# ── 5. Process exit detected ────────────────────────────────────────
+
+
+@requires_container
+@requires_socket
+@pytest.mark.asyncio
+async def test_process_exit_detected(box_server):
+    """When a managed process exits, its status should reflect EXITED."""
+    ws_relay_url, client = box_server
+
+    spec = BoxSpec(
+        cmd='',
+        session_id='mcp-int-exit',
+        workdir='/tmp',
+        image=_TEST_IMAGE,
+    )
+    await client.create_session(spec)
+
+    # Start a process that exits immediately
+    proc_spec = BoxManagedProcessSpec(
+        command='sh',
+        args=['-c', 'echo done && exit 0'],
+        cwd='/tmp',
+    )
+    await client.start_managed_process('mcp-int-exit', proc_spec)
+
+    # Wait a bit for process to exit
+    await asyncio.sleep(2)
+
+    info = await client.get_managed_process('mcp-int-exit')
+    assert info.status == BoxManagedProcessStatus.EXITED
+    assert info.exit_code == 0
+
+    await client.delete_session('mcp-int-exit')
+
+
+# ── 6. Instance ID orphan cleanup ───────────────────────────────────
+
+
+@requires_container
+@requires_socket
+@pytest.mark.asyncio
+async def test_orphan_cleanup_preserves_own_containers(box_server):
+    """Orphan cleanup should not remove containers belonging to the current instance."""
+    ws_relay_url, client = box_server
+
+    # Create a session (container gets current instance ID label)
+    spec = BoxSpec(
+        cmd='',
+        session_id='mcp-int-orphan',
+        workdir='/tmp',
+        image=_TEST_IMAGE,
+    )
+    await client.create_session(spec)
+
+    # Verify session exists
+    sessions = await client.get_sessions()
+    assert any(s['session_id'] == 'mcp-int-orphan' for s in sessions)
+
+    # Trigger status check (which doesn't clean up own containers)
+    status = await client.get_status()
+    assert status['active_sessions'] >= 1
+
+    # Our session should still exist
+    sessions = await client.get_sessions()
+    assert any(s['session_id'] == 'mcp-int-orphan' for s in sessions)
+
+    await client.delete_session('mcp-int-orphan')

tests/unit_tests/box/test_box_connector.py

@@ -0,0 +1,106 @@
+from __future__ import annotations
+
+from types import SimpleNamespace
+from unittest.mock import Mock
+
+import pytest
+
+from langbot_plugin.box.client import ActionRPCBoxClient
+from langbot.pkg.box.connector import BoxRuntimeConnector
+
+
+def make_app(logger: Mock, runtime_endpoint: str = ''):
+    return SimpleNamespace(
+        logger=logger,
+        instance_config=SimpleNamespace(
+            data={
+                'box': {
+                    'backend': 'local',
+                    'runtime': {'endpoint': runtime_endpoint},
+                    'local': {
+                        'profile': 'default',
+                        'allowed_mount_roots': [],
+                        'default_workspace': '',
+                    },
+                    'e2b': {'api_key': '', 'api_url': '', 'template': ''},
+                }
+            }
+        ),
+    )
+
+
+def test_box_runtime_connector_stdio_when_no_url(monkeypatch: pytest.MonkeyPatch):
+    """Without runtime.endpoint, on a non-Docker Unix platform, use stdio."""
+    monkeypatch.setattr('langbot.pkg.utils.platform.get_platform', lambda: 'linux')
+    monkeypatch.setattr('langbot.pkg.utils.platform.standalone_box', False)
+    connector = BoxRuntimeConnector(make_app(Mock()))
+
+    assert connector._uses_websocket() is False
+    assert isinstance(connector.client, ActionRPCBoxClient)
+
+
+def test_box_runtime_connector_ws_when_url_configured(monkeypatch: pytest.MonkeyPatch):
+    """With an explicit runtime.endpoint, always use WebSocket."""
+    monkeypatch.setattr('langbot.pkg.utils.platform.get_platform', lambda: 'linux')
+    monkeypatch.setattr('langbot.pkg.utils.platform.standalone_box', False)
+    logger = Mock()
+    connector = BoxRuntimeConnector(make_app(logger, runtime_endpoint='http://box-runtime:5410'))
+
+    assert connector._uses_websocket() is True
+    assert isinstance(connector.client, ActionRPCBoxClient)
+
+
+def test_box_runtime_connector_ws_in_docker(monkeypatch: pytest.MonkeyPatch):
+    """Inside Docker (no explicit URL), use WebSocket to reach a sibling container."""
+    monkeypatch.setattr('langbot.pkg.utils.platform.get_platform', lambda: 'docker')
+    monkeypatch.setattr('langbot.pkg.utils.platform.standalone_box', False)
+    connector = BoxRuntimeConnector(make_app(Mock()))
+
+    assert connector._uses_websocket() is True
+    assert connector.ws_relay_base_url == 'http://langbot_box:5410'
+
+
+def test_box_runtime_connector_ws_with_standalone_flag(monkeypatch: pytest.MonkeyPatch):
+    """With --standalone-box flag, use WebSocket even on a local Unix platform."""
+    monkeypatch.setattr('langbot.pkg.utils.platform.get_platform', lambda: 'linux')
+    monkeypatch.setattr('langbot.pkg.utils.platform.standalone_box', True)
+    connector = BoxRuntimeConnector(make_app(Mock()))
+
+    assert connector._uses_websocket() is True
+
+
+def test_box_runtime_connector_ws_relay_url_default(monkeypatch: pytest.MonkeyPatch):
+    monkeypatch.setattr('langbot.pkg.utils.platform.get_platform', lambda: 'linux')
+    monkeypatch.setattr('langbot.pkg.utils.platform.standalone_box', False)
+    connector = BoxRuntimeConnector(make_app(Mock()))
+
+    assert connector.ws_relay_base_url == 'http://127.0.0.1:5410'
+
+
+def test_box_runtime_connector_ws_relay_url_explicit(monkeypatch: pytest.MonkeyPatch):
+    monkeypatch.setattr('langbot.pkg.utils.platform.get_platform', lambda: 'linux')
+    monkeypatch.setattr('langbot.pkg.utils.platform.standalone_box', False)
+    connector = BoxRuntimeConnector(make_app(Mock(), runtime_endpoint='http://box-runtime:5410'))
+    assert connector.ws_relay_base_url == 'http://box-runtime:5410'
+
+
+def test_box_runtime_connector_dispose_terminates_subprocess(monkeypatch: pytest.MonkeyPatch):
+    monkeypatch.setattr('langbot.pkg.utils.platform.get_platform', lambda: 'linux')
+    monkeypatch.setattr('langbot.pkg.utils.platform.standalone_box', False)
+    logger = Mock()
+    connector = BoxRuntimeConnector(make_app(logger))
+    subprocess = Mock()
+    subprocess.returncode = None
+    handler_task = Mock()
+    ctrl_task = Mock()
+    connector._subprocess = subprocess
+    connector._handler_task = handler_task
+    connector._ctrl_task = ctrl_task
+
+    connector.dispose()
+
+    subprocess.terminate.assert_called_once()
+    handler_task.cancel.assert_called_once()
+    ctrl_task.cancel.assert_called_once()
+    assert connector._handler_task is None
+    assert connector._ctrl_task is None

tests/unit_tests/box/test_workspace.py

@@ -0,0 +1,147 @@
+from __future__ import annotations
+
+import os
+import tempfile
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, Mock
+
+import pytest
+
+from langbot.pkg.box.workspace import (
+    BoxWorkspaceSession,
+    classify_python_workspace,
+    infer_workspace_host_path,
+    rewrite_mounted_path,
+    wrap_python_command_with_env,
+)
+
+
+def test_rewrite_mounted_path_translates_host_prefix():
+    result = rewrite_mounted_path('/tmp/demo/project/app.py', '/tmp/demo/project')
+    assert result == '/workspace/app.py'
+
+
+def test_infer_workspace_host_path_unwraps_virtualenv_bin_dir():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        project_root = os.path.join(tmpdir, 'project')
+        os.makedirs(os.path.join(project_root, '.venv', 'bin'))
+        python_bin = os.path.join(project_root, '.venv', 'bin', 'python')
+        script = os.path.join(project_root, 'server.py')
+
+        with open(python_bin, 'w', encoding='utf-8') as handle:
+            handle.write('')
+        with open(script, 'w', encoding='utf-8') as handle:
+            handle.write('print("ok")\n')
+
+        result = infer_workspace_host_path(python_bin, [script])
+
+        assert result == os.path.realpath(project_root)
+
+
+def test_classify_python_workspace_detects_package_and_requirements():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        assert classify_python_workspace(tmpdir) is None
+
+        with open(os.path.join(tmpdir, 'requirements.txt'), 'w', encoding='utf-8') as handle:
+            handle.write('requests\n')
+        assert classify_python_workspace(tmpdir) == 'requirements'
+
+        with open(os.path.join(tmpdir, 'pyproject.toml'), 'w', encoding='utf-8') as handle:
+            handle.write('[project]\nname = "demo"\n')
+        assert classify_python_workspace(tmpdir) == 'package'
+
+
+def test_wrap_python_command_with_env_contains_bootstrap_and_command():
+    command = wrap_python_command_with_env('python script.py')
+
+    assert 'python -m venv "$_LB_VENV_DIR"' in command
+    assert 'export VIRTUAL_ENV="$_LB_VENV_DIR"' in command
+    assert command.rstrip().endswith('python script.py')
+
+
+@pytest.mark.asyncio
+async def test_workspace_session_execute_for_query_uses_session_payload():
+    box_service = SimpleNamespace(execute_spec_payload=AsyncMock(return_value={'ok': True}))
+    workspace = BoxWorkspaceSession(
+        box_service,
+        'skill-person_123-demo',
+        host_path='/tmp/project',
+        host_path_mode='rw',
+        env={'FOO': 'bar'},
+    )
+
+    query = SimpleNamespace(query_id='q1')
+    result = await workspace.execute_for_query(query, 'python run.py', workdir='/workspace', timeout_sec=30)
+
+    assert result == {'ok': True}
+    payload = box_service.execute_spec_payload.await_args.args[0]
+    assert payload == {
+        'session_id': 'skill-person_123-demo',
+        'workdir': '/workspace',
+        'env': {'FOO': 'bar'},
+        'persistent': False,
+        'host_path': '/tmp/project',
+        'host_path_mode': 'rw',
+        'cmd': 'python run.py',
+        'timeout_sec': 30,
+    }
+
+
+@pytest.mark.asyncio
+async def test_workspace_session_start_managed_process_rewrites_command_and_args():
+    box_service = SimpleNamespace(start_managed_process=AsyncMock(return_value={'status': 'running'}))
+    workspace = BoxWorkspaceSession(
+        box_service,
+        'mcp-u1',
+        host_path='/tmp/project',
+        host_path_mode='ro',
+    )
+
+    result = await workspace.start_managed_process(
+        '/tmp/project/.venv/bin/python',
+        ['/tmp/project/server.py', '--config', '/tmp/project/config.json'],
+        env={'TOKEN': '1'},
+    )
+
+    assert result == {'status': 'running'}
+    session_id = box_service.start_managed_process.await_args.args[0]
+    payload = box_service.start_managed_process.await_args.args[1]
+    assert session_id == 'mcp-u1'
+    assert payload == {
+        'command': 'python',
+        'args': ['/workspace/server.py', '--config', '/workspace/config.json'],
+        'env': {'TOKEN': '1'},
+        'cwd': '/workspace',
+        'process_id': 'default',
+    }
+
+
+def test_workspace_session_build_session_payload_keeps_generic_workspace_shape():
+    workspace = BoxWorkspaceSession(
+        Mock(),
+        'workspace-1',
+        host_path='/tmp/project',
+        host_path_mode='rw',
+        env={'FOO': 'bar'},
+        network='on',
+        read_only_rootfs=False,
+        image='python:3.11',
+        cpus=1.0,
+        memory_mb=512,
+        pids_limit=128,
+    )
+
+    assert workspace.build_session_payload() == {
+        'session_id': 'workspace-1',
+        'workdir': '/workspace',
+        'env': {'FOO': 'bar'},
+        'persistent': False,
+        'network': 'on',
+        'read_only_rootfs': False,
+        'host_path': '/tmp/project',
+        'host_path_mode': 'rw',
+        'image': 'python:3.11',
+        'cpus': 1.0,
+        'memory_mb': 512,
+        'pids_limit': 128,
+    }

tests/unit_tests/pipeline/conftest.py

@@ -12,6 +12,12 @@ from __future__ import annotations
 import pytest
 from unittest.mock import AsyncMock, Mock
 
+# Preload pipelinemgr so the pipeline.stage module is fully initialised before
+# any individual stage test (e.g. preproc, longtext) tries to import it. Without
+# this, running a stage test in isolation triggers a circular-import error:
+#   stage.py → core.app → pipelinemgr → stage.stage_class (not yet bound).
+import langbot.pkg.pipeline.pipelinemgr  # noqa: F401
+
 import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
 import langbot_plugin.api.entities.builtin.platform.message as platform_message
 import langbot_plugin.api.entities.builtin.platform.events as platform_events
@@ -34,6 +40,9 @@ class MockApplication:
         self.query_pool = self._create_mock_query_pool()
         self.instance_config = self._create_mock_instance_config()
         self.task_mgr = self._create_mock_task_manager()
+        # Skill manager is optional; PreProcessor only touches it for the
+        # local-agent runner. None keeps the skill-binding branch inert.
+        self.skill_mgr = None
 
     def _create_mock_logger(self):
         logger = Mock()

tests/unit_tests/pipeline/test_chat_handler_logging.py

@@ -0,0 +1,78 @@
+from __future__ import annotations
+
+from unittest.mock import Mock
+
+import pytest
+import langbot_plugin.api.entities.builtin.provider.message as provider_message
+
+# TODO: unskip once the handler ↔ app circular import is resolved
+pytest.skip(
+    'circular import in handler ↔ app; will be unblocked once resolved',
+    allow_module_level=True,
+)
+
+from langbot.pkg.pipeline.process.handler import MessageHandler  # noqa: E402
+
+
+class _StubHandler(MessageHandler):
+    async def handle(self, query):
+        raise NotImplementedError
+
+
+handler = _StubHandler(ap=Mock())
+
+
+def test_chat_handler_formats_tool_call_request_log():
+    result = provider_message.Message(
+        role='assistant',
+        content='',
+        tool_calls=[
+            provider_message.ToolCall(
+                id='call-1',
+                type='function',
+                function=provider_message.FunctionCall(name='exec', arguments='{}'),
+            )
+        ],
+    )
+
+    summary = handler.format_result_log(result)
+
+    assert summary == 'assistant: requested tools: exec'
+
+
+def test_chat_handler_formats_tool_result_log():
+    result = provider_message.Message(
+        role='tool',
+        content='{"status":"completed","exit_code":0,"backend":"podman","stdout":"42\\n"}',
+        tool_call_id='call-1',
+    )
+
+    summary = handler.format_result_log(result)
+
+    # Tool results use generic cut_str truncation
+    assert summary is not None
+    assert summary.startswith('tool: {"status":"com')
+    assert summary.endswith('...')
+
+
+def test_chat_handler_formats_tool_error_log():
+    result = provider_message.MessageChunk(
+        role='tool',
+        content='err: host_path must point to an existing directory on the host',
+        tool_call_id='call-1',
+        is_final=True,
+    )
+
+    summary = handler.format_result_log(result)
+
+    assert summary is not None
+    assert summary.startswith('tool error: err: host_path must')
+    assert summary.endswith('...')
+
+
+def test_chat_handler_skips_empty_assistant_log():
+    result = provider_message.Message(role='assistant', content='')
+
+    summary = handler.format_result_log(result)
+
+    assert summary is None

tests/unit_tests/pipeline/test_n8nsvapi.py

@@ -14,33 +14,43 @@ import json
 import sys
 from unittest.mock import AsyncMock, MagicMock, Mock, patch
 
-# Break the circular import chain before importing n8nsvapi:
+import pytest
+import langbot_plugin.api.entities.builtin.provider.message as provider_message
+
+# Break the circular import chain while importing n8nsvapi:
 #   n8nsvapi → runner → app → pipelinemgr → all runners → runner (partially init)
-_mock_runner = MagicMock()
-_mock_runner.runner_class = lambda name: (lambda cls: cls)  # no-op decorator
-_mock_runner.RequestRunner = object
-_mocked_imports = {
-    'langbot.pkg.provider.runner': _mock_runner,
+# The stubs are restored in a ``finally`` block so this module does NOT pollute
+# sys.modules for other test modules (e.g. ones importing the real
+# LocalAgentRunner, which would otherwise inherit ``object`` and break).
+# Mirrors master's intent but uses try/finally so a raised import doesn't
+# leave the global namespace in a stubbed state, and includes
+# ``langbot.pkg.utils.httpclient`` which master didn't stub.
+_runner_stub = MagicMock()
+_runner_stub.runner_class = lambda name: (lambda cls: cls)  # no-op decorator
+_runner_stub.RequestRunner = object
+_import_stubs = {
+    'langbot.pkg.provider.runner': _runner_stub,
     'langbot.pkg.core.app': MagicMock(),
+    'langbot.pkg.utils.httpclient': MagicMock(),
 }
-_original_imports = {name: sys.modules.get(name) for name in _mocked_imports}
-sys.modules.update(_mocked_imports)
-
-import pytest  # noqa: E402
-import langbot_plugin.api.entities.builtin.provider.message as provider_message  # noqa: E402
-from langbot.pkg.provider.runners.n8nsvapi import N8nServiceAPIRunner  # noqa: E402
-
-for _name, _original in _original_imports.items():
-    if _original is None:
-        sys.modules.pop(_name, None)
-    else:
-        sys.modules[_name] = _original
+_saved_modules = {name: sys.modules.get(name) for name in _import_stubs}
+for _name, _stub in _import_stubs.items():
+    sys.modules[_name] = _stub
+try:
+    from langbot.pkg.provider.runners.n8nsvapi import N8nServiceAPIRunner
+finally:
+    for _name, _original in _saved_modules.items():
+        if _original is None:
+            sys.modules.pop(_name, None)
+        else:
+            sys.modules[_name] = _original
 
 
 # ---------------------------------------------------------------------------
 # Helpers
 # ---------------------------------------------------------------------------
 
+
 def make_runner(output_key: str = 'response') -> N8nServiceAPIRunner:
     ap = Mock()
     ap.logger = Mock()
@@ -83,6 +93,7 @@ async def collect_chunks(runner: N8nServiceAPIRunner, chunks: list[bytes | str])
 # _process_response: stream format (type:item/end)
 # ---------------------------------------------------------------------------
 
+
 @pytest.mark.asyncio
 async def test_stream_format_single_item():
     """Single item + end in one chunk yields final chunk with full content."""
@@ -165,6 +176,7 @@ async def test_stream_format_no_spurious_empty_yield():
 # _process_response: plain JSON fallback
 # ---------------------------------------------------------------------------
 
+
 @pytest.mark.asyncio
 async def test_plain_json_with_output_key():
     """Plain JSON with matching output_key extracts value via output_key."""
@@ -235,6 +247,7 @@ async def test_invalid_json_returns_raw_text():
 # _call_webhook: output type depends on is_stream
 # ---------------------------------------------------------------------------
 
+
 def make_query(is_stream: bool):
     """Build a minimal Query mock."""
     query = Mock()

tests/unit_tests/provider/test_localagent_sandbox_exec.py

@@ -0,0 +1,242 @@
+from __future__ import annotations
+
+import json
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, Mock
+
+import pytest
+
+import langbot_plugin.api.entities.builtin.pipeline.query as pipeline_query
+import langbot_plugin.api.entities.builtin.provider.message as provider_message
+import langbot_plugin.api.entities.builtin.provider.session as provider_session
+
+from langbot.pkg.provider.runners.localagent import LocalAgentRunner
+
+
+class RecordingProvider:
+    def __init__(self):
+        self.requests: list[dict] = []
+
+    async def invoke_llm(self, query, model, messages, funcs, extra_args=None, remove_think=None):
+        self.requests.append(
+            {
+                'messages': list(messages),
+                'funcs': list(funcs),
+                'remove_think': remove_think,
+            }
+        )
+
+        if len(self.requests) == 1:
+            return provider_message.Message(
+                role='assistant',
+                content='Let me calculate that exactly.',
+                tool_calls=[
+                    provider_message.ToolCall(
+                        id='call-1',
+                        type='function',
+                        function=provider_message.FunctionCall(
+                            name='exec',
+                            arguments=json.dumps(
+                                {'command': ("python - <<'PY'\nnums = [1, 2, 3, 4]\nprint(sum(nums) / len(nums))\nPY")}
+                            ),
+                        ),
+                    )
+                ],
+            )
+
+        tool_result = json.loads(messages[-1].content)
+        return provider_message.Message(
+            role='assistant',
+            content=f'The average is {tool_result["stdout"]}.',
+        )
+
+
+class RecordingStreamProvider:
+    def __init__(self):
+        self.stream_requests: list[dict] = []
+
+    def invoke_llm_stream(self, query, model, messages, funcs, extra_args=None, remove_think=None):
+        self.stream_requests.append(
+            {
+                'messages': list(messages),
+                'funcs': list(funcs),
+                'remove_think': remove_think,
+            }
+        )
+
+        async def _stream():
+            if len(self.stream_requests) == 1:
+                yield provider_message.MessageChunk(
+                    role='assistant',
+                    tool_calls=[
+                        provider_message.ToolCall(
+                            id='call-1',
+                            type='function',
+                            function=provider_message.FunctionCall(
+                                name='exec',
+                                arguments=json.dumps({'command': "python -c 'print(1)'"}),
+                            ),
+                        )
+                    ],
+                    is_final=True,
+                )
+                return
+
+            yield provider_message.MessageChunk(
+                role='assistant',
+                content='Tool execution failed.',
+                is_final=True,
+            )
+
+        return _stream()
+
+
+def make_query() -> pipeline_query.Query:
+    adapter = AsyncMock()
+    adapter.is_stream_output_supported = AsyncMock(return_value=False)
+
+    return pipeline_query.Query.model_construct(
+        query_id='avg-query',
+        launcher_type=provider_session.LauncherTypes.PERSON,
+        launcher_id=12345,
+        sender_id=12345,
+        message_chain=[],
+        message_event=None,
+        adapter=adapter,
+        pipeline_uuid='pipeline-uuid',
+        bot_uuid='bot-uuid',
+        pipeline_config={
+            'ai': {
+                'runner': {'runner': 'local-agent'},
+                'local-agent': {'model': {'primary': 'test-model-uuid', 'fallbacks': []}, 'prompt': 'test-prompt'},
+            },
+            'output': {'misc': {'remove-think': False}},
+        },
+        prompt=SimpleNamespace(messages=[]),
+        messages=[],
+        user_message=provider_message.Message(
+            role='user',
+            content='Please calculate the average of 1, 2, 3, and 4.',
+        ),
+        use_funcs=[SimpleNamespace(name='exec')],
+        use_llm_model_uuid='test-model-uuid',
+        variables={},
+    )
+
+
+@pytest.mark.asyncio
+async def test_localagent_uses_exec_for_exact_calculation():
+    provider = RecordingProvider()
+    model = SimpleNamespace(
+        provider=provider,
+        model_entity=SimpleNamespace(
+            uuid='test-model-uuid',
+            name='test-model',
+            abilities=['func_call'],
+            extra_args={},
+        ),
+    )
+
+    tool_manager = SimpleNamespace(
+        execute_func_call=AsyncMock(
+            return_value={
+                'session_id': 'avg-query',
+                'backend': 'podman',
+                'status': 'completed',
+                'ok': True,
+                'exit_code': 0,
+                'stdout': '2.5',
+                'stderr': '',
+                'duration_ms': 18,
+            }
+        )
+    )
+
+    app = SimpleNamespace(
+        logger=Mock(),
+        model_mgr=SimpleNamespace(get_model_by_uuid=AsyncMock(return_value=model)),
+        tool_mgr=tool_manager,
+        rag_mgr=SimpleNamespace(),
+        box_service=SimpleNamespace(
+            get_system_guidance=Mock(
+                return_value=(
+                    'When the exec tool is available, use it for exact calculations, statistics, '
+                    'structured data parsing, and code execution instead of estimating mentally. '
+                    'Unless the user explicitly asks for the script, code, or implementation details, '
+                    'do not include the generated script in the final answer. '
+                    'A default workspace is mounted at /workspace for file tasks.'
+                )
+            ),
+        ),
+        skill_mgr=SimpleNamespace(
+            get_skills_for_pipeline=AsyncMock(return_value=[]),
+            detect_skill_activation=AsyncMock(return_value=None),
+            build_activation_prompt=Mock(return_value=None),
+        ),
+    )
+
+    runner = LocalAgentRunner(app, pipeline_config={})
+    query = make_query()
+
+    results = [message async for message in runner.run(query)]
+
+    assert [message.role for message in results] == ['assistant', 'tool', 'assistant']
+    assert results[-1].content == 'The average is 2.5.'
+
+    tool_manager.execute_func_call.assert_awaited_once()
+    tool_name, tool_parameters = tool_manager.execute_func_call.await_args.args[:2]
+    assert tool_name == 'exec'
+    assert 'print(sum(nums) / len(nums))' in tool_parameters['command']
+
+    first_request = provider.requests[0]
+    assert any(
+        message.role == 'system'
+        and 'exec' in str(message.content)
+        and 'exact calculations' in str(message.content)
+        and 'Unless the user explicitly asks for the script' in str(message.content)
+        and '/workspace' in str(message.content)
+        for message in first_request['messages']
+    )
+    assert [tool.name for tool in first_request['funcs']] == ['exec']
+
+
+@pytest.mark.asyncio
+async def test_localagent_streaming_tool_error_yields_message_chunks():
+    provider = RecordingStreamProvider()
+    model = SimpleNamespace(
+        provider=provider,
+        model_entity=SimpleNamespace(
+            uuid='test-model-uuid',
+            name='test-model',
+            abilities=['func_call'],
+            extra_args={},
+        ),
+    )
+
+    adapter = AsyncMock()
+    adapter.is_stream_output_supported = AsyncMock(return_value=True)
+
+    query = make_query()
+    query.adapter = adapter
+
+    app = SimpleNamespace(
+        logger=Mock(),
+        model_mgr=SimpleNamespace(get_model_by_uuid=AsyncMock(return_value=model)),
+        tool_mgr=SimpleNamespace(execute_func_call=AsyncMock(side_effect=RuntimeError('boom'))),
+        rag_mgr=SimpleNamespace(),
+        box_service=SimpleNamespace(
+            get_system_guidance=Mock(return_value='sandbox guidance'),
+        ),
+        skill_mgr=SimpleNamespace(
+            get_skills_for_pipeline=AsyncMock(return_value=[]),
+            detect_skill_activation=AsyncMock(return_value=None),
+            build_activation_prompt=Mock(return_value=None),
+        ),
+    )
+
+    runner = LocalAgentRunner(app, pipeline_config={})
+
+    results = [message async for message in runner.run(query)]
+
+    assert all(isinstance(message, provider_message.MessageChunk) for message in results)
+    assert any(message.role == 'tool' and message.content == 'err: boom' for message in results)

tests/unit_tests/provider/test_mcp_box_integration.py

@@ -0,0 +1,712 @@
+"""Tests for MCP Box integration: path rewriting, host_path inference, config model, payloads.
+
+Uses importlib.util.spec_from_file_location to load mcp.py directly without
+triggering the circular import chain through the app module.
+"""
+
+from __future__ import annotations
+
+import importlib
+import importlib.util
+import os
+import sys
+import tempfile
+import types
+from contextlib import asynccontextmanager
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, Mock
+
+import pytest
+
+
+# ---------------------------------------------------------------------------
+# Load mcp.py directly from file path, with stub dependencies
+# ---------------------------------------------------------------------------
+
+
+def _stub_module(fqn: str, attrs: dict | None = None, is_package: bool = False):
+    """Create or return a stub module and register it in sys.modules."""
+    if fqn in sys.modules:
+        mod = sys.modules[fqn]
+    else:
+        mod = types.ModuleType(fqn)
+        mod.__spec__ = importlib.machinery.ModuleSpec(fqn, None, is_package=is_package)
+        if is_package:
+            mod.__path__ = []
+        sys.modules[fqn] = mod
+    parts = fqn.rsplit('.', 1)
+    if len(parts) == 2 and parts[0] in sys.modules:
+        setattr(sys.modules[parts[0]], parts[1], mod)
+    if attrs:
+        for k, v in attrs.items():
+            setattr(mod, k, v)
+    return mod
+
+
+@pytest.fixture(scope='module', autouse=True)
+def mcp_module():
+    """Load mcp.py with minimal stubs to avoid circular imports."""
+    saved = {}
+
+    def _save_and_stub(name, attrs=None, is_package=False):
+        saved[name] = sys.modules.get(name)
+        # Don't overwrite modules that already exist (from other test modules)
+        if name in sys.modules:
+            return
+        _stub_module(name, attrs, is_package)
+
+    # Stub entire dependency chains as packages / modules
+    _save_and_stub('langbot_plugin', is_package=True)
+    _save_and_stub('langbot_plugin.api', is_package=True)
+    _save_and_stub('langbot_plugin.api.entities', is_package=True)
+    _save_and_stub('langbot_plugin.api.entities.events', is_package=True)
+    _save_and_stub('langbot_plugin.api.entities.events.pipeline_query', {})
+    _save_and_stub('langbot_plugin.api.entities.builtin', is_package=True)
+    _save_and_stub('langbot_plugin.api.entities.builtin.resource', is_package=True)
+    _save_and_stub(
+        'langbot_plugin.api.entities.builtin.resource.tool',
+        {
+            'LLMTool': type('LLMTool', (), {}),
+        },
+    )
+    _save_and_stub('langbot_plugin.api.entities.builtin.provider', is_package=True)
+    _save_and_stub('langbot_plugin.api.entities.builtin.provider.message', {})
+    _save_and_stub('sqlalchemy', {'select': Mock()})
+    _save_and_stub('httpx', {'AsyncClient': Mock()})
+    _save_and_stub('mcp', {'ClientSession': Mock, 'StdioServerParameters': Mock}, is_package=True)
+    _save_and_stub('mcp.client', is_package=True)
+    _save_and_stub('mcp.client.stdio', {'stdio_client': Mock()})
+    _save_and_stub('mcp.client.sse', {'sse_client': Mock()})
+    _save_and_stub('mcp.client.streamable_http', {'streamable_http_client': Mock()})
+    _save_and_stub('mcp.client.websocket', {'websocket_client': Mock()})
+
+    # Stub the provider.tools.loader (source of circular import)
+    _save_and_stub('langbot', is_package=True)
+    _save_and_stub('langbot.pkg', is_package=True)
+    _save_and_stub('langbot.pkg.provider', is_package=True)
+    _save_and_stub('langbot.pkg.provider.tools', is_package=True)
+    _save_and_stub(
+        'langbot.pkg.provider.tools.loader',
+        {
+            'ToolLoader': type('ToolLoader', (), {'__init__': lambda self, ap: None}),
+        },
+    )
+    _save_and_stub('langbot.pkg.provider.tools.loaders', is_package=True)
+    _save_and_stub('langbot.pkg.core', is_package=True)
+    _save_and_stub('langbot.pkg.core.app', {'Application': type('Application', (), {})})
+    _save_and_stub('langbot.pkg.entity', is_package=True)
+    _save_and_stub('langbot.pkg.entity.persistence', is_package=True)
+    _save_and_stub('langbot.pkg.entity.persistence.mcp', {})
+
+    # box models
+    import enum as _enum
+
+    class _BPS(str, _enum.Enum):
+        RUNNING = 'running'
+        EXITED = 'exited'
+
+    _save_and_stub('langbot_plugin.box', is_package=True)
+    _save_and_stub('langbot_plugin.box.models', {'BoxManagedProcessStatus': _BPS})
+
+    # Now load mcp.py via spec_from_file_location
+    mod_fqn = 'langbot.pkg.provider.tools.loaders.mcp'
+    sys.modules.pop(mod_fqn, None)
+    mcp_path = os.path.join(
+        os.path.dirname(__file__),
+        '..',
+        '..',
+        '..',
+        'src',
+        'langbot',
+        'pkg',
+        'provider',
+        'tools',
+        'loaders',
+        'mcp.py',
+    )
+    mcp_path = os.path.normpath(mcp_path)
+    pkg_root = os.path.dirname(os.path.dirname(os.path.dirname(os.path.dirname(mcp_path))))
+    sys.modules['langbot.pkg'].__path__ = [pkg_root]
+    sys.modules['langbot.pkg.provider.tools.loaders'].__path__ = [os.path.dirname(mcp_path)]
+    spec = importlib.util.spec_from_file_location(mod_fqn, mcp_path)
+    mod = importlib.util.module_from_spec(spec)
+    sys.modules[mod_fqn] = mod
+    spec.loader.exec_module(mod)
+
+    yield mod
+
+    # Cleanup
+    sys.modules.pop(mod_fqn, None)
+    sys.modules.pop('langbot.pkg.provider.tools.loaders.mcp_stdio', None)
+    sys.modules.pop('langbot.pkg.box.workspace', None)
+    for name in reversed(list(saved)):
+        if saved[name] is None:
+            sys.modules.pop(name, None)
+        else:
+            sys.modules[name] = saved[name]
+
+
+# ---------------------------------------------------------------------------
+# Helpers
+# ---------------------------------------------------------------------------
+
+
+def _make_ap():
+    ap = Mock()
+    ap.logger = Mock()
+    ap.box_service = Mock()
+    return ap
+
+
+def _make_session(mcp_module, server_config: dict, ap=None):
+    if ap is None:
+        ap = _make_ap()
+    return mcp_module.RuntimeMCPSession(
+        server_name=server_config.get('name', 'test-server'),
+        server_config=server_config,
+        enable=True,
+        ap=ap,
+    )
+
+
+# ── MCPServerBoxConfig ──────────────────────────────────────────────
+
+
+class TestMCPServerBoxConfig:
+    def test_default_values(self, mcp_module):
+        cfg = mcp_module.MCPServerBoxConfig.model_validate({})
+        assert cfg.image is None
+        assert cfg.network == 'on'
+        assert cfg.host_path is None
+        assert cfg.host_path_mode == 'ro'
+        assert cfg.env == {}
+        assert cfg.startup_timeout_sec == 120
+        assert cfg.cpus is None
+        assert cfg.memory_mb is None
+        assert cfg.pids_limit is None
+        assert cfg.read_only_rootfs is None
+
+    def test_custom_values(self, mcp_module):
+        cfg = mcp_module.MCPServerBoxConfig.model_validate(
+            {
+                'image': 'node:20',
+                'network': 'on',
+                'host_path': '/home/user/mcp',
+                'host_path_mode': 'rw',
+                'env': {'FOO': 'bar'},
+                'startup_timeout_sec': 60,
+                'cpus': 2.0,
+                'memory_mb': 1024,
+                'pids_limit': 256,
+                'read_only_rootfs': False,
+            }
+        )
+        assert cfg.image == 'node:20'
+        assert cfg.network == 'on'
+        assert cfg.cpus == 2.0
+        assert cfg.memory_mb == 1024
+
+    def test_extra_fields_ignored(self, mcp_module):
+        cfg = mcp_module.MCPServerBoxConfig.model_validate(
+            {
+                'image': 'node:20',
+                'unknown_field': 'whatever',
+            }
+        )
+        assert cfg.image == 'node:20'
+        assert not hasattr(cfg, 'unknown_field')
+
+
+# ── Path Rewriting ──────────────────────────────────────────────────
+
+
+class TestRewritePath:
+    def test_no_host_path_returns_unchanged(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+            },
+        )
+        assert s._rewrite_path('/some/path', None) == '/some/path'
+
+    def test_empty_path_returns_empty(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+            },
+        )
+        assert s._rewrite_path('', '/home/user/mcp') == ''
+
+    def test_prefix_match_rewrites(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+            },
+        )
+        result = s._rewrite_path('/home/user/mcp/server.py', '/home/user/mcp')
+        assert result == '/workspace/server.py'
+
+    def test_exact_match_rewrites_to_workspace(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+            },
+        )
+        result = s._rewrite_path('/home/user/mcp', '/home/user/mcp')
+        assert result == '/workspace'
+
+    def test_non_matching_path_unchanged(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+            },
+        )
+        result = s._rewrite_path('/opt/other/server.py', '/home/user/mcp')
+        assert result == '/opt/other/server.py'
+
+    def test_similar_prefix_not_rewritten(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+            },
+        )
+        result = s._rewrite_path('/home/user/mcp-other/file.py', '/home/user/mcp')
+        assert result == '/home/user/mcp-other/file.py'
+
+    def test_nested_subpath_rewrites(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+            },
+        )
+        result = s._rewrite_path('/home/user/mcp/src/lib/main.py', '/home/user/mcp')
+        assert result == '/workspace/src/lib/main.py'
+
+
+# ── host_path Inference ─────────────────────────────────────────────
+
+
+class TestInferHostPath:
+    def test_no_absolute_paths_returns_none(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': ['server.py'],
+            },
+        )
+        assert s._infer_host_path() is None
+
+    def test_nonexistent_path_returns_none(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': '/nonexistent/path/to/python',
+                'args': [],
+            },
+        )
+        assert s._infer_host_path() is None
+
+    def test_existing_absolute_path_infers_directory(self, mcp_module):
+        with tempfile.NamedTemporaryFile(suffix='.py') as f:
+            s = _make_session(
+                mcp_module,
+                {
+                    'name': 'test',
+                    'uuid': 'u1',
+                    'mode': 'sse',
+                    'command': 'python',
+                    'args': [f.name],
+                },
+            )
+            result = s._infer_host_path()
+            assert result is not None
+            assert result == os.path.dirname(os.path.realpath(f.name))
+
+
+# ── Build Box Session Payload ───────────────────────────────────────
+
+
+class TestBuildBoxSessionPayload:
+    def test_minimal_config(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+            },
+        )
+        payload = s._build_box_session_payload('session-123')
+        assert payload['session_id'] == 'session-123'
+        assert payload['workdir'] == '/workspace'
+        assert payload['env'] == {}
+        assert 'host_path' not in payload
+
+    def test_with_host_path(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+                'box': {'host_path': '/home/user/mcp', 'host_path_mode': 'ro'},
+            },
+        )
+        payload = s._build_box_session_payload('session-123')
+        assert payload['host_path'] == '/home/user/mcp'
+        assert payload['host_path_mode'] == 'ro'
+
+    def test_optional_fields_included_when_set(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+                'box': {'image': 'node:20', 'cpus': 2.0, 'memory_mb': 1024, 'pids_limit': 256},
+            },
+        )
+        payload = s._build_box_session_payload('session-123')
+        assert payload['image'] == 'node:20'
+        assert payload['cpus'] == 2.0
+        assert payload['memory_mb'] == 1024
+        assert payload['pids_limit'] == 256
+
+    def test_none_fields_excluded(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+            },
+        )
+        payload = s._build_box_session_payload('session-123')
+        assert 'image' not in payload
+        assert 'cpus' not in payload
+
+
+# ── Build Box Process Payload ───────────────────────────────────────
+
+
+class TestBuildBoxProcessPayload:
+    def test_basic_payload(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': ['server.py'],
+                'env': {'KEY': 'val'},
+            },
+        )
+        payload = s._build_box_process_payload()
+        assert payload['command'] == 'python'
+        assert payload['args'] == ['server.py']
+        assert payload['env'] == {'KEY': 'val'}
+        assert payload['cwd'] == '/workspace'
+
+    def test_path_rewriting_applied(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': '/home/user/mcp/venv/bin/python',
+                'args': ['/home/user/mcp/server.py', '--config', '/home/user/mcp/config.json'],
+                'env': {},
+                'box': {'host_path': '/home/user/mcp'},
+            },
+        )
+        payload = s._build_box_process_payload()
+        # venv python is replaced with plain 'python' (deps installed in-container)
+        assert payload['command'] == 'python'
+        assert payload['args'] == ['/workspace/server.py', '--config', '/workspace/config.json']
+
+    def test_non_matching_args_not_rewritten(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': ['/opt/other/server.py', '--flag'],
+                'env': {},
+                'box': {'host_path': '/home/user/mcp'},
+            },
+        )
+        payload = s._build_box_process_payload()
+        assert payload['command'] == 'python'
+        assert payload['args'] == ['/opt/other/server.py', '--flag']
+
+
+# ── get_runtime_info_dict ───────────────────────────────────────────
+
+
+class TestGetRuntimeInfoDict:
+    def test_non_stdio_session(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'test-uuid',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+            },
+        )
+        info = s.get_runtime_info_dict()
+        assert info['status'] == 'connecting'
+        assert 'box_session_id' not in info
+
+    def test_runtime_tools_include_parameters(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'test-uuid',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+            },
+        )
+        s.functions = [
+            SimpleNamespace(
+                name='create-service',
+                description='Create a service',
+                parameters={
+                    'type': 'object',
+                    'properties': {
+                        'project_id': {'type': 'string'},
+                    },
+                    'required': ['project_id'],
+                },
+            )
+        ]
+
+        info = s.get_runtime_info_dict()
+
+        assert info['tools'][0]['parameters']['properties']['project_id']['type'] == 'string'
+        assert info['tools'][0]['parameters']['required'] == ['project_id']
+
+    def test_stdio_session_includes_box_info(self, mcp_module):
+        ap = _make_ap()
+        ap.box_service.available = True
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'test-uuid',
+                'mode': 'stdio',
+                'command': 'python',
+                'args': [],
+            },
+            ap=ap,
+        )
+        info = s.get_runtime_info_dict()
+        assert info['box_session_id'] == 'mcp-shared'
+        assert info['box_enabled'] is True
+
+    def test_stdio_session_refuses_when_box_unavailable(self, mcp_module):
+        """Policy: when Box is configured but unavailable (disabled in config
+        OR connection failed), stdio MCP servers are NOT treated as box-stdio.
+        ``_init_stdio_python_server`` will raise a clear refusal at start
+        time; until then, the runtime info simply omits box_session_id so the
+        UI can render the disabled state cleanly."""
+        ap = _make_ap()
+        ap.box_service.available = False
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'test-uuid',
+                'mode': 'stdio',
+                'command': 'python',
+                'args': [],
+            },
+            ap=ap,
+        )
+        info = s.get_runtime_info_dict()
+        assert 'box_session_id' not in info
+        assert 'box_enabled' not in info
+
+    def test_stdio_session_without_box_service_uses_local_stdio(self, mcp_module):
+        ap = _make_ap()
+        del ap.box_service
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'test-uuid',
+                'mode': 'stdio',
+                'command': 'python',
+                'args': [],
+            },
+            ap=ap,
+        )
+        info = s.get_runtime_info_dict()
+        assert 'box_session_id' not in info
+
+
+# ── Box config parsing ──────────────────────────────────────────────
+
+
+class TestBoxConfigParsing:
+    def test_box_config_parsed_from_server_config(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+                'box': {'image': 'node:20', 'host_path': '/home/user/mcp'},
+            },
+        )
+        assert isinstance(s.box_config, mcp_module.MCPServerBoxConfig)
+        assert s.box_config.image == 'node:20'
+        assert s.box_config.host_path == '/home/user/mcp'
+
+    def test_missing_box_key_uses_defaults(self, mcp_module):
+        s = _make_session(
+            mcp_module,
+            {
+                'name': 'test',
+                'uuid': 'u1',
+                'mode': 'sse',
+                'command': 'python',
+                'args': [],
+            },
+        )
+        assert isinstance(s.box_config, mcp_module.MCPServerBoxConfig)
+        assert s.box_config.image is None
+        assert s.box_config.host_path_mode == 'ro'
+
+
+@pytest.mark.asyncio
+async def test_init_box_stdio_server_stages_host_path_in_shared_workspace(mcp_module, tmp_path):
+    mcp_stdio_module = sys.modules['langbot.pkg.provider.tools.loaders.mcp_stdio']
+
+    class FakeClientSession:
+        def __init__(self, *_args):
+            pass
+
+        async def __aenter__(self):
+            return self
+
+        async def __aexit__(self, exc_type, exc, tb):
+            return False
+
+        async def initialize(self):
+            return None
+
+    @asynccontextmanager
+    async def fake_websocket_client(_url: str):
+        yield ('read-stream', 'write-stream')
+
+    mcp_stdio_module.ClientSession = FakeClientSession
+    mcp_stdio_module.websocket_client = fake_websocket_client
+
+    ap = _make_ap()
+    ap.box_service.available = True
+    ap.box_service.default_workspace = str(tmp_path / 'shared-box-workspace')
+    ap.box_service.create_session = AsyncMock(return_value={})
+    ap.box_service.build_spec = Mock(return_value='validated-spec')
+    ap.box_service.client = SimpleNamespace(
+        execute=AsyncMock(return_value=SimpleNamespace(ok=True, stderr='', exit_code=0))
+    )
+    ap.box_service.start_managed_process = AsyncMock(return_value={})
+    ap.box_service.get_managed_process_websocket_url = Mock(return_value='ws://box.example/process')
+
+    host_path = tmp_path / 'mcp-source'
+    host_path.mkdir()
+    server_file = host_path / 'server.py'
+    server_file.write_text('print("hello")\n', encoding='utf-8')
+
+    session = _make_session(
+        mcp_module,
+        {
+            'name': 'test',
+            'uuid': 'u1',
+            'mode': 'stdio',
+            'command': str(host_path / '.venv' / 'bin' / 'python'),
+            'args': [str(server_file)],
+            'box': {'host_path': str(host_path)},
+        },
+        ap=ap,
+    )
+
+    await session._init_box_stdio_server()
+    await session.exit_stack.aclose()
+
+    assert ap.box_service.create_session.await_count == 1
+    session_payload = ap.box_service.create_session.await_args.args[0]
+    assert session_payload['session_id'] == 'mcp-shared'
+    assert 'host_path' not in session_payload
+    assert ap.box_service.build_spec.call_count == 1
+    assert ap.box_service.build_spec.call_args.kwargs.get('skip_host_mount_validation', False) is False
+    assert ap.box_service.build_spec.call_args.args[0]['host_path'] == str(host_path)
+
+    staged_file = tmp_path / 'shared-box-workspace' / '.mcp' / 'u1' / 'workspace' / 'server.py'
+    assert staged_file.read_text(encoding='utf-8') == 'print("hello")\n'
+
+    process_payload = ap.box_service.start_managed_process.await_args.args[1]
+    assert process_payload['process_id'] == 'u1'
+    assert process_payload['command'] == 'python'
+    assert process_payload['args'] == ['/workspace/.mcp/u1/workspace/server.py']
+    assert process_payload['cwd'] == '/workspace/.mcp/u1/workspace'

tests/unit_tests/provider/test_model_service.py

@@ -169,6 +169,7 @@ async def test_updated_llm_model_is_immediately_usable_by_local_agent_pipeline()
     ap.logger = Mock()
     ap.persistence_mgr = SimpleNamespace(execute_async=AsyncMock())
     ap.tool_mgr = SimpleNamespace(get_all_tools=AsyncMock(return_value=[]))
+    ap.skill_mgr = None  # PreProcessor only uses skill_mgr for the local-agent skill-binding branch
     ap.plugin_connector = SimpleNamespace(
         emit_event=AsyncMock(return_value=SimpleNamespace(event=SimpleNamespace(default_prompt=[], prompt=[])))
     )

tests/unit_tests/provider/test_skill_tools.py

@@ -0,0 +1,479 @@
+from __future__ import annotations
+
+import os
+import tempfile
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, Mock
+
+import pytest
+
+
+def _make_ap(logger=None):
+    ap = SimpleNamespace()
+    ap.logger = logger or Mock()
+    ap.persistence_mgr = Mock()
+    ap.persistence_mgr.execute_async = AsyncMock(return_value=Mock(all=Mock(return_value=[])))
+    ap.persistence_mgr.serialize_model = Mock(side_effect=lambda cls, row: row)
+    return ap
+
+
+def _make_skill_data(
+    name='test-skill',
+    instructions='Do something',
+    package_root='',
+    entry_file='SKILL.md',
+    **kwargs,
+):
+    return {
+        'name': name,
+        'display_name': kwargs.pop('display_name', name),
+        'description': kwargs.pop('description', f'Description of {name}'),
+        'instructions': instructions,
+        'package_root': package_root,
+        'entry_file': entry_file,
+        **kwargs,
+    }
+
+
+class TestSkillManagerCache:
+    """The Box runtime is the only source of truth — SkillManager just holds
+    an in-memory cache populated by ``reload_skills``. There is no local
+    filesystem reader anymore."""
+
+    def test_refresh_skill_from_disk_reports_cache_presence(self):
+        """Box is the only source of truth for skill content. refresh_skill_from_disk
+        now just reports whether the skill is still in the in-memory cache —
+        the actual content refresh is driven by SkillService awaiting
+        ``reload_skills`` after every Box mutation."""
+        from langbot.pkg.skill.manager import SkillManager
+
+        ap = _make_ap()
+        mgr = SkillManager(ap)
+
+        # Empty cache → returns False
+        assert mgr.refresh_skill_from_disk('test-skill') is False
+
+        # Cache populated → returns True; method does NOT mutate the cache
+        cached = _make_skill_data(name='test-skill', instructions='Cached')
+        mgr.skills['test-skill'] = cached
+        assert mgr.refresh_skill_from_disk('test-skill') is True
+        assert mgr.skills['test-skill'] is cached
+        assert mgr.refresh_skill_from_disk('') is False
+
+    @pytest.mark.asyncio
+    async def test_reload_skills_drops_box_skills_with_missing_package_root(self):
+        """When Box reports a skill whose package_root is gone from the
+        LangBot-visible filesystem, the cache must drop it instead of
+        keeping a stale entry that would later produce a bad mount."""
+        from langbot.pkg.skill.manager import SkillManager
+
+        with tempfile.TemporaryDirectory() as live_dir:
+            ghost_dir = os.path.join(live_dir, '_does_not_exist')
+            box_service = SimpleNamespace(
+                available=True,
+                list_skills=AsyncMock(
+                    return_value=[
+                        _make_skill_data(name='alive', package_root=live_dir),
+                        _make_skill_data(name='ghost', package_root=ghost_dir),
+                    ]
+                ),
+            )
+
+            ap = _make_ap()
+            ap.box_service = box_service
+            mgr = SkillManager(ap)
+
+            await mgr.reload_skills()
+
+        assert list(mgr.skills) == ['alive']
+        # Warning fired with the dropped skill name so operators can see it.
+        warning_messages = [str(call.args[0]) for call in ap.logger.warning.call_args_list]
+        assert any('ghost' in msg and 'package_root missing' in msg for msg in warning_messages)
+
+
+class TestSkillActivationHelper:
+    """Skill activation is now Tool-Call based.
+
+    The legacy text-marker mechanism (``[ACTIVATE_SKILL: x]`` detection,
+    ``build_activation_prompt_for_skills``, ``remove_activation_marker``,
+    ``prepare_skill_activation``) has been removed. Activation now goes
+    through ``skill.activation.register_activated_skill``, invoked by the
+    ``activate`` Tool Call.
+    """
+
+    def test_register_activated_skill_records_known_skill(self):
+        from langbot.pkg.skill.activation import register_activated_skill
+        from langbot.pkg.provider.tools.loaders.skill import ACTIVATED_SKILLS_KEY
+        from langbot.pkg.skill.manager import SkillManager
+
+        ap = _make_ap()
+        mgr = SkillManager(ap)
+        mgr.skills = {
+            'primary': _make_skill_data(name='primary', instructions='Primary instructions'),
+        }
+        ap.skill_mgr = mgr
+
+        query = SimpleNamespace(variables={})
+
+        assert register_activated_skill(ap, query, 'primary') is True
+        assert set(query.variables[ACTIVATED_SKILLS_KEY].keys()) == {'primary'}
+        assert query.variables[ACTIVATED_SKILLS_KEY]['primary']['name'] == 'primary'
+
+    def test_register_activated_skill_rejects_unknown_skill(self):
+        from langbot.pkg.skill.activation import register_activated_skill
+        from langbot.pkg.provider.tools.loaders.skill import ACTIVATED_SKILLS_KEY
+        from langbot.pkg.skill.manager import SkillManager
+
+        ap = _make_ap()
+        mgr = SkillManager(ap)
+        mgr.skills = {'primary': _make_skill_data(name='primary')}
+        ap.skill_mgr = mgr
+
+        query = SimpleNamespace(variables={})
+
+        assert register_activated_skill(ap, query, 'missing') is False
+        assert ACTIVATED_SKILLS_KEY not in query.variables
+
+    def test_register_activated_skill_without_skill_manager_returns_false(self):
+        from langbot.pkg.skill.activation import register_activated_skill
+
+        ap = _make_ap()  # no skill_mgr attribute
+        query = SimpleNamespace(variables={})
+
+        assert register_activated_skill(ap, query, 'primary') is False
+
+
+class TestSkillPathHelpers:
+    def test_get_visible_skills_filters_by_bound_names(self):
+        from langbot.pkg.provider.tools.loaders.skill import PIPELINE_BOUND_SKILLS_KEY, get_visible_skills
+
+        ap = _make_ap()
+        ap.skill_mgr = SimpleNamespace(
+            skills={
+                'visible': _make_skill_data(name='visible'),
+                'hidden': _make_skill_data(name='hidden'),
+            }
+        )
+        query = SimpleNamespace(variables={PIPELINE_BOUND_SKILLS_KEY: ['visible']})
+
+        result = get_visible_skills(ap, query)
+
+        assert list(result.keys()) == ['visible']
+
+    def test_resolve_virtual_skill_path_allows_visible_skill_reads(self):
+        from langbot.pkg.provider.tools.loaders.skill import (
+            PIPELINE_BOUND_SKILLS_KEY,
+            resolve_virtual_skill_path,
+        )
+
+        ap = _make_ap()
+        ap.skill_mgr = SimpleNamespace(skills={'demo': _make_skill_data(name='demo')})
+        query = SimpleNamespace(variables={PIPELINE_BOUND_SKILLS_KEY: ['demo']})
+
+        skill, rewritten = resolve_virtual_skill_path(
+            ap,
+            query,
+            '/workspace/.skills/demo/SKILL.md',
+            include_visible=True,
+            include_activated=False,
+        )
+
+        assert skill['name'] == 'demo'
+        assert rewritten == '/workspace/SKILL.md'
+
+    def test_build_skill_session_id_uses_name_based_identifier(self):
+        from langbot.pkg.provider.tools.loaders.skill import build_skill_session_id
+
+        with_launcher = build_skill_session_id(
+            {'name': 'writer'},
+            SimpleNamespace(query_id=42, launcher_type='person', launcher_id='123'),
+        )
+        fallback = build_skill_session_id({'name': 'writer'}, SimpleNamespace(query_id=99))
+
+        assert with_launcher == 'skill-person_123-writer'
+        assert fallback == 'skill-99-writer'
+
+    def test_should_prepare_skill_python_env_detects_manifests_and_venv(self):
+        from langbot.pkg.provider.tools.loaders.skill import should_prepare_skill_python_env
+
+        with tempfile.TemporaryDirectory() as tmpdir:
+            assert should_prepare_skill_python_env(tmpdir) is False
+
+            with open(os.path.join(tmpdir, 'requirements.txt'), 'w', encoding='utf-8') as f:
+                f.write('requests==2.32.0\n')
+            assert should_prepare_skill_python_env(tmpdir) is True
+
+        with tempfile.TemporaryDirectory() as tmpdir:
+            os.makedirs(os.path.join(tmpdir, '.venv'))
+            assert should_prepare_skill_python_env(tmpdir) is True
+
+    def test_wrap_skill_command_with_python_env_bootstraps_then_runs_command(self):
+        from langbot.pkg.provider.tools.loaders.skill import wrap_skill_command_with_python_env
+
+        command = wrap_skill_command_with_python_env('python scripts/run.py')
+
+        assert 'python -m venv "$_LB_VENV_DIR"' in command
+        assert 'export VIRTUAL_ENV="$_LB_VENV_DIR"' in command
+        assert command.rstrip().endswith('python scripts/run.py')
+
+
+class TestSkillToolLoader:
+    """The skill tool surface is now just ``activate`` + ``register_skill``.
+
+    The legacy CRUD authoring tools (create/list/get/update/delete/
+    import_skill_from_directory/reload_skills) were removed; skill CRUD is
+    handled by SkillService via the HTTP API / web UI instead.
+    """
+
+    @pytest.mark.asyncio
+    async def test_activate_returns_instructions_and_registers_skill(self):
+        from langbot.pkg.provider.tools.loaders.skill_authoring import (
+            ACTIVATE_SKILL_TOOL_NAME,
+            SkillToolLoader,
+        )
+        from langbot.pkg.provider.tools.loaders.skill import ACTIVATED_SKILLS_KEY
+
+        skill = _make_skill_data(name='demo', package_root='/data/skills/demo', instructions='Step 1')
+        ap = _make_ap()
+        ap.skill_mgr = SimpleNamespace(
+            skills={'demo': skill},
+            get_skill_by_name=lambda name: skill if name == 'demo' else None,
+        )
+
+        loader = SkillToolLoader(ap)
+        query = SimpleNamespace(variables={})
+
+        result = await loader.invoke_tool(ACTIVATE_SKILL_TOOL_NAME, {'skill_name': 'demo'}, query)
+
+        assert result['activated'] is True
+        assert result['skill_name'] == 'demo'
+        assert result['mount_path'] == '/workspace/.skills/demo'
+        assert 'Step 1' in result['content']
+        assert set(query.variables[ACTIVATED_SKILLS_KEY].keys()) == {'demo'}
+
+    @pytest.mark.asyncio
+    async def test_activate_unknown_skill_raises(self):
+        from langbot.pkg.provider.tools.loaders.skill_authoring import (
+            ACTIVATE_SKILL_TOOL_NAME,
+            SkillToolLoader,
+        )
+
+        ap = _make_ap()
+        ap.skill_mgr = SimpleNamespace(
+            skills={'demo': _make_skill_data(name='demo')},
+            get_skill_by_name=lambda name: None,
+        )
+
+        loader = SkillToolLoader(ap)
+
+        with pytest.raises(ValueError, match='not found'):
+            await loader.invoke_tool(
+                ACTIVATE_SKILL_TOOL_NAME,
+                {'skill_name': 'ghost'},
+                SimpleNamespace(variables={}),
+            )
+
+    @pytest.mark.asyncio
+    async def test_register_skill_scans_directory_and_creates_skill(self):
+        from langbot.pkg.provider.tools.loaders.skill_authoring import (
+            REGISTER_SKILL_TOOL_NAME,
+            SkillToolLoader,
+        )
+
+        with tempfile.TemporaryDirectory() as tmpdir:
+            repo_dir = os.path.join(tmpdir, 'repo')
+            os.makedirs(repo_dir)
+
+            ap = _make_ap()
+            ap.box_service = SimpleNamespace(default_workspace=tmpdir, available=True)
+            ap.skill_service = SimpleNamespace(
+                scan_directory_async=AsyncMock(
+                    return_value={
+                        'name': 'cloned-skill',
+                        'display_name': 'Cloned Skill',
+                        'description': 'Imported from clone',
+                        'instructions': 'Do work',
+                    }
+                ),
+                create_skill=AsyncMock(
+                    return_value=_make_skill_data(name='cloned-skill', package_root=os.path.realpath(repo_dir))
+                ),
+            )
+
+            loader = SkillToolLoader(ap)
+            result = await loader.invoke_tool(
+                REGISTER_SKILL_TOOL_NAME,
+                {'path': '/workspace/repo'},
+                SimpleNamespace(),
+            )
+
+        ap.skill_service.scan_directory_async.assert_awaited_once_with(os.path.realpath(repo_dir))
+        ap.skill_service.create_skill.assert_awaited_once_with(
+            {
+                'name': 'cloned-skill',
+                'display_name': 'Cloned Skill',
+                'description': 'Imported from clone',
+                'instructions': 'Do work',
+                'package_root': os.path.realpath(repo_dir),
+            }
+        )
+        assert result['registered'] is True
+        assert result['skill_name'] == 'cloned-skill'
+        assert result['source_path'] == '/workspace/repo'
+
+    @pytest.mark.asyncio
+    async def test_register_skill_rejects_workspace_escape(self):
+        from langbot.pkg.provider.tools.loaders.skill_authoring import (
+            REGISTER_SKILL_TOOL_NAME,
+            SkillToolLoader,
+        )
+
+        with tempfile.TemporaryDirectory() as tmpdir:
+            ap = _make_ap()
+            ap.box_service = SimpleNamespace(default_workspace=tmpdir, available=True)
+            ap.skill_service = SimpleNamespace(scan_directory_async=AsyncMock(), create_skill=AsyncMock())
+
+            loader = SkillToolLoader(ap)
+
+            with pytest.raises(ValueError, match='escapes the workspace boundary'):
+                await loader.invoke_tool(
+                    REGISTER_SKILL_TOOL_NAME,
+                    {'path': '/workspace/../../etc'},
+                    SimpleNamespace(),
+                )
+
+    @pytest.mark.asyncio
+    async def test_register_skill_requires_skill_service(self):
+        from langbot.pkg.provider.tools.loaders.skill_authoring import (
+            REGISTER_SKILL_TOOL_NAME,
+            SkillToolLoader,
+        )
+
+        with tempfile.TemporaryDirectory() as tmpdir:
+            ap = _make_ap()  # no skill_service attribute
+            ap.box_service = SimpleNamespace(default_workspace=tmpdir, available=True)
+
+            loader = SkillToolLoader(ap)
+
+            with pytest.raises(ValueError, match='Skill service not available'):
+                await loader.invoke_tool(
+                    REGISTER_SKILL_TOOL_NAME,
+                    {'path': '/workspace/foo'},
+                    SimpleNamespace(),
+                )
+
+    @pytest.mark.asyncio
+    async def test_tools_hidden_when_sandbox_backend_unavailable(self):
+        from langbot.pkg.provider.tools.loaders.skill_authoring import SkillToolLoader
+
+        ap = _make_ap()
+        ap.skill_mgr = SimpleNamespace(skills={})
+        ap.box_service = SimpleNamespace(
+            available=True,
+            get_status=AsyncMock(return_value={'backend': {'available': False}}),
+        )
+
+        loader = SkillToolLoader(ap)
+        await loader.initialize()
+
+        assert await loader.get_tools() == []
+        assert await loader.has_tool('activate') is False
+        assert await loader.has_tool('register_skill') is False
+
+    @pytest.mark.asyncio
+    async def test_tools_exposed_when_sandbox_backend_available(self):
+        from langbot.pkg.provider.tools.loaders.skill_authoring import SkillToolLoader
+
+        ap = _make_ap()
+        ap.skill_mgr = SimpleNamespace(skills={'demo': _make_skill_data(name='demo')})
+        ap.box_service = SimpleNamespace(
+            available=True,
+            get_status=AsyncMock(return_value={'backend': {'available': True}}),
+        )
+
+        loader = SkillToolLoader(ap)
+        await loader.initialize()
+
+        tools = await loader.get_tools()
+
+        assert sorted(tool.name for tool in tools) == ['activate', 'register_skill']
+        assert await loader.has_tool('activate') is True
+        assert await loader.has_tool('register_skill') is True
+
+
+class TestNativeToolLoaderSkillPaths:
+    @pytest.mark.asyncio
+    async def test_read_visible_skill_file(self):
+        from langbot.pkg.provider.tools.loaders.native import NativeToolLoader
+        from langbot.pkg.provider.tools.loaders.skill import PIPELINE_BOUND_SKILLS_KEY
+
+        with tempfile.TemporaryDirectory() as tmpdir:
+            skill_md = os.path.join(tmpdir, 'SKILL.md')
+            with open(skill_md, 'w', encoding='utf-8') as f:
+                f.write('demo instructions')
+
+            ap = _make_ap()
+            ap.box_service = SimpleNamespace(available=True, default_workspace=tmpdir)
+            ap.skill_mgr = SimpleNamespace(skills={'demo': _make_skill_data(name='demo', package_root=tmpdir)})
+            loader = NativeToolLoader(ap)
+
+            result = await loader.invoke_tool(
+                'read',
+                {'path': '/workspace/.skills/demo/SKILL.md'},
+                SimpleNamespace(query_id='q1', variables={PIPELINE_BOUND_SKILLS_KEY: ['demo']}),
+            )
+
+            assert result == {'ok': True, 'content': 'demo instructions'}
+
+    @pytest.mark.asyncio
+    async def test_exec_in_activated_skill_mount_rewrites_command_and_refreshes(self):
+        from langbot.pkg.provider.tools.loaders.native import NativeToolLoader
+        from langbot.pkg.provider.tools.loaders.skill import register_activated_skill
+
+        with tempfile.TemporaryDirectory() as tmpdir:
+            ap = _make_ap()
+            ap.box_service = SimpleNamespace(
+                available=True,
+                default_workspace=tmpdir,
+                execute_tool=AsyncMock(return_value={'ok': True}),
+            )
+            ap.skill_mgr = SimpleNamespace(refresh_skill_from_disk=Mock())
+            loader = NativeToolLoader(ap)
+
+            query = SimpleNamespace(query_id='q1', launcher_type='person', launcher_id='123', variables={})
+            register_activated_skill(query, _make_skill_data(name='demo', package_root=tmpdir))
+
+            result = await loader.invoke_tool(
+                'exec',
+                {
+                    'command': 'python /workspace/.skills/demo/scripts/run.py',
+                    'workdir': '/workspace/.skills/demo',
+                },
+                query,
+            )
+
+            assert result == {'ok': True}
+            tool_parameters = ap.box_service.execute_tool.await_args.args[0]
+            assert tool_parameters['command'] == 'python /workspace/.skills/demo/scripts/run.py'
+            assert tool_parameters['workdir'] == '/workspace/.skills/demo'
+            ap.skill_mgr.refresh_skill_from_disk.assert_called_once_with('demo')
+
+    @pytest.mark.asyncio
+    async def test_write_requires_skill_activation(self):
+        from langbot.pkg.provider.tools.loaders.native import NativeToolLoader
+        from langbot.pkg.provider.tools.loaders.skill import PIPELINE_BOUND_SKILLS_KEY
+
+        with tempfile.TemporaryDirectory() as tmpdir:
+            ap = _make_ap()
+            ap.box_service = SimpleNamespace(available=True, default_workspace=tmpdir)
+            ap.skill_mgr = SimpleNamespace(skills={'demo': _make_skill_data(name='demo', package_root=tmpdir)})
+            loader = NativeToolLoader(ap)
+
+            query = SimpleNamespace(query_id='q1', variables={PIPELINE_BOUND_SKILLS_KEY: ['demo']})
+
+            with pytest.raises(ValueError, match='Skill "demo" is not available at this path'):
+                await loader.invoke_tool(
+                    'write',
+                    {'path': '/workspace/.skills/demo/notes.txt', 'content': 'hi'},
+                    query,
+                )

tests/unit_tests/provider/test_tool_manager.py

@@ -4,6 +4,7 @@ Tests cover:
 - Tool schema generation for OpenAI and Anthropic
 - Tool execution dispatch
 """
+
 from __future__ import annotations
 
 import pytest
@@ -52,11 +53,12 @@ class TestToolManagerSchemaGeneration:
     @pytest.fixture
     def sample_tools(self):
         """Create sample LLMTool list for testing."""
+
         def dummy_weather_func(**kwargs):
-            return "weather result"
+            return 'weather result'
 
         def dummy_calc_func(**kwargs):
-            return "calc result"
+            return 'calc result'
 
         tools = [
             resource_tool.LLMTool(
@@ -65,15 +67,10 @@ class TestToolManagerSchemaGeneration:
                 description='Get current weather for a location',
                 parameters={
                     'type': 'object',
-                    'properties': {
-                        'location': {
-                            'type': 'string',
-                            'description': 'City name'
-                        }
-                    },
-                    'required': ['location']
+                    'properties': {'location': {'type': 'string', 'description': 'City name'}},
+                    'required': ['location'],
                 },
-                func=dummy_weather_func
+                func=dummy_weather_func,
             ),
             resource_tool.LLMTool(
                 name='calculate',
@@ -81,15 +78,10 @@ class TestToolManagerSchemaGeneration:
                 description='Perform a calculation',
                 parameters={
                     'type': 'object',
-                    'properties': {
-                        'expression': {
-                            'type': 'string',
-                            'description': 'Math expression'
-                        }
-                    },
-                    'required': ['expression']
+                    'properties': {'expression': {'type': 'string', 'description': 'Math expression'}},
+                    'required': ['expression'],
                 },
-                func=dummy_calc_func
+                func=dummy_calc_func,
             ),
         ]
         return tools
@@ -188,26 +180,48 @@ class TestToolManagerExecuteFuncCall:
 
     @pytest.fixture
     def mock_app_with_loaders(self):
-        """Create mock app with mock tool loaders."""
+        """Create mock app with mock tool loaders.
+
+        Returns (app, plugin_loader, mcp_loader). The native and skill loaders
+        are attached directly to the app for tests that don't need to assert
+        against them — they all default to ``has_tool == False`` so the
+        execute_func_call probe falls through to the plugin/mcp pair.
+        """
         mock_app = Mock()
         mock_app.logger = Mock()
 
+        def _make_inert_loader():
+            loader = Mock()
+            loader.has_tool = AsyncMock(return_value=False)
+            loader.invoke_tool = AsyncMock(return_value=None)
+            loader.initialize = AsyncMock()
+            loader.shutdown = AsyncMock()
+            return loader
+
         # Create mock plugin loader
-        mock_plugin_loader = Mock()
-        mock_plugin_loader.has_tool = AsyncMock(return_value=False)
+        mock_plugin_loader = _make_inert_loader()
         mock_plugin_loader.invoke_tool = AsyncMock(return_value='plugin_result')
-        mock_plugin_loader.initialize = AsyncMock()
-        mock_plugin_loader.shutdown = AsyncMock()
 
         # Create mock MCP loader
-        mock_mcp_loader = Mock()
-        mock_mcp_loader.has_tool = AsyncMock(return_value=False)
+        mock_mcp_loader = _make_inert_loader()
         mock_mcp_loader.invoke_tool = AsyncMock(return_value='mcp_result')
-        mock_mcp_loader.initialize = AsyncMock()
-        mock_mcp_loader.shutdown = AsyncMock()
+
+        # Stash inert native/skill loaders so the ToolManager probe order
+        # (native → plugin → mcp → skill) doesn't AttributeError. Tests that
+        # need to override these can replace the attributes on the manager.
+        mock_app._inert_native_loader = _make_inert_loader()
+        mock_app._inert_skill_loader = _make_inert_loader()
 
         return mock_app, mock_plugin_loader, mock_mcp_loader
 
+    @staticmethod
+    def _wire_loaders(manager, mock_app, plugin_loader, mcp_loader):
+        """Attach all four loaders (native + plugin + mcp + skill) to manager."""
+        manager.native_tool_loader = mock_app._inert_native_loader
+        manager.plugin_tool_loader = plugin_loader
+        manager.mcp_tool_loader = mcp_loader
+        manager.skill_tool_loader = mock_app._inert_skill_loader
+
     @pytest.fixture
     def sample_query(self):
         """Create sample query for testing."""
@@ -215,9 +229,7 @@ class TestToolManagerExecuteFuncCall:
         return query
 
     @pytest.mark.asyncio
-    async def test_execute_calls_plugin_loader_when_has_tool(
-        self, mock_app_with_loaders, sample_query
-    ):
+    async def test_execute_calls_plugin_loader_when_has_tool(self, mock_app_with_loaders, sample_query):
         """Test that execute_func_call uses plugin loader when tool exists there."""
         toolmgr = get_toolmgr_module()
 
@@ -225,26 +237,17 @@ class TestToolManagerExecuteFuncCall:
         mock_plugin_loader.has_tool = AsyncMock(return_value=True)
 
         manager = toolmgr.ToolManager(mock_app)
-        manager.plugin_tool_loader = mock_plugin_loader
-        manager.mcp_tool_loader = mock_mcp_loader
+        self._wire_loaders(manager, mock_app, mock_plugin_loader, mock_mcp_loader)
 
-        result = await manager.execute_func_call(
-            'test_tool',
-            {'param': 'value'},
-            sample_query
-        )
+        result = await manager.execute_func_call('test_tool', {'param': 'value'}, sample_query)
 
         assert result == 'plugin_result'
-        mock_plugin_loader.invoke_tool.assert_called_once_with(
-            'test_tool', {'param': 'value'}, sample_query
-        )
+        mock_plugin_loader.invoke_tool.assert_called_once_with('test_tool', {'param': 'value'}, sample_query)
         # MCP loader should not be called
         mock_mcp_loader.invoke_tool.assert_not_called()
 
     @pytest.mark.asyncio
-    async def test_execute_calls_mcp_loader_when_plugin_not_found(
-        self, mock_app_with_loaders, sample_query
-    ):
+    async def test_execute_calls_mcp_loader_when_plugin_not_found(self, mock_app_with_loaders, sample_query):
         """Test that execute_func_call uses MCP loader when plugin doesn't have tool."""
         toolmgr = get_toolmgr_module()
 
@@ -253,24 +256,15 @@ class TestToolManagerExecuteFuncCall:
         mock_mcp_loader.has_tool = AsyncMock(return_value=True)
 
         manager = toolmgr.ToolManager(mock_app)
-        manager.plugin_tool_loader = mock_plugin_loader
-        manager.mcp_tool_loader = mock_mcp_loader
+        self._wire_loaders(manager, mock_app, mock_plugin_loader, mock_mcp_loader)
 
-        result = await manager.execute_func_call(
-            'test_tool',
-            {'param': 'value'},
-            sample_query
-        )
+        result = await manager.execute_func_call('test_tool', {'param': 'value'}, sample_query)
 
         assert result == 'mcp_result'
-        mock_mcp_loader.invoke_tool.assert_called_once_with(
-            'test_tool', {'param': 'value'}, sample_query
-        )
+        mock_mcp_loader.invoke_tool.assert_called_once_with('test_tool', {'param': 'value'}, sample_query)
 
     @pytest.mark.asyncio
-    async def test_execute_raises_when_tool_not_found(
-        self, mock_app_with_loaders, sample_query
-    ):
+    async def test_execute_raises_when_tool_not_found(self, mock_app_with_loaders, sample_query):
         """Test that execute_func_call raises ValueError when tool not found."""
         toolmgr = get_toolmgr_module()
 
@@ -279,20 +273,13 @@ class TestToolManagerExecuteFuncCall:
         mock_mcp_loader.has_tool = AsyncMock(return_value=False)
 
         manager = toolmgr.ToolManager(mock_app)
-        manager.plugin_tool_loader = mock_plugin_loader
-        manager.mcp_tool_loader = mock_mcp_loader
+        self._wire_loaders(manager, mock_app, mock_plugin_loader, mock_mcp_loader)
 
         with pytest.raises(ValueError, match='未找到工具'):
-            await manager.execute_func_call(
-                'unknown_tool',
-                {},
-                sample_query
-            )
+            await manager.execute_func_call('unknown_tool', {}, sample_query)
 
     @pytest.mark.asyncio
-    async def test_plugin_loader_checked_first(
-        self, mock_app_with_loaders, sample_query
-    ):
+    async def test_plugin_loader_checked_first(self, mock_app_with_loaders, sample_query):
         """Test that plugin loader is checked before MCP loader."""
         toolmgr = get_toolmgr_module()
 
@@ -302,8 +289,7 @@ class TestToolManagerExecuteFuncCall:
         mock_mcp_loader.has_tool = AsyncMock(return_value=True)
 
         manager = toolmgr.ToolManager(mock_app)
-        manager.plugin_tool_loader = mock_plugin_loader
-        manager.mcp_tool_loader = mock_mcp_loader
+        self._wire_loaders(manager, mock_app, mock_plugin_loader, mock_mcp_loader)
 
         await manager.execute_func_call('test_tool', {}, sample_query)
 
@@ -317,20 +303,30 @@ class TestToolManagerShutdown:
 
     @pytest.mark.asyncio
     async def test_shutdown_calls_loader_shutdown(self):
-        """Test that shutdown calls shutdown on both loaders."""
+        """Test that shutdown calls shutdown on every registered loader."""
         toolmgr = get_toolmgr_module()
 
         mock_app = Mock()
-        mock_plugin_loader = Mock()
-        mock_plugin_loader.shutdown = AsyncMock()
-        mock_mcp_loader = Mock()
-        mock_mcp_loader.shutdown = AsyncMock()
+
+        def _make_loader():
+            loader = Mock()
+            loader.shutdown = AsyncMock()
+            return loader
+
+        mock_native_loader = _make_loader()
+        mock_plugin_loader = _make_loader()
+        mock_mcp_loader = _make_loader()
+        mock_skill_loader = _make_loader()
 
         manager = toolmgr.ToolManager(mock_app)
+        manager.native_tool_loader = mock_native_loader
         manager.plugin_tool_loader = mock_plugin_loader
         manager.mcp_tool_loader = mock_mcp_loader
+        manager.skill_tool_loader = mock_skill_loader
 
         await manager.shutdown()
 
+        mock_native_loader.shutdown.assert_called_once()
         mock_plugin_loader.shutdown.assert_called_once()
-        mock_mcp_loader.shutdown.assert_called_once()
+        mock_mcp_loader.shutdown.assert_called_once()
+        mock_skill_loader.shutdown.assert_called_once()

tests/unit_tests/provider/test_tool_manager_native.py

@@ -0,0 +1,250 @@
+from __future__ import annotations
+
+import os
+import tempfile
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, Mock
+
+import pytest
+
+import langbot_plugin.api.entities.builtin.resource.tool as resource_tool
+
+from langbot.pkg.provider.tools.loaders.native import NativeToolLoader
+from langbot.pkg.provider.tools.toolmgr import ToolManager
+
+
+class StubLoader:
+    def __init__(self, tools: list[resource_tool.LLMTool] | None = None, invoke_result=None):
+        self._tools = tools or []
+        self._invoke_result = invoke_result
+
+    async def get_tools(self, *_args, **_kwargs):
+        return self._tools
+
+    async def has_tool(self, name: str) -> bool:
+        return any(tool.name == name for tool in self._tools)
+
+    async def invoke_tool(self, name: str, parameters: dict, query):
+        return self._invoke_result(name, parameters, query) if callable(self._invoke_result) else self._invoke_result
+
+    async def shutdown(self):
+        return None
+
+
+def make_tool(name: str) -> resource_tool.LLMTool:
+    return resource_tool.LLMTool(
+        name=name,
+        human_desc=name,
+        description=name,
+        parameters={'type': 'object', 'properties': {}},
+        func=lambda parameters: parameters,
+    )
+
+
+@pytest.mark.asyncio
+async def test_tool_manager_omits_skill_authoring_tools_by_default():
+    manager = ToolManager(SimpleNamespace())
+    manager.native_tool_loader = StubLoader([make_tool('exec')])
+    manager.skill_tool_loader = StubLoader([make_tool('activate')])
+    manager.plugin_tool_loader = StubLoader([make_tool('plugin_tool')])
+    manager.mcp_tool_loader = StubLoader([make_tool('mcp_tool')])
+
+    tools = await manager.get_all_tools()
+
+    assert [tool.name for tool in tools] == ['exec', 'plugin_tool', 'mcp_tool']
+
+
+@pytest.mark.asyncio
+async def test_tool_manager_includes_skill_authoring_tools_when_requested():
+    manager = ToolManager(SimpleNamespace())
+    manager.native_tool_loader = StubLoader([make_tool('exec')])
+    manager.skill_tool_loader = StubLoader([make_tool('activate')])
+    manager.plugin_tool_loader = StubLoader([make_tool('plugin_tool')])
+    manager.mcp_tool_loader = StubLoader([make_tool('mcp_tool')])
+
+    tools = await manager.get_all_tools(include_skill_authoring=True)
+
+    assert [tool.name for tool in tools] == ['exec', 'activate', 'plugin_tool', 'mcp_tool']
+
+
+@pytest.mark.asyncio
+async def test_tool_manager_routes_native_tool_calls():
+    app = SimpleNamespace()
+    manager = ToolManager(app)
+    manager.native_tool_loader = StubLoader([make_tool('exec')], invoke_result={'backend': 'fake'})
+    manager.skill_tool_loader = StubLoader([make_tool('activate')])
+    manager.plugin_tool_loader = StubLoader([make_tool('plugin_tool')])
+    manager.mcp_tool_loader = StubLoader([make_tool('mcp_tool')])
+
+    result = await manager.execute_func_call('exec', {'command': 'pwd'}, query=Mock())
+
+    assert result == {'backend': 'fake'}
+
+
+@pytest.mark.asyncio
+async def test_native_tool_loader_hides_tools_when_box_unavailable():
+    loader = NativeToolLoader(SimpleNamespace(box_service=SimpleNamespace(available=False)))
+
+    assert await loader.get_tools() == []
+    for tool_name in ('exec', 'read', 'write', 'edit', 'glob', 'grep'):
+        assert await loader.has_tool(tool_name) is False
+
+
+@pytest.mark.asyncio
+async def test_native_tool_loader_exposes_all_tools_when_box_available():
+    box_service = SimpleNamespace(
+        available=True,
+        get_status=AsyncMock(return_value={'backend': {'available': True}}),
+    )
+    loader = NativeToolLoader(SimpleNamespace(box_service=box_service, logger=Mock()))
+    await loader.initialize()
+
+    tools = await loader.get_tools()
+
+    assert [tool.name for tool in tools] == ['exec', 'read', 'write', 'edit', 'glob', 'grep']
+    for tool_name in ('exec', 'read', 'write', 'edit', 'glob', 'grep'):
+        assert await loader.has_tool(tool_name) is True
+
+
+# ── read/write/edit file tool tests ─────────────────────────────
+
+
+def _make_loader_with_workspace(tmpdir: str) -> tuple[NativeToolLoader, Mock]:
+    logger = Mock()
+    box_service = SimpleNamespace(available=True, default_workspace=tmpdir)
+    ap = SimpleNamespace(box_service=box_service, logger=logger)
+    return NativeToolLoader(ap), logger
+
+
+def _make_query() -> Mock:
+    q = Mock()
+    q.query_id = 'test-query-1'
+    return q
+
+
+@pytest.mark.asyncio
+async def test_read_file():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        loader, _ = _make_loader_with_workspace(tmpdir)
+        with open(os.path.join(tmpdir, 'hello.txt'), 'w') as f:
+            f.write('hello world')
+
+        result = await loader.invoke_tool('read', {'path': '/workspace/hello.txt'}, _make_query())
+
+        assert result['ok'] is True
+        assert result['content'] == 'hello world'
+
+
+@pytest.mark.asyncio
+async def test_read_nonexistent_file():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        loader, _ = _make_loader_with_workspace(tmpdir)
+
+        result = await loader.invoke_tool('read', {'path': '/workspace/no_such.txt'}, _make_query())
+
+        assert result['ok'] is False
+        assert 'not found' in result['error'].lower()
+
+
+@pytest.mark.asyncio
+async def test_read_directory():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        loader, _ = _make_loader_with_workspace(tmpdir)
+        os.makedirs(os.path.join(tmpdir, 'subdir'))
+        with open(os.path.join(tmpdir, 'a.txt'), 'w') as f:
+            f.write('a')
+
+        result = await loader.invoke_tool('read', {'path': '/workspace'}, _make_query())
+
+        assert result['ok'] is True
+        assert result['is_directory'] is True
+        assert 'a.txt' in result['content']
+
+
+@pytest.mark.asyncio
+async def test_write_creates_file():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        loader, _ = _make_loader_with_workspace(tmpdir)
+
+        result = await loader.invoke_tool(
+            'write', {'path': '/workspace/new.txt', 'content': 'new content'}, _make_query()
+        )
+
+        assert result['ok'] is True
+        with open(os.path.join(tmpdir, 'new.txt')) as f:
+            assert f.read() == 'new content'
+
+
+@pytest.mark.asyncio
+async def test_write_creates_subdirectories():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        loader, _ = _make_loader_with_workspace(tmpdir)
+
+        result = await loader.invoke_tool(
+            'write', {'path': '/workspace/sub/deep/file.txt', 'content': 'nested'}, _make_query()
+        )
+
+        assert result['ok'] is True
+        with open(os.path.join(tmpdir, 'sub', 'deep', 'file.txt')) as f:
+            assert f.read() == 'nested'
+
+
+@pytest.mark.asyncio
+async def test_edit_replaces_unique_string():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        loader, _ = _make_loader_with_workspace(tmpdir)
+        with open(os.path.join(tmpdir, 'code.py'), 'w') as f:
+            f.write('def foo():\n    return 1\n')
+
+        result = await loader.invoke_tool(
+            'edit',
+            {'path': '/workspace/code.py', 'old_string': 'return 1', 'new_string': 'return 42'},
+            _make_query(),
+        )
+
+        assert result['ok'] is True
+        with open(os.path.join(tmpdir, 'code.py')) as f:
+            assert f.read() == 'def foo():\n    return 42\n'
+
+
+@pytest.mark.asyncio
+async def test_edit_rejects_ambiguous_match():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        loader, _ = _make_loader_with_workspace(tmpdir)
+        with open(os.path.join(tmpdir, 'dup.txt'), 'w') as f:
+            f.write('aaa\naaa\n')
+
+        result = await loader.invoke_tool(
+            'edit',
+            {'path': '/workspace/dup.txt', 'old_string': 'aaa', 'new_string': 'bbb'},
+            _make_query(),
+        )
+
+        assert result['ok'] is False
+        assert '2' in result['error']
+
+
+@pytest.mark.asyncio
+async def test_edit_rejects_missing_string():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        loader, _ = _make_loader_with_workspace(tmpdir)
+        with open(os.path.join(tmpdir, 'x.txt'), 'w') as f:
+            f.write('hello')
+
+        result = await loader.invoke_tool(
+            'edit',
+            {'path': '/workspace/x.txt', 'old_string': 'nope', 'new_string': 'yes'},
+            _make_query(),
+        )
+
+        assert result['ok'] is False
+        assert 'not found' in result['error'].lower()
+
+
+@pytest.mark.asyncio
+async def test_path_escape_blocked():
+    with tempfile.TemporaryDirectory() as tmpdir:
+        loader, _ = _make_loader_with_workspace(tmpdir)
+
+        with pytest.raises(ValueError, match='escapes'):
+            await loader.invoke_tool('read', {'path': '/workspace/../../etc/passwd'}, _make_query())

tests/unit_tests/test_paths.py

@@ -0,0 +1,23 @@
+from pathlib import Path
+
+from src.langbot.pkg.utils import paths
+
+
+def test_get_data_root_uses_source_root_in_repo_checkout():
+    data_root = Path(paths.get_data_root())
+    repo_root = Path(__file__).resolve().parents[2]
+
+    assert data_root == repo_root / 'data'
+
+
+def test_get_data_path_joins_under_data_root():
+    data_path = Path(paths.get_data_path('skills', 'demo-skill'))
+    repo_root = Path(__file__).resolve().parents[2]
+
+    assert data_path == repo_root / 'data' / 'skills' / 'demo-skill'
+
+
+def test_get_data_root_honors_env_override(monkeypatch, tmp_path):
+    monkeypatch.setenv('LANGBOT_DATA_ROOT', str(tmp_path / 'custom-data'))
+
+    assert Path(paths.get_data_root()) == (tmp_path / 'custom-data').resolve()

tests/unit_tests/test_preproc.py

@@ -0,0 +1,204 @@
+from __future__ import annotations
+
+import importlib
+import sys
+import types
+from types import SimpleNamespace
+from unittest.mock import AsyncMock, Mock
+
+import pytest
+
+from langbot_plugin.api.entities.builtin.pipeline.query import Query
+from langbot_plugin.api.entities.builtin.platform.entities import Friend
+from langbot_plugin.api.entities.builtin.platform.events import FriendMessage
+from langbot_plugin.api.entities.builtin.platform.message import MessageChain, Plain
+from langbot_plugin.api.entities.builtin.provider.message import Message
+from langbot_plugin.api.entities.builtin.provider.prompt import Prompt
+from langbot_plugin.api.entities.builtin.provider.session import Conversation, LauncherTypes, Session
+
+
+def _make_query() -> Query:
+    message_chain = MessageChain([Plain(text='create a skill')])
+    return Query(
+        query_id=1,
+        launcher_type=LauncherTypes.PERSON,
+        launcher_id='launcher-1',
+        sender_id='sender-1',
+        message_event=FriendMessage(
+            message_chain=message_chain,
+            time=0,
+            sender=Friend(id='sender-1', nickname='Tester', remark='Tester'),
+        ),
+        message_chain=message_chain,
+        bot_uuid='bot-1',
+        pipeline_uuid='pipe-1',
+        pipeline_config={
+            'ai': {
+                'runner': {'runner': 'local-agent'},
+                'local-agent': {
+                    'model': {'primary': 'model-1', 'fallbacks': []},
+                    'prompt': 'default',
+                    'knowledge-bases': [],
+                },
+            },
+            'trigger': {'misc': {}},
+        },
+        variables={},
+    )
+
+
+def _make_conversation() -> Conversation:
+    return Conversation(
+        prompt=Prompt(name='default', messages=[Message(role='system', content='system prompt')]),
+        messages=[],
+        pipeline_uuid='pipe-1',
+        bot_uuid='bot-1',
+        uuid='conv-1',
+    )
+
+
+def _make_app(*, skill_service) -> SimpleNamespace:
+    session = Session(launcher_type=LauncherTypes.PERSON, launcher_id='launcher-1', sender_id='sender-1')
+    conversation = _make_conversation()
+    model = SimpleNamespace(model_entity=SimpleNamespace(uuid='model-1', abilities={'func_call'}))
+    tool_mgr = SimpleNamespace(get_all_tools=AsyncMock(return_value=[]))
+
+    return SimpleNamespace(
+        sess_mgr=SimpleNamespace(
+            get_session=AsyncMock(return_value=session),
+            get_conversation=AsyncMock(return_value=conversation),
+        ),
+        model_mgr=SimpleNamespace(get_model_by_uuid=AsyncMock(return_value=model)),
+        tool_mgr=tool_mgr,
+        plugin_connector=SimpleNamespace(
+            emit_event=AsyncMock(
+                return_value=SimpleNamespace(
+                    event=SimpleNamespace(
+                        default_prompt=conversation.prompt.messages.copy(),
+                        prompt=conversation.messages.copy(),
+                    )
+                )
+            )
+        ),
+        pipeline_service=SimpleNamespace(
+            get_pipeline=AsyncMock(return_value={'extensions_preferences': {'enable_all_skills': True}})
+        ),
+        skill_mgr=SimpleNamespace(
+            build_skill_aware_prompt_addition=Mock(return_value=''),
+            skills={},
+        ),
+        skill_service=skill_service,
+        logger=Mock(),
+    )
+
+
+def _import_preproc_modules():
+    fake_app_module = types.ModuleType('langbot.pkg.core.app')
+    fake_app_module.Application = object
+    sys.modules['langbot.pkg.core.app'] = fake_app_module
+
+    for module_name in (
+        'langbot.pkg.pipeline.preproc.preproc',
+        'langbot.pkg.pipeline.stage',
+    ):
+        sys.modules.pop(module_name, None)
+
+    preproc_module = importlib.import_module('langbot.pkg.pipeline.preproc.preproc')
+    entities_module = importlib.import_module('langbot.pkg.pipeline.entities')
+    return preproc_module, entities_module
+
+
+@pytest.mark.asyncio
+async def test_preproc_enables_skill_authoring_tools_when_skill_service_available():
+    preproc_module, entities_module = _import_preproc_modules()
+
+    app = _make_app(skill_service=SimpleNamespace())
+    stage = preproc_module.PreProcessor(app)
+
+    result = await stage.process(_make_query(), 'PreProcessor')
+
+    assert result.result_type == entities_module.ResultType.CONTINUE
+    app.tool_mgr.get_all_tools.assert_awaited_once_with(None, None, include_skill_authoring=True)
+
+
+@pytest.mark.asyncio
+async def test_preproc_disables_skill_authoring_tools_when_skill_service_missing():
+    preproc_module, entities_module = _import_preproc_modules()
+
+    app = _make_app(skill_service=None)
+    stage = preproc_module.PreProcessor(app)
+
+    result = await stage.process(_make_query(), 'PreProcessor')
+
+    assert result.result_type == entities_module.ResultType.CONTINUE
+    app.tool_mgr.get_all_tools.assert_awaited_once_with(None, None, include_skill_authoring=False)
+
+
+@pytest.mark.asyncio
+async def test_preproc_injects_skill_index_into_system_prompt():
+    """The Tool Call activation pattern still needs the LLM to know which
+    skills exist. PreProcessor must append the SkillManager's index
+    addendum to the first system message."""
+    preproc_module, entities_module = _import_preproc_modules()
+
+    app = _make_app(skill_service=SimpleNamespace())
+    addendum = '\n\nAvailable Skills:\n- demo (demo): Demo skill.\n\nCall activate ...'
+    app.skill_mgr.build_skill_aware_prompt_addition = Mock(return_value=addendum)
+
+    query = _make_query()
+    result = await stage_process_capture(preproc_module, app, query)
+
+    assert result.result_type == entities_module.ResultType.CONTINUE
+    app.skill_mgr.build_skill_aware_prompt_addition.assert_called_once_with(bound_skills=None)
+    head = query.prompt.messages[0]
+    assert head.role == 'system'
+    assert head.content.endswith(addendum)
+
+
+@pytest.mark.asyncio
+async def test_preproc_respects_pipeline_bound_skills_subset():
+    """When ``enable_all_skills`` is false the bound list is passed through
+    so the addendum only mentions skills allowed for this pipeline."""
+    preproc_module, entities_module = _import_preproc_modules()
+
+    app = _make_app(skill_service=SimpleNamespace())
+    app.pipeline_service.get_pipeline = AsyncMock(
+        return_value={
+            'extensions_preferences': {
+                'enable_all_skills': False,
+                'skills': ['only-this'],
+            }
+        }
+    )
+    app.skill_mgr.build_skill_aware_prompt_addition = Mock(return_value='')
+
+    query = _make_query()
+    result = await stage_process_capture(preproc_module, app, query)
+
+    assert result.result_type == entities_module.ResultType.CONTINUE
+    app.skill_mgr.build_skill_aware_prompt_addition.assert_called_once_with(bound_skills=['only-this'])
+    assert query.variables.get('_pipeline_bound_skills') == ['only-this']
+
+
+@pytest.mark.asyncio
+async def test_preproc_skips_injection_when_addendum_is_empty():
+    """No visible skills → system prompt is left untouched (no
+    ``Available Skills`` block appended)."""
+    preproc_module, entities_module = _import_preproc_modules()
+
+    app = _make_app(skill_service=SimpleNamespace())
+    app.skill_mgr.build_skill_aware_prompt_addition = Mock(return_value='')
+
+    query = _make_query()
+    result = await stage_process_capture(preproc_module, app, query)
+
+    assert result.result_type == entities_module.ResultType.CONTINUE
+    if query.prompt and query.prompt.messages:
+        assert 'Available Skills' not in (query.prompt.messages[0].content or '')
+
+
+async def stage_process_capture(preproc_module, app, query):
+    """Run PreProcessor.process and return the result while keeping ``query``
+    accessible to the assertions (process mutates query in place)."""
+    stage = preproc_module.PreProcessor(app)
+    return await stage.process(query, 'PreProcessor')

tests/unit_tests/test_skill_service.py

@@ -0,0 +1,89 @@
+from types import SimpleNamespace
+from unittest.mock import AsyncMock
+
+import pytest
+
+from langbot.pkg.api.http.service.skill import SkillService
+
+
+class TestRequireBoxForWrite:
+    """Box is the only source of truth for skills — there is no local
+    filesystem fallback. Every write and (most) read methods refuse cleanly
+    when the Box runtime is disabled, unreachable, or simply not installed."""
+
+    def _ap_with_disabled_box(self):
+        return SimpleNamespace(
+            skill_mgr=SimpleNamespace(reload_skills=AsyncMock()),
+            box_service=SimpleNamespace(
+                available=False,
+                enabled=False,
+                _connector_error='Box runtime is disabled in config (box.enabled = false)',
+            ),
+        )
+
+    def _ap_with_failed_box(self):
+        return SimpleNamespace(
+            skill_mgr=SimpleNamespace(reload_skills=AsyncMock()),
+            box_service=SimpleNamespace(
+                available=False,
+                enabled=True,
+                _connector_error='docker daemon not running',
+            ),
+        )
+
+    @pytest.mark.asyncio
+    async def test_create_skill_refused_when_box_disabled(self):
+        service = SkillService(self._ap_with_disabled_box())
+        with pytest.raises(ValueError, match='disabled in config'):
+            await service.create_skill({'name': 'x'})
+
+    @pytest.mark.asyncio
+    async def test_create_skill_refused_when_box_failed(self):
+        service = SkillService(self._ap_with_failed_box())
+        with pytest.raises(ValueError, match='docker daemon not running'):
+            await service.create_skill({'name': 'x'})
+
+    @pytest.mark.asyncio
+    async def test_update_skill_refused_when_box_disabled(self):
+        service = SkillService(self._ap_with_disabled_box())
+        with pytest.raises(ValueError, match='Editing a skill requires the Box runtime'):
+            await service.update_skill('x', {})
+
+    @pytest.mark.asyncio
+    async def test_write_skill_file_refused_when_box_disabled(self):
+        service = SkillService(self._ap_with_disabled_box())
+        with pytest.raises(ValueError, match='Editing skill files requires the Box runtime'):
+            await service.write_skill_file('x', 'a.txt', 'hi')
+
+    @pytest.mark.asyncio
+    async def test_install_from_github_refused_when_box_disabled(self):
+        service = SkillService(self._ap_with_disabled_box())
+        with pytest.raises(ValueError, match='Installing a skill from GitHub'):
+            await service.install_from_github({'owner': 'o', 'repo': 'r', 'asset_url': 'https://example/x.zip'})
+
+    @pytest.mark.asyncio
+    async def test_install_from_zip_upload_refused_when_box_disabled(self):
+        service = SkillService(self._ap_with_disabled_box())
+        with pytest.raises(ValueError, match='Installing a skill from upload'):
+            await service.install_from_zip_upload(file_bytes=b'', filename='x.zip')
+
+    @pytest.mark.asyncio
+    async def test_create_skill_refused_when_box_service_missing_entirely(self):
+        """No ap.box_service attribute at all (truly minimal setup):
+        Box is the only source of truth, so creation must still refuse."""
+        service = SkillService(SimpleNamespace(skill_mgr=SimpleNamespace(reload_skills=AsyncMock())))
+        with pytest.raises(ValueError, match='not initialised'):
+            await service.create_skill({'name': 'x'})
+
+    @pytest.mark.asyncio
+    async def test_list_skills_returns_empty_when_box_unavailable(self):
+        """list_skills should render an empty surface (not crash) so the
+        skills page can show a banner instead of a broken state."""
+        service = SkillService(self._ap_with_disabled_box())
+        assert await service.list_skills() == []
+
+    @pytest.mark.asyncio
+    async def test_read_skill_file_refused_when_box_unavailable(self):
+        service = SkillService(self._ap_with_disabled_box())
+        with pytest.raises(ValueError, match='Reading a skill file'):
+            await service.read_skill_file('x', 'a.txt')

tests/unit_tests/utils/test_paths.py

@@ -11,7 +11,6 @@ Uses tmp_path for file system isolation where applicable.
 
 import os
 import pytest
-from unittest.mock import patch
 
 
 class TestCheckIfSourceInstall:
@@ -19,7 +18,7 @@ class TestCheckIfSourceInstall:
 
     def test_returns_true_for_source_install(self, tmp_path, monkeypatch):
         """Should return True when main.py with LangBot marker exists."""
-        main_py = tmp_path / "main.py"
+        main_py = tmp_path / 'main.py'
         main_py.write_text('# LangBot/main.py\n# This is the entry point')
 
         monkeypatch.chdir(tmp_path)
@@ -33,52 +32,14 @@ class TestCheckIfSourceInstall:
 
         paths._is_source_install = None
 
-    def test_returns_false_when_no_main_py(self, tmp_path, monkeypatch):
-        """Should return False when main.py doesn't exist."""
-        monkeypatch.chdir(tmp_path)
-
-        from langbot.pkg.utils import paths
-
-        paths._is_source_install = None
-
-        result = paths._check_if_source_install()
-        assert result is False
-
-        paths._is_source_install = None
-
-    def test_returns_false_when_main_py_without_marker(self, tmp_path, monkeypatch):
-        """Should return False when main.py exists but lacks LangBot marker."""
-        main_py = tmp_path / "main.py"
-        main_py.write_text('# Some other project\nprint("hello")')
-
-        monkeypatch.chdir(tmp_path)
-
-        from langbot.pkg.utils import paths
-
-        paths._is_source_install = None
-
-        result = paths._check_if_source_install()
-        assert result is False
-
-        paths._is_source_install = None
-
-    def test_handles_io_error_gracefully(self, tmp_path, monkeypatch):
-        """Should return False when main.py cannot be read."""
-        main_py = tmp_path / "main.py"
-        main_py.write_text('# LangBot/main.py\n')
-
-        monkeypatch.chdir(tmp_path)
-
-        from langbot.pkg.utils import paths
-
-        paths._is_source_install = None
-
-        # Patch open to raise IOError
-        with patch("builtins.open", side_effect=IOError("Cannot read")):
-            result = paths._check_if_source_install()
-            assert result is False
-
-        paths._is_source_install = None
+    # Note: ``_check_if_source_install`` was refactored to walk
+    # ``Path(__file__).resolve().parents`` looking for ``pyproject.toml`` +
+    # ``main.py`` instead of relying on the cwd. That makes it robust to where
+    # the process is launched from but also means the old "cwd doesn't have
+    # main.py" / "main.py without marker" / "IOError on read" cases no longer
+    # apply — there's no file read at all. The corresponding negative tests
+    # were removed; ``test_returns_true_for_source_install`` still exercises
+    # the positive path because the repo checkout itself is a source install.
 
 
 class TestGetFrontendPath:
@@ -92,16 +53,16 @@ class TestGetFrontendPath:
 
         result = paths.get_frontend_path()
         # The result should contain web/dist or be an absolute path to it
-        assert "web/dist" in result or result.endswith("dist")
+        assert 'web/dist' in result or result.endswith('dist')
 
         paths._is_source_install = None
 
     def test_finds_dist_directory_in_source_mode(self, tmp_path, monkeypatch):
         """Should find web/dist when running from source mode."""
-        main_py = tmp_path / "main.py"
+        main_py = tmp_path / 'main.py'
         main_py.write_text('# LangBot/main.py\n')
 
-        web_dist = tmp_path / "web" / "dist"
+        web_dist = tmp_path / 'web' / 'dist'
         web_dist.mkdir(parents=True)
 
         monkeypatch.chdir(tmp_path)
@@ -111,18 +72,18 @@ class TestGetFrontendPath:
         paths._is_source_install = None
 
         result = paths.get_frontend_path()
-        assert result == "web/dist"
+        assert result == 'web/dist'
 
         paths._is_source_install = None
 
     def test_prefers_dist_over_out_in_source_mode(self, tmp_path, monkeypatch):
         """Should prefer web/dist over web/out when both exist in source mode."""
-        main_py = tmp_path / "main.py"
+        main_py = tmp_path / 'main.py'
         main_py.write_text('# LangBot/main.py\n')
 
-        web_dist = tmp_path / "web" / "dist"
+        web_dist = tmp_path / 'web' / 'dist'
         web_dist.mkdir(parents=True)
-        web_out = tmp_path / "web" / "out"
+        web_out = tmp_path / 'web' / 'out'
         web_out.mkdir(parents=True)
 
         monkeypatch.chdir(tmp_path)
@@ -132,7 +93,7 @@ class TestGetFrontendPath:
         paths._is_source_install = None
 
         result = paths.get_frontend_path()
-        assert result == "web/dist"
+        assert result == 'web/dist'
 
         paths._is_source_install = None
 
@@ -148,19 +109,19 @@ class TestGetResourcePath:
 
         paths._is_source_install = None
 
-        result = paths.get_resource_path("nonexistent/file.txt")
-        assert result == "nonexistent/file.txt"
+        result = paths.get_resource_path('nonexistent/file.txt')
+        assert result == 'nonexistent/file.txt'
 
         paths._is_source_install = None
 
     def test_finds_resource_in_current_directory_source_mode(self, tmp_path, monkeypatch):
         """Should find resource in current directory when in source mode."""
-        main_py = tmp_path / "main.py"
+        main_py = tmp_path / 'main.py'
         main_py.write_text('# LangBot/main.py\n')
 
-        resource_file = tmp_path / "templates" / "config.yaml"
+        resource_file = tmp_path / 'templates' / 'config.yaml'
         resource_file.parent.mkdir(parents=True, exist_ok=True)
-        resource_file.write_text("test: value")
+        resource_file.write_text('test: value')
 
         monkeypatch.chdir(tmp_path)
 
@@ -168,18 +129,18 @@ class TestGetResourcePath:
 
         paths._is_source_install = None
 
-        result = paths.get_resource_path("templates/config.yaml")
+        result = paths.get_resource_path('templates/config.yaml')
         assert os.path.exists(result)
 
         paths._is_source_install = None
 
     def test_returns_relative_path_in_source_mode(self, tmp_path, monkeypatch):
         """Should return relative path if resource exists in source mode."""
-        main_py = tmp_path / "main.py"
+        main_py = tmp_path / 'main.py'
         main_py.write_text('# LangBot/main.py\n')
 
-        resource_file = tmp_path / "test_resource.txt"
-        resource_file.write_text("test content")
+        resource_file = tmp_path / 'test_resource.txt'
+        resource_file.write_text('test content')
 
         monkeypatch.chdir(tmp_path)
 
@@ -187,8 +148,8 @@ class TestGetResourcePath:
 
         paths._is_source_install = None
 
-        result = paths.get_resource_path("test_resource.txt")
-        assert result == "test_resource.txt"
+        result = paths.get_resource_path('test_resource.txt')
+        assert result == 'test_resource.txt'
 
         paths._is_source_install = None
 
@@ -198,7 +159,7 @@ class TestPathFunctionsCaching:
 
     def test_source_install_cache_is_used(self, tmp_path, monkeypatch):
         """_check_if_source_install should use cached result."""
-        main_py = tmp_path / "main.py"
+        main_py = tmp_path / 'main.py'
         main_py.write_text('# LangBot/main.py\n')
 
         monkeypatch.chdir(tmp_path)
@@ -219,5 +180,5 @@ class TestPathFunctionsCaching:
         paths._is_source_install = None
 
 
-if __name__ == "__main__":
-    pytest.main([__file__, "-v"])
+if __name__ == '__main__':
+    pytest.main([__file__, '-v'])

tests/unit_tests/utils/test_version.py

@@ -1,136 +0,0 @@
-"""
-Unit tests for version utility functions.
-
-Tests version comparison logic without network calls.
-"""
-
-from __future__ import annotations
-
-from unittest.mock import Mock
-
-from langbot.pkg.utils.version import VersionManager
-
-
-class TestVersionComparison:
-    """Tests for version comparison functions."""
-
-    def _create_version_manager(self):
-        """Create a VersionManager with mock app."""
-        mock_app = Mock()
-        mock_app.proxy_mgr = Mock()
-        mock_app.proxy_mgr.get_forward_providers = Mock(return_value={})
-        mock_app.logger = Mock()
-        return VersionManager(mock_app)
-
-    def test_is_newer_same_version(self):
-        """is_newer returns False for same version."""
-        vm = self._create_version_manager()
-        result = vm.is_newer('v1.0.0', 'v1.0.0')
-        assert result is False
-
-    def test_is_newer_different_major_version(self):
-        """is_newer returns False for different major version."""
-        # Note: is_newer ignores major version changes
-        vm = self._create_version_manager()
-        result = vm.is_newer('v2.0.0', 'v1.0.0')
-        assert result is False
-
-    def test_is_newer_minor_update(self):
-        """is_newer returns True for minor update within same major."""
-        vm = self._create_version_manager()
-        result = vm.is_newer('v1.1.0', 'v1.0.0')
-        assert result is True
-
-    def test_is_newer_patch_update(self):
-        """is_newer returns True for patch update within same major."""
-        vm = self._create_version_manager()
-        result = vm.is_newer('v1.0.1', 'v1.0.0')
-        assert result is True
-
-    def test_is_newer_with_fourth_segment(self):
-        """is_newer ignores fourth version segment."""
-        # Both have same first 3 segments
-        vm = self._create_version_manager()
-        result = vm.is_newer('v1.0.0.1', 'v1.0.0.0')
-        assert result is False
-
-    def test_is_newer_short_version(self):
-        """is_newer handles short version numbers."""
-        vm = self._create_version_manager()
-        result = vm.is_newer('v1.0', 'v1.0')
-        assert result is False
-
-    def test_is_newer_older_version(self):
-        """is_newer returns True when new > old."""
-        vm = self._create_version_manager()
-        result = vm.is_newer('v1.2.0', 'v1.1.0')
-        assert result is True
-
-
-class TestCompareVersionStr:
-    """Tests for compare_version_str static method."""
-
-    def test_compare_equal_versions(self):
-        """Equal versions return 0."""
-        result = VersionManager.compare_version_str('v1.0.0', 'v1.0.0')
-        assert result == 0
-
-    def test_compare_without_v_prefix(self):
-        """Versions without v prefix work the same."""
-        result = VersionManager.compare_version_str('1.0.0', '1.0.0')
-        assert result == 0
-
-    def test_compare_mixed_prefix(self):
-        """Mixed v prefix works correctly."""
-        result = VersionManager.compare_version_str('v1.0.0', '1.0.0')
-        assert result == 0
-
-    def test_compare_first_greater(self):
-        """First version greater returns 1."""
-        result = VersionManager.compare_version_str('v1.1.0', 'v1.0.0')
-        assert result == 1
-
-    def test_compare_first_smaller(self):
-        """First version smaller returns -1."""
-        result = VersionManager.compare_version_str('v1.0.0', 'v1.1.0')
-        assert result == -1
-
-    def test_compare_different_lengths(self):
-        """Different length versions are padded with zeros."""
-        result = VersionManager.compare_version_str('v1.0', 'v1.0.0')
-        assert result == 0
-
-    def test_compare_shorter_greater(self):
-        """Shorter version padded, first still greater."""
-        result = VersionManager.compare_version_str('v1.1', 'v1.0.0')
-        assert result == 1
-
-    def test_compare_longer_greater(self):
-        """Longer version, first smaller."""
-        result = VersionManager.compare_version_str('v1.0', 'v1.0.1')
-        assert result == -1
-
-    def test_compare_major_version(self):
-        """Major version comparison."""
-        result = VersionManager.compare_version_str('v2.0.0', 'v1.9.9')
-        assert result == 1
-
-    def test_compare_minor_version(self):
-        """Minor version comparison."""
-        result = VersionManager.compare_version_str('v1.5.0', 'v1.4.9')
-        assert result == 1
-
-    def test_compare_patch_version(self):
-        """Patch version comparison."""
-        result = VersionManager.compare_version_str('v1.0.1', 'v1.0.0')
-        assert result == 1
-
-    def test_compare_four_segments(self):
-        """Four segment version comparison."""
-        result = VersionManager.compare_version_str('v1.0.0.1', 'v1.0.0.0')
-        assert result == 1
-
-    def test_compare_long_versions(self):
-        """Long version strings work correctly."""
-        result = VersionManager.compare_version_str('v1.2.3.4.5', 'v1.2.3.4.4')
-        assert result == 1

uv.lock

@@ -560,6 +560,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/ef/71/9a2c88abb5fe47b46168b262254d5b5d635de371eba4bd01ea5c8c109575/botocore-1.42.39-py3-none-any.whl", hash = "sha256:9e0d0fed9226449cc26fcf2bbffc0392ac698dd8378e8395ce54f3ec13f81d58", size = 14591958, upload-time = "2026-01-30T20:38:14.814Z" },
 ]
 
+[[package]]
+name = "bracex"
+version = "2.6"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/63/9a/fec38644694abfaaeca2798b58e276a8e61de49e2e37494ace423395febc/bracex-2.6.tar.gz", hash = "sha256:98f1347cd77e22ee8d967a30ad4e310b233f7754dbf31ff3fceb76145ba47dc7", size = 26642, upload-time = "2025-06-22T19:12:31.254Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/9d/2a/9186535ce58db529927f6cf5990a849aa9e052eea3e2cfefe20b9e1802da/bracex-2.6-py3-none-any.whl", hash = "sha256:0b0049264e7340b3ec782b5cb99beb325f36c3782a32e36e876452fd49a09952", size = 11508, upload-time = "2025-06-22T19:12:29.781Z" },
+]
+
 [[package]]
 name = "build"
 version = "1.4.0"
@@ -1086,6 +1095,15 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/12/b3/231ffd4ab1fc9d679809f356cebee130ac7daa00d6d6f3206dd4fd137e9e/distro-1.9.0-py3-none-any.whl", hash = "sha256:7bffd925d65168f85027d8da9af6bddab658135b840670a223589bc0c8ef02b2", size = 20277, upload-time = "2023-12-24T09:54:30.421Z" },
 ]
 
+[[package]]
+name = "dockerfile-parse"
+version = "2.0.1"
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/92/df/929ee0b5d2c8bd8d713c45e71b94ab57c7e11e322130724d54f469b2cd48/dockerfile-parse-2.0.1.tar.gz", hash = "sha256:3184ccdc513221983e503ac00e1aa504a2aa8f84e5de673c46b0b6eee99ec7bc", size = 24556, upload-time = "2023-07-18T13:36:07.897Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/7a/6c/79cd5bc1b880d8c1a9a5550aa8dacd57353fa3bb2457227e1fb47383eb49/dockerfile_parse-2.0.1-py2.py3-none-any.whl", hash = "sha256:bdffd126d2eb26acf1066acb54cb2e336682e1d72b974a40894fac76a4df17f6", size = 14845, upload-time = "2023-07-18T13:36:06.052Z" },
+]
+
 [[package]]
 name = "docstring-parser"
 version = "0.17.0"
@@ -1115,6 +1133,28 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/b0/0d/9feae160378a3553fa9a339b0e9c1a048e147a4127210e286ef18b730f03/durationpy-0.10-py3-none-any.whl", hash = "sha256:3b41e1b601234296b4fb368338fdcd3e13e0b4fb5b67345948f4f2bf9868b286", size = 3922, upload-time = "2025-05-17T13:52:36.463Z" },
 ]
 
+[[package]]
+name = "e2b"
+version = "2.21.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "attrs" },
+    { name = "dockerfile-parse" },
+    { name = "h2" },
+    { name = "httpcore" },
+    { name = "httpx" },
+    { name = "packaging" },
+    { name = "protobuf" },
+    { name = "python-dateutil" },
+    { name = "rich" },
+    { name = "typing-extensions" },
+    { name = "wcmatch" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/f7/97/0e86ccb9e05c18e6e795e0808f14e2dc9f5c9ffb7be2a5cb77afd6d9f59e/e2b-2.21.1.tar.gz", hash = "sha256:2eff473ca03173cee1ccd9f9ec9e90c2b4705cca418e080e3104753d7ec33490", size = 157458, upload-time = "2026-05-14T17:36:02.318Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/6f/d4/8b6a9a120e724dd8f91aededa89348a667a01fffbba28ae1a42cb397b0f0/e2b-2.21.1-py3-none-any.whl", hash = "sha256:9ec4646f3dba4a6da855baa8adeab239aa988e15904611e38bf12aeec2562ac9", size = 297476, upload-time = "2026-05-14T17:36:00.351Z" },
+]
+
 [[package]]
 name = "ebooklib"
 version = "0.20"
@@ -1859,7 +1899,7 @@ wheels = [
 
 [[package]]
 name = "langbot"
-version = "4.9.7"
+version = "4.10.0b1"
 source = { editable = "." }
 dependencies = [
     { name = "aiocqhttp" },
@@ -1973,7 +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 = "==0.3.11" },
+    { name = "langbot-plugin", specifier = "==0.4.0b1" },
     { name = "langchain", specifier = ">=0.2.0" },
     { name = "langchain-core", specifier = ">=1.2.28" },
     { name = "langchain-text-splitters", specifier = ">=1.1.2" },
@@ -2036,11 +2076,13 @@ dev = [
 
 [[package]]
 name = "langbot-plugin"
-version = "0.3.11"
+version = "0.4.0b1"
 source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "aiofiles" },
+    { name = "aiohttp" },
     { name = "dotenv" },
+    { name = "e2b" },
     { name = "httpx" },
     { name = "jinja2" },
     { name = "pip" },
@@ -2054,9 +2096,9 @@ dependencies = [
     { name = "watchdog" },
     { name = "websockets" },
 ]
-sdist = { url = "https://files.pythonhosted.org/packages/91/83/93b86bcdbfe51d820fa59232aaa73cc802d6ce614f67d8f8b33957419538/langbot_plugin-0.3.11.tar.gz", hash = "sha256:8d10c98c771b468b2d35cc007778439c39922a88265fcc16a5881234bc7c1b19", size = 190315, upload-time = "2026-05-12T15:45:24.262Z" }
+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" }
 wheels = [
-    { url = "https://files.pythonhosted.org/packages/8f/22/de7977a6a5cbf557b80043eb3ed39e5feff24033a5d6db4ab88d48ccb6ea/langbot_plugin-0.3.11-py3-none-any.whl", hash = "sha256:c1d2e84eda1584902d99efa316b850c08c1c04fcc199306ff4af1dca1431304a", size = 165574, upload-time = "2026-05-12T15:45:22.908Z" },
+    { 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" },
 ]
 
 [[package]]
@@ -2751,7 +2793,7 @@ wheels = [
 [[package]]
 name = "moto"
 version = "5.2.1"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "boto3" },
     { name = "botocore" },
@@ -2761,9 +2803,9 @@ dependencies = [
     { name = "werkzeug" },
     { name = "xmltodict" },
 ]
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/f6/e9/c38202162db2e76623176be9f1dbc9aa41228ffa91ee8da2d3986082c3e3/moto-5.2.1.tar.gz", hash = "sha256:ccb2f3e1dfa82e50e054bda98b0be708d244d2668364dcc1d45e8d3de6091bde", size = 8634437, upload-time = "2026-05-10T19:11:57.286Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/f6/e9/c38202162db2e76623176be9f1dbc9aa41228ffa91ee8da2d3986082c3e3/moto-5.2.1.tar.gz", hash = "sha256:ccb2f3e1dfa82e50e054bda98b0be708d244d2668364dcc1d45e8d3de6091bde", size = 8634437, upload-time = "2026-05-10T19:11:57.286Z" }
 wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/15/79/8085b7c1ecd48d0535c3c8444a1d8df2926e457dce8e55fabc332a382c9c/moto-5.2.1-py3-none-any.whl", hash = "sha256:19d2fbd6e613aa5b4e364c52cd5d3cea371643a0f4210689a703227bd2924c5c", size = 6671379, upload-time = "2026-05-10T19:11:53.543Z" },
+    { url = "https://files.pythonhosted.org/packages/15/79/8085b7c1ecd48d0535c3c8444a1d8df2926e457dce8e55fabc332a382c9c/moto-5.2.1-py3-none-any.whl", hash = "sha256:19d2fbd6e613aa5b4e364c52cd5d3cea371643a0f4210689a703227bd2924c5c", size = 6671379, upload-time = "2026-05-10T19:11:53.543Z" },
 ]
 
 [[package]]
@@ -4767,15 +4809,15 @@ wheels = [
 [[package]]
 name = "responses"
 version = "0.26.0"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
+source = { registry = "https://pypi.org/simple" }
 dependencies = [
     { name = "pyyaml" },
     { name = "requests" },
     { name = "urllib3" },
 ]
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/9f/b4/b7e040379838cc71bf5aabdb26998dfbe5ee73904c92c1c161faf5de8866/responses-0.26.0.tar.gz", hash = "sha256:c7f6923e6343ef3682816ba421c006626777893cb0d5e1434f674b649bac9eb4", size = 81303, upload-time = "2026-02-19T14:38:05.574Z" }
+sdist = { url = "https://files.pythonhosted.org/packages/9f/b4/b7e040379838cc71bf5aabdb26998dfbe5ee73904c92c1c161faf5de8866/responses-0.26.0.tar.gz", hash = "sha256:c7f6923e6343ef3682816ba421c006626777893cb0d5e1434f674b649bac9eb4", size = 81303, upload-time = "2026-02-19T14:38:05.574Z" }
 wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/ce/04/7f73d05b556da048923e31a0cc878f03be7c5425ed1f268082255c75d872/responses-0.26.0-py3-none-any.whl", hash = "sha256:03ec4409088cd5c66b71ecbbbd27fe2c58ddfad801c66203457b3e6a04868c37", size = 35099, upload-time = "2026-02-19T14:38:03.847Z" },
+    { url = "https://files.pythonhosted.org/packages/ce/04/7f73d05b556da048923e31a0cc878f03be7c5425ed1f268082255c75d872/responses-0.26.0-py3-none-any.whl", hash = "sha256:03ec4409088cd5c66b71ecbbbd27fe2c58ddfad801c66203457b3e6a04868c37", size = 35099, upload-time = "2026-02-19T14:38:03.847Z" },
 ]
 
 [[package]]
@@ -5931,6 +5973,18 @@ wheels = [
     { url = "https://files.pythonhosted.org/packages/6e/d4/ed38dd3b1767193de971e694aa544356e63353c33a85d948166b5ff58b9e/watchfiles-1.1.1-pp311-pypy311_pp73-manylinux_2_17_x86_64.manylinux2014_x86_64.whl", hash = "sha256:3e6f39af2eab0118338902798b5aa6664f46ff66bc0280de76fca67a7f262a49", size = 457546, upload-time = "2025-10-14T15:06:13.372Z" },
 ]
 
+[[package]]
+name = "wcmatch"
+version = "10.1"
+source = { registry = "https://pypi.org/simple" }
+dependencies = [
+    { name = "bracex" },
+]
+sdist = { url = "https://files.pythonhosted.org/packages/79/3e/c0bdc27cf06f4e47680bd5803a07cb3dfd17de84cde92dd217dcb9e05253/wcmatch-10.1.tar.gz", hash = "sha256:f11f94208c8c8484a16f4f48638a85d771d9513f4ab3f37595978801cb9465af", size = 117421, upload-time = "2025-06-22T19:14:02.49Z" }
+wheels = [
+    { url = "https://files.pythonhosted.org/packages/eb/d8/0d1d2e9d3fabcf5d6840362adcf05f8cf3cd06a73358140c3a97189238ae/wcmatch-10.1-py3-none-any.whl", hash = "sha256:5848ace7dbb0476e5e55ab63c6bbd529745089343427caa5537f230cc01beb8a", size = 39854, upload-time = "2025-06-22T19:14:00.978Z" },
+]
+
 [[package]]
 name = "websocket-client"
 version = "1.9.0"
@@ -6072,10 +6126,10 @@ wheels = [
 [[package]]
 name = "xmltodict"
 version = "1.0.4"
-source = { registry = "https://pypi.tuna.tsinghua.edu.cn/simple" }
-sdist = { url = "https://pypi.tuna.tsinghua.edu.cn/packages/19/70/80f3b7c10d2630aa66414bf23d210386700aa390547278c789afa994fd7e/xmltodict-1.0.4.tar.gz", hash = "sha256:6d94c9f834dd9e44514162799d344d815a3a4faec913717a9ecbfa5be1bb8e61", size = 26124, upload-time = "2026-02-22T02:21:22.074Z" }
+source = { registry = "https://pypi.org/simple" }
+sdist = { url = "https://files.pythonhosted.org/packages/19/70/80f3b7c10d2630aa66414bf23d210386700aa390547278c789afa994fd7e/xmltodict-1.0.4.tar.gz", hash = "sha256:6d94c9f834dd9e44514162799d344d815a3a4faec913717a9ecbfa5be1bb8e61", size = 26124, upload-time = "2026-02-22T02:21:22.074Z" }
 wheels = [
-    { url = "https://pypi.tuna.tsinghua.edu.cn/packages/38/34/98a2f52245f4d47be93b580dae5f9861ef58977d73a79eb47c58f1ad1f3a/xmltodict-1.0.4-py3-none-any.whl", hash = "sha256:a4a00d300b0e1c59fc2bfccb53d7b2e88c32f200df138a0dd2229f842497026a", size = 13580, upload-time = "2026-02-22T02:21:21.039Z" },
+    { url = "https://files.pythonhosted.org/packages/38/34/98a2f52245f4d47be93b580dae5f9861ef58977d73a79eb47c58f1ad1f3a/xmltodict-1.0.4-py3-none-any.whl", hash = "sha256:a4a00d300b0e1c59fc2bfccb53d7b2e88c32f200df138a0dd2229f842497026a", size = 13580, upload-time = "2026-02-22T02:21:21.039Z" },
 ]
 
 [[package]]

web/src/app/home/bots/components/bot-card/BotCard.tsx

@@ -4,6 +4,7 @@ import { httpClient } from '@/app/infra/http/HttpClient';
 import { Switch } from '@/components/ui/switch';
 import { useTranslation } from 'react-i18next';
 import { toast } from 'sonner';
+import { MessageSquare, Workflow } from 'lucide-react';
 
 export default function BotCard({
   botCardVO,
@@ -42,28 +43,14 @@ export default function BotCard({
           </div>
 
           <div className={`${styles.basicInfoAdapterContainer}`}>
-            <svg
-              className={`${styles.basicInfoAdapterIcon}`}
-              xmlns="http://www.w3.org/2000/svg"
-              viewBox="0 0 24 24"
-              fill="currentColor"
-            >
-              <path d="M2 8.99374C2 5.68349 4.67654 3 8.00066 3H15.9993C19.3134 3 22 5.69478 22 8.99374V21H8.00066C4.68659 21 2 18.3052 2 15.0063V8.99374ZM20 19V8.99374C20 6.79539 18.2049 5 15.9993 5H8.00066C5.78458 5 4 6.78458 4 8.99374V15.0063C4 17.2046 5.79512 19 8.00066 19H20ZM14 11H16V13H14V11ZM8 11H10V13H8V11Z"></path>
-            </svg>
+            <MessageSquare className={`${styles.basicInfoAdapterIcon}`} />
             <span className={`${styles.basicInfoAdapterLabel}`}>
               {botCardVO.adapterLabel}
             </span>
           </div>
 
           <div className={`${styles.basicInfoPipelineContainer}`}>
-            <svg
-              className={`${styles.basicInfoPipelineIcon}`}
-              xmlns="http://www.w3.org/2000/svg"
-              viewBox="0 0 24 24"
-              fill="currentColor"
-            >
-              <path d="M6 21.5C4.067 21.5 2.5 19.933 2.5 18C2.5 16.067 4.067 14.5 6 14.5C7.5852 14.5 8.92427 15.5539 9.35481 16.9992L15 16.9994V15L17 14.9994V9.24339L14.757 6.99938H9V9.00003H3V3.00003H9V4.99939H14.757L18 1.75739L22.2426 6.00003L19 9.24139V14.9994L21 15V21H15V18.9994L9.35499 19.0003C8.92464 20.4459 7.58543 21.5 6 21.5ZM6 16.5C5.17157 16.5 4.5 17.1716 4.5 18C4.5 18.8285 5.17157 19.5 6 19.5C6.82843 19.5 7.5 18.8285 7.5 18C7.5 17.1716 6.82843 16.5 6 16.5ZM19 17H17V19H19V17ZM18 4.58581L16.5858 6.00003L18 7.41424L19.4142 6.00003L18 4.58581ZM7 5.00003H5V7.00003H7V5.00003Z"></path>
-            </svg>
+            <Workflow className={`${styles.basicInfoPipelineIcon}`} />
             <span className={`${styles.basicInfoPipelineLabel}`}>
               {botCardVO.usePipelineName}
             </span>

web/src/app/home/components/BoxUnavailableNotice.tsx

@@ -0,0 +1,53 @@
+import { useTranslation } from 'react-i18next';
+import { Info, ShieldAlert } from 'lucide-react';
+
+import { Alert, AlertDescription } from '@/components/ui/alert';
+
+/**
+ * Banner shown when a feature depends on the Box sandbox runtime but it is
+ * currently disabled in config or otherwise unavailable. Pass the ``hint``
+ * key returned by ``useBoxStatus`` (``'boxDisabled' | 'boxUnavailable'``).
+ *
+ * Renders nothing when there is no hint — safe to drop at the top of any
+ * page that may or may not need to surface the notice.
+ */
+export interface BoxUnavailableNoticeProps {
+  hint: 'boxDisabled' | 'boxUnavailable' | null;
+  /** Specific failure reason from the backend (``connector_error``). Shown
+   *  on a dedicated line so the user sees WHY (e.g. ``Configured sandbox
+   *  backend "nsjail" is unavailable``) instead of just the generic
+   *  "unavailable" wording. Ignored when ``hint === 'boxDisabled'``
+   *  because the disabled-by-config message already carries the reason. */
+  reason?: string | null;
+  className?: string;
+}
+
+export function BoxUnavailableNotice({
+  hint,
+  reason,
+  className,
+}: BoxUnavailableNoticeProps) {
+  const { t } = useTranslation();
+  if (!hint) return null;
+
+  const variant = hint === 'boxDisabled' ? 'default' : 'destructive';
+  const Icon = hint === 'boxDisabled' ? Info : ShieldAlert;
+  const showReason = hint === 'boxUnavailable' && reason;
+
+  return (
+    <Alert variant={variant} className={className}>
+      <Icon className="h-4 w-4" />
+      <AlertDescription className="space-y-1">
+        <div>{t(`monitoring.${hint}`)}</div>
+        {showReason && (
+          <div className="text-xs font-mono opacity-80 break-all">{reason}</div>
+        )}
+        <div className="text-xs opacity-80">
+          {t('monitoring.boxRequiredHint')}
+        </div>
+      </AlertDescription>
+    </Alert>
+  );
+}
+
+export default BoxUnavailableNotice;

web/src/app/home/components/account-settings-dialog/AccountSettingsDialog.tsx

@@ -20,7 +20,7 @@ import {
 } from '@/components/ui/item';
 import { httpClient } from '@/app/infra/http/HttpClient';
 import { systemInfo } from '@/app/infra/http';
-import { Loader2, ExternalLink, KeyRound } from 'lucide-react';
+import { Loader2, ExternalLink, KeyRound, Layers } from 'lucide-react';
 import PasswordChangeDialog from '../password-change-dialog/PasswordChangeDialog';
 
 interface AccountSettingsDialogProps {
@@ -136,34 +136,7 @@ export default function AccountSettingsDialog({
               {/* Space Account Item */}
               <Item size="sm" variant="muted" className="rounded-lg">
                 <ItemMedia variant="icon">
-                  <svg
-                    className="h-4 w-4"
-                    viewBox="0 0 24 24"
-                    fill="none"
-                    xmlns="http://www.w3.org/2000/svg"
-                  >
-                    <path
-                      d="M12 2L2 7L12 12L22 7L12 2Z"
-                      stroke="currentColor"
-                      strokeWidth="2"
-                      strokeLinecap="round"
-                      strokeLinejoin="round"
-                    />
-                    <path
-                      d="M2 17L12 22L22 17"
-                      stroke="currentColor"
-                      strokeWidth="2"
-                      strokeLinecap="round"
-                      strokeLinejoin="round"
-                    />
-                    <path
-                      d="M2 12L12 17L22 12"
-                      stroke="currentColor"
-                      strokeWidth="2"
-                      strokeLinecap="round"
-                      strokeLinejoin="round"
-                    />
-                  </svg>
+                  <Layers className="h-4 w-4" />
                 </ItemMedia>
                 <ItemContent>
                   <ItemTitle>{t('account.spaceStatus')}</ItemTitle>

web/src/app/home/components/dynamic-form/DynamicFormComponent.tsx

@@ -20,8 +20,14 @@ import { useTranslation } from 'react-i18next';
 import { cn } from '@/lib/utils';
 import { Input } from '@/components/ui/input';
 import { Button } from '@/components/ui/button';
-import { Copy, Check, Globe, QrCode } from 'lucide-react';
+import { Copy, Check, Globe, Info, QrCode } from 'lucide-react';
 import { copyToClipboard } from '@/app/utils/clipboard';
+import {
+  Tooltip,
+  TooltipContent,
+  TooltipProvider,
+  TooltipTrigger,
+} from '@/components/ui/tooltip';
 import { systemInfo } from '@/app/infra/http';
 
 /**
@@ -123,13 +129,13 @@ function WebhookUrlField({
   };
 
   return (
-    <FormItem>
-      <FormLabel>{label}</FormLabel>
-      <div className="flex items-center gap-2">
+    <FormItem className="min-w-0">
+      <FormLabel className="break-words">{label}</FormLabel>
+      <div className="flex min-w-0 items-center gap-2">
         <Input
           value={url}
           readOnly
-          className="flex-1 bg-muted"
+          className="min-w-0 flex-1 bg-muted"
           onClick={(e) => (e.target as HTMLInputElement).select()}
         />
         <Button
@@ -146,11 +152,11 @@ function WebhookUrlField({
         </Button>
       </div>
       {extraUrl && (
-        <div className="flex items-center gap-2 mt-2">
+        <div className="mt-2 flex min-w-0 items-center gap-2">
           <Input
             value={extraUrl}
             readOnly
-            className="flex-1 bg-muted"
+            className="min-w-0 flex-1 bg-muted"
             onClick={(e) => (e.target as HTMLInputElement).select()}
           />
           <Button
@@ -168,12 +174,14 @@ function WebhookUrlField({
         </div>
       )}
       {description && (
-        <p className="text-sm text-muted-foreground">{description}</p>
+        <p className="text-sm break-words text-muted-foreground">
+          {description}
+        </p>
       )}
       {systemInfo.edition === 'community' && (
-        <div className="flex items-start gap-2.5 rounded-md border border-border/60 bg-muted/40 px-3 py-2.5 mt-1 max-w-2xl">
+        <div className="mt-1 flex max-w-full min-w-0 items-start gap-2.5 rounded-md border border-border/60 bg-muted/40 px-3 py-2.5">
           <Globe className="h-4 w-4 text-muted-foreground shrink-0 mt-0.5" />
-          <p className="text-sm text-muted-foreground leading-relaxed">
+          <p className="text-sm leading-relaxed break-words text-muted-foreground">
             {t('bots.webhookSaasHint')}{' '}
             <a
               href="https://space.langbot.app/cloud?utm_source=local_webui&utm_medium=webhook_alert&utm_campaign=saas_conversion"
@@ -462,7 +470,7 @@ export default function DynamicFormComponent({
 
   return (
     <Form {...form}>
-      <div className="space-y-4">
+      <div className="min-w-0 max-w-full space-y-4 overflow-x-hidden">
         {/* QR code login dialog */}
         <QrCodeLoginDialog
           open={qrDialogOpen}
@@ -507,8 +515,53 @@ export default function DynamicFormComponent({
             }
           }
 
-          // All fields are disabled when editing (creation_settings are immutable)
-          const isFieldDisabled = !!isEditing;
+          // ``disable_if`` mirrors ``show_if``'s evaluator but instead of
+          // hiding the field, leaves it visible and inert. Use it when the
+          // operator needs to see that the field exists yet cannot edit it
+          // under the current runtime state (e.g. sandbox-bound fields when
+          // Box is disabled).
+          let isDisabledByCondition = false;
+          if (config.disable_if) {
+            const dependValue = resolveShowIfValue(
+              config.disable_if.field,
+              watchedValues as Record<string, unknown>,
+              externalDependentValues,
+              systemContext,
+            );
+            const cond = config.disable_if;
+            if (cond.operator === 'eq' && dependValue === cond.value) {
+              isDisabledByCondition = true;
+            } else if (cond.operator === 'neq' && dependValue !== cond.value) {
+              isDisabledByCondition = true;
+            } else if (
+              cond.operator === 'in' &&
+              Array.isArray(cond.value) &&
+              cond.value.includes(dependValue)
+            ) {
+              isDisabledByCondition = true;
+            }
+          }
+
+          // All fields are disabled when editing (creation_settings are
+          // immutable) or when ``disable_if`` matches.
+          const isFieldDisabled = !!isEditing || isDisabledByCondition;
+          const disabledTooltip =
+            isDisabledByCondition && config.disabled_tooltip
+              ? extractI18nObject(config.disabled_tooltip)
+              : '';
+          const renderDisabledTooltipIcon = () =>
+            disabledTooltip ? (
+              <TooltipProvider delayDuration={100}>
+                <Tooltip>
+                  <TooltipTrigger asChild>
+                    <Info className="h-3.5 w-3.5 text-muted-foreground cursor-help shrink-0" />
+                  </TooltipTrigger>
+                  <TooltipContent className="max-w-xs">
+                    {disabledTooltip}
+                  </TooltipContent>
+                </Tooltip>
+              </TooltipProvider>
+            ) : null;
 
           // Webhook URL fields are display-only; render outside of form binding
           if (config.type === 'webhook-url') {
@@ -631,19 +684,20 @@ export default function DynamicFormComponent({
                 control={form.control}
                 name={config.name as keyof FormValues}
                 render={({ field }) => (
-                  <FormItem>
+                  <FormItem className="min-w-0">
                     <div
                       className={cn(
-                        'flex flex-row items-center justify-between rounded-lg border p-4 max-w-2xl',
+                        'flex w-full min-w-0 max-w-full flex-row items-center justify-between rounded-lg border p-4',
                         isFieldDisabled && 'pointer-events-none opacity-60',
                       )}
                     >
-                      <div className="space-y-0.5">
-                        <FormLabel className="text-base">
+                      <div className="min-w-0 space-y-0.5">
+                        <FormLabel className="flex min-w-0 items-center gap-1.5 text-base">
                           {extractI18nObject(config.label)}
+                          {renderDisabledTooltipIcon()}
                         </FormLabel>
                         {config.description && (
-                          <p className="text-sm text-muted-foreground">
+                          <p className="text-sm break-words text-muted-foreground">
                             {extractI18nObject(config.description)}
                           </p>
                         )}
@@ -669,16 +723,22 @@ export default function DynamicFormComponent({
               control={form.control}
               name={config.name as keyof FormValues}
               render={({ field }) => (
-                <FormItem>
-                  <FormLabel>
-                    {extractI18nObject(config.label)}{' '}
-                    {config.required && <span className="text-red-500">*</span>}
+                <FormItem className="min-w-0">
+                  <FormLabel className="flex min-w-0 items-center gap-1.5">
+                    <span className="min-w-0 break-words">
+                      {extractI18nObject(config.label)}{' '}
+                      {config.required && (
+                        <span className="text-red-500">*</span>
+                      )}
+                    </span>
+                    {renderDisabledTooltipIcon()}
                   </FormLabel>
                   <FormControl>
                     <div
-                      className={
-                        isFieldDisabled ? 'pointer-events-none opacity-60' : ''
-                      }
+                      className={cn(
+                        'min-w-0 max-w-full overflow-x-hidden',
+                        isFieldDisabled && 'pointer-events-none opacity-60',
+                      )}
                     >
                       <DynamicFormItemComponent
                         config={config}
@@ -688,7 +748,7 @@ export default function DynamicFormComponent({
                     </div>
                   </FormControl>
                   {config.description && (
-                    <p className="text-sm text-muted-foreground">
+                    <p className="text-sm break-words text-muted-foreground">
                       {extractI18nObject(config.description)}
                     </p>
                   )}

web/src/app/home/components/dynamic-form/DynamicFormItemComponent.tsx

@@ -69,7 +69,6 @@ export default function DynamicFormItemComponent({
   onFileUploaded,
 }: {
   config: IDynamicFormItemSchema;
-  // eslint-disable-next-line @typescript-eslint/no-explicit-any
   field: ControllerRenderProps<any, any>;
   onFileUploaded?: (fileKey: string) => void;
 }) {
@@ -251,7 +250,7 @@ export default function DynamicFormItemComponent({
       return (
         <Input
           type="number"
-          className="max-w-xs"
+          className="w-full max-w-xs"
           {...field}
           onChange={(e) => field.onChange(Number(e.target.value))}
         />
@@ -260,8 +259,8 @@ export default function DynamicFormItemComponent({
     case DynamicFormItemType.STRING:
       if (config.options && config.options.length > 0) {
         return (
-          <div className="flex items-center gap-1.5 max-w-md">
-            <Input className="flex-1" {...field} />
+          <div className="flex w-full max-w-md min-w-0 items-center gap-1.5">
+            <Input className="min-w-0 flex-1" {...field} />
             <DropdownMenu>
               <DropdownMenuTrigger asChild>
                 <Button
@@ -292,21 +291,26 @@ export default function DynamicFormItemComponent({
           </div>
         );
       }
-      return <Input className="max-w-md" {...field} />;
+      return <Input className="w-full max-w-md" {...field} />;
 
     case DynamicFormItemType.TEXT:
-      return <Textarea {...field} className="min-h-[120px] max-w-2xl" />;
+      return (
+        <Textarea
+          {...field}
+          className="min-h-[120px] w-full max-w-full resize-y overflow-x-hidden break-all"
+        />
+      );
 
     case DynamicFormItemType.BOOLEAN:
       return <Switch checked={field.value} onCheckedChange={field.onChange} />;
 
     case DynamicFormItemType.STRING_ARRAY:
       return (
-        <div className="space-y-2 max-w-md">
+        <div className="w-full max-w-md min-w-0 space-y-2">
           {field.value.map((item: string, index: number) => (
-            <div key={index} className="flex gap-1.5 items-center">
+            <div key={index} className="flex min-w-0 items-center gap-1.5">
               <Input
-                className="flex-1"
+                className="min-w-0 flex-1"
                 value={item}
                 onChange={(e) => {
                   const newValue = [...field.value];
@@ -347,7 +351,7 @@ export default function DynamicFormItemComponent({
     case DynamicFormItemType.SELECT:
       return (
         <Select value={field.value} onValueChange={field.onChange}>
-          <SelectTrigger className="max-w-md bg-[#ffffff] dark:bg-[#2a2a2e]">
+          <SelectTrigger className="w-full max-w-md bg-[#ffffff] dark:bg-[#2a2a2e]">
             <SelectValue placeholder={t('common.select')} />
           </SelectTrigger>
           <SelectContent>
@@ -409,10 +413,10 @@ export default function DynamicFormItemComponent({
       ];
 
       return (
-        <div className="max-w-md flex items-center gap-1.5">
-          <div className="flex-1">
+        <div className="flex w-full max-w-md min-w-0 items-center gap-1.5">
+          <div className="min-w-0 flex-1">
             <Select value={field.value} onValueChange={field.onChange}>
-              <SelectTrigger className="bg-[#ffffff] dark:bg-[#2a2a2e]">
+              <SelectTrigger className="min-w-0 bg-[#ffffff] dark:bg-[#2a2a2e]">
                 <SelectValue placeholder={t('models.selectModel')} />
               </SelectTrigger>
               <SelectContent>
@@ -577,9 +581,9 @@ export default function DynamicFormItemComponent({
       );
 
       return (
-        <div className="max-w-md">
+        <div className="w-full max-w-md min-w-0">
           <Select value={field.value} onValueChange={field.onChange}>
-            <SelectTrigger className="bg-[#ffffff] dark:bg-[#2a2a2e]">
+            <SelectTrigger className="min-w-0 bg-[#ffffff] dark:bg-[#2a2a2e]">
               <SelectValue placeholder={t('knowledge.selectEmbeddingModel')} />
             </SelectTrigger>
             <SelectContent>
@@ -612,12 +616,12 @@ export default function DynamicFormItemComponent({
       );
 
       return (
-        <div className="max-w-md">
+        <div className="w-full max-w-md min-w-0">
           <Select
             value={field.value || '__none__'}
             onValueChange={(v) => field.onChange(v === '__none__' ? '' : v)}
           >
-            <SelectTrigger className="bg-[#ffffff] dark:bg-[#2a2a2e]">
+            <SelectTrigger className="min-w-0 bg-[#ffffff] dark:bg-[#2a2a2e]">
               <SelectValue placeholder={t('models.rerank')} />
             </SelectTrigger>
             <SelectContent>
@@ -713,7 +717,7 @@ export default function DynamicFormItemComponent({
         placeholder: string,
       ) => (
         <Select value={value} onValueChange={onChange}>
-          <SelectTrigger className="bg-[#ffffff] dark:bg-[#2a2a2e]">
+          <SelectTrigger className="min-w-0 bg-[#ffffff] dark:bg-[#2a2a2e]">
             <SelectValue placeholder={placeholder} />
           </SelectTrigger>
           <SelectContent>
@@ -879,14 +883,14 @@ export default function DynamicFormItemComponent({
       };
 
       return (
-        <div className="space-y-3">
+        <div className="w-full min-w-0 space-y-3">
           {/* Primary model selector */}
           <div>
             <p className="text-xs text-muted-foreground mb-1">
               {t('models.fallback.primary')}
             </p>
-            <div className="flex items-center gap-1.5">
-              <div className="flex-1">
+            <div className="flex min-w-0 items-center gap-1.5">
+              <div className="min-w-0 flex-1">
                 {renderModelSelect(
                   modelValue.primary,
                   (val) => updateValue({ primary: val }),
@@ -918,16 +922,16 @@ export default function DynamicFormItemComponent({
 
           {/* Fallback models */}
           {modelValue.fallbacks.length > 0 && (
-            <div className="space-y-2">
+            <div className="min-w-0 space-y-2">
               <p className="text-xs text-muted-foreground">
                 {t('models.fallback.fallbackList')}
               </p>
               {modelValue.fallbacks.map((fbUuid: string, index: number) => (
-                <div key={index} className="flex items-center gap-2">
+                <div key={index} className="flex min-w-0 items-center gap-2">
                   <span className="text-xs text-muted-foreground w-4 shrink-0">
                     {index + 1}.
                   </span>
-                  <div className="flex-1">
+                  <div className="min-w-0 flex-1">
                     {renderModelSelect(
                       fbUuid,
                       (val) => updateFallbackModel(index, val),
@@ -1003,20 +1007,22 @@ export default function DynamicFormItemComponent({
 
       return (
         <Select value={field.value} onValueChange={field.onChange}>
-          <SelectTrigger className="bg-[#ffffff] dark:bg-[#2a2a2e]">
+          <SelectTrigger className="min-w-0 bg-[#ffffff] dark:bg-[#2a2a2e]">
             {field.value && field.value !== '__none__' ? (
               (() => {
                 const selectedKb = knowledgeBases.find(
                   (kb) => kb.uuid === field.value,
                 );
                 return (
-                  <div className="flex items-center gap-2">
+                  <div className="flex min-w-0 items-center gap-2">
                     {selectedKb?.emoji && (
                       <span className="text-sm shrink-0">
                         {selectedKb.emoji}
                       </span>
                     )}
-                    <span>{selectedKb?.name ?? field.value}</span>
+                    <span className="truncate">
+                      {selectedKb?.name ?? field.value}
+                    </span>
                   </div>
                 );
               })()
@@ -1066,9 +1072,9 @@ export default function DynamicFormItemComponent({
 
       return (
         <>
-          <div className="space-y-2">
+          <div className="min-w-0 space-y-2">
             {field.value && field.value.length > 0 ? (
-              <div className="space-y-2">
+              <div className="min-w-0 space-y-2">
                 {field.value.map((kbId: string) => {
                   const currentKb = knowledgeBases.find(
                     (base) => base.uuid === kbId,
@@ -1078,17 +1084,17 @@ export default function DynamicFormItemComponent({
                   return (
                     <div
                       key={kbId}
-                      className="flex items-center justify-between rounded-lg border p-3 hover:bg-accent"
+                      className="flex min-w-0 items-center justify-between rounded-lg border p-3 hover:bg-accent"
                     >
-                      <div className="flex items-center gap-2 flex-1">
+                      <div className="flex min-w-0 flex-1 items-center gap-2">
                         <div className="flex-1 min-w-0">
-                          <div className="font-medium flex items-center gap-2">
+                          <div className="flex min-w-0 items-center gap-2 font-medium">
                             {currentKb.emoji && (
                               <span className="text-sm shrink-0">
                                 {currentKb.emoji}
                               </span>
                             )}
-                            {currentKb.name}
+                            <span className="truncate">{currentKb.name}</span>
                             {currentKb.knowledge_engine?.name && (
                               <span className="text-xs px-2 py-0.5 rounded-full bg-purple-100 text-purple-700 dark:bg-purple-900 dark:text-purple-300">
                                 {extractI18nObject(
@@ -1098,7 +1104,7 @@ export default function DynamicFormItemComponent({
                             )}
                           </div>
                           {currentKb.description && (
-                            <div className="text-sm text-muted-foreground">
+                            <div className="text-sm break-words text-muted-foreground">
                               {currentKb.description}
                             </div>
                           )}
@@ -1221,7 +1227,7 @@ export default function DynamicFormItemComponent({
     case DynamicFormItemType.BOT_SELECTOR:
       return (
         <Select value={field.value} onValueChange={field.onChange}>
-          <SelectTrigger className="bg-[#ffffff] dark:bg-[#2a2a2e]">
+          <SelectTrigger className="min-w-0 bg-[#ffffff] dark:bg-[#2a2a2e]">
             <SelectValue placeholder={t('bots.selectBot')} />
           </SelectTrigger>
           <SelectContent>
@@ -1239,9 +1245,9 @@ export default function DynamicFormItemComponent({
     case DynamicFormItemType.TOOLS_SELECTOR:
       return (
         <>
-          <div className="space-y-2">
+          <div className="min-w-0 space-y-2">
             {field.value && field.value.length > 0 ? (
-              <div className="space-y-2">
+              <div className="min-w-0 space-y-2">
                 {field.value.map((toolName: string) => {
                   const currentTool = tools.find(
                     (tool) => tool.name === toolName,
@@ -1250,12 +1256,12 @@ export default function DynamicFormItemComponent({
                   return (
                     <div
                       key={toolName}
-                      className="flex items-center justify-between rounded-lg border p-3 hover:bg-accent"
+                      className="flex min-w-0 items-center justify-between rounded-lg border p-3 hover:bg-accent"
                     >
-                      <div className="flex items-center gap-2 flex-1">
+                      <div className="flex min-w-0 flex-1 items-center gap-2">
                         <Wrench className="h-4 w-4 shrink-0 text-muted-foreground" />
                         <div className="flex-1 min-w-0">
-                          <div className="font-medium">{toolName}</div>
+                          <div className="truncate font-medium">{toolName}</div>
                           {currentTool?.human_desc && (
                             <div className="text-sm text-muted-foreground truncate">
                               {currentTool.human_desc}
@@ -1379,13 +1385,16 @@ export default function DynamicFormItemComponent({
         ? field.value
         : [{ role: 'system', content: '' }];
       return (
-        <div className="space-y-2">
+        <div className="min-w-0 space-y-2">
           {promptItems.map(
             (item: { role: string; content: string }, index: number) => (
-              <div key={index} className="flex gap-2 items-center">
+              <div
+                key={index}
+                className="flex min-w-0 flex-col gap-2 sm:flex-row sm:items-center"
+              >
                 {/* 角色选择 */}
                 {index === 0 ? (
-                  <div className="w-[120px] px-3 py-2 border rounded bg-gray-50 dark:bg-[#2a292e] text-gray-500 dark:text-white dark:border-gray-600">
+                  <div className="w-full shrink-0 rounded border bg-gray-50 px-3 py-2 text-gray-500 sm:w-[120px] dark:border-gray-600 dark:bg-[#2a292e] dark:text-white">
                     system
                   </div>
                 ) : (
@@ -1410,7 +1419,7 @@ export default function DynamicFormItemComponent({
                 )}
                 {/* 内容输入 */}
                 <Textarea
-                  className="w-[300px]"
+                  className="min-h-20 w-full min-w-0 flex-1 resize-y overflow-x-hidden break-all sm:w-[300px]"
                   value={item.content}
                   onChange={(e) => {
                     const newValue = [...(field.value ?? promptItems)];
@@ -1428,20 +1437,12 @@ export default function DynamicFormItemComponent({
                     className="p-2 hover:bg-gray-100 rounded"
                     onClick={() => {
                       const newValue = (field.value ?? promptItems).filter(
-                        // eslint-disable-next-line @typescript-eslint/no-explicit-any
                         (_: any, i: number) => i !== index,
                       );
                       field.onChange(newValue);
                     }}
                   >
-                    <svg
-                      xmlns="http://www.w3.org/2000/svg"
-                      viewBox="0 0 24 24"
-                      fill="currentColor"
-                      className="w-5 h-5 text-red-500"
-                    >
-                      <path d="M7 4V2H17V4H22V6H20V21C20 21.5523 19.5523 22 19 22H5C4.44772 22 4 21.5523 4 21V6H2V4H7ZM6 6V20H18V6H6ZM9 9H11V17H9V9ZM13 9H15V17H13V9Z"></path>
-                    </svg>
+                    <Trash2 className="w-5 h-5 text-red-500" />
                   </button>
                 )}
               </div>
@@ -1492,14 +1493,7 @@ export default function DynamicFormItemComponent({
                   }}
                   title={t('common.delete')}
                 >
-                  <svg
-                    xmlns="http://www.w3.org/2000/svg"
-                    viewBox="0 0 24 24"
-                    fill="currentColor"
-                    className="w-4 h-4 text-destructive"
-                  >
-                    <path d="M7 4V2H17V4H22V6H20V21C20 21.5523 19.5523 22 19 22H5C4.44772 22 4 21.5523 4 21V6H2V4H7ZM6 6V20H18V6H6ZM9 9H11V17H9V9ZM13 9H15V17H13V9Z"></path>
-                  </svg>
+                  <Trash2 className="w-4 h-4 text-destructive" />
                 </Button>
               </CardContent>
             </Card>
@@ -1531,14 +1525,7 @@ export default function DynamicFormItemComponent({
                   document.getElementById(`file-input-${config.name}`)?.click()
                 }
               >
-                <svg
-                  className="w-4 h-4 mr-2"
-                  xmlns="http://www.w3.org/2000/svg"
-                  viewBox="0 0 24 24"
-                  fill="currentColor"
-                >
-                  <path d="M11 11V5H13V11H19V13H13V19H11V13H5V11H11Z"></path>
-                </svg>
+                <Plus className="w-4 h-4 mr-2" />
                 {uploading
                   ? t('plugins.fileUpload.uploading')
                   : t('plugins.fileUpload.chooseFile')}
@@ -1584,14 +1571,7 @@ export default function DynamicFormItemComponent({
                     }}
                     title={t('common.delete')}
                   >
-                    <svg
-                      xmlns="http://www.w3.org/2000/svg"
-                      viewBox="0 0 24 24"
-                      fill="currentColor"
-                      className="w-4 h-4 text-destructive"
-                    >
-                      <path d="M7 4V2H17V4H22V6H20V21C20 21.5523 19.5523 22 19 22H5C4.44772 22 4 21.5523 4 21V6H2V4H7ZM6 6V20H18V6H6ZM9 9H11V17H9V9ZM13 9H15V17H13V9Z"></path>
-                    </svg>
+                    <Trash2 className="w-4 h-4 text-destructive" />
                   </Button>
                 </CardContent>
               </Card>
@@ -1626,14 +1606,7 @@ export default function DynamicFormItemComponent({
                   ?.click()
               }
             >
-              <svg
-                className="w-4 h-4 mr-2"
-                xmlns="http://www.w3.org/2000/svg"
-                viewBox="0 0 24 24"
-                fill="currentColor"
-              >
-                <path d="M11 11V5H13V11H19V13H13V19H11V13H5V11H11Z"></path>
-              </svg>
+              <Plus className="w-4 h-4 mr-2" />
               {uploading
                 ? t('plugins.fileUpload.uploading')
                 : t('plugins.fileUpload.addFile')}

web/src/app/home/components/dynamic-form/N8nAuthFormComponent.tsx

@@ -1,4 +1,4 @@
-import { useEffect, useState } from 'react';
+import { useEffect, useRef, useState } from 'react';
 import { useForm } from 'react-hook-form';
 import { zodResolver } from '@hookform/resolvers/zod';
 import { z } from 'zod';
@@ -102,9 +102,30 @@ export default function N8nAuthFormComponent({
     }, {} as FormValues),
   });
 
+  const isInitialMount = useRef(true);
+  const previousInitialValues = useRef(initialValues);
+
+  // Stable ref for onSubmit to avoid re-triggering the effect when the
+  // parent passes a new closure on every render (matches DynamicFormComponent pattern).
+  const onSubmitRef = useRef(onSubmit);
+  onSubmitRef.current = onSubmit;
+
   // 当 initialValues 变化时更新表单值
   useEffect(() => {
-    if (initialValues) {
+    // Skip the first mount — defaultValues already handles it
+    if (isInitialMount.current) {
+      isInitialMount.current = false;
+      previousInitialValues.current = initialValues;
+      return;
+    }
+
+    // Deep compare to avoid reacting to parent re-renders that pass
+    // the same values back (e.g. after our own onSubmit emission).
+    const hasRealChange =
+      JSON.stringify(previousInitialValues.current) !==
+      JSON.stringify(initialValues);
+
+    if (initialValues && hasRealChange) {
       // 合并默认值和初始值
       const mergedValues = itemConfigList.reduce(
         (acc, item) => {
@@ -120,11 +141,28 @@ export default function N8nAuthFormComponent({
 
       // 更新认证类型
       setAuthType((mergedValues['auth-type'] as string) || 'none');
+      previousInitialValues.current = initialValues;
     }
   }, [initialValues, form, itemConfigList]);
 
   // 监听表单值变化
   useEffect(() => {
+    // Emit initial form values on mount so the parent form's
+    // initializedStagesRef registers this stage (matches DynamicFormComponent).
+    const formValues = form.getValues();
+    const initialFinalValues = itemConfigList.reduce(
+      (acc, item) => {
+        acc[item.name] = formValues[item.name] ?? item.default;
+        return acc;
+      },
+      {} as Record<string, string>,
+    );
+    onSubmitRef.current?.(initialFinalValues);
+    previousInitialValues.current = initialFinalValues as Record<
+      string,
+      string
+    >;
+
     const subscription = form.watch((value, { name }) => {
       // 如果认证类型变化，更新状态
       if (name === 'auth-type') {
@@ -141,10 +179,11 @@ export default function N8nAuthFormComponent({
         {} as Record<string, string>,
       );
 
-      onSubmit?.(finalValues);
+      onSubmitRef.current?.(finalValues);
+      previousInitialValues.current = finalValues as Record<string, string>;
     });
     return () => subscription.unsubscribe();
-  }, [form, onSubmit, itemConfigList]);
+  }, [form, itemConfigList]);
 
   // 根据认证类型过滤表单项
   const filteredConfigList = itemConfigList.filter((config) => {

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

@@ -26,11 +26,10 @@ export interface SidebarEntityItem {
   installInfo?: Record<string, unknown>;
   hasUpdate?: boolean;
   debug?: boolean;
+  // Set when this item appears in the unified extensions list
+  extensionType?: 'plugin' | 'mcp' | 'skill';
 }
 
-// Install action types that can be triggered from sidebar
-export type PluginInstallAction = 'local' | 'github' | null;
-
 // Plugin page registered by a plugin
 export interface PluginPageItem {
   id: string; // "author/name/pageId"
@@ -50,19 +49,21 @@ export interface SidebarDataContextValue {
   knowledgeBases: SidebarEntityItem[];
   plugins: SidebarEntityItem[];
   mcpServers: SidebarEntityItem[];
+  skills: SidebarEntityItem[];
   pluginPages: PluginPageItem[];
   refreshBots: () => Promise<void>;
   refreshPipelines: () => Promise<void>;
   refreshKnowledgeBases: () => Promise<void>;
   refreshPlugins: () => Promise<void>;
   refreshMCPServers: () => Promise<void>;
+  refreshSkills: () => Promise<void>;
   refreshAll: () => Promise<void>;
   // Breadcrumb: entity name shown when viewing a detail page
   detailEntityName: string | null;
   setDetailEntityName: (name: string | null) => void;
-  // Pending plugin install action triggered from sidebar
-  pendingPluginInstallAction: PluginInstallAction;
-  setPendingPluginInstallAction: (action: PluginInstallAction) => void;
+  // Whether the extensions list is grouped by type (shared between page and sidebar)
+  extensionsGroupByType: boolean;
+  setExtensionsGroupByType: (enabled: boolean) => void;
 }
 
 const SidebarDataContext = createContext<SidebarDataContextValue | null>(null);
@@ -77,10 +78,22 @@ export function SidebarDataProvider({
   const [knowledgeBases, setKnowledgeBases] = useState<SidebarEntityItem[]>([]);
   const [plugins, setPlugins] = useState<SidebarEntityItem[]>([]);
   const [mcpServers, setMCPServers] = useState<SidebarEntityItem[]>([]);
+  const [skills, setSkills] = useState<SidebarEntityItem[]>([]);
   const [pluginPages, setPluginPages] = useState<PluginPageItem[]>([]);
   const [detailEntityName, setDetailEntityName] = useState<string | null>(null);
-  const [pendingPluginInstallAction, setPendingPluginInstallAction] =
-    useState<PluginInstallAction>(null);
+  const [extensionsGroupByType, setExtensionsGroupByTypeState] =
+    useState<boolean>(() => {
+      if (typeof window === 'undefined') return false;
+      return localStorage.getItem('extensions_group_by_type') === 'true';
+    });
+  const setExtensionsGroupByType = useCallback((enabled: boolean) => {
+    setExtensionsGroupByTypeState(enabled);
+    try {
+      localStorage.setItem('extensions_group_by_type', String(enabled));
+    } catch {
+      // ignore
+    }
+  }, []);
 
   const refreshBots = useCallback(async () => {
     try {
@@ -224,8 +237,8 @@ export function SidebarDataProvider({
       const resp = await httpClient.getMCPServers();
       setMCPServers(
         resp.servers.map((server) => ({
-          id: server.name,
-          name: server.name,
+          id: server.name, // Keep __ for API calls
+          name: server.name.replace(/__/g, '/'), // Display with / for readability
           enabled: server.enable,
           runtimeStatus: server.runtime_info?.status,
         })),
@@ -235,6 +248,22 @@ export function SidebarDataProvider({
     }
   }, []);
 
+  const refreshSkills = useCallback(async () => {
+    try {
+      const resp = await httpClient.getSkills();
+      setSkills(
+        resp.skills.map((skill) => ({
+          id: skill.name,
+          name: skill.display_name || skill.name,
+          description: skill.description,
+          updatedAt: skill.updated_at,
+        })),
+      );
+    } catch (error) {
+      console.error('Failed to fetch skills for sidebar:', error);
+    }
+  }, []);
+
   const refreshAll = useCallback(async () => {
     await Promise.all([
       refreshBots(),
@@ -242,6 +271,7 @@ export function SidebarDataProvider({
       refreshKnowledgeBases(),
       refreshPlugins(),
       refreshMCPServers(),
+      refreshSkills(),
     ]);
   }, [
     refreshBots,
@@ -249,6 +279,7 @@ export function SidebarDataProvider({
     refreshKnowledgeBases,
     refreshPlugins,
     refreshMCPServers,
+    refreshSkills,
   ]);
 
   // Fetch all entity lists on mount
@@ -264,17 +295,19 @@ export function SidebarDataProvider({
         knowledgeBases,
         plugins,
         mcpServers,
+        skills,
         pluginPages,
         refreshBots,
         refreshPipelines,
         refreshKnowledgeBases,
         refreshPlugins,
         refreshMCPServers,
+        refreshSkills,
         refreshAll,
         detailEntityName,
         setDetailEntityName,
-        pendingPluginInstallAction,
-        setPendingPluginInstallAction,
+        extensionsGroupByType,
+        setExtensionsGroupByType,
       }}
     >
       {children}

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

@@ -1,5 +1,14 @@
 import { SidebarChildVO } from '@/app/home/components/home-sidebar/HomeSidebarChild';
 import i18n from '@/i18n';
+import {
+  Zap,
+  LayoutDashboard,
+  Bot,
+  Workflow,
+  BookMarked,
+  Puzzle,
+  PlusCircle,
+} from 'lucide-react';
 
 const t = (key: string) => {
   return i18n.t(key);
@@ -10,16 +19,7 @@ export const sidebarConfigList = [
   new SidebarChildVO({
     id: 'wizard',
     name: t('sidebar.quickStart'),
-    icon: (
-      <svg
-        xmlns="http://www.w3.org/2000/svg"
-        viewBox="0 0 24 24"
-        fill="currentColor"
-        className="text-blue-500"
-      >
-        <path d="M13 9H21L11 24V15H4L13 0V9ZM11 11V7.22063L7.53238 13H13V17.3944L17.263 11H11Z"></path>
-      </svg>
-    ),
+    icon: <Zap className="text-blue-500" />,
     route: '/wizard',
     description: t('wizard.sidebarDescription'),
     helpLink: {
@@ -33,16 +33,7 @@ export const sidebarConfigList = [
   new SidebarChildVO({
     id: 'monitoring',
     name: t('monitoring.title'),
-    icon: (
-      <svg
-        xmlns="http://www.w3.org/2000/svg"
-        viewBox="0 0 24 24"
-        fill="currentColor"
-        className="text-blue-500"
-      >
-        <path d="M2 3.9934C2 3.44476 2.45531 3 2.9918 3H21.0082C21.556 3 22 3.44495 22 3.9934V20.0066C22 20.5552 21.5447 21 21.0082 21H2.9918C2.44405 21 2 20.5551 2 20.0066V3.9934ZM4 5V19H20V5H4ZM6 7H18V9H6V7ZM6 11H18V13H6V11ZM6 15H12V17H6V15Z"></path>
-      </svg>
-    ),
+    icon: <LayoutDashboard className="text-blue-500" />,
     route: '/home/monitoring',
     description: t('monitoring.description'),
     helpLink: {
@@ -54,16 +45,7 @@ export const sidebarConfigList = [
   new SidebarChildVO({
     id: 'bots',
     name: t('bots.title'),
-    icon: (
-      <svg
-        xmlns="http://www.w3.org/2000/svg"
-        viewBox="0 0 24 24"
-        fill="currentColor"
-        className="text-blue-500"
-      >
-        <path d="M13.5 2C13.5 2.44425 13.3069 2.84339 13 3.11805V5H18C19.6569 5 21 6.34315 21 8V18C21 19.6569 19.6569 21 18 21H6C4.34315 21 3 19.6569 3 18V8C3 6.34315 4.34315 5 6 5H11V3.11805C10.6931 2.84339 10.5 2.44425 10.5 2C10.5 1.17157 11.1716 0.5 12 0.5C12.8284 0.5 13.5 1.17157 13.5 2ZM6 7C5.44772 7 5 7.44772 5 8V18C5 18.5523 5.44772 19 6 19H18C18.5523 19 19 18.5523 19 18V8C19 7.44772 18.5523 7 18 7H13H11H6ZM2 10H0V16H2V10ZM22 10H24V16H22V10ZM9 14.5C9.82843 14.5 10.5 13.8284 10.5 13C10.5 12.1716 9.82843 11.5 9 11.5C8.17157 11.5 7.5 12.1716 7.5 13C7.5 13.8284 8.17157 14.5 9 14.5ZM15 14.5C15.8284 14.5 16.5 13.8284 16.5 13C16.5 12.1716 15.8284 11.5 15 11.5C14.1716 11.5 13.5 12.1716 13.5 13C13.5 13.8284 14.1716 14.5 15 14.5Z"></path>
-      </svg>
-    ),
+    icon: <Bot className="text-blue-500" />,
     route: '/home/bots',
     description: t('bots.description'),
     helpLink: {
@@ -76,16 +58,7 @@ export const sidebarConfigList = [
   new SidebarChildVO({
     id: 'pipelines',
     name: t('pipelines.title'),
-    icon: (
-      <svg
-        xmlns="http://www.w3.org/2000/svg"
-        viewBox="0 0 24 24"
-        fill="currentColor"
-        className="text-blue-500"
-      >
-        <path d="M6 21.5C4.067 21.5 2.5 19.933 2.5 18C2.5 16.067 4.067 14.5 6 14.5C7.5852 14.5 8.92427 15.5539 9.35481 16.9992L15 16.9994V15L17 14.9994V9.24339L14.757 6.99938H9V9.00003H3V3.00003H9V4.99939H14.757L18 1.75739L22.2426 6.00003L19 9.24139V14.9994L21 15V21H15V18.9994L9.35499 19.0003C8.92464 20.4459 7.58543 21.5 6 21.5ZM6 16.5C5.17157 16.5 4.5 17.1716 4.5 18C4.5 18.8285 5.17157 19.5 6 19.5C6.82843 19.5 7.5 18.8285 7.5 18C7.5 17.1716 6.82843 16.5 6 16.5ZM19 17H17V19H19V17ZM18 4.58581L16.5858 6.00003L18 7.41424L19.4142 6.00003L18 4.58581ZM7 5.00003H5V7.00003H7V5.00003Z"></path>
-      </svg>
-    ),
+    icon: <Workflow className="text-blue-500" />,
     route: '/home/pipelines',
     description: t('pipelines.description'),
     helpLink: {
@@ -98,16 +71,7 @@ export const sidebarConfigList = [
   new SidebarChildVO({
     id: 'knowledge',
     name: t('knowledge.title'),
-    icon: (
-      <svg
-        xmlns="http://www.w3.org/2000/svg"
-        viewBox="0 0 24 24"
-        fill="currentColor"
-        className="text-blue-500"
-      >
-        <path d="M3 18.5V5C3 3.34315 4.34315 2 6 2H20C20.5523 2 21 2.44772 21 3V21C21 21.5523 20.5523 22 20 22H6.5C4.567 22 3 20.433 3 18.5ZM19 20V17H6.5C5.67157 17 5 17.6716 5 18.5C5 19.3284 5.67157 20 6.5 20H19ZM10 4H6C5.44772 4 5 4.44772 5 5V15.3368C5.45463 15.1208 5.9632 15 6.5 15H19V4H17V12L13.5 10L10 12V4Z"></path>
-      </svg>
-    ),
+    icon: <BookMarked className="text-blue-500" />,
     route: '/home/knowledge',
     description: t('knowledge.description'),
     helpLink: {
@@ -117,22 +81,12 @@ export const sidebarConfigList = [
     },
     section: 'home',
   }),
-
   // ── Extensions section ──
   new SidebarChildVO({
     id: 'plugins',
     name: t('sidebar.installedPlugins'),
-    icon: (
-      <svg
-        xmlns="http://www.w3.org/2000/svg"
-        viewBox="0 0 24 24"
-        fill="currentColor"
-        className="text-blue-500"
-      >
-        <path d="M7 5C7 2.79086 8.79086 1 11 1C13.2091 1 15 2.79086 15 5H18C18.5523 5 19 5.44772 19 6V9C21.2091 9 23 10.7909 23 13C23 15.2091 21.2091 17 19 17V20C19 20.5523 18.5523 21 18 21H4C3.44772 21 3 20.5523 3 20V6C3 5.44772 3.44772 5 4 5H7ZM11 3C9.89543 3 9 3.89543 9 5C9 5.23554 9.0403 5.45952 9.11355 5.66675C9.22172 5.97282 9.17461 6.31235 8.98718 6.57739C8.79974 6.84243 8.49532 7 8.17071 7H5V19H17V15.8293C17 15.5047 17.1576 15.2003 17.4226 15.0128C17.6877 14.8254 18.0272 14.7783 18.3332 14.8865C18.5405 14.9597 18.7645 15 19 15C20.1046 15 21 14.1046 21 13C21 11.8954 20.1046 11 19 11C18.7645 11 18.5405 11.0403 18.3332 11.1135C18.0272 11.2217 17.6877 11.1746 17.4226 10.9872C17.1576 10.7997 17 10.4953 17 10.1707V7H13.8293C13.5047 7 13.2003 6.84243 13.0128 6.57739C12.8254 6.31235 12.7783 5.97282 12.8865 5.66675C12.9597 5.45952 13 5.23555 13 5C13 3.89543 12.1046 3 11 3Z"></path>
-      </svg>
-    ),
-    route: '/home/plugins',
+    icon: <Puzzle className="text-blue-500" />,
+    route: '/home/extensions',
     description: t('plugins.description'),
     helpLink: {
       en_US: 'https://link.langbot.app/en/docs/plugins',
@@ -142,19 +96,10 @@ export const sidebarConfigList = [
     section: 'extensions',
   }),
   new SidebarChildVO({
-    id: 'market',
-    name: t('sidebar.pluginMarket'),
-    icon: (
-      <svg
-        xmlns="http://www.w3.org/2000/svg"
-        viewBox="0 0 24 24"
-        fill="currentColor"
-        className="text-blue-500"
-      >
-        <path d="M21 13.242V20H22V22H2V20H3V13.242C1.79401 12.435 1 11.0602 1 9.5C1 8.67286 1.25027 7.90335 1.67755 7.2612L4.5547 2.36088C4.80513 1.93859 5.26028 1.67578 5.76 1.67578H18.24C18.7397 1.67578 19.1949 1.93859 19.4453 2.36088L22.3225 7.2612C22.7497 7.90335 23 8.67286 23 9.5C23 11.0602 22.206 12.435 21 13.242ZM19 13.972C18.4511 14.0706 17.8794 14.0706 17.3305 13.972C16.1644 13.7566 15.1377 13.0712 14.5 12.1C13.8623 13.0712 12.8356 13.7566 11.6695 13.972C11.1206 14.0706 10.5489 14.0706 10 13.972C9.45108 14.0706 8.87938 14.0706 8.33053 13.972C7.16437 13.7566 6.13771 13.0712 5.5 12.1C4.86229 13.0712 3.83563 13.7566 2.66947 13.972C2.44883 14.0124 2.22434 14.0352 2 14.0404V20H5V15H10V20H19V13.972Z"></path>
-      </svg>
-    ),
-    route: '/home/market',
+    id: 'add-extension',
+    name: t('sidebar.addExtension'),
+    icon: <PlusCircle className="text-blue-500" />,
+    route: '/home/add-extension',
     description: t('plugins.description'),
     helpLink: {
       en_US: 'https://link.langbot.app/en/docs/plugins',
@@ -163,25 +108,4 @@ export const sidebarConfigList = [
     },
     section: 'extensions',
   }),
-  new SidebarChildVO({
-    id: 'mcp',
-    name: t('sidebar.mcpServers'),
-    icon: (
-      <svg
-        xmlns="http://www.w3.org/2000/svg"
-        viewBox="0 0 24 24"
-        fill="currentColor"
-        className="text-blue-500"
-      >
-        <path d="M4.5 7.65311V16.3469L12 20.689L19.5 16.3469V7.65311L12 3.311L4.5 7.65311ZM12 1L21.5 6.5V17.5L12 23L2.5 17.5V6.5L12 1ZM6.49896 9.97065L11 12.5765V17.625H13V12.5765L17.501 9.97066L16.499 8.2398L12 10.8445L7.50104 8.2398L6.49896 9.97065Z"></path>
-      </svg>
-    ),
-    route: '/home/mcp',
-    description: t('mcp.title'),
-    helpLink: {
-      en_US: '',
-      zh_Hans: '',
-    },
-    section: 'extensions',
-  }),
 ];

web/src/app/home/knowledge/components/kb-card/KBCard.tsx

@@ -1,6 +1,7 @@
 import { KnowledgeBaseVO } from '@/app/home/knowledge/components/kb-card/KBCardVO';
 import { useTranslation } from 'react-i18next';
 import styles from './KBCard.module.css';
+import { Clock } from 'lucide-react';
 
 export default function KBCard({ kbCardVO }: { kbCardVO: KnowledgeBaseVO }) {
   const { t } = useTranslation();
@@ -27,14 +28,7 @@ export default function KBCard({ kbCardVO }: { kbCardVO: KnowledgeBaseVO }) {
         </div>
 
         <div className={`${styles.basicInfoLastUpdatedTimeContainer}`}>
-          <svg
-            className={`${styles.basicInfoUpdateTimeIcon}`}
-            xmlns="http://www.w3.org/2000/svg"
-            viewBox="0 0 24 24"
-            fill="currentColor"
-          >
-            <path d="M12 22C6.47715 22 2 17.5228 2 12C2 6.47715 6.47715 2 12 2C17.5228 2 22 6.47715 22 12C22 17.5228 17.5228 22 12 22ZM12 20C16.4183 20 20 16.4183 20 12C20 7.58172 16.4183 4 12 4C7.58172 4 4 7.58172 4 12C4 16.4183 7.58172 20 12 20ZM13 12H17V14H11V7H13V12Z"></path>
-          </svg>
+          <Clock className={`${styles.basicInfoUpdateTimeIcon}`} />
           <div className={`${styles.basicInfoUpdateTimeText}`}>
             {t('knowledge.updateTime')}
             {kbCardVO.lastUpdatedTimeAgo}

web/src/app/home/knowledge/components/kb-docs/FileUploadZone.tsx

@@ -1,5 +1,6 @@
 import React, { useCallback, useEffect, useState } from 'react';
 import { Link } from 'react-router-dom';
+import { CloudUpload } from 'lucide-react';
 import { Card, CardContent } from '@/components/ui/card';
 import {
   Select,
@@ -221,7 +222,7 @@ export default function FileUploadZone({
                   {t('knowledge.documentsTab.noParserAvailable')}
                 </p>
                 <Link
-                  to="/home/market?category=Parser"
+                  to="/home/add-extension"
                   className="text-sm text-primary hover:underline mt-1 inline-block"
                 >
                   {t('knowledge.documentsTab.installParserHint')}
@@ -297,19 +298,7 @@ export default function FileUploadZone({
             <label htmlFor="file-upload" className="cursor-pointer block">
               <div className="space-y-2">
                 <div className="mx-auto w-10 h-10 bg-gray-100 rounded-full flex items-center justify-center">
-                  <svg
-                    className="w-5 h-5 text-gray-400"
-                    fill="none"
-                    stroke="currentColor"
-                    viewBox="0 0 24 24"
-                  >
-                    <path
-                      strokeLinecap="round"
-                      strokeLinejoin="round"
-                      strokeWidth={2}
-                      d="M7 16a4 4 0 01-.88-7.903A5 5 0 1115.9 6L16 6a5 5 0 011 9.9M15 13l-3-3m0 0l-3 3m3-3v12"
-                    />
-                  </svg>
+                  <CloudUpload className="w-5 h-5 text-gray-400" />
                 </div>
 
                 <div>

web/src/app/home/knowledge/components/kb-form/KBForm.tsx

@@ -324,7 +324,7 @@ export default function KBForm({
           {t('knowledge.noEnginesAvailable')}
         </p>
         <Link
-          to="/home/market?category=KnowledgeEngine"
+          to="/home/add-extension"
           className="text-sm text-primary hover:underline"
         >
           {t('knowledge.installEngineHint')}

web/src/app/home/layout.tsx

@@ -45,9 +45,10 @@ import {
 
 // Routes that belong to the "Extensions" section
 const EXTENSIONS_ROUTES = [
-  '/home/plugins',
-  '/home/market',
+  '/home/extensions',
+  '/home/add-extension',
   '/home/mcp',
+  '/home/skills',
   '/home/plugin-pages',
 ];
 
@@ -57,12 +58,17 @@ function isExtensionsRoute(pathname: string): boolean {
   );
 }
 
+const HOME_CONTENT_MAX_WIDTH = 'max-w-[1360px]';
+const BACKEND_UNAVAILABLE_RETURN_TO_STORAGE_KEY =
+  'langbot_backend_unavailable_return_to';
+
 export default function HomeLayout({
   children,
 }: Readonly<{
   children: React.ReactNode;
 }>) {
   const navigate = useNavigate();
+  const location = useLocation();
 
   // Initialize user info if not already initialized
   useEffect(() => {
@@ -73,19 +79,35 @@ export default function HomeLayout({
 
   // Auto-redirect to wizard on first visit (wizard not yet completed on this instance)
   useEffect(() => {
+    let cancelled = false;
+
     const checkWizard = async () => {
       try {
         // Always re-fetch to ensure we have the latest wizard_status from backend
-        await initializeSystemInfo();
-        if (systemInfo.wizard_status === 'none') {
-          navigate('/wizard');
+        await initializeSystemInfo({ throwOnError: true });
+        if (!cancelled && systemInfo.wizard_status === 'none') {
+          navigate('/wizard', { replace: true });
         }
       } catch {
-        // If fetching system info fails, don't redirect
+        if (!cancelled) {
+          const returnTo = `${location.pathname}${location.search}${location.hash}`;
+          sessionStorage.setItem(
+            BACKEND_UNAVAILABLE_RETURN_TO_STORAGE_KEY,
+            returnTo,
+          );
+          navigate('/backend-unavailable', {
+            replace: true,
+            state: { from: returnTo },
+          });
+        }
       }
     };
     checkWizard();
-  }, [navigate]);
+
+    return () => {
+      cancelled = true;
+    };
+  }, [location.hash, location.pathname, location.search, navigate]);
 
   return (
     <SidebarDataProvider>
@@ -123,7 +145,7 @@ function HomeLayoutInner({ children }: { children: React.ReactNode }) {
   const sectionLabel = isExtensions
     ? t('sidebar.extensions')
     : t('sidebar.home');
-  const sectionLink = isExtensions ? '/home/plugins' : '/home/monitoring';
+  const sectionLink = isExtensions ? '/home/extensions' : '/home/monitoring';
 
   return (
     <SidebarProvider>
@@ -133,7 +155,7 @@ function HomeLayoutInner({ children }: { children: React.ReactNode }) {
 
       <SidebarInset>
         <header className="flex h-16 shrink-0 items-center gap-2 transition-[width,height] ease-linear group-has-data-[collapsible=icon]/sidebar-wrapper:h-12">
-          <div className="flex items-center gap-2 px-4">
+          <div className="flex w-full items-center gap-2 px-4">
             <SidebarTrigger className="-ml-1" />
             <Separator
               orientation="vertical"
@@ -177,9 +199,13 @@ function HomeLayoutInner({ children }: { children: React.ReactNode }) {
           </div>
         </header>
 
-        <div className="flex-1 overflow-hidden p-4 pt-0 min-w-0">
-          {mainContent}
-        </div>
+        <main className="flex-1 overflow-hidden min-w-0 px-4 pb-4 pt-0">
+          <div
+            className={`mx-auto h-full w-full min-w-0 ${HOME_CONTENT_MAX_WIDTH}`}
+          >
+            {mainContent}
+          </div>
+        </main>
 
         <SurveyWidget />
       </SidebarInset>

web/src/app/home/market/page.tsx

@@ -1,202 +0,0 @@
-import MarketPage from '@/app/home/plugins/components/plugin-market/PluginMarketComponent';
-import {
-  Dialog,
-  DialogContent,
-  DialogHeader,
-  DialogTitle,
-  DialogFooter,
-} from '@/components/ui/dialog';
-import { Button } from '@/components/ui/button';
-import { Download } from 'lucide-react';
-import React, { useState, useCallback, useEffect } from 'react';
-import { httpClient } from '@/app/infra/http/HttpClient';
-import { systemInfo } from '@/app/infra/http/HttpClient';
-import { toast } from 'sonner';
-import { useTranslation } from 'react-i18next';
-import { PluginV4 } from '@/app/infra/entities/plugin';
-import { useSidebarData } from '@/app/home/components/home-sidebar/SidebarDataContext';
-import { usePluginInstallTasks } from '@/app/home/plugins/components/plugin-install-task';
-
-enum PluginInstallStatus {
-  ASK_CONFIRM = 'ask_confirm',
-  INSTALLING = 'installing',
-  ERROR = 'error',
-}
-
-export default function MarketplacePage() {
-  const { t } = useTranslation();
-
-  if (!systemInfo?.enable_marketplace) {
-    return (
-      <div className="flex flex-col items-center justify-center h-[60vh] text-center">
-        <p className="text-muted-foreground">{t('plugins.marketplace')}</p>
-      </div>
-    );
-  }
-
-  return <MarketplaceContent />;
-}
-
-function MarketplaceContent() {
-  const { t } = useTranslation();
-  const { refreshPlugins } = useSidebarData();
-  const {
-    addTask,
-    setSelectedTaskId,
-    registerOnTaskComplete,
-    unregisterOnTaskComplete,
-  } = usePluginInstallTasks();
-  const [modalOpen, setModalOpen] = useState(false);
-  const [installInfo, setInstallInfo] = useState<Record<string, string>>({});
-  const [pluginInstallStatus, setPluginInstallStatus] =
-    useState<PluginInstallStatus>(PluginInstallStatus.ASK_CONFIRM);
-  const [installError, setInstallError] = useState<string | null>(null);
-
-  async function checkExtensionsLimit(): Promise<boolean> {
-    const maxExtensions = systemInfo.limitation?.max_extensions ?? -1;
-    if (maxExtensions < 0) return true;
-    try {
-      const [pluginsResp, mcpResp] = await Promise.all([
-        httpClient.getPlugins(),
-        httpClient.getMCPServers(),
-      ]);
-      const total =
-        (pluginsResp.plugins?.length ?? 0) + (mcpResp.servers?.length ?? 0);
-      if (total >= maxExtensions) {
-        toast.error(
-          t('limitation.maxExtensionsReached', { max: maxExtensions }),
-        );
-        return false;
-      }
-    } catch {
-      // If we can't check, let backend handle it
-    }
-    return true;
-  }
-
-  // Register task completion callback for toast and plugin list refresh
-  useEffect(() => {
-    const onComplete = (_taskId: number, success: boolean, error?: string) => {
-      if (success) {
-        toast.success(t('plugins.installSuccess'));
-        refreshPlugins();
-      } else {
-        toast.error(error || t('plugins.installFailed'));
-      }
-    };
-    registerOnTaskComplete(onComplete);
-    return () => {
-      unregisterOnTaskComplete(onComplete);
-    };
-  }, [registerOnTaskComplete, unregisterOnTaskComplete, refreshPlugins, t]);
-
-  const handleInstallPlugin = useCallback(
-    async (plugin: PluginV4) => {
-      if (!(await checkExtensionsLimit())) return;
-      setInstallInfo({
-        plugin_author: plugin.author,
-        plugin_name: plugin.name,
-        plugin_version: plugin.latest_version,
-      });
-      setPluginInstallStatus(PluginInstallStatus.ASK_CONFIRM);
-      setInstallError(null);
-      setModalOpen(true);
-    },
-    [t],
-  );
-
-  function handleModalConfirm() {
-    setPluginInstallStatus(PluginInstallStatus.INSTALLING);
-    const pluginDisplayName = `${installInfo.plugin_author}/${installInfo.plugin_name}`;
-    httpClient
-      .installPluginFromMarketplace(
-        installInfo.plugin_author,
-        installInfo.plugin_name,
-        installInfo.plugin_version,
-      )
-      .then((resp) => {
-        const taskId = resp.task_id;
-        const taskKey = `marketplace-${taskId}`;
-        addTask({
-          taskId,
-          pluginName: pluginDisplayName,
-          source: 'marketplace',
-        });
-        setSelectedTaskId(taskKey);
-        setModalOpen(false);
-      })
-      .catch((err) => {
-        setInstallError(err.msg);
-        setPluginInstallStatus(PluginInstallStatus.ERROR);
-      });
-  }
-
-  return (
-    <>
-      <div className="h-full overflow-y-auto">
-        <MarketPage installPlugin={handleInstallPlugin} />
-      </div>
-
-      <Dialog
-        open={modalOpen}
-        onOpenChange={(open) => {
-          setModalOpen(open);
-          if (!open) {
-            setInstallError(null);
-          }
-        }}
-      >
-        <DialogContent className="w-[500px] max-h-[80vh] p-6 bg-white dark:bg-[#1a1a1e] overflow-y-auto">
-          <DialogHeader>
-            <DialogTitle className="flex items-center gap-4">
-              <Download className="size-6" />
-              <span>{t('plugins.installPlugin')}</span>
-            </DialogTitle>
-          </DialogHeader>
-
-          {pluginInstallStatus === PluginInstallStatus.ASK_CONFIRM && (
-            <div className="mt-4">
-              <p className="mb-2">
-                {t('plugins.askConfirm', {
-                  name: installInfo.plugin_name,
-                  version: installInfo.plugin_version,
-                })}
-              </p>
-            </div>
-          )}
-
-          {pluginInstallStatus === PluginInstallStatus.INSTALLING && (
-            <div className="mt-4">
-              <p className="mb-2">{t('plugins.installing')}</p>
-            </div>
-          )}
-
-          {pluginInstallStatus === PluginInstallStatus.ERROR && (
-            <div className="mt-4">
-              <p className="mb-2">{t('plugins.installFailed')}</p>
-              <p className="mb-2 text-red-500">{installError}</p>
-            </div>
-          )}
-
-          <DialogFooter>
-            {pluginInstallStatus === PluginInstallStatus.ASK_CONFIRM && (
-              <>
-                <Button variant="outline" onClick={() => setModalOpen(false)}>
-                  {t('common.cancel')}
-                </Button>
-                <Button onClick={handleModalConfirm}>
-                  {t('common.confirm')}
-                </Button>
-              </>
-            )}
-            {pluginInstallStatus === PluginInstallStatus.ERROR && (
-              <Button variant="default" onClick={() => setModalOpen(false)}>
-                {t('common.close')}
-              </Button>
-            )}
-          </DialogFooter>
-        </DialogContent>
-      </Dialog>
-    </>
-  );
-}

web/src/app/home/mcp/MCPDetailContent.tsx

@@ -3,6 +3,7 @@ import { useNavigate } from 'react-router-dom';
 import { Button } from '@/components/ui/button';
 import { Switch } from '@/components/ui/switch';
 import { Label } from '@/components/ui/label';
+import { Badge } from '@/components/ui/badge';
 import {
   Card,
   CardContent,
@@ -23,31 +24,43 @@ import type { MCPFormHandle } from '@/app/home/mcp/components/mcp-form/MCPForm';
 import { httpClient, systemInfo } from '@/app/infra/http/HttpClient';
 import { useSidebarData } from '@/app/home/components/home-sidebar/SidebarDataContext';
 import { useTranslation } from 'react-i18next';
-import { Trash2 } from 'lucide-react';
+import { Server, Trash2 } from 'lucide-react';
 import { toast } from 'sonner';
 
+type MCPRuntimeState = 'connected' | 'connecting' | 'error';
+type MCPConnectionState =
+  | 'connected'
+  | 'connecting'
+  | 'error'
+  | 'disabled'
+  | 'disconnected';
+
 export default function MCPDetailContent({ id }: { id: string }) {
   const isCreateMode = id === 'new';
   const navigate = useNavigate();
   const { t } = useTranslation();
   const { refreshMCPServers, mcpServers, setDetailEntityName } =
     useSidebarData();
+  const server = mcpServers.find((s) => s.id === id);
+  const displayName = (server?.name ?? id).replace(/__/g, '/');
 
   // Set breadcrumb entity name
   useEffect(() => {
     if (isCreateMode) {
       setDetailEntityName(t('mcp.createServer'));
     } else {
-      const server = mcpServers.find((s) => s.id === id);
-      setDetailEntityName(server?.name ?? id);
+      setDetailEntityName(displayName);
     }
     return () => setDetailEntityName(null);
-  }, [id, isCreateMode, mcpServers, setDetailEntityName, t]);
+  }, [displayName, isCreateMode, setDetailEntityName, t]);
 
   const [showDeleteConfirm, setShowDeleteConfirm] = useState(false);
 
   // Track whether the form has unsaved changes
   const [formDirty, setFormDirty] = useState(false);
+  // True when the form picked stdio mode but Box is disabled/unreachable —
+  // saving would create a server that can never start, so block it.
+  const [saveBlockedByBox, setSaveBlockedByBox] = useState(false);
 
   // Ref to MCPForm for triggering test from header
   const formRef = useRef<MCPFormHandle>(null);
@@ -56,13 +69,55 @@ export default function MCPDetailContent({ id }: { id: string }) {
   // Enable state managed here so the header switch works
   const [serverEnabled, setServerEnabled] = useState(true);
   const [enableLoaded, setEnableLoaded] = useState(false);
+  const [detailRuntimeStatus, setDetailRuntimeStatus] =
+    useState<MCPRuntimeState | null>(null);
+
+  const runtimeStatus = detailRuntimeStatus ?? server?.runtimeStatus;
+
+  const currentConnectionState: MCPConnectionState =
+    (enableLoaded ? serverEnabled : server?.enabled) === false
+      ? 'disabled'
+      : runtimeStatus === 'connected' ||
+          runtimeStatus === 'connecting' ||
+          runtimeStatus === 'error'
+        ? runtimeStatus
+        : 'disconnected';
+
+  const connectionStatusLabel: Record<MCPConnectionState, string> = {
+    connected: t('mcp.statusConnected'),
+    connecting: t('mcp.connecting'),
+    error: t('mcp.statusError'),
+    disabled: t('mcp.statusDisabled'),
+    disconnected: t('mcp.statusDisconnected'),
+  };
+
+  const connectionStatusClassName: Record<MCPConnectionState, string> = {
+    connected:
+      'border-green-200 bg-green-50 text-green-700 dark:border-green-900/70 dark:bg-green-950/40 dark:text-green-300',
+    connecting:
+      'border-amber-200 bg-amber-50 text-amber-700 dark:border-amber-900/70 dark:bg-amber-950/40 dark:text-amber-300',
+    error:
+      'border-red-200 bg-red-50 text-red-700 dark:border-red-900/70 dark:bg-red-950/40 dark:text-red-300',
+    disabled: 'border-muted-foreground/20 bg-muted text-muted-foreground',
+    disconnected: 'border-muted-foreground/20 bg-muted text-muted-foreground',
+  };
+
+  const connectionDotClassName: Record<MCPConnectionState, string> = {
+    connected: 'bg-green-500',
+    connecting: 'bg-amber-500',
+    error: 'bg-red-500',
+    disabled: 'bg-muted-foreground/50',
+    disconnected: 'bg-muted-foreground/50',
+  };
 
   // Fetch server enable state
   useEffect(() => {
     if (!isCreateMode) {
+      setDetailRuntimeStatus(null);
       httpClient.getMCPServer(id).then((res) => {
         const server = res.server ?? res;
         setServerEnabled(server.enable ?? true);
+        setDetailRuntimeStatus(server.runtime_info?.status ?? null);
         setEnableLoaded(true);
       });
     }
@@ -142,10 +197,24 @@ export default function MCPDetailContent({ id }: { id: string }) {
   if (isCreateMode) {
     return (
       <div className="flex h-full flex-col">
-        {/* Header */}
-        <div className="flex items-center justify-between pb-4 shrink-0">
-          <h1 className="text-xl font-semibold">{t('mcp.createServer')}</h1>
-          <div className="flex items-center gap-2">
+        <div className="flex shrink-0 flex-col gap-3 pb-4 sm:flex-row sm:items-start sm:justify-between">
+          <div className="flex min-w-0 items-center gap-3">
+            <h1 className="truncate text-xl font-semibold">
+              {t('mcp.createServer')}
+            </h1>
+            <Badge variant="outline" className="shrink-0 text-[0.7rem]">
+              <Server className="size-3.5" />
+              {t('mcp.title')}
+            </Badge>
+          </div>
+          <div className="flex flex-wrap gap-2">
+            <Button
+              type="button"
+              variant="outline"
+              onClick={() => navigate('/home/add-extension')}
+            >
+              {t('common.cancel')}
+            </Button>
             <Button
               type="button"
               variant="outline"
@@ -157,6 +226,7 @@ export default function MCPDetailContent({ id }: { id: string }) {
             <Button
               type="submit"
               form="mcp-form"
+              disabled={saveBlockedByBox}
               onClick={async (e) => {
                 if (!(await checkExtensionsLimit())) {
                   e.preventDefault();
@@ -168,47 +238,99 @@ export default function MCPDetailContent({ id }: { id: string }) {
           </div>
         </div>
 
-        {/* Content */}
-        <div className="flex-1 overflow-y-auto min-h-0">
-          <div className="mx-auto max-w-3xl pb-8">
-            <MCPForm
-              ref={formRef}
-              initServerName={undefined}
-              onFormSubmit={handleFormSubmit}
-              onNewServerCreated={handleNewServerCreated}
-              onTestingChange={setMcpTesting}
-            />
-          </div>
+        <div className="min-h-0 flex-1">
+          <MCPForm
+            ref={formRef}
+            initServerName={undefined}
+            layout="split"
+            onFormSubmit={handleFormSubmit}
+            onNewServerCreated={handleNewServerCreated}
+            onTestingChange={setMcpTesting}
+            onSaveBlockedChange={setSaveBlockedByBox}
+          />
         </div>
       </div>
     );
   }
 
+  const enableControl = enableLoaded && (
+    <Card>
+      <CardHeader>
+        <CardTitle>{t('common.enable')}</CardTitle>
+      </CardHeader>
+      <CardContent>
+        <div className="flex items-center justify-between">
+          <Label
+            htmlFor="mcp-enable-switch"
+            className="cursor-pointer text-sm font-medium"
+          >
+            {t('common.enable')}
+          </Label>
+          <Switch
+            id="mcp-enable-switch"
+            checked={serverEnabled}
+            onCheckedChange={handleEnableToggle}
+          />
+        </div>
+      </CardContent>
+    </Card>
+  );
+
+  const editActions = (
+    <Card className="border-destructive/50">
+      <CardHeader>
+        <CardTitle className="text-destructive">
+          {t('mcp.dangerZone')}
+        </CardTitle>
+        <CardDescription>{t('mcp.dangerZoneDescription')}</CardDescription>
+      </CardHeader>
+      <CardContent>
+        <div className="flex flex-col gap-3 sm:flex-row sm:items-center sm:justify-between">
+          <div className="space-y-1">
+            <p className="text-sm font-medium">{t('mcp.deleteMCPAction')}</p>
+            <p className="text-sm text-muted-foreground">
+              {t('mcp.deleteMCPHint')}
+            </p>
+          </div>
+          <Button
+            type="button"
+            variant="destructive"
+            size="sm"
+            onClick={() => setShowDeleteConfirm(true)}
+            className="shrink-0"
+          >
+            <Trash2 className="mr-1.5 size-4" />
+            {t('common.delete')}
+          </Button>
+        </div>
+      </CardContent>
+    </Card>
+  );
+
   // ==================== Edit Mode ====================
   return (
     <>
       <div className="flex h-full flex-col">
-        {/* Header: title + enable switch + save button */}
-        <div className="flex items-center justify-between pb-4 shrink-0">
-          <div className="flex items-center gap-4">
-            <h1 className="text-xl font-semibold">{t('mcp.editServer')}</h1>
-            {enableLoaded && (
-              <div className="flex items-center gap-2">
-                <Switch
-                  id="mcp-enable-switch"
-                  checked={serverEnabled}
-                  onCheckedChange={handleEnableToggle}
+        <div className="flex shrink-0 flex-col gap-3 pb-4 sm:flex-row sm:items-start sm:justify-between">
+          <div className="min-w-0 space-y-1">
+            <div className="flex min-w-0 items-center gap-3">
+              <h1 className="truncate text-xl font-semibold">{displayName}</h1>
+              <Badge variant="outline" className="shrink-0 text-[0.7rem]">
+                <Server className="size-3.5" />
+                {t('mcp.title')}
+              </Badge>
+              <Badge
+                variant="outline"
+                className={`shrink-0 gap-1.5 text-[0.7rem] ${connectionStatusClassName[currentConnectionState]}`}
+              >
+                <span
+                  className={`size-1.5 rounded-full ${connectionDotClassName[currentConnectionState]}`}
                 />
-                <Label
-                  htmlFor="mcp-enable-switch"
-                  className="text-sm text-muted-foreground cursor-pointer"
-                >
-                  {t('common.enable')}
-                </Label>
-              </div>
-            )}
+                {connectionStatusLabel[currentConnectionState]}
+              </Badge>
+            </div>
           </div>
-          <div className="flex items-center gap-2">
+          <div className="flex flex-wrap gap-2">
             <Button
               type="button"
               variant="outline"
@@ -217,57 +339,32 @@ export default function MCPDetailContent({ id }: { id: string }) {
             >
               {t('common.test')}
             </Button>
-            <Button type="submit" form="mcp-form" disabled={!formDirty}>
+            <Button
+              type="submit"
+              form="mcp-form"
+              disabled={!formDirty || saveBlockedByBox}
+            >
               {t('common.save')}
             </Button>
           </div>
         </div>
 
-        {/* Content */}
-        <div className="flex-1 overflow-y-auto min-h-0">
-          <div className="mx-auto max-w-3xl space-y-6 pb-8">
-            <MCPForm
-              ref={formRef}
-              initServerName={id}
-              onFormSubmit={handleFormSubmit}
-              onNewServerCreated={handleNewServerCreated}
-              onDirtyChange={setFormDirty}
-              onTestingChange={setMcpTesting}
-            />
-
-            {/* Card: Danger Zone */}
-            <Card className="border-destructive/50">
-              <CardHeader>
-                <CardTitle className="text-destructive">
-                  {t('mcp.dangerZone')}
-                </CardTitle>
-                <CardDescription>
-                  {t('mcp.dangerZoneDescription')}
-                </CardDescription>
-              </CardHeader>
-              <CardContent>
-                <div className="flex items-center justify-between">
-                  <div className="space-y-1">
-                    <p className="text-sm font-medium">
-                      {t('mcp.deleteMCPAction')}
-                    </p>
-                    <p className="text-sm text-muted-foreground">
-                      {t('mcp.deleteMCPHint')}
-                    </p>
-                  </div>
-                  <Button
-                    type="button"
-                    variant="destructive"
-                    size="sm"
-                    onClick={() => setShowDeleteConfirm(true)}
-                  >
-                    <Trash2 className="size-4 mr-1.5" />
-                    {t('common.delete')}
-                  </Button>
-                </div>
-              </CardContent>
-            </Card>
-          </div>
+        <div className="min-h-0 flex-1">
+          <MCPForm
+            ref={formRef}
+            initServerName={id}
+            layout="split"
+            sideHeader={enableControl}
+            sideFooter={editActions}
+            onFormSubmit={handleFormSubmit}
+            onNewServerCreated={handleNewServerCreated}
+            onDirtyChange={setFormDirty}
+            onTestingChange={setMcpTesting}
+            onSaveBlockedChange={setSaveBlockedByBox}
+            onRuntimeInfoChange={(runtimeInfo) =>
+              setDetailRuntimeStatus(runtimeInfo?.status ?? null)
+            }
+          />
         </div>
       </div>
 

web/src/app/home/monitoring/components/FeedbackCard.tsx

@@ -6,6 +6,8 @@ import {
   TrendingUp,
   TrendingDown,
   Minus,
+  Heart,
+  Smile,
 } from 'lucide-react';
 
 interface FeedbackCardProps {
@@ -133,11 +135,7 @@ export function FeedbackStatsCards({ stats, loading }: FeedbackStatsProps) {
     {
       title: t('monitoring.feedback.totalFeedback'),
       value: stats?.totalFeedback ?? 0,
-      icon: (
-        <svg className="w-6 h-6" viewBox="0 0 24 24" fill="currentColor">
-          <path d="M12 21.35l-1.45-1.32C5.4 15.36 2 12.28 2 8.5 2 5.42 4.42 3 7.5 3c1.74 0 3.41.81 4.5 2.09C13.09 3.81 14.76 3 16.5 3 19.58 3 22 5.42 22 8.5c0 3.78-3.4 6.86-8.55 11.54L12 21.35z" />
-        </svg>
-      ),
+      icon: <Heart className="w-6 h-6" />,
       variant: 'default' as const,
     },
     {
@@ -155,11 +153,7 @@ export function FeedbackStatsCards({ stats, loading }: FeedbackStatsProps) {
     {
       title: t('monitoring.feedback.satisfactionRate'),
       value: stats ? `${stats.satisfactionRate}%` : '0%',
-      icon: (
-        <svg className="w-6 h-6" viewBox="0 0 24 24" fill="currentColor">
-          <path d="M11.99 2C6.47 2 2 6.48 2 12s4.47 10 9.99 10C17.52 22 22 17.52 22 12S17.52 2 11.99 2zM12 20c-4.42 0-8-3.58-8-8s3.58-8 8-8 8 3.58 8 8-3.58 8-8 8zm3.5-9c.83 0 1.5-.67 1.5-1.5S16.33 8 15.5 8 14 8.67 14 9.5s.67 1.5 1.5 1.5zm-7 0c.83 0 1.5-.67 1.5-1.5S9.33 8 8.5 8 7 8.67 7 9.5 7.67 11 8.5 11zm3.5 6.5c2.33 0 4.31-1.46 5.11-3.5H6.89c.8 2.04 2.78 3.5 5.11 3.5z" />
-        </svg>
-      ),
+      icon: <Smile className="w-6 h-6" />,
       variant: (stats && stats.satisfactionRate >= 80
         ? 'success'
         : stats && stats.satisfactionRate >= 50

web/src/app/home/monitoring/components/FeedbackList.tsx

@@ -6,6 +6,7 @@ import {
   ChevronRight,
   ChevronDown,
   ExternalLink,
+  Heart,
 } from 'lucide-react';
 import { FeedbackRecord } from '../types/monitoring';
 import { Button } from '@/components/ui/button';
@@ -40,19 +41,7 @@ export function FeedbackList({
   if (!feedback || feedback.length === 0) {
     return (
       <div className="text-center text-gray-500 dark:text-gray-400 py-16">
-        <svg
-          className="w-16 h-16 mx-auto mb-4 text-gray-300 dark:text-gray-600"
-          fill="none"
-          viewBox="0 0 24 24"
-          stroke="currentColor"
-        >
-          <path
-            strokeLinecap="round"
-            strokeLinejoin="round"
-            strokeWidth={1.5}
-            d="M4.318 6.318a4.5 4.5 0 000 6.364L12 20.364l7.682-7.682a4.5 4.5 0 00-6.364-6.364L12 7.636l-1.318-1.318a4.5 4.5 0 00-6.364 0z"
-          />
-        </svg>
+        <Heart className="w-16 h-16 mx-auto mb-4 text-gray-300 dark:text-gray-600" />
         <p className="text-base font-medium mb-2">
           {t('monitoring.feedback.noFeedback')}
         </p>

web/src/app/home/monitoring/components/MessageContentRenderer.tsx

@@ -1,4 +1,5 @@
 import React, { useState } from 'react';
+import { Paperclip, AudioLines } from 'lucide-react';
 import {
   MessageChainComponent,
   Image as ImageComponent,
@@ -104,13 +105,7 @@ export function MessageContentRenderer({
             key={index}
             className="inline-flex items-center px-1.5 py-0.5 mx-0.5 rounded bg-muted text-muted-foreground text-sm"
           >
-            <svg
-              className="w-3.5 h-3.5 mr-1"
-              fill="currentColor"
-              viewBox="0 0 20 20"
-            >
-              <path d="M8 4a3 3 0 00-3 3v4a5 5 0 0010 0V7a1 1 0 112 0v4a7 7 0 11-14 0V7a5 5 0 0110 0v4a3 3 0 11-6 0V7a1 1 0 012 0v4a1 1 0 102 0V7a3 3 0 00-3-3z" />
-            </svg>
+            <Paperclip className="w-3.5 h-3.5 mr-1" />
             {file.name || 'File'}
           </span>
         );
@@ -123,13 +118,7 @@ export function MessageContentRenderer({
             key={index}
             className="inline-flex items-center px-1.5 py-0.5 mx-0.5 rounded bg-muted text-muted-foreground text-sm"
           >
-            <svg
-              className="w-3.5 h-3.5 mr-1"
-              fill="currentColor"
-              viewBox="0 0 20 20"
-            >
-              <path d="M18 3a1 1 0 00-1.196-.98l-10 2A1 1 0 006 5v9.114A4.369 4.369 0 005 14c-1.657 0-3 .895-3 2s1.343 2 3 2 3-.895 3-2V7.82l8-1.6v5.894A4.37 4.37 0 0015 12c-1.657 0-3 .895-3 2s1.343 2 3 2 3-.895 3-2V3z" />
-            </svg>
+            <AudioLines className="w-3.5 h-3.5 mr-1" />
             Voice{voice.length ? ` ${voice.length}s` : ''}
           </span>
         );

web/src/app/home/monitoring/components/MessageDetailsCard.tsx

@@ -1,5 +1,6 @@
 import React, { useMemo } from 'react';
 import { useTranslation } from 'react-i18next';
+import { Info, Clock, AlertCircle, Braces } from 'lucide-react';
 import { MessageDetails } from '../types/monitoring';
 
 interface MessageDetailsCardProps {
@@ -25,14 +26,7 @@ export function MessageDetailsCard({ details }: MessageDetailsCardProps) {
       {details.message && (
         <div className="bg-muted rounded-lg p-3">
           <h4 className="text-sm font-semibold text-foreground mb-3 flex items-center">
-            <svg
-              className="w-4 h-4 mr-2"
-              xmlns="http://www.w3.org/2000/svg"
-              viewBox="0 0 24 24"
-              fill="currentColor"
-            >
-              <path d="M12 22C6.47715 22 2 17.5228 2 12C2 6.47715 6.47715 2 12 2C17.5228 2 22 6.47715 22 12C22 17.5228 17.5228 22 12 22ZM12 20C16.4183 20 20 16.4183 20 12C20 7.58172 16.4183 4 12 4C7.58172 4 4 7.58172 4 12C4 16.4183 7.58172 20 12 20ZM11 7H13V9H11V7ZM11 11H13V17H11V11Z"></path>
-            </svg>
+            <Info className="w-4 h-4 mr-2" />
             {t('monitoring.messageList.viewDetails')}
           </h4>
 
@@ -92,14 +86,7 @@ export function MessageDetailsCard({ details }: MessageDetailsCardProps) {
       {details.llmCalls && details.llmCalls.length > 0 && (
         <div className="bg-muted rounded-lg p-3">
           <h4 className="text-sm font-semibold text-foreground mb-3 flex items-center">
-            <svg
-              className="w-4 h-4 mr-2"
-              xmlns="http://www.w3.org/2000/svg"
-              viewBox="0 0 24 24"
-              fill="currentColor"
-            >
-              <path d="M12 2C17.52 2 22 6.48 22 12C22 17.52 17.52 22 12 22C6.48 22 2 17.52 2 12C2 6.48 6.48 2 12 2ZM12 20C16.42 20 20 16.42 20 12C20 7.58 16.42 4 12 4C7.58 4 4 7.58 4 12C4 16.42 7.58 20 12 20ZM13 12V7H11V14H17V12H13Z"></path>
-            </svg>
+            <Clock className="w-4 h-4 mr-2" />
             {t('monitoring.llmCalls.title')} ({details.llmCalls.length})
           </h4>
 
@@ -183,14 +170,7 @@ export function MessageDetailsCard({ details }: MessageDetailsCardProps) {
       {details.errors && details.errors.length > 0 && (
         <div className="bg-muted rounded-lg p-3">
           <h4 className="text-sm font-semibold text-red-700 dark:text-red-400 mb-3 flex items-center">
-            <svg
-              className="w-4 h-4 mr-2"
-              xmlns="http://www.w3.org/2000/svg"
-              viewBox="0 0 24 24"
-              fill="currentColor"
-            >
-              <path d="M12 22C6.47715 22 2 17.5228 2 12C2 6.47715 6.47715 2 12 2C17.5228 2 22 6.47715 22 12C22 17.5228 17.5228 22 12 22ZM12 20C16.4183 20 20 16.4183 20 12C20 7.58172 16.4183 4 12 4C7.58172 4 4 7.58172 4 12C4 16.4183 7.58172 20 12 20ZM11 15H13V17H11V15ZM11 7H13V13H11V7Z"></path>
-            </svg>
+            <AlertCircle className="w-4 h-4 mr-2" />
             {t('monitoring.errors.title')} ({details.errors.length})
           </h4>
           <div className="space-y-2">
@@ -227,14 +207,7 @@ export function MessageDetailsCard({ details }: MessageDetailsCardProps) {
         details.message?.runnerName !== 'local-agent' && (
           <div className="bg-muted rounded-lg p-3">
             <h4 className="text-sm font-semibold text-foreground mb-3 flex items-center">
-              <svg
-                className="w-4 h-4 mr-2"
-                xmlns="http://www.w3.org/2000/svg"
-                viewBox="0 0 24 24"
-                fill="currentColor"
-              >
-                <path d="M4 18V14.3C4 13.4716 3.32843 12.8 2.5 12.8H2V11.2H2.5C3.32843 11.2 4 10.5284 4 9.7V6C4 4.34315 5.34315 3 7 3H8V5H7C6.44772 5 6 5.44772 6 6V9.7C6 10.7065 5.41099 11.5849 4.55132 12C5.41099 12.4151 6 13.2935 6 14.3V18C6 18.5523 6.44772 19 7 19H8V21H7C5.34315 21 4 19.6569 4 18ZM20 14.3V18C20 19.6569 18.6569 21 17 21H16V19H17C17.5523 19 18 18.5523 18 18V14.3C18 13.2935 18.589 12.4151 19.4487 12C18.589 11.5849 18 10.7065 18 9.7V6C18 5.44772 17.5523 5 17 5H16V3H17C18.6569 3 20 4.34315 20 6V9.7C20 10.5284 20.6716 11.2 21.5 11.2H22V12.8H21.5C20.6716 12.8 20 13.4716 20 14.3Z"></path>
-              </svg>
+              <Braces className="w-4 h-4 mr-2" />
               {t('monitoring.queryVariables.title')}
             </h4>
             <div className="grid grid-cols-2 md:grid-cols-4 gap-2 text-xs">