style: format core skill orchestration

refactor(skill): compose generic box mounts in core
feat(skill): use SDK store without box execution
2026-09-05 17:17:14 +00:00 · 2026-09-05 23:18:17 +08:00 · 2026-09-05 23:09:46 +08:00 · 2026-09-05 19:49:35 +08:00 · 2026-09-05 01:19:28 +08:00 · 2026-09-05 00:55:18 +08:00
132 changed files with 3346 additions and 1323 deletions
@@ -1,5 +1,5 @@
 name: 漏洞反馈
-description: 【供中文用户】报错或漏洞请使用这个模板创建，不使用此模板创建的异常、漏洞相关issue将被直接关闭。由于自己操作不当/不甚了解所用技术栈引起的网络连接问题恕无法解决，请勿提 issue。容器间网络连接问题，参考文档 https://link.langbot.app/zh/docs/network  
+description: 【供中文用户】报错或漏洞请使用这个模板创建，不使用此模板创建的异常、漏洞相关issue将被直接关闭。由于自己操作不当/不甚了解所用技术栈引起的网络连接问题恕无法解决，请勿提 issue。容器间网络连接问题，参考文档 https://langbot.app/docs/zh/workshop/network-details
 title: "[Bug]: "
 labels: ["bug?"]
 body:
@@ -22,7 +22,7 @@ body:
  - type: textarea
    attributes:
      label: 异常情况
-      description: 完整描述异常情况，什么时候发生的、发生了什么。**请附带日志信息。** 
+      description: 完整描述异常情况，什么时候发生的、发生了什么。**请附带日志信息。**
    validations:
      required: true
  - type: textarea
@@ -1,5 +1,5 @@
 name: Bug report
-description: Report bugs or vulnerabilities using this template. For container network connection issues, refer to the documentation https://link.langbot.app/en/docs/network
+description: Report bugs or vulnerabilities using this template. For container network connection issues, refer to the documentation https://langbot.app/docs/en/workshop/network-details
 title: "[Bug]: "
 labels: ["bug?"]
 body:
@@ -43,8 +43,8 @@ Run the narrowest useful test first, then broader checks when confidence is need
 ## Where to Look

 - Architecture map: `ARCHITECTURE.md`.
- Dev environment guide: https://docs.langbot.app/zh/develop/dev-config.
- Plugin runtime / CLI / SDK debugging: https://docs.langbot.app/zh/develop/plugin-runtime.
+- Dev environment guide: https://langbot.app/docs/zh/develop/dev-config.
+- Plugin runtime / CLI / SDK debugging: https://langbot.app/docs/zh/develop/plugin-runtime.
 - API-key auth: `docs/API_KEY_AUTH.md`.
 - Box deep-dive notes: `docs/review/box-architecture.md` and related files.
 - In-repo skills: `skills/` is the single source of truth for LangBot agent skills.
@@ -169,14 +169,17 @@ The Plugin Runtime supports stdio and WebSocket control transports. Direct local

 ## Box Runtime and Skills

-Box is the sandbox subsystem used by native agent tools, stdio MCP servers, skill authoring, and managed processes.
+Box is the optional sandbox subsystem used by native execution tools, stdio MCP servers, agent-side skill authoring, and managed processes. Skill storage and read-only access are Core responsibilities and remain available without Box.

 In this repo:

- `pkg/box/service.py` is the application-facing facade for exec, sessions, managed processes, skill CRUD, status, reconnects, quotas, mounts, and sandbox profiles.
+- `pkg/box/service.py` is the application-facing facade for exec, sessions, managed processes, status, reconnects, quotas, generic mounts, and sandbox profiles.
 - `pkg/box/connector.py` connects to the Box Runtime over stdio, Windows subprocess+WebSocket, or remote WebSocket.
- `pkg/provider/tools/loaders/native.py`, `mcp_stdio.py`, and skill loaders depend on Box availability.
- `pkg/skill/manager.py` loads skills from the Box runtime, falling back to local `data/skills` when needed.
+- `pkg/provider/tools/loaders/native.py` is the Core orchestration seam: the
+  Skill loader supplies generic read-only mounts to Box execution. `mcp_stdio.py`
+  and execution-backed tools depend on Box availability.
+- `pkg/skill/repository.py` is the thin async/Workspace adapter over the Plugin SDK's execution-independent `SkillStore`; `skills.root` owns its location independently of Box.
+- `pkg/skill/manager.py` caches the Core repository catalog for progressive disclosure. Activation and read-only resource tools do not require Box; script execution and Workspace mutation still do.

 Durable Box Workspace storage is shared across placement generations, but
 sandbox sessions and managed processes are generation-scoped. LangBot validates
@@ -187,11 +190,17 @@ retires stale processes and closes already-attached relays.
 In `langbot-plugin-sdk`:

 - `src/langbot_plugin/box/server.py` implements `lbp box` and the WebSocket endpoints on `:5410`.
- `src/langbot_plugin/box/runtime.py` owns sandbox sessions and managed processes.
+- `src/langbot_plugin/box/runtime.py` owns sandbox sessions, generic read-only mounts, and managed processes.
 - `backend.py`, `nsjail_backend.py`, and `e2b_backend.py` implement sandbox backends.
- `skill_store.py` manages skill packages from the Box side.
+- `src/langbot_plugin/skill_store.py` is consumed by Core, not Box. Core turns
+  selected package roots into generic read-only mounts; Box does not understand
+  Skill names, metadata, revisions, files, or CRUD.

-Important config keys live under `box:` in `src/langbot/templates/config.yaml`: `box.enabled`, `box.backend`, `box.runtime.endpoint`, and `box.local.*`. Start LangBot with `--standalone-box` when connecting to an externally launched Box runtime.
+Skill storage uses `skills.root`. Box execution config lives under `box:`:
+`box.enabled`, `box.backend`, `box.runtime.endpoint`, and `box.local.*`. The old
+`box.local.skills_root` key is read only as an online-upgrade fallback and is
+marked for removal in the next major version. Start LangBot with
+`--standalone-box` when connecting to an externally launched Box runtime.

 ## HTTP API, Web UI, and MCP Server

@@ -19,9 +19,9 @@ English / [简体中文](README_CN.md) / [繁體中文](README_TW.md) / [日本
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)

 <a href="https://langbot.app">Website</a> ｜
-<a href="https://link.langbot.app/en/docs/features">Features</a> ｜
-<a href="https://link.langbot.app/en/docs/guide">Docs</a> ｜
-<a href="https://link.langbot.app/en/docs/api">API</a> ｜
+<a href="https://langbot.app/docs/en/insight/features">Features</a> ｜
+<a href="https://langbot.app/docs/en/insight/guide">Docs</a> ｜
+<a href="https://langbot.app/docs/en/tags/readme">API</a> ｜
 <a href="https://space.langbot.app/cloud">Cloud</a> ｜
 <a href="https://space.langbot.app">Plugin Market</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">Roadmap</a>
@@ -49,7 +49,7 @@ LangBot is an **open-source, production-grade platform** for building AI-powered
 - **Web Management Panel** — Configure, manage, and monitor your bots through an intuitive browser interface. No YAML editing required.
 - **Multi-Pipeline Architecture** — Different bots for different scenarios, with comprehensive monitoring and exception handling.

-[→ Learn more about all features](https://link.langbot.app/en/docs/features)
+[→ Learn more about all features](https://langbot.app/docs/en/insight/features)

 📍 Practical guides: [deploy a multi-platform AI bot in 5 minutes](https://langbot.app/en/blog/deploy-ai-bot-in-5-minutes/), [connect DeepSeek to WeChat, Discord, and Telegram](https://langbot.app/en/blog/connect-deepseek-to-wechat/), [run a Dify Agent in Discord, Telegram, and Slack](https://langbot.app/en/blog/dify-agent-discord-telegram-slack/), and [build an n8n-powered chatbot](https://langbot.app/en/blog/n8n-multi-platform-ai-chatbot/).

@@ -89,7 +89,7 @@ docker compose --profile all up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)

-**More options:** [Docker](https://link.langbot.app/en/docs/docker) · [Manual](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [Kubernetes](https://docs.langbot.app/en/deploy/langbot/kubernetes)
+**More options:** [Docker](https://langbot.app/docs/en/deploy/langbot/docker) · [Manual](https://langbot.app/docs/en/deploy/langbot/manual) · [BTPanel](https://langbot.app/docs/en/deploy/langbot/one-click/bt) · [Kubernetes](https://langbot.app/docs/en/deploy/langbot/kubernetes)

 ---

@@ -151,7 +151,7 @@ _Note: Public demo environment. Do not enter sensitive information._
 | [302.AI](https://share.302ai.cn/SuTG99)                                                                             | Gateway      | ✅     |
 | [Qiniu](https://www.qiniu.com/ai/agent)                                                                           | Gateway      | ✅     |

-[→ View all integrations](https://link.langbot.app/en/docs/features)
+[→ View all integrations](https://langbot.app/docs/en/insight/features)

 ---

@@ -21,9 +21,9 @@
 [![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)

 <a href="https://langbot.app">官网</a> ｜
-<a href="https://link.langbot.app/zh/docs/features">特性</a> ｜
-<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://langbot.app/docs/zh/insight/features">特性</a> ｜
+<a href="https://langbot.app/docs/zh/insight/guide">文档</a> ｜
+<a href="https://langbot.app/docs/zh/tags/readme">API</a> ｜
 <a href="https://space.langbot.app/cloud">Cloud</a> ｜
 <a href="https://space.langbot.app">扩展市场</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">路线图</a>
@@ -49,7 +49,7 @@ LangBot 是一个**开源的生产级平台**，用于构建 AI 驱动的即时
 - **Web 管理面板** — 通过浏览器直观地配置、管理和监控机器人，无需手动编辑配置文件。
 - **多流水线架构** — 不同机器人用于不同场景，具备全面的监控和异常处理能力。

-[→ 了解更多功能特性](https://link.langbot.app/zh/docs/features)
+[→ 了解更多功能特性](https://langbot.app/docs/zh/insight/features)

 📍 实践指南：[5 分钟部署多平台 AI 机器人](https://langbot.app/zh/blog/deploy-ai-bot-in-5-minutes/)、[将 DeepSeek 接入微信、企业微信与 Discord](https://langbot.app/zh/blog/connect-deepseek-to-wechat/)、[让 Dify Agent 跑在 Discord、Telegram 和 Slack 上](https://langbot.app/zh/blog/dify-agent-discord-telegram-slack/)，以及[用 n8n 构建多平台 AI 聊天机器人](https://langbot.app/zh/blog/n8n-multi-platform-ai-chatbot/)。

@@ -89,7 +89,7 @@ docker compose --profile all up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/zh-CN/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)

-**更多方式：** [Docker](https://link.langbot.app/zh/docs/docker) · [手动部署](https://link.langbot.app/zh/docs/manual-deploy) · [宝塔面板](https://link.langbot.app/zh/docs/bt-panel) · [Kubernetes](https://docs.langbot.app/zh/deploy/langbot/kubernetes)
+**更多方式：** [Docker](https://langbot.app/docs/zh/deploy/langbot/docker) · [手动部署](https://langbot.app/docs/zh/deploy/langbot/manual) · [宝塔面板](https://langbot.app/docs/zh/deploy/langbot/one-click/bt) · [Kubernetes](https://langbot.app/docs/zh/deploy/langbot/kubernetes)

 ---

@@ -152,7 +152,7 @@ docker compose --profile all up -d
 | [百宝箱Tbox](https://www.tbox.cn/open) | 智能体平台 | ✅ |
 | [七牛云Qiniu](https://www.qiniu.com/ai/agent) | 聚合平台 | ✅ |

-[→ 查看完整集成列表](https://link.langbot.app/zh/docs/features)
+[→ 查看完整集成列表](https://langbot.app/docs/zh/insight/features)

 ### TTS（语音合成）

@@ -19,9 +19,9 @@
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)

 <a href="https://langbot.app">Inicio</a> ｜
-<a href="https://link.langbot.app/en/docs/features">Características</a> ｜
-<a href="https://link.langbot.app/en/docs/guide">Documentación</a> ｜
-<a href="https://link.langbot.app/en/docs/api">API</a> ｜
+<a href="https://langbot.app/docs/en/insight/features">Características</a> ｜
+<a href="https://langbot.app/docs/en/insight/guide">Documentación</a> ｜
+<a href="https://langbot.app/docs/en/tags/readme">API</a> ｜
 <a href="https://space.langbot.app">Mercado de Plugins</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">Hoja de Ruta</a>

@@ -48,7 +48,7 @@ LangBot es una **plataforma de código abierto y grado de producción** para con
 - **Panel de Gestión Web** — Configure, gestione y monitoree sus bots a través de una interfaz de navegador intuitiva. Sin necesidad de editar YAML.
 - **Arquitectura Multi-Pipeline** — Diferentes bots para diferentes escenarios, con monitoreo completo y manejo de excepciones.

-[→ Conocer más sobre todas las funcionalidades](https://link.langbot.app/en/docs/features)
+[→ Conocer más sobre todas las funcionalidades](https://langbot.app/docs/en/insight/features)

 📍 Guías prácticas: [desplegar un bot de IA multiplataforma en 5 minutos](https://langbot.app/en/blog/deploy-ai-bot-in-5-minutes/), [conectar DeepSeek a WeChat, Discord y Telegram](https://langbot.app/en/blog/connect-deepseek-to-wechat/), [ejecutar un Dify Agent en Discord, Telegram y Slack](https://langbot.app/en/blog/dify-agent-discord-telegram-slack/) y [crear un chatbot con n8n](https://langbot.app/en/blog/n8n-multi-platform-ai-chatbot/).

@@ -88,7 +88,7 @@ docker compose --profile all up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)

-**Más opciones:** [Docker](https://link.langbot.app/en/docs/docker) · [Manual](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [Kubernetes](https://docs.langbot.app/en/deploy/langbot/kubernetes)
+**Más opciones:** [Docker](https://langbot.app/docs/en/deploy/langbot/docker) · [Manual](https://langbot.app/docs/en/deploy/langbot/manual) · [BTPanel](https://langbot.app/docs/en/deploy/langbot/one-click/bt) · [Kubernetes](https://langbot.app/docs/en/deploy/langbot/kubernetes)

 ---

@@ -149,7 +149,7 @@ docker compose --profile all up -d
 | [302.AI](https://share.302ai.cn/SuTG99) | Pasarela | ✅ |
 | [Qiniu](https://www.qiniu.com/ai/agent) | Pasarela | ✅ |

-[→ Ver todas las integraciones](https://link.langbot.app/en/docs/features)
+[→ Ver todas las integraciones](https://langbot.app/docs/en/insight/features)

 ---

@@ -19,9 +19,9 @@
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)

 <a href="https://langbot.app">Accueil</a> ｜
-<a href="https://link.langbot.app/en/docs/features">Fonctionnalités</a> ｜
-<a href="https://link.langbot.app/en/docs/guide">Documentation</a> ｜
-<a href="https://link.langbot.app/en/docs/api">API</a> ｜
+<a href="https://langbot.app/docs/en/insight/features">Fonctionnalités</a> ｜
+<a href="https://langbot.app/docs/en/insight/guide">Documentation</a> ｜
+<a href="https://langbot.app/docs/en/tags/readme">API</a> ｜
 <a href="https://space.langbot.app">Marché des Plugins</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">Feuille de Route</a>

@@ -48,7 +48,7 @@ LangBot est une **plateforme open-source de niveau production** pour créer des
 - **Panneau de Gestion Web** — Configurez, gérez et surveillez vos bots via une interface navigateur intuitive. Aucune édition de YAML requise.
 - **Architecture Multi-Pipeline** — Différents bots pour différents scénarios, avec surveillance complète et gestion des exceptions.

-[→ En savoir plus sur toutes les fonctionnalités](https://link.langbot.app/en/docs/features)
+[→ En savoir plus sur toutes les fonctionnalités](https://langbot.app/docs/en/insight/features)

 📍 Guides pratiques : [déployer un bot IA multiplateforme en 5 minutes](https://langbot.app/en/blog/deploy-ai-bot-in-5-minutes/), [connecter DeepSeek à WeChat, Discord et Telegram](https://langbot.app/en/blog/connect-deepseek-to-wechat/), [exécuter un Dify Agent dans Discord, Telegram et Slack](https://langbot.app/en/blog/dify-agent-discord-telegram-slack/) et [créer un chatbot avec n8n](https://langbot.app/en/blog/n8n-multi-platform-ai-chatbot/).

@@ -88,7 +88,7 @@ docker compose --profile all up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)

-**Plus d'options :** [Docker](https://link.langbot.app/en/docs/docker) · [Manuel](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [Kubernetes](https://docs.langbot.app/en/deploy/langbot/kubernetes)
+**Plus d'options :** [Docker](https://langbot.app/docs/en/deploy/langbot/docker) · [Manuel](https://langbot.app/docs/en/deploy/langbot/manual) · [BTPanel](https://langbot.app/docs/en/deploy/langbot/one-click/bt) · [Kubernetes](https://langbot.app/docs/en/deploy/langbot/kubernetes)

 ---

@@ -149,7 +149,7 @@ docker compose --profile all up -d
 | [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | Plateforme GPU | ✅ |
 | [Qiniu](https://www.qiniu.com/ai/agent) | Passerelle | ✅ |

-[→ Voir toutes les intégrations](https://link.langbot.app/en/docs/features)
+[→ Voir toutes les intégrations](https://langbot.app/docs/en/insight/features)

 ---

@@ -19,9 +19,9 @@
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)

 <a href="https://langbot.app">ホーム</a> ｜
-<a href="https://link.langbot.app/ja/docs/features">機能</a> ｜
-<a href="https://link.langbot.app/ja/docs/guide">ドキュメント</a> ｜
-<a href="https://link.langbot.app/ja/docs/api">API</a> ｜
+<a href="https://langbot.app/docs/ja/insight/features">機能</a> ｜
+<a href="https://langbot.app/docs/ja/insight/guide">ドキュメント</a> ｜
+<a href="https://langbot.app/docs/ja/tags/readme">API</a> ｜
 <a href="https://space.langbot.app">プラグインマーケット</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">ロードマップ</a>

@@ -48,7 +48,7 @@ LangBot は、AI搭載のインスタントメッセージングボットを構
 - **Web管理パネル** — 直感的なブラウザインターフェースからボットの設定、管理、監視が可能。YAML編集は不要。
 - **マルチパイプラインアーキテクチャ** — 異なるシナリオに異なるボットを配置し、包括的な監視と例外処理を実現。

-[→ すべての機能について詳しく見る](https://link.langbot.app/ja/docs/features)
+[→ すべての機能について詳しく見る](https://langbot.app/docs/ja/insight/features)

 📍 実践ガイド: [5分でマルチプラットフォームAIボットをデプロイ](https://langbot.app/en/blog/deploy-ai-bot-in-5-minutes/)、[DeepSeekをWeChat・Discord・Telegramに接続](https://langbot.app/en/blog/connect-deepseek-to-wechat/)、[Dify AgentをDiscord・Telegram・Slackで動かす](https://langbot.app/en/blog/dify-agent-discord-telegram-slack/)、[n8n連携チャットボットを構築](https://langbot.app/en/blog/n8n-multi-platform-ai-chatbot/)。

@@ -88,7 +88,7 @@ docker compose --profile all up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)

-**その他:** [Docker](https://link.langbot.app/en/docs/docker) · [手動デプロイ](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [Kubernetes](https://docs.langbot.app/en/deploy/langbot/kubernetes)
+**その他:** [Docker](https://langbot.app/docs/en/deploy/langbot/docker) · [手動デプロイ](https://langbot.app/docs/en/deploy/langbot/manual) · [BTPanel](https://langbot.app/docs/en/deploy/langbot/one-click/bt) · [Kubernetes](https://langbot.app/docs/en/deploy/langbot/kubernetes)

 ---

@@ -149,7 +149,7 @@ docker compose --profile all up -d
 | [302.AI](https://share.302ai.cn/SuTG99) | ゲートウェイ | ✅ |
 | [Qiniu](https://www.qiniu.com/ai/agent) | ゲートウェイ | ✅ |

-[→ すべての統合を表示](https://link.langbot.app/en/docs/features)
+[→ すべての統合を表示](https://langbot.app/docs/en/insight/features)

 ---

@@ -19,9 +19,9 @@
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)

 <a href="https://langbot.app">홈</a> ｜
-<a href="https://link.langbot.app/en/docs/features">기능</a> ｜
-<a href="https://link.langbot.app/en/docs/guide">문서</a> ｜
-<a href="https://link.langbot.app/en/docs/api">API</a> ｜
+<a href="https://langbot.app/docs/en/insight/features">기능</a> ｜
+<a href="https://langbot.app/docs/en/insight/guide">문서</a> ｜
+<a href="https://langbot.app/docs/en/tags/readme">API</a> ｜
 <a href="https://space.langbot.app">플러그인 마켓</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">로드맵</a>

@@ -48,7 +48,7 @@ LangBot은 AI 기반 인스턴트 메시징 봇을 구축하기 위한 **오픈
 - **웹 관리 패널** — 직관적인 브라우저 인터페이스로 봇을 구성, 관리 및 모니터링. YAML 편집 불필요.
 - **멀티 파이프라인 아키텍처** — 다양한 시나리오에 맞는 다양한 봇 구성, 종합 모니터링 및 예외 처리.

-[→ 모든 기능 자세히 보기](https://link.langbot.app/en/docs/features)
+[→ 모든 기능 자세히 보기](https://langbot.app/docs/en/insight/features)

 📍 실전 가이드: [5분 만에 멀티 플랫폼 AI 봇 배포하기](https://langbot.app/en/blog/deploy-ai-bot-in-5-minutes/), [DeepSeek를 WeChat, Discord, Telegram에 연결하기](https://langbot.app/en/blog/connect-deepseek-to-wechat/), [Dify Agent를 Discord, Telegram, Slack에서 실행하기](https://langbot.app/en/blog/dify-agent-discord-telegram-slack/), [n8n 기반 챗봇 만들기](https://langbot.app/en/blog/n8n-multi-platform-ai-chatbot/).

@@ -88,7 +88,7 @@ docker compose --profile all up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)

-**더 많은 옵션:** [Docker](https://link.langbot.app/en/docs/docker) · [수동 배포](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [Kubernetes](https://docs.langbot.app/en/deploy/langbot/kubernetes)
+**더 많은 옵션:** [Docker](https://langbot.app/docs/en/deploy/langbot/docker) · [수동 배포](https://langbot.app/docs/en/deploy/langbot/manual) · [BTPanel](https://langbot.app/docs/en/deploy/langbot/one-click/bt) · [Kubernetes](https://langbot.app/docs/en/deploy/langbot/kubernetes)

 ---

@@ -149,7 +149,7 @@ docker compose --profile all up -d
 | [302.AI](https://share.302ai.cn/SuTG99) | 게이트웨이 | ✅ |
 | [Qiniu](https://www.qiniu.com/ai/agent) | 게이트웨이 | ✅ |

-[→ 모든 통합 보기](https://link.langbot.app/en/docs/features)
+[→ 모든 통합 보기](https://langbot.app/docs/en/insight/features)

 ---

@@ -19,9 +19,9 @@
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)

 <a href="https://langbot.app">Главная</a> ｜
-<a href="https://link.langbot.app/en/docs/features">Возможности</a> ｜
-<a href="https://link.langbot.app/en/docs/guide">Документация</a> ｜
-<a href="https://link.langbot.app/en/docs/api">API</a> ｜
+<a href="https://langbot.app/docs/en/insight/features">Возможности</a> ｜
+<a href="https://langbot.app/docs/en/insight/guide">Документация</a> ｜
+<a href="https://langbot.app/docs/en/tags/readme">API</a> ｜
 <a href="https://space.langbot.app">Магазин плагинов</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">Дорожная карта</a>

@@ -48,7 +48,7 @@ LangBot — это **платформа с открытым исходным к
 - **Веб-панель управления** — Настраивайте, управляйте и мониторьте ваших ботов через интуитивный браузерный интерфейс. Ручное редактирование YAML не требуется.
 - **Мультиконвейерная архитектура** — Разные боты для разных сценариев с комплексным мониторингом и обработкой исключений.

-[→ Подробнее обо всех возможностях](https://link.langbot.app/en/docs/features)
+[→ Подробнее обо всех возможностях](https://langbot.app/docs/en/insight/features)

 📍 Практические руководства: [развернуть мультиплатформенного ИИ-бота за 5 минут](https://langbot.app/en/blog/deploy-ai-bot-in-5-minutes/), [подключить DeepSeek к WeChat, Discord и Telegram](https://langbot.app/en/blog/connect-deepseek-to-wechat/), [запустить Dify Agent в Discord, Telegram и Slack](https://langbot.app/en/blog/dify-agent-discord-telegram-slack/) и [создать чат-бота на n8n](https://langbot.app/en/blog/n8n-multi-platform-ai-chatbot/).

@@ -88,7 +88,7 @@ docker compose --profile all up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)

-**Другие варианты:** [Docker](https://link.langbot.app/en/docs/docker) · [Ручная установка](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [Kubernetes](https://docs.langbot.app/en/deploy/langbot/kubernetes)
+**Другие варианты:** [Docker](https://langbot.app/docs/en/deploy/langbot/docker) · [Ручная установка](https://langbot.app/docs/en/deploy/langbot/manual) · [BTPanel](https://langbot.app/docs/en/deploy/langbot/one-click/bt) · [Kubernetes](https://langbot.app/docs/en/deploy/langbot/kubernetes)

 ---

@@ -149,7 +149,7 @@ docker compose --profile all up -d
 | [ShengSuanYun](https://www.shengsuanyun.com/?from=CH_KYIPP758) | Платформа GPU | ✅ |
 | [Qiniu](https://www.qiniu.com/ai/agent) | Шлюз | ✅ |

-[→ Смотреть все интеграции](https://link.langbot.app/en/docs/features)
+[→ Смотреть все интеграции](https://langbot.app/docs/en/insight/features)

 ---

@@ -21,9 +21,9 @@
 [![star](https://gitcode.com/RockChinQ/LangBot/star/badge.svg)](https://gitcode.com/RockChinQ/LangBot)

 <a href="https://langbot.app">官網</a> ｜
-<a href="https://link.langbot.app/zh/docs/features">特性</a> ｜
-<a href="https://link.langbot.app/zh/docs/guide">文件</a> ｜
-<a href="https://link.langbot.app/zh/docs/api">API</a> ｜
+<a href="https://langbot.app/docs/zh/insight/features">特性</a> ｜
+<a href="https://langbot.app/docs/zh/insight/guide">文件</a> ｜
+<a href="https://langbot.app/docs/zh/tags/readme">API</a> ｜
 <a href="https://space.langbot.app">外掛市場</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">路線圖</a>

@@ -50,7 +50,7 @@ LangBot 是一個**開源的生產級平台**，用於建構 AI 驅動的即時
 - **Web 管理面板** — 透過瀏覽器直觀地配置、管理和監控機器人，無需手動編輯設定檔。
 - **多流水線架構** — 不同機器人用於不同場景，具備全面的監控和異常處理能力。

-[→ 了解更多功能特性](https://link.langbot.app/zh/docs/features)
+[→ 了解更多功能特性](https://langbot.app/docs/zh/insight/features)

 📍 實踐指南：[5 分鐘部署多平台 AI 機器人](https://langbot.app/zh/blog/deploy-ai-bot-in-5-minutes/)、[將 DeepSeek 接入微信、企業微信與 Discord](https://langbot.app/zh/blog/connect-deepseek-to-wechat/)、[讓 Dify Agent 跑在 Discord、Telegram 和 Slack 上](https://langbot.app/zh/blog/dify-agent-discord-telegram-slack/)，以及[用 n8n 建構多平台 AI 聊天機器人](https://langbot.app/zh/blog/n8n-multi-platform-ai-chatbot/)。

@@ -90,7 +90,7 @@ docker compose --profile all up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/zh-CN/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)

-**更多方式：** [Docker](https://link.langbot.app/zh/docs/docker) · [手動部署](https://link.langbot.app/zh/docs/manual-deploy) · [寶塔面板](https://link.langbot.app/zh/docs/bt-panel) · [Kubernetes](https://docs.langbot.app/zh/deploy/langbot/kubernetes)
+**更多方式：** [Docker](https://langbot.app/docs/zh/deploy/langbot/docker) · [手動部署](https://langbot.app/docs/zh/deploy/langbot/manual) · [寶塔面板](https://langbot.app/docs/zh/deploy/langbot/one-click/bt) · [Kubernetes](https://langbot.app/docs/zh/deploy/langbot/kubernetes)

 ---

@@ -165,7 +165,7 @@ docker compose --profile all up -d
 |-----------|------|
 | 阿里雲百煉 | [外掛](https://github.com/Thetail001/LangBot_BailianTextToImagePlugin) |

-[→ 查看完整整合列表](https://link.langbot.app/zh/docs/features)
+[→ 查看完整整合列表](https://langbot.app/docs/zh/insight/features)

 ---

@@ -19,9 +19,9 @@
 [![GitHub stars](https://img.shields.io/github/stars/langbot-app/LangBot?style=social)](https://github.com/langbot-app/LangBot/stargazers)

 <a href="https://langbot.app">Trang chủ</a> ｜
-<a href="https://link.langbot.app/en/docs/features">Tính năng</a> ｜
-<a href="https://link.langbot.app/en/docs/guide">Tài liệu</a> ｜
-<a href="https://link.langbot.app/en/docs/api">API</a> ｜
+<a href="https://langbot.app/docs/en/insight/features">Tính năng</a> ｜
+<a href="https://langbot.app/docs/en/insight/guide">Tài liệu</a> ｜
+<a href="https://langbot.app/docs/en/tags/readme">API</a> ｜
 <a href="https://space.langbot.app">Chợ Plugin</a> ｜
 <a href="https://langbot.featurebase.app/roadmap">Lộ trình</a>

@@ -48,7 +48,7 @@ LangBot là một **nền tảng mã nguồn mở, cấp sản xuất** để x
 - **Bảng quản lý Web** — Cấu hình, quản lý và giám sát bot thông qua giao diện trình duyệt trực quan. Không cần chỉnh sửa YAML.
 - **Kiến trúc đa Pipeline** — Các bot khác nhau cho các kịch bản khác nhau, với giám sát toàn diện và xử lý ngoại lệ.

-[→ Tìm hiểu thêm về tất cả tính năng](https://link.langbot.app/en/docs/features)
+[→ Tìm hiểu thêm về tất cả tính năng](https://langbot.app/docs/en/insight/features)

 📍 Hướng dẫn thực hành: [triển khai bot AI đa nền tảng trong 5 phút](https://langbot.app/en/blog/deploy-ai-bot-in-5-minutes/), [kết nối DeepSeek với WeChat, Discord và Telegram](https://langbot.app/en/blog/connect-deepseek-to-wechat/), [chạy Dify Agent trên Discord, Telegram và Slack](https://langbot.app/en/blog/dify-agent-discord-telegram-slack/) và [xây dựng chatbot với n8n](https://langbot.app/en/blog/n8n-multi-platform-ai-chatbot/).

@@ -88,7 +88,7 @@ docker compose --profile all up -d
 [![Deploy on Zeabur](https://zeabur.com/button.svg)](https://zeabur.com/en-US/templates/ZKTBDH)
 [![Deploy on Railway](https://railway.com/button.svg)](https://railway.app/template/yRrAyL?referralCode=vogKPF)

-**Thêm tùy chọn:** [Docker](https://link.langbot.app/en/docs/docker) · [Thủ công](https://link.langbot.app/en/docs/manual-deploy) · [BTPanel](https://link.langbot.app/en/docs/bt-panel) · [Kubernetes](https://docs.langbot.app/en/deploy/langbot/kubernetes)
+**Thêm tùy chọn:** [Docker](https://langbot.app/docs/en/deploy/langbot/docker) · [Thủ công](https://langbot.app/docs/en/deploy/langbot/manual) · [BTPanel](https://langbot.app/docs/en/deploy/langbot/one-click/bt) · [Kubernetes](https://langbot.app/docs/en/deploy/langbot/kubernetes)

 ---

@@ -149,7 +149,7 @@ docker compose --profile all up -d
 | [302.AI](https://share.302ai.cn/SuTG99) | Cổng | ✅ |
 | [Qiniu](https://www.qiniu.com/ai/agent) | Cổng | ✅ |

-[→ Xem tất cả tích hợp](https://link.langbot.app/en/docs/features)
+[→ Xem tất cả tích hợp](https://langbot.app/docs/en/insight/features)

 ---

@@ -1,5 +1,5 @@
 # Docker Compose configuration for LangBot
-# For Kubernetes deployment, see kubernetes.yaml and the deployment guide at https://docs.langbot.app
+# For Kubernetes deployment, see kubernetes.yaml and the deployment guide at https://langbot.app/docs
 version: "3"

 services:
@@ -27,8 +27,8 @@ services:

  # 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 —
+  # up``). With Box off, LangBot keeps skill management, activation, and
+  # read-only resources available but disables execution tools 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:
@@ -73,6 +73,10 @@ services:
    container_name: langbot
    volumes:
      - ./data:/app/data
+      # Core owns the SkillRepository even when the Box profile is disabled.
+      # Keep this path identical to langbot_box so optional execution can
+      # consume the same Workspace-scoped package revisions.
+      - ${LANGBOT_BOX_ROOT:-${PWD}/data/box}:${LANGBOT_BOX_ROOT:-${PWD}/data/box}
    restart: on-failure
    environment:
      - TZ=Asia/Shanghai
@@ -92,7 +96,9 @@ services:
      # box.* 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
+      # TODO(next-major): default LANGBOT_SKILLS_ROOT to ${PWD}/data/skills
+      # after the historical Box storage path no longer needs zero-copy upgrades.
+      - SKILLS__ROOT=${LANGBOT_SKILLS_ROOT:-${LANGBOT_BOX_ROOT:-${PWD}/data/box}/skills}
      - BOX__LOCAL__ALLOWED_MOUNT_ROOTS=${LANGBOT_BOX_ROOT:-${PWD}/data/box}
      - BOX__DOCKER__CPU_LIMIT_ENABLED=${LANGBOT_BOX_DOCKER_CPU_LIMIT_ENABLED:-true}
    ports:
@@ -1,7 +1,7 @@
 # Kubernetes Deployment for LangBot
 # This file provides Kubernetes deployment manifests for LangBot based on docker-compose.yaml
 #
-# Full deployment guide (zh/en/ja): https://docs.langbot.app -> Installation -> Kubernetes
+# Full deployment guide (zh/en/ja): https://langbot.app/docs -> Installation -> Kubernetes
 #
 # Usage:
 #   kubectl -n langbot create secret generic langbot-plugin-runtime-control \
@@ -214,8 +214,9 @@ spec:
 # Deployment for LangBot Box (sandbox) runtime
 #
 # The Box runtime backs LangBot's sandbox tools (exec / read / write / edit /
-# glob / grep), the `activate` skill tool, skill add/edit, and stdio-mode MCP
-# servers. It is OPTIONAL: if you do not deploy it, set `BOX__ENABLED=false` on
+# glob / grep), Skill script execution, and stdio-mode MCP servers. Skill
+# activation, resources, and management remain Core-owned without Box. Box is
+# OPTIONAL: if you do not deploy it, set `BOX__ENABLED=false` on
 # the langbot Deployment (or `box.enabled: false` in config.yaml) so the
 # dashboard renders cleanly with sandbox features disabled.
 #
@@ -448,14 +449,15 @@ spec:
              key: token
        # box.local.* config — forwarded to the Box runtime via INIT RPC. The
        # host_root MUST match the box-root hostPath mountPath below AND the box
-        # Deployment's box-root mountPath, so that skill package paths resolve
-        # identically on both sides and on the node's Docker daemon.
+        # Deployment's box-root mountPath, so generic package mount paths
+        # resolve identically on both sides and on the node's Docker daemon.
        - name: BOX__LOCAL__HOST_ROOT
          value: "/app/data/box"
        - name: BOX__LOCAL__DEFAULT_WORKSPACE
          value: "default"
-        - name: BOX__LOCAL__SKILLS_ROOT
-          value: "skills"
+        - name: SKILLS__ROOT
+          # TODO(next-major): use /app/data/skills after the legacy path window.
+          value: "/app/data/box/skills"
        - name: BOX__LOCAL__ALLOWED_MOUNT_ROOTS
          value: "/app/data/box"
        volumeMounts:
@@ -218,8 +218,8 @@ metadata:
 spec:
  categories: [popular, global]
  help_links:
-    zh: https://docs.langbot.app/zh/platforms/http-bot
-    en: https://docs.langbot.app/en/platforms/http-bot
+    zh: https://langbot.app/docs/zh/platforms/http-bot
+    en: https://langbot.app/docs/en/platforms/http-bot
  config:
    - { name: inbound_secret,       type: string, required: true,  default: "" }
    - { name: callback_url,         type: string, required: false, default: "" }
@@ -243,7 +243,7 @@ For large datasets:
 - SeekDB GitHub: https://github.com/oceanbase/seekdb
 - pyseekdb SDK: https://github.com/oceanbase/pyseekdb
 - OceanBase Documentation: https://oceanbase.ai
- LangBot Documentation: https://docs.langbot.app
+- LangBot Documentation: https://langbot.app/docs

 ## License

@@ -22,6 +22,7 @@
 │       │                    │       (shared 容器, 多 process)       │
 │       │                    │                                      │
 │       │                    ├──> SkillToolLoader (activate 工具)    │
+│       │                    │       └─ build_execution_mounts()    │
 │       │                    │                                      │
 │       │                    ├──> SkillAuthoringToolLoader          │
 │       │                    │                                      │
@@ -33,7 +34,7 @@
 │    ├─ 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)                      │
+│    ├─ 通用只读挂载接收 (read_only_mounts)                          │
 │    ├─ 重连循环 (_reconnect_loop, 指数退避)                          │
 │    └─ BoxRuntimeConnector                                          │
 │         ├─ 心跳 loop (20s ping)                                    │
@@ -41,7 +42,7 @@
 │              │  Action RPC (stdio 或 WebSocket)                    │
 │                                                                    │
 │  SkillManager (skill_mgr)                                          │
-│    └─ 从 Box runtime 拉取 skills, 不可用时回落 data/skills          │
+│    └─ 从 Core SkillRepository 加载 Workspace-scoped skills          │
 └──────────────────────────────────────────────────────────────────┘
               │
               ▼
@@ -59,10 +60,8 @@
 │    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)        │
+│  Generic mount admission                                         │
+│    └─ allow-list + read-only + normalized target validation       │
 │                                                                   │
 │  aiohttp 单端口服务 (默认 :5410):                                    │
 │    /rpc/ws                                       — Action RPC      │
@@ -85,7 +84,7 @@
 **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)）
+- Skill 仅是 Core 组装 mount 的业务来源；Box 与默认 exec / MCP Server 只共享通用 session 和 mount 机制（详见 [box-session-scope.md](./box-session-scope.md)）

 ---

@@ -93,7 +92,7 @@

 ### 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：
+应用层门面，协调 Profile、安全校验、配额、连接、Core 生成的只读挂载与 Session 模板：

 主要公开方法（按定义顺序）：

@@ -105,7 +104,7 @@ BoxService
  ├─ 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(..., read_only_mounts=...)   接收 Core 组装的通用只读挂载
  │
  ├─ execute_tool(parameters, query)           Agent 调用 exec 时的入口
  │    ├─ _apply_profile / build_spec
@@ -122,12 +121,6 @@ BoxService
  ├─ 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
@@ -137,7 +130,7 @@ BoxService

 **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。
+**Skill 挂载合并**: native loader 调用 `skill.build_execution_mounts()`，把当前 pipeline-bound 的所有 skill 的 `package_root` 转成普通只读 mount，再通过 `BoxService.execute_tool(..., read_only_mounts=...)` 交给 Box，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；BoxService 和 Box Runtime 都不知道这些 mount 来自 Skill。

 ### 2.2 BoxRuntimeConnector (`pkg/box/connector.py`, 357 行)

@@ -171,11 +164,10 @@ BoxService
 ```
 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
+  ├─ reload_skills()               从 Core SkillRepository 加载
+  ├─ refresh_skill_from_disk()     检查单 skill 的缓存状态
  ├─ get_skill_by_name(name)
-  └─ get_managed_skills_root()     返回 Box 视角的 skills_root 路径
+  └─ build_skill_aware_prompt_addition() 生成渐进披露索引
 ```

 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）。
@@ -295,7 +287,7 @@ start_managed_process(session, spec):

 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
+1. **Action RPC** (`/rpc/ws`): `BoxServerHandler` 处理 `INIT`、exec、session、managed-process 与状态等通用 action
 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。
@@ -304,7 +296,7 @@ stdio 模式同样会在 5410 启动 aiohttp，专门承担 managed process atta

 `ActionRPCBoxClient` 封装 `Handler.call_action()` 调用：

- 25+ 方法对应 25+ 个 RPC action（exec / session / managed-process / skill / status / shutdown）
+- 方法对应 exec / session / managed-process / status / shutdown 等通用 RPC action，不暴露 Skill CRUD
 - 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
@@ -343,23 +335,32 @@ stdio 模式同样会在 5410 启动 aiohttp，专门承担 managed process atta

 `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)
+### 3.7 SkillStore (`langbot_plugin.skill_store`)

-新增模块（commit `4ab3502`），把 skill 持久化收归 Box runtime：
+Skill 包存储最初位于 Box Runtime；issue #2410 将通用实现抽到 Plugin SDK 顶层，由 Core 独占存储和 revision 语义：

 ```
-BoxSkillStore
+SkillStore
  ├─ 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)
+  ├─ list_skill_resources(name, path, revision)  按 revision 浏览只读资源
+  ├─ read_skill_resource(name, path, revision)   按 revision 读取 UTF-8 资源
+  ├─ read_skill_file(...) / write_skill_file(...) 管理侧文件接口
  ├─ 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/`。
+GitHub 安装路径由 Core HTTP 层下载归档，再交给 SkillRepository。Skill 文件位于独立的 `skills.root`，执行时由 Core 组装成通用只读 `BoxMountSpec` 并挂载到 `/workspace/.skills/`。Box 的正常模型、客户端和 Runtime 不包含 `skill_name`、Skill CRUD、revision 或 `SKILL.md` 语义。
+
+滚动升级只保留一个隔离桥：`box/legacy_skill_compat.py` 让旧 Core 暂时调用新 Box，并把旧 `skill_name` 转为普通只读 mount。部署顺序必须先升级 Box、再升级 Core。该模块有 `TODO(next-major)`，下一大版本删除；正常架构不依赖它。
+
+下一大版本的删除清单（当前均有 `TODO(next-major)`）：
+
+1. 删除 SDK `box/legacy_skill_compat.py` 及 Server 中唯一的注册/转换钩子。
+2. 删除 Core 对 `box.local.skills_root` 的配置 fallback。
+3. 新安装默认从历史 `./data/box/skills` 切到 `./data/skills`；届时 Box 部署只需只读访问 Core 明确下发的通用 artifact root。

 ### 3.8 Security (`box/security.py`, 52 行)

@@ -463,7 +464,7 @@ BuildAppStage.run(ap)
  ├─ ap.tool_mgr = tool_mgr
  │
  ├─ ... (platform, pipeline) ...
-  ├─ SkillManager.initialize()    (从 Box runtime 加载 skill 列表)
+  ├─ SkillManager.initialize()    (从 Core SkillRepository 加载 skill 列表)
  └─ ... (RAG, HTTP, plugins) ...
 ```

@@ -480,7 +481,7 @@ except Exception as e:
    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）。
+**静默降级**: Box 初始化失败不会阻止应用启动。6 个 native tool、`register_skill` 和 MCP-in-Box 工具不暴露给 LLM；`activate` 与 Skill 只读资源工具继续由 Core 提供。与 Plugin 的行为不同（Plugin 失败会抛异常）。

 ### 5.3 销毁流程

@@ -504,13 +505,16 @@ Box 额外做了 RPC SHUTDOWN 通知 Runtime 主动清理容器，比 Plugin 的
 ### config.yaml (重构后)

 ```yaml
+skills:
+    root: './data/box/skills'  # Core-owned；Box 关闭时仍可管理/读取
+
 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
+                          #  - Agent 从 sandbox 注册 skill 的能力不可用
                          #  - 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
+                          #  - skill 管理、激活和只读资源保持可用
                          # 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
@@ -522,7 +526,6 @@ box:
        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'
@@ -561,16 +564,17 @@ volumes:
 | 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** |
+| `activate` / Skill resource 工具 | 暴露给 LLM | 暴露给 LLM |
+| `register_skill` 工具 | 暴露给 LLM | **不暴露**；直接调用返回 `sandbox_unavailable` |
 | 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`) |
+| Skill 列表/读取 (`list_skills`/`get_skill`/`read_skill_file`) | 走 Core SkillRepository | 走 Core SkillRepository |
+| Skill 创建/编辑/安装/写文件 | 走 Core SkillRepository | 走 Core SkillRepository |
 | 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 |
+| Pipeline 扩展页 `enable_all_skills` / 绑定 skill | 可编辑 | 可编辑 |
 | 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。
+> Core 的 SkillRepository 是 `langbot_plugin.skill_store.SkillStore` 的异步 Workspace 适配层。默认 `skills.root` 保持原 `data/box/skills/tenants/...` 布局，升级时无需移动已安装 Skill；旧 `box.local.skills_root` 仅作为在线升级 fallback，并将在下一大版本删除。Box 只消费 Core 下发的通用只读 mount。

 ### Pipeline 配置 (templates/metadata/pipeline/ai.yaml)

@@ -52,8 +52,8 @@
 ### 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。
+- **现状**: grant-enforced 模式已经由 Core 与 Runtime 双重校验通用只读 mount（绝对路径 allow-list、存在性、只读模式、规范化且位于 `/workspace` 下的目标）；它不再有 Skill 特例。遗留风险仅在 admission-disabled 的低信任直连场景：通用 `extra_mounts` 仍未统一套用 grant-enforced 白名单。
+- **要求**: admission-disabled 的外部控制面也复用同一套通用 mount 校验；SDK 黑名单加入 `/`（或全面改白名单）。

 ### S6. 容器加固缺失 — Med

@@ -18,7 +18,7 @@ has shipped the design largely as written:
 | 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.build_execution_mounts(ap, query)` | ✅ Shipped | Core composes read-only packages; Box receives generic mounts |
 | 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]` |
@@ -51,7 +51,7 @@
 | 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 |
+| BoxService session / mount contract | 良好 | `resolve_box_session_id` + generic `read_only_mounts`; Skill mount composition is covered in the Core loader |
 | 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 |
@@ -6,7 +6,7 @@ Minimal, dependency-light clients for the LangBot **HTTP Bot** platform adapter.
 They show the whole loop: signing a request, pushing a message, and receiving
 multi-part replies on a callback endpoint.

-Full guide: [docs.langbot.app — HTTP Bot](https://docs.langbot.app/en/usage/platforms/http-bot).
+Full guide: [docs.langbot.app — HTTP Bot](https://langbot.app/docs/en/usage/platforms/http-bot).
 Machine-readable contract: [`docs/http-bot-openapi.json`](../../docs/http-bot-openapi.json).

 ## Files
@@ -6,7 +6,7 @@
 它们完整展示了整条链路:对请求签名、推送一条消息、在回调端点接收
 1→M 的多段回复。

-完整指南:[docs.langbot.app —— HTTP Bot](https://docs.langbot.app/zh/usage/platforms/http-bot)。
+完整指南:[docs.langbot.app —— HTTP Bot](https://langbot.app/docs/zh/usage/platforms/http-bot)。
 机器可读的接口契约:[`docs/http-bot-openapi.json`](../../docs/http-bot-openapi.json)。

 ## 文件清单
@@ -6,7 +6,7 @@ A single self-contained HTML page that demos the LangBot **Page Bot**
 (`web_page_bot`) embeddable chat widget — the one you drop onto any website with
 a single `<script>` tag.

-Full guide: [docs.langbot.app — Page Bot](https://docs.langbot.app/en/usage/platforms/webpage).
+Full guide: [docs.langbot.app — Page Bot](https://langbot.app/docs/en/usage/platforms/webpage).

 ## Files

@@ -6,7 +6,7 @@
 (`web_page_bot`) 的可嵌入聊天组件 —— 也就是你用一行 `<script>` 标签就能放到任意
 网站上的那个组件。

-完整指南：[docs.langbot.app —— 页面机器人](https://docs.langbot.app/zh/usage/platforms/webpage)。
+完整指南：[docs.langbot.app —— 页面机器人](https://langbot.app/docs/zh/usage/platforms/webpage)。

 ## 文件清单

@@ -1,6 +1,6 @@
 [project]
 name = "langbot"
-version = "4.10.9"
+version = "4.10.10"
 description = "Production-grade platform for building agentic IM bots"
 readme = "README.md"
 license-files = ["LICENSE"]
@@ -70,7 +70,7 @@ dependencies = [
    "langchain-text-splitters>=1.1.2",
    "chromadb>=1.0.0,<2.0.0",
    "qdrant-client (>=1.15.1,<2.0.0)",
-    "langbot-plugin==0.5.6",
+    "langbot-plugin==0.5.7",
    "asyncpg>=0.30.0",
    "line-bot-sdk>=3.19.0",
    "matrix-nio>=0.25.2",
@@ -114,7 +114,7 @@ seekdb = [

 [project.urls]
 Homepage = "https://langbot.app"
-Documentation = "https://docs.langbot.app"
+Documentation = "https://langbot.app/docs"
 Repository = "https://github.com/langbot-app/LangBot"

 [project.scripts]
@@ -1349,7 +1349,8 @@
            "local-agent",
            "tools",
            "e2b",
-            "nsjail"
+            "nsjail",
+            "host"
          ],
          "automation": "",
          "setup_automation": [],
@@ -48,7 +48,7 @@ tools, skill add/edit, and stdio MCP are disabled. Set `box.enabled: false`
 ## Kubernetes

 See `docker/kubernetes.yaml` and the deployment guide at
-https://docs.langbot.app. `docker/deploy-k8s-test.sh` is a test helper.
+https://langbot.app/docs. `docker/deploy-k8s-test.sh` is a test helper.

 ## config.yaml (generated at `data/config.yaml` on first run)

@@ -63,7 +63,7 @@ Key settings:
 | `api.global_api_key` | **Global API key** for the HTTP API + MCP server. Non-empty = accepted with no login/DB record; no `lbk_` prefix required. Empty = disabled. Plaintext — trusted/internal only, serve over HTTPS. |
 | `plugin.runtime_ws_url` | Standalone plugin runtime WS URL (e.g. `ws://langbot_plugin_runtime:5400/control/ws`) |
 | `box.enabled` | Master switch for the Box sandbox runtime |
-| `box.backend` | `local` (Docker/nsjail autopick) / `docker` / `nsjail` / `e2b`; env override `BOX__BACKEND` |
+| `box.backend` | `local` (Docker/nsjail autopick) / `docker` / `nsjail` / `e2b` / explicit unsafe `host`; env override `BOX__BACKEND` |
 | `box.runtime.endpoint` | External Box runtime URL (e.g. `ws://127.0.0.1:5410`); empty = local auto-managed |

 Many keys have `ENV__SUBKEY` overrides (e.g. `BOX__BACKEND`, `BOX__ENABLED`).
@@ -75,6 +75,10 @@ Many keys have `ENV__SUBKEY` overrides (e.g. `BOX__BACKEND`, `BOX__ENABLED`).
  with `--standalone-runtime`.
 - Box has a parallel `--standalone-box` flag; the Docker box host is
  `langbot_box:5410`.
+- `box.backend: host` runs commands directly as the Box Runtime system user.
+  It is never auto-selected, provides no sandbox isolation, and is only for
+  trusted local development. A WebSocket-controlled host backend requires
+  `LANGBOT_BOX_CONTROL_TOKEN`; local stdio control is allowed.

 ## Global API key — enabling for agents/automation

@@ -93,5 +97,7 @@ login session. See `langbot-mcp-ops` for using it, and `docs/API_KEY_AUTH.md`.
 - "No supported sandbox backend (Docker / nsjail / E2B)" with Docker running
  usually means the user isn't in the `docker` group →
  `sudo usermod -aG docker <user>` and restart in a new shell.
+- Do not use `box.backend: host` as a production fallback. It cannot enforce
+  image, filesystem, network, PID, CPU, memory, or storage isolation.
 - Box root host/container path mismatch breaks sandbox container creation.
 - Don't commit a non-empty `api.global_api_key` to version control.
@@ -13,6 +13,7 @@ tags:
  - tools
  - e2b
  - nsjail
+  - host
 skills:
  - langbot-env-setup
  - langbot-testing
@@ -23,7 +24,7 @@ env:
  - LANGBOT_LOCAL_AGENT_PIPELINE_NAME
 preconditions:
  - "LANGBOT_LOCAL_AGENT_PIPELINE_URL or LANGBOT_LOCAL_AGENT_PIPELINE_NAME points to the local-agent pipeline under test."
-  - "LangBot is started with the sandbox backend intended for this run, such as e2b or nsjail."
+  - "LangBot is started with the Box backend intended for this run, such as e2b, nsjail, or explicit host development mode."
  - "The selected model route supports tool/function calling strongly enough to invoke sandbox tools."
 steps:
  - "Start LangBot with the target sandbox backend and confirm the Box status UI or LANGBOT_BACKEND_URL /api/v1/box/status reports the expected backend."
@@ -33,7 +34,7 @@ steps:
 checks:
  - "UI: Debug Chat final assistant response contains E2E_OK:<skill-name>."
  - "Logs: The model called exec, register_skill, activate, then exec again from the activated skill path."
-  - "Logs: The selected backend name is the expected one, such as e2b or nsjail."
+  - "Logs: The selected backend name is the expected one, such as e2b, nsjail, or host."
  - "Skill store: The registered package and activated writeback match references/sandbox-skill-authoring.md."
  - "Box status: recent_error_count is 0 after the run."
 evidence_required:
@@ -4,7 +4,7 @@

 Verify that Local Agent can use sandbox tools to create, register, activate, and use a LangBot skill package through the same path a user would exercise in Debug Chat.

-This flow applies to Docker, nsjail, and E2B backends. API calls are useful diagnostics, but the primary pass/fail signal is the model-driven Debug Chat tool sequence.
+This flow applies to Docker, nsjail, E2B, and the explicit host development backend. Host runs commands directly as the Box Runtime user and must never be treated as sandbox-isolation coverage. API calls are useful diagnostics, but the primary pass/fail signal is the model-driven Debug Chat tool sequence.

 ## Preconditions

@@ -13,6 +13,7 @@ This flow applies to Docker, nsjail, and E2B backends. API calls are useful diag
   - `BOX_BACKEND=e2b` when validating E2B.
   - `BOX_BACKEND=nsjail` when validating nsjail.
   - `BOX_BACKEND=local` or `docker` when validating local container fallback.
+   - `BOX_BACKEND=host` only when validating explicit, trusted local direct execution.
 3. Confirm `/api/v1/box/status` reports `available: true` and the expected backend name.
 4. Confirm Debug Chat uses a model with function-calling ability.
 5. Confirm backend logs say native sandbox tools are available.
@@ -71,7 +72,7 @@ Backend logs should show:
 - `register_skill`
 - `activate`
 - a second `exec` whose workdir is `/workspace/.skills/<skill-name>`
- `backend=e2b`, `backend=nsjail`, or the expected local backend
+- `backend=e2b`, `backend=nsjail`, `backend=host`, or the expected local backend

 After the run, verify the skill store through the UI or API:

@@ -125,6 +126,8 @@ For E2B raw HTTP diagnostics, include a valid template id such as `base`; a miss
 - Session metadata should keep LangBot logical paths such as `/workspace`; storing provider-internal paths can make later requests look incompatible.
 - nsjail versions differ. Some expose only `--disable_clone_new*` flags and use `--bindmount` instead of `--rw_bind`.
 - On WSL, cgroup v2 may exist but not be writable. The backend should warn and fall back to rlimits rather than fail the sandbox.
+- The host backend does not honor sandbox image, network, rootfs, process, or
+  resource isolation. Use a disposable workspace and low-privilege account.
 - If `ALL_PROXY` uses a SOCKS URL and `socksio` is not installed, some Python HTTP clients can fail during startup. Prefer consistent HTTP proxy variables unless SOCKS support is installed.

 ## Related Troubleshooting
@@ -3,7 +3,7 @@ title: "Native sandbox tools are unavailable even though a backend is configured
 date: 2026-05-18
 symptoms:
  - "Backend logs show Native sandbox tools (exec/read/write/edit/glob/grep) are NOT available."
-  - "The Box runtime later reports that E2B, nsjail, or Docker is configured."
+  - "The Box runtime later reports that E2B, nsjail, Docker, or explicit host mode is configured."
  - "Debug Chat does not expose exec, register_skill, or activate as usable tools."
 patterns:
  - "Native sandbox tools ... are NOT available"
@@ -19,6 +19,7 @@ fix_steps:
  - "Ensure the Box runtime reselects a backend when get_backend_info is called and the cached backend is empty."
  - "For E2B, verify the key without printing it and confirm any required template setting."
  - "For nsjail, run nsjail --help and confirm the binary is on PATH for the LangBot process."
+  - "For trusted local development only, explicitly set box.backend=host; never use host as a production sandbox fallback."
 verification: "Run sandbox-skill-authoring-e2e. Logs should show Native sandbox tools are available and /api/v1/box/status should report available=true with the expected backend."
 related_cases:
  - sandbox-skill-authoring-e2e
@@ -16,7 +16,7 @@ asciiart = r"""
               |___/              

 ⭐️ Open Source 开源地址: https://github.com/langbot-app/LangBot
-📖 Documentation 文档地址: https://docs.langbot.app
+📖 Documentation 文档地址: https://langbot.app/docs
 """


@@ -697,9 +697,10 @@ class DingTalkClient:
        if not await self.check_access_token():
            await self.get_access_token()

-        cardData: dict = {'cardParamMap': _stringify_card_param_map(card_param_map)}
+        template_params = dict(card_param_map or {})
        if card_data_config is not None:
-            cardData['config'] = json.dumps(card_data_config)
+            template_params['config'] = card_data_config
+        cardData: dict = {'cardParamMap': _stringify_card_param_map(template_params)}

        body: dict = {
            'cardTemplateId': card_template_id,
@@ -218,6 +218,7 @@ class MonitoringRouterGroup(group.RouterGroup):
            pipeline_ids = quart.request.args.getlist('pipelineId')
            start_time_str = quart.request.args.get('startTime')
            end_time_str = quart.request.args.get('endTime')
+            user_query = quart.request.args.get('userQuery')
            is_active_str = quart.request.args.get('isActive')
            limit = int(quart.request.args.get('limit', 100))
            offset = int(quart.request.args.get('offset', 0))
@@ -237,6 +238,7 @@ class MonitoringRouterGroup(group.RouterGroup):
                pipeline_ids=pipeline_ids if pipeline_ids else None,
                start_time=start_time,
                end_time=end_time,
+                user_query=user_query,
                is_active=is_active,
                limit=limit,
                offset=offset,
@@ -396,7 +398,14 @@ class MonitoringRouterGroup(group.RouterGroup):
        @self.route('/sessions/<session_id>/analysis', methods=['GET'], permission=Permission.RESOURCE_VIEW)
        async def get_session_analysis(session_id: str, request_context: RequestContext) -> str:
            """Get detailed analysis for a specific session"""
-            analysis = await self.ap.monitoring_service.get_session_analysis(request_context, session_id)
+            start_time = parse_iso_datetime(quart.request.args.get('startTime'))
+            end_time = parse_iso_datetime(quart.request.args.get('endTime'))
+            analysis = await self.ap.monitoring_service.get_session_analysis(
+                request_context,
+                session_id,
+                start_time=start_time,
+                end_time=end_time,
+            )

            # Always return success with the analysis data
            # The frontend will handle the 'found: false' case
@@ -2,9 +2,6 @@ from __future__ import annotations

 import quart

-from langbot.pkg.cloud.entitlements import EntitlementFeatureUnavailableError
-from langbot_plugin.box.errors import BoxError
-
 from ...authz import Permission
 from ...context import RequestContext
 from .. import group
@@ -24,12 +21,7 @@ class SkillsRouterGroup(group.RouterGroup):
        async def list_skills(request_context: RequestContext) -> quart.Response:
            try:
                skills = await self.ap.skill_service.list_skills(request_context)
-            except EntitlementFeatureUnavailableError:
-                # Plans without managed sandbox support have no runnable skills.
-                # Treat that capability absence as an empty collection so the
-                # shared UI can render normally instead of surfacing a 500.
-                return self.success(data={'skills': []})
-            except (ValueError, BoxError) as exc:
+            except ValueError as exc:
                return self.http_status(400, -1, str(exc))
            return self.success(data={'skills': skills})

@@ -47,7 +39,7 @@ class SkillsRouterGroup(group.RouterGroup):
            try:
                skill = await self.ap.skill_service.create_skill(request_context, data)
                return self.success(data={'skill': skill})
-            except (ValueError, BoxError) as exc:
+            except ValueError as exc:
                return self.http_status(400, -1, str(exc))

        @self.route(
@@ -59,7 +51,7 @@ class SkillsRouterGroup(group.RouterGroup):
        async def get_skill(skill_name: str, request_context: RequestContext) -> quart.Response:
            try:
                skill = await self.ap.skill_service.get_skill(request_context, skill_name)
-            except (ValueError, BoxError) as exc:
+            except ValueError as exc:
                return self.http_status(400, -1, str(exc))
            if not skill:
                return self.http_status(404, -1, 'Skill not found')
@@ -77,13 +69,13 @@ class SkillsRouterGroup(group.RouterGroup):
                try:
                    skill = await self.ap.skill_service.update_skill(request_context, skill_name, data)
                    return self.success(data={'skill': skill})
-                except (ValueError, BoxError) as exc:
+                except ValueError as exc:
                    return self.http_status(400, -1, str(exc))

            try:
                await self.ap.skill_service.delete_skill(request_context, skill_name)
                return self.success()
-            except (ValueError, BoxError) as exc:
+            except ValueError as exc:
                return self.http_status(400, -1, str(exc))

        @self.route(
@@ -105,7 +97,7 @@ class SkillsRouterGroup(group.RouterGroup):
                    include_hidden=include_hidden,
                )
                return self.success(data=result)
-            except (ValueError, BoxError) as exc:
+            except ValueError as exc:
                return self.http_status(400, -1, str(exc))

        @self.route(
@@ -118,7 +110,7 @@ class SkillsRouterGroup(group.RouterGroup):
            try:
                result = await self.ap.skill_service.read_skill_file(request_context, skill_name, path)
                return self.success(data=result)
-            except (ValueError, BoxError) as exc:
+            except ValueError as exc:
                return self.http_status(400, -1, str(exc))

        @self.route(
@@ -136,7 +128,7 @@ class SkillsRouterGroup(group.RouterGroup):
            try:
                result = await self.ap.skill_service.write_skill_file(request_context, skill_name, path, content)
                return self.success(data=result)
-            except (ValueError, BoxError) as exc:
+            except ValueError as exc:
                return self.http_status(400, -1, str(exc))

        @self.route(
@@ -170,7 +162,7 @@ class SkillsRouterGroup(group.RouterGroup):
            try:
                skill = await self.ap.skill_service.install_from_github(request_context, data)
                return self.success(data={'skills': skill})
-            except (ValueError, BoxError) as exc:
+            except ValueError as exc:
                return self.http_status(400, -1, str(exc))
            except Exception:
                raise
@@ -194,7 +186,7 @@ class SkillsRouterGroup(group.RouterGroup):
            try:
                preview = await self.ap.skill_service.preview_install_from_github(request_context, data)
                return self.success(data={'skills': preview})
-            except (ValueError, BoxError) as exc:
+            except ValueError as exc:
                return self.http_status(400, -1, str(exc))
            except Exception:
                raise
@@ -219,7 +211,7 @@ class SkillsRouterGroup(group.RouterGroup):
                    source_paths=form.getlist('source_paths'),
                )
                return self.success(data={'skills': skill})
-            except (ValueError, BoxError) as exc:
+            except ValueError as exc:
                return self.http_status(400, -1, str(exc))
            except Exception:
                raise
@@ -242,7 +234,7 @@ class SkillsRouterGroup(group.RouterGroup):
                    filename=file.filename or '',
                )
                return self.success(data={'skills': preview})
-            except (ValueError, BoxError) as exc:
+            except ValueError as exc:
                return self.http_status(400, -1, str(exc))
            except Exception:
                raise
@@ -261,5 +253,5 @@ class SkillsRouterGroup(group.RouterGroup):
            try:
                result = await self.ap.skill_service.scan_directory_async(request_context, path)
                return self.success(data=result)
-            except (ValueError, BoxError) as exc:
+            except ValueError as exc:
                return self.http_status(400, -1, str(exc))
@@ -186,6 +186,9 @@ class UserRouterGroup(group.RouterGroup):
            json_data = await quart.request.json
            code = json_data.get('code')
            state = json_data.get('state')
+            redirect_uri = json_data.get('redirect_uri') or (
+                quart.request.url_root.rstrip('/') + '/auth/space/callback'
+            )
            launch_assertion = json_data.get('launch_assertion')
            workspace_uuid = json_data.get('workspace_uuid')

@@ -199,8 +202,11 @@ class UserRouterGroup(group.RouterGroup):
                return self.fail(1, 'Missing authorization code')
            if not state:
                return self.fail(1, 'Missing state parameter')
+            if not str(code).startswith('v4_'):
+                return self.fail(1, 'Unsupported Space OAuth code contract')

            try:
+                redirect_uri = self._validate_space_redirect_uri(str(redirect_uri), bind=False)
                consumed_state = await self.ap.user_service.consume_space_oauth_state_details(state, 'login')
                # Exchange code for tokens
                launch_workspace_uuid = consumed_state.launch_workspace_uuid
@@ -218,24 +224,36 @@ class UserRouterGroup(group.RouterGroup):
                    code,
                    workspace_uuids,
                    workspace_created_ats,
+                    redirect_uri=redirect_uri,
                )
                access_token = token_data.get('access_token')
                refresh_token = token_data.get('refresh_token')
                expires_in = token_data.get('expires_in', 0)
+                cloud_workspace_uuid = token_data.get('cloud_workspace_uuid')

                if not access_token:
                    return self.fail(1, 'Failed to get access token from Space')

-                # Authenticate and create/update local user
+                cloud_mode = getattr(getattr(self.ap, 'deployment', None), 'mode', 'oss') == 'cloud'
+                if cloud_mode and launch_workspace_uuid and launch_workspace_uuid != cloud_workspace_uuid:
+                    return self.fail(1, 'Space OAuth Workspace binding mismatch')
+                target_workspace_uuid = launch_workspace_uuid or cloud_workspace_uuid
+                if cloud_mode:
+                    if not target_workspace_uuid:
+                        return self.fail(1, 'Space OAuth response is missing the Cloud Workspace binding')
+                    await self.ap.directory_projection_service.reconcile_workspaces((target_workspace_uuid,))
+
+                # Authenticate only after the signed, exact Workspace delta has
+                # established the Account and membership runtime shadow rows.
                jwt_token, user_obj = await self.ap.user_service.authenticate_space_user(
                    access_token, refresh_token, expires_in
                )

-                if launch_workspace_uuid:
+                if target_workspace_uuid:
                    try:
                        access = await self.ap.workspace_collaboration_service.resolve_account_workspace(
                            user_obj.uuid,
-                            launch_workspace_uuid,
+                            target_workspace_uuid,
                        )
                    except Exception:
                        self.ap.logger.warning('Rejected Space OAuth launch for unauthorized Workspace')
@@ -367,12 +385,17 @@ class UserRouterGroup(group.RouterGroup):
            json_data = await quart.request.json
            code = json_data.get('code')
            state = json_data.get('state')
+            redirect_uri = json_data.get('redirect_uri') or (
+                quart.request.url_root.rstrip('/') + '/auth/space/callback?mode=bind'
+            )

            if not code:
                return self.http_status(400, -1, 'Missing authorization code')

            if not state:
                return self.http_status(400, -1, 'Missing state parameter')
+            if not str(code).startswith('v4_'):
+                return self.http_status(400, -1, 'Unsupported Space OAuth code contract')

            try:
                user_obj = await self.ap.user_service.consume_space_oauth_state(state, 'bind')
@@ -385,7 +408,10 @@ class UserRouterGroup(group.RouterGroup):
                return self.http_status(400, -1, 'Only local accounts can bind to Space')

            try:
-                updated_user = await self.ap.user_service.bind_space_account(user_obj.user, code)
+                redirect_uri = self._validate_space_redirect_uri(str(redirect_uri), bind=True)
+                updated_user = await self.ap.user_service.bind_space_account(
+                    user_obj.user, code, redirect_uri=redirect_uri
+                )
                jwt_token = await self.ap.user_service.generate_jwt_token(updated_user)
                return self.success(
                    data={
@@ -428,6 +454,10 @@ class UserRouterGroup(group.RouterGroup):
                    }
                )

+            projection_service = self.ap.directory_projection_service
+            if projection_service is None:
+                raise SpaceLaunchError('Cloud directory projection is unavailable')
+            await projection_service.reconcile_workspaces((launch['workspace_uuid'],))
            account = await self.ap.user_service.get_user_by_uuid(launch['account_uuid'])
            if account is None:
                raise SpaceLaunchError('Launch Account is not projected into Core')
@@ -137,7 +137,16 @@ class BotService:

        bot = await self.get_bot(context, bot_data['uuid'], include_secret=True)

-        await self.ap.platform_mgr.load_bot(context, bot)
+        try:
+            await self.ap.platform_mgr.load_bot(context, bot)
+        except Exception:
+            # The bot row was already inserted above; without this rollback a
+            # failing adapter constructor (e.g. a missing optional credential
+            # key) would leave a permanently disabled orphan bot in the DB.
+            await self.ap.persistence_mgr.execute_async(
+                sqlalchemy.delete(persistence_bot.Bot).where(persistence_bot.Bot.uuid == bot_data['uuid'])
+            )
+            raise

        return bot_data['uuid']

@@ -1257,6 +1257,7 @@ class MonitoringService:
        pipeline_ids: list[str] | None = None,
        start_time: datetime.datetime | None = None,
        end_time: datetime.datetime | None = None,
+        user_query: str | None = None,
        is_active: bool | None = None,
        limit: int = 100,
        offset: int = 0,
@@ -1274,6 +1275,14 @@ class MonitoringService:
            conditions.append(persistence_monitoring.MonitoringSession.start_time >= start_time)
        if end_time:
            conditions.append(persistence_monitoring.MonitoringSession.start_time <= end_time)
+        if user_query and user_query.strip():
+            user_pattern = f'%{user_query.strip()}%'
+            conditions.append(
+                sqlalchemy.or_(
+                    persistence_monitoring.MonitoringSession.user_id.ilike(user_pattern),
+                    persistence_monitoring.MonitoringSession.user_name.ilike(user_pattern),
+                )
+            )
        if is_active is not None:
            conditions.append(persistence_monitoring.MonitoringSession.is_active == is_active)

@@ -1365,6 +1374,8 @@ class MonitoringService:
        self,
        context: TenantContext,
        session_id: str,
+        start_time: datetime.datetime | None = None,
+        end_time: datetime.datetime | None = None,
    ) -> dict:
        """Get bounded session details with full statistics computed in SQL."""
        workspace_uuid = require_workspace_uuid(context)
@@ -1478,12 +1489,17 @@ class MonitoringService:
            )
        )
        tool_stats = tool_stats_result.one()
+        tool_conditions = [
+            persistence_monitoring.MonitoringToolCall.workspace_uuid == workspace_uuid,
+            persistence_monitoring.MonitoringToolCall.session_id == session_id,
+        ]
+        if start_time is not None:
+            tool_conditions.append(persistence_monitoring.MonitoringToolCall.timestamp >= start_time)
+        if end_time is not None:
+            tool_conditions.append(persistence_monitoring.MonitoringToolCall.timestamp <= end_time)
        tool_query = (
            sqlalchemy.select(persistence_monitoring.MonitoringToolCall)
-            .where(
-                persistence_monitoring.MonitoringToolCall.workspace_uuid == workspace_uuid,
-                persistence_monitoring.MonitoringToolCall.session_id == session_id,
-            )
+            .where(*tool_conditions)
            .order_by(persistence_monitoring.MonitoringToolCall.timestamp.asc())
            .limit(detail_limit + 1)
        )
@@ -25,6 +25,7 @@ _PUBLIC_SKILL_FIELDS = (
    'description',
    'instructions',
    'package_root',
+    'revision',
    'created_at',
    'updated_at',
 )
@@ -53,38 +54,11 @@ class SkillService:
    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)
+    def _repository(self):
+        repository = getattr(self.ap, 'skill_repository', None)
+        if repository is None:
+            raise ValueError('Skill repository is not initialised')
+        return repository

    async def _execution_context(self, context: TenantContext) -> ExecutionContext:
        workspace_uuid = require_workspace_uuid(context)
@@ -113,20 +87,11 @@ class SkillService:

    async def list_skills(self, context: TenantContext) -> list[dict]:
        execution_context = await self._execution_context(context)
-        # 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(execution_context)]
+        return [self._serialize_skill(skill) for skill in await self._repository().list_skills(execution_context)]

    async def get_skill(self, context: TenantContext, skill_name: str) -> Optional[dict]:
        execution_context = await self._execution_context(context)
-        box_service = self._box_service()
-        if box_service is None:
-            return None
-        skill = await box_service.get_skill(execution_context, skill_name)
+        skill = await self._repository().get_skill(execution_context, skill_name, snapshot=True)
        return self._serialize_skill(skill) if skill else None

    async def get_skill_by_name(self, context: TenantContext, name: str) -> Optional[dict]:
@@ -134,22 +99,25 @@ class SkillService:

    async def create_skill(self, context: TenantContext, data: dict) -> dict:
        execution_context = await self._execution_context(context)
-        box_service = self._require_box('Creating a skill')
-        created = await box_service.create_skill(execution_context, data)
+        created = await self._repository().create_skill(execution_context, data)
+        await self._reload_skills(execution_context)
+        return self._serialize_skill(created)
+
+    async def import_skill_directory(self, context: TenantContext, path: str, data: dict) -> dict:
+        execution_context = await self._execution_context(context)
+        created = await self._repository().import_skill_directory(execution_context, path, data)
        await self._reload_skills(execution_context)
        return self._serialize_skill(created)

    async def update_skill(self, context: TenantContext, skill_name: str, data: dict) -> dict:
        execution_context = await self._execution_context(context)
-        box_service = self._require_box('Editing a skill')
-        updated = await box_service.update_skill(execution_context, skill_name, data)
+        updated = await self._repository().update_skill(execution_context, skill_name, data)
        await self._reload_skills(execution_context)
        return self._serialize_skill(updated)

    async def delete_skill(self, context: TenantContext, skill_name: str) -> bool:
        execution_context = await self._execution_context(context)
-        box_service = self._require_box('Deleting a skill')
-        await box_service.delete_skill(execution_context, skill_name)
+        await self._repository().delete_skill(execution_context, skill_name)
        await self._reload_skills(execution_context)
        return True

@@ -162,24 +130,27 @@ class SkillService:
        max_entries: int = 200,
    ) -> dict:
        execution_context = await self._execution_context(context)
-        box_service = self._require_box('Browsing skill files')
-        return await box_service.list_skill_files(execution_context, skill_name, path, include_hidden, max_entries)
+        return await self._repository().list_skill_files(
+            execution_context,
+            skill_name,
+            path,
+            include_hidden,
+            max_entries,
+        )

    async def read_skill_file(self, context: TenantContext, skill_name: str, path: str) -> dict:
        execution_context = await self._execution_context(context)
-        box_service = self._require_box('Reading a skill file')
-        return await box_service.read_skill_file(execution_context, skill_name, path)
+        return await self._repository().read_skill_file(execution_context, skill_name, path)

    async def write_skill_file(self, context: TenantContext, skill_name: str, path: str, content: str) -> dict:
        execution_context = await self._execution_context(context)
-        box_service = self._require_box('Editing skill files')
-        result = await box_service.write_skill_file(execution_context, skill_name, path, content)
+        result = await self._repository().write_skill_file(execution_context, skill_name, path, content)
        await self._reload_skills(execution_context)
        return result

    async def install_from_github(self, context: TenantContext, data: dict) -> list[dict]:
        execution_context = await self._execution_context(context)
-        box_service = self._require_box('Installing a skill from GitHub')
+        repository = self._repository()
        owner = str(data['owner']).strip()
        repo = str(data['repo']).strip()
        release_tag = str(data.get('release_tag', '')).strip()
@@ -198,7 +169,7 @@ class SkillService:

        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(
+        installed = await repository.install_skill_zip(
            execution_context,
            zip_bytes,
            filename,
@@ -211,7 +182,7 @@ class SkillService:

    async def preview_install_from_github(self, context: TenantContext, data: dict) -> list[dict]:
        execution_context = await self._execution_context(context)
-        box_service = self._require_box('Previewing a skill from GitHub')
+        repository = self._repository()
        owner = str(data['owner']).strip()
        repo = str(data['repo']).strip()
        release_tag = str(data.get('release_tag', '')).strip()
@@ -228,7 +199,7 @@ class SkillService:
        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(
+        return await repository.preview_skill_zip(
            execution_context,
            zip_bytes,
            f'{repo}-{release_tag.lstrip("v").replace("/", "-") or "source"}.zip',
@@ -245,8 +216,7 @@ class SkillService:
        source_path: str = '',
    ) -> list[dict]:
        execution_context = await self._execution_context(context)
-        box_service = self._require_box('Installing a skill from upload')
-        installed = await box_service.install_skill_zip(
+        installed = await self._repository().install_skill_zip(
            execution_context,
            file_bytes,
            filename,
@@ -264,8 +234,7 @@ class SkillService:
        filename: str,
    ) -> list[dict]:
        execution_context = await self._execution_context(context)
-        box_service = self._require_box('Previewing a skill upload')
-        return await box_service.preview_skill_zip(execution_context, file_bytes, filename)
+        return await self._repository().preview_skill_zip(execution_context, file_bytes, filename)

    async def _install_github_skill_md(
        self,
@@ -276,14 +245,14 @@ class SkillService:
        repo: str,
        data: dict,
    ) -> list[dict]:
-        box_service = self._require_box('Installing a skill from GitHub')
+        repository = self._repository()
        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(
+        installed = await repository.install_skill_zip(
            context,
            zip_bytes,
            filename,
@@ -302,13 +271,13 @@ class SkillService:
        owner: str,
        repo: str,
    ) -> list[dict]:
-        box_service = self._require_box('Previewing a skill from GitHub')
+        repository = self._repository()
        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(context, zip_bytes, f'{package_name}.zip', target_suffix='')
+        return await repository.preview_skill_zip(context, zip_bytes, f'{package_name}.zip', target_suffix='')

    async def reload_skills(self, context: TenantContext) -> list[dict]:
        execution_context = await self._execution_context(context)
@@ -317,8 +286,7 @@ class SkillService:

    async def scan_directory_async(self, context: TenantContext, path: str) -> dict:
        execution_context = await self._execution_context(context)
-        box_service = self._require_box('Scanning a skill directory')
-        return await box_service.scan_skill_directory(execution_context, path)
+        return await self._repository().scan_skill_directory(execution_context, path)

    async def _reload_skills(self, context: TenantContext) -> None:
        skill_mgr = getattr(self.ap, 'skill_mgr', None)
@@ -119,7 +119,7 @@ class SpaceService:

        space_config = self._get_space_config()
        authorize_url = space_config['oauth_authorize_url']
-        params = {'redirect_uri': redirect_uri}
+        params = {'redirect_uri': redirect_uri, 'code_contract': 'redirect-v1'}
        if state:
            params['state'] = state
        return f'{authorize_url}?{urlencode(params)}'
@@ -129,6 +129,8 @@ class SpaceService:
        code: str,
        workspace_uuids: list[str] | None = None,
        workspace_created_ats: dict[str, int] | None = None,
+        *,
+        redirect_uri: str = '',
    ) -> typing.Dict:
        """Exchange OAuth authorization code for tokens"""
        from langbot.pkg.utils import constants
@@ -141,6 +143,7 @@ class SpaceService:
            f'{space_url}/api/v1/accounts/oauth/token',
            json={
                'code': code,
+                'redirect_uri': redirect_uri,
                'instance_id': constants.instance_id,
                # Sending an explicit empty list tells new Space servers not to
                # synthesize a legacy instance-derived Workspace binding.
@@ -774,7 +774,7 @@ class UserService:
            f'email:{normalized_email}',
        )

-    async def bind_space_account(self, user_email: str, code: str) -> user.User:
+    async def bind_space_account(self, user_email: str, code: str, *, redirect_uri: str = '') -> user.User:
        """Bind Space account to existing local account"""
        local_account = await self.get_user_by_email(user_email)
        if local_account is None:
@@ -794,12 +794,13 @@ class UserService:
                code,
                [binding.workspace_uuid],
                {binding.workspace_uuid: created_ts},
+                redirect_uri=redirect_uri,
            )
        else:
            # Compatibility for early/bootstrap call sites that have not wired
            # WorkspaceService yet; old Space servers still derive the legacy
            # Workspace identity from instance_id when the field is omitted.
-            token_data = await self.ap.space_service.exchange_oauth_code(code)
+            token_data = await self.ap.space_service.exchange_oauth_code(code, redirect_uri=redirect_uri)
        access_token = token_data.get('access_token')
        refresh_token = token_data.get('refresh_token')
        expires_in = token_data.get('expires_in', 0)
@@ -147,10 +147,9 @@ class BoxRuntimeConnector(ManagedRuntimeConnector):
          - An explicit ``runtime.endpoint`` was configured

        When this is True the Box runtime lives in a separate process with its
-        own filesystem view (container, pod sidecar, or remote host), so paths
-        it reports (e.g. skill ``package_root``) are NOT resolvable on the
-        LangBot side. When False, Box runs as a stdio child process that shares
-        LangBot's filesystem.
+        own filesystem view (container, pod sidecar, or remote host), so only
+        explicitly shared paths are usable on both sides. When False, Box runs
+        as a stdio child process that shares LangBot's filesystem.
        """
        return bool(
            self.configured_runtime_endpoint
@@ -28,8 +28,10 @@ from langbot_plugin.box.errors import BoxAdmissionError, BoxError, BoxValidation
 from langbot_plugin.box.models import (
    BUILTIN_PROFILES,
    BoxExecutionResult,
+    BoxHostMountMode,
    BoxManagedProcessInfo,
    BoxManagedProcessSpec,
+    BoxMountSpec,
    BoxProfile,
    BoxSpec,
 )
@@ -169,7 +171,7 @@ class BoxService:
            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.'
+                'stdio MCP, executable package scripts) will be unavailable.'
            )
            return
        try:
@@ -275,10 +277,6 @@ class BoxService:
                        await self._purge_attachment_dirs()
                    self._available = True
                    self._connector_error = ''
-                    skill_mgr = getattr(self.ap, 'skill_mgr', None)
-                    reload_skills = getattr(skill_mgr, 'reload_skills', None)
-                    if callable(reload_skills) and not self._cloud_managed:
-                        await reload_skills()
                    self.ap.logger.info('Box runtime reconnected, sandbox features restored.')
                    return
                except Exception as exc:
@@ -358,19 +356,17 @@ class BoxService:
        """Whether LangBot and the Box runtime share a filesystem view.

        This is True only when Box runs as a local stdio child process of
-        LangBot (same container/host). In that case paths the Box runtime
-        reports — notably skill ``package_root`` — resolve identically on the
-        LangBot side, so LangBot may validate them against its own filesystem.
+        LangBot (same container/host). In that case host paths resolve
+        identically on both sides and Core may perform local filesystem work.

        It is False for every separated deployment (Docker Compose, k8s
        sidecar, ``--standalone-box``, or an explicit ``runtime.endpoint``),
-        where the Box runtime owns its own filesystem and LangBot must trust
-        the paths it reports rather than checking them locally.
+        where only explicitly shared and identically mounted roots can cross
+        the process boundary.

        When Box is wired up with an injected client (tests, custom embeds)
-        there is no connector to introspect; we conservatively report False so
-        LangBot never wrongly drops Box-reported skills. An explicit override
-        can be set via ``_shares_filesystem_with_box`` (used by tests and any
+        there is no connector to introspect; we conservatively report False.
+        An explicit override can be set via ``_shares_filesystem_with_box`` (used by tests and any
        embedder that knows the real topology).
        """
        if self._shares_filesystem_with_box_override is not None:
@@ -455,7 +451,9 @@ class BoxService:

    async def _require_validated_workspace_sandbox(self, execution_context: ExecutionContext) -> None:
        if not self._available:
-            raise BoxError('Box runtime is not available. Install and start Docker to use sandbox features.')
+            raise BoxError(
+                'Box runtime is not available. Configure an available Box backend before using Box features.'
+            )
        if self._cloud_managed:
            if self._admission is None:
                raise BoxAdmissionError('Cloud Box sandbox admission is unavailable')
@@ -481,11 +479,18 @@ class BoxService:
        self,
        context: TenantContext,
        spec_payload: dict,
+        *,
+        trusted_read_only_mounts: list[dict] | None = None,
    ) -> dict:
        """Reject tenant-owned policy fields and apply the Cloud hard policy."""

        payload = dict(spec_payload)
+        trusted_mounts = self._normalize_trusted_read_only_mounts(trusted_read_only_mounts or [])
        if not self._cloud_managed:
+            if trusted_mounts:
+                if payload.get('extra_mounts'):
+                    raise BoxValidationError('extra_mounts and trusted_read_only_mounts cannot both be supplied')
+                payload['extra_mounts'] = trusted_mounts
            return payload
        policy = self._admission_policy
        if policy is None:
@@ -535,7 +540,7 @@ class BoxService:
                'network': 'off',
                'host_path': canonical_host_path,
                'mount_path': '/workspace',
-                'extra_mounts': [],
+                'extra_mounts': trusted_mounts,
                'persistent': True,
                'timeout_sec': min(timeout, policy.max_timeout_sec),
                'cpus': policy.cpus,
@@ -547,6 +552,22 @@ class BoxService:
        )
        return payload

+    def _normalize_trusted_read_only_mounts(self, mounts: list[dict]) -> list[dict]:
+        """Validate Core-composed artifacts before crossing into Box."""
+
+        normalized: list[dict] = []
+        for raw_mount in mounts:
+            mount = BoxMountSpec.model_validate(raw_mount)
+            if mount.mode != BoxHostMountMode.READ_ONLY:
+                raise BoxAdmissionError('Core-composed additional mounts must be read-only')
+            host_path = os.path.realpath(mount.host_path)
+            if not os.path.isdir(host_path):
+                raise BoxAdmissionError('Core-composed read-only mount source is unavailable')
+            if not any(_is_path_under(host_path, root) for root in self.allowed_mount_roots):
+                raise BoxAdmissionError('Core-composed read-only mount source is outside allowed_mount_roots')
+            normalized.append(mount.model_copy(update={'host_path': host_path}).model_dump(mode='json'))
+        return normalized
+
    def _reject_cloud_managed_process(self) -> None:
        if self._cloud_managed:
            raise BoxAdmissionError('Managed processes are disabled for Cloud sandboxes')
@@ -563,11 +584,18 @@ class BoxService:
        query: pipeline_query.Query,
        *,
        skip_host_mount_validation: bool = False,
+        trusted_read_only_mounts: list[dict] | None = None,
    ) -> dict:
        if not self._available:
-            raise BoxError('Box runtime is not available. Install and start Docker to use sandbox features.')
+            raise BoxError(
+                'Box runtime is not available. Configure an available Box backend before using Box features.'
+            )
        execution_context = await self._validated_execution_context(self._query_execution_context(query))
-        spec_payload = self._managed_policy_payload(execution_context, spec_payload)
+        spec_payload = self._managed_policy_payload(
+            execution_context,
+            spec_payload,
+            trusted_read_only_mounts=trusted_read_only_mounts,
+        )
        await self._require_validated_workspace_sandbox(execution_context)
        if spec_payload.get('host_path') in (None, ''):
            tenant_workspace = self._tenant_workspace(execution_context)
@@ -654,70 +682,12 @@ class BoxService:
        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.
-
-        Path validation is filesystem-topology dependent. When LangBot and the
-        Box runtime share a filesystem (local stdio mode), a skill whose
-        ``package_root`` is missing or no longer a directory is skipped with a
-        warning instead of being passed through to the backend. Without that
-        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.
-
-        When Box runs as a separate process (Docker Compose, k8s sidecar,
-        ``--standalone-box``, or a remote ``runtime.endpoint``), the
-        ``package_root`` reported by ``list_skills`` is the Box runtime's own
-        filesystem path and is NOT resolvable on the LangBot side. Validating
-        it locally would wrongly drop every skill, so LangBot trusts the path
-        and lets the Box runtime resolve it. The Box runtime only ever reports
-        skills it discovered on its own filesystem, so the path is valid there
-        by construction.
-        """
-        if self._cloud_managed:
-            return []
-        skill_mgr = getattr(self.ap, 'skill_mgr', None)
-        if skill_mgr is None:
-            return []
-
-        from ..provider.tools.loaders import skill as skill_loader
-
-        validate_locally = self.shares_filesystem_with_box
-
-        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 validate_locally and 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,
        *,
-        skill_name: str | None = None,
+        read_only_mounts: list[dict] | None = None,
    ) -> dict:
        """Execute an agent-facing ``exec`` tool call.

@@ -725,8 +695,6 @@ class BoxService:
        ``BoxSpec.cmd`` field and injects the session id from the query.
        """
        spec_payload: dict = {'cmd': parameters['command']}
-        if skill_name is not None:
-            spec_payload['skill_name'] = skill_name

        # Pass through allowed agent-facing fields
        for key in ('workdir', 'timeout_sec', 'env'):
@@ -736,11 +704,11 @@ class BoxService:
        # 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)
+        return await self.execute_spec_payload(
+            spec_payload,
+            query,
+            trusted_read_only_mounts=read_only_mounts,
+        )

    async def execute_in_context(
        self,
@@ -1271,8 +1239,6 @@ class BoxService:
            'timeout_sec': 120,
            'session_id': self.resolve_box_session_id(query),
        }
-        if 'extra_mounts' not in spec_payload:
-            spec_payload['extra_mounts'] = self.build_skill_extra_mounts(query)
        try:
            spec = self.build_spec(spec_payload)
            result = await self.client.execute(spec)
@@ -1523,126 +1489,6 @@ class BoxService:
            self._runtime_connector.get_relay_headers(action_context),
        )

-    async def list_skills(self, context: TenantContext) -> list[dict]:
-        execution_context = await self._validated_skill_execution_context(context)
-        return await self.client.list_skills(action_context=self._action_context(execution_context))
-
-    async def get_skill(self, context: TenantContext, name: str) -> dict | None:
-        execution_context = await self._validated_skill_execution_context(context)
-        return await self.client.get_skill(name, action_context=self._action_context(execution_context))
-
-    async def create_skill(self, context: TenantContext, skill: dict) -> dict:
-        execution_context = await self._validated_skill_execution_context(context)
-        payload = dict(skill)
-        payload.pop('workspace_uuid', None)
-        if self._cloud_managed and str(payload.get('package_root', '') or '').strip():
-            raise BoxAdmissionError('Cloud skill package_root is runtime-owned')
-        if self._cloud_managed:
-            payload.pop('package_root', None)
-        return await self.client.create_skill(payload, action_context=self._action_context(execution_context))
-
-    async def update_skill(self, context: TenantContext, name: str, skill: dict) -> dict:
-        execution_context = await self._validated_skill_execution_context(context)
-        payload = dict(skill)
-        payload.pop('workspace_uuid', None)
-        if self._cloud_managed:
-            # The runtime already owns the package path for an existing skill.
-            # A serialized read response may contain it, but it is never an
-            # authority-bearing update field in shared Cloud mode.
-            payload.pop('package_root', None)
-        return await self.client.update_skill(
-            name,
-            payload,
-            action_context=self._action_context(execution_context),
-        )
-
-    async def delete_skill(self, context: TenantContext, name: str) -> None:
-        execution_context = await self._validated_skill_execution_context(context)
-        await self.client.delete_skill(name, action_context=self._action_context(execution_context))
-
-    async def scan_skill_directory(self, context: TenantContext, path: str) -> dict:
-        execution_context = await self._validated_skill_execution_context(context)
-        if self._cloud_managed:
-            raise BoxAdmissionError('Scanning arbitrary host skill directories is disabled in Cloud')
-        return await self.client.scan_skill_directory(path, action_context=self._action_context(execution_context))
-
-    async def _validated_skill_execution_context(self, context: TenantContext) -> ExecutionContext:
-        execution_context = await self._validated_execution_context(context)
-        await self._require_validated_workspace_sandbox(execution_context)
-        return execution_context
-
-    async def list_skill_files(
-        self,
-        context: TenantContext,
-        name: str,
-        path: str = '.',
-        include_hidden: bool = False,
-        max_entries: int = 200,
-    ) -> dict:
-        execution_context = await self._validated_skill_execution_context(context)
-        return await self.client.list_skill_files(
-            name,
-            path,
-            include_hidden,
-            max_entries,
-            action_context=self._action_context(execution_context),
-        )
-
-    async def read_skill_file(self, context: TenantContext, name: str, path: str) -> dict:
-        execution_context = await self._validated_skill_execution_context(context)
-        return await self.client.read_skill_file(
-            name,
-            path,
-            action_context=self._action_context(execution_context),
-        )
-
-    async def write_skill_file(self, context: TenantContext, name: str, path: str, content: str) -> dict:
-        execution_context = await self._validated_skill_execution_context(context)
-        return await self.client.write_skill_file(
-            name,
-            path,
-            content,
-            action_context=self._action_context(execution_context),
-        )
-
-    async def preview_skill_zip(
-        self,
-        context: TenantContext,
-        file_bytes: bytes,
-        filename: str,
-        source_subdir: str = '',
-        target_suffix: str = 'upload',
-    ) -> list[dict]:
-        execution_context = await self._validated_skill_execution_context(context)
-        return await self.client.preview_skill_zip(
-            file_bytes,
-            filename,
-            source_subdir,
-            target_suffix,
-            action_context=self._action_context(execution_context),
-        )
-
-    async def install_skill_zip(
-        self,
-        context: TenantContext,
-        file_bytes: bytes,
-        filename: str,
-        source_paths: list[str] | None = None,
-        source_path: str = '',
-        source_subdir: str = '',
-        target_suffix: str = 'upload',
-    ) -> list[dict]:
-        execution_context = await self._validated_skill_execution_context(context)
-        return await self.client.install_skill_zip(
-            file_bytes,
-            filename,
-            source_paths,
-            source_path,
-            source_subdir,
-            target_suffix,
-            action_context=self._action_context(execution_context),
-        )
-
    def _serialize_result(self, result: BoxExecutionResult) -> dict:
        stdout, stdout_truncated = self._truncate(result.stdout)
        stderr, stderr_truncated = self._truncate(result.stderr)
@@ -1779,14 +1625,6 @@ class BoxService:
            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,
@@ -2142,5 +1980,8 @@ class BoxService:
            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'
+                payload['connector_error'] = (
+                    'No supported sandbox backend (Docker / nsjail / E2B) is available. '
+                    'Trusted local development may explicitly select the unsafe host backend.'
+                )
        return payload
@@ -1,43 +1,28 @@
 """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.
+This module is the middle layer between raw Box runtime primitives and
+application-specific consumers.

 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
+Higher layers add their own semantics on top; BoxWorkspaceSession retains only
+workspace, execution, and managed-process concepts.
 """

 from __future__ import annotations

 import os
-import textwrap
 from typing import Any

-PYTHON_MANIFEST_FILES = (
-    'requirements.txt',
-    'pyproject.toml',
-    'setup.py',
-    'setup.cfg',
-)
+from ..utils.python_workspace import list_python_manifest_files
+
 _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:
@@ -98,13 +83,6 @@ def rewrite_venv_command(command: str, host_path: str | None, *, mount_path: str
    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))
@@ -117,163 +95,6 @@ def classify_python_workspace(host_path: str | None) -> str | None:
    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',
-    state_path: str | None = None,
-) -> str:
-    """Wrap a command with a reusable sandbox-local Python env bootstrap.
-
-    ``mount_path`` is always the source tree used for manifest hashing and
-    installation. ``state_path`` may point at a separate writable directory
-    for read-only source mounts; when omitted, legacy mutable-workspace behavior
-    stores the environment beside the source.
-    """
-    writable_state_path = state_path or mount_path
-    bootstrap = textwrap.dedent(
-        f"""
-        set -e
-
-        _LB_VENV_DIR="{writable_state_path}/.venv"
-        _LB_META_DIR="{writable_state_path}/.langbot"
-        _LB_META_FILE="$_LB_META_DIR/python-env.json"
-        _LB_LOCK_DIR="$_LB_META_DIR/python-env.lock"
-        _LB_TMP_DIR="{writable_state_path}/.tmp"
-        _LB_PIP_CACHE_DIR="{writable_state_path}/.cache/pip"
-
-        mkdir -p "$_LB_META_DIR" "$_LB_TMP_DIR" "$_LB_PIP_CACHE_DIR"
-        _LB_SYSTEM_PYTHON="$(command -v python3 || command -v python || true)"
-        if [ -z "$_LB_SYSTEM_PYTHON" ]; then
-          echo "python3 or python is required to prepare the workspace Python environment" >&2
-          exit 127
-        fi
-
-        export TMPDIR="$_LB_TMP_DIR"
-        export TEMP="$_LB_TMP_DIR"
-        export TMP="$_LB_TMP_DIR"
-        export PIP_CACHE_DIR="$_LB_PIP_CACHE_DIR"
-
-        _lb_python_meta() {{
-          "$_LB_SYSTEM_PYTHON" - <<'PY'
-        import hashlib
-        import json
-        import os
-        import sys
-
-        root = "{mount_path}"
-        max_manifest_bytes = 10 * 1024 * 1024
-        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
-            if os.path.getsize(path) > max_manifest_bytes:
-                raise RuntimeError(
-                    f"Python project manifest exceeds {{max_manifest_bytes}} bytes: {{rel}}"
-                )
-            manifest_files.append(rel)
-            with open(path, "rb") as handle:
-                digest.update(rel.encode("utf-8"))
-                digest.update(b"\\0")
-                while chunk := handle.read(1024 * 1024):
-                    digest.update(chunk)
-                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 [ "$_LB_LOCK_WAIT" -ge 120 ]; then
-              _LB_LOCK_OWNER="$(cat "$_LB_LOCK_DIR/pid" 2>/dev/null || true)"
-              if [ -n "$_LB_LOCK_OWNER" ] && kill -0 "$_LB_LOCK_OWNER" 2>/dev/null; then
-                echo "Timed out waiting for active Python environment lock: $_LB_LOCK_DIR" >&2
-                exit 1
-              fi
-              echo "Timed out waiting for Python environment lock, clearing stale lock: $_LB_LOCK_DIR" >&2
-              rm -rf "$_LB_LOCK_DIR" 2>/dev/null || true
-              if mkdir "$_LB_LOCK_DIR" 2>/dev/null; then
-                break
-              fi
-              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
-          printf '%s\\n' "$$" > "$_LB_LOCK_DIR/pid" 2>/dev/null || true
-
-          _lb_cleanup_lock() {{
-            rm -rf "$_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"
-            "$_LB_SYSTEM_PYTHON" -m venv "$_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.

@@ -125,10 +125,21 @@ class DirectoryProjectionService:
        # The database cursor remains the shared projection high-water mark,
        # while this cursor tracks what this process has actually observed.
        self._consumer_cursor: int | None = None
+        self._sync_lock = asyncio.Lock()

    async def initialize(self) -> None:
        """Block Cloud startup until one full signed snapshot is committed."""

+        async with self._sync_lock:
+            await self._refresh_snapshot()
+
+    async def refresh_snapshot(self) -> None:
+        """Refresh from one full signed snapshot within the sync single-flight."""
+
+        async with self._sync_lock:
+            await self._refresh_snapshot()
+
+    async def _refresh_snapshot(self) -> None:
        last_superseded: _DirectorySnapshotSuperseded | None = None
        for _attempt in range(5):
            snapshot = await self.provider.fetch_snapshot(self.instance_uuid)
@@ -159,9 +170,84 @@ class DirectoryProjectionService:
                delay = min(max(delay * 2, self.sync_interval_seconds), self.max_staleness_seconds / 2)

    async def sync_once(self) -> None:
+        async with self._sync_lock:
+            await self._sync_once()
+
+    async def reconcile_workspaces(self, workspace_uuids: Iterable[str]) -> None:
+        """Synchronously project an exact Workspace set without moving the event cursor."""
+
+        requested = tuple(sorted({str(value).strip() for value in workspace_uuids if str(value).strip()}))
+        if not requested:
+            raise DirectoryProjectionUnavailableError('Targeted directory reconciliation requires a Workspace')
+        if len(requested) > self.event_limit:
+            raise DirectoryProjectionUnavailableError('Targeted directory reconciliation exceeds the batch limit')
+        async with self._sync_lock:
+            delta = await self.provider.fetch_workspaces(self.instance_uuid, requested)
+            await self._apply_targeted_delta(delta, requested)
+
+    async def _apply_targeted_delta(
+        self,
+        delta: DirectoryDelta,
+        requested_workspace_uuids: tuple[str, ...],
+    ) -> None:
+        if not isinstance(delta, DirectoryDelta):
+            raise DirectoryProjectionUnavailableError('Directory provider returned an invalid delta')
+        workspace_count, membership_count = self._validate_batch_capacity(
+            delta.workspaces,
+            full_snapshot=False,
+        )
+        delta = DirectoryDelta.model_validate(delta.model_dump())
+        if delta.instance_uuid != self.instance_uuid:
+            raise DirectoryProjectionUnavailableError('Directory delta targets another LangBot instance')
+        requested = set(requested_workspace_uuids)
+        if set(delta.requested_workspace_uuids) != requested:
+            raise DirectoryProjectionUnavailableError('Directory delta does not match the requested Workspaces')
+        if {workspace.uuid for workspace in delta.workspaces} != requested:
+            raise DirectoryProjectionUnavailableError('Directory delta omitted a requested Workspace')
+
+        directory_uow = getattr(self.ap.persistence_mgr, 'directory_projection_uow', None)
+        if not callable(directory_uow):
+            raise DirectoryProjectionUnavailableError('Directory projection persistence scope is unavailable')
+
+        async with directory_uow(self.instance_uuid) as uow:
+            session = uow.session
+            state = await session.scalar(
+                sqlalchemy.select(DirectoryProjectionState)
+                .where(DirectoryProjectionState.instance_uuid == self.instance_uuid)
+                .with_for_update()
+            )
+            if state is None:
+                raise DirectoryProjectionUnavailableError('Directory projection is not initialized')
+            snapshot = DirectorySnapshot(
+                instance_uuid=self.instance_uuid,
+                cursor=state.cursor,
+                generated_at=delta.generated_at,
+                workspaces=delta.workspaces,
+            )
+            accounts_by_uuid = await self._apply_accounts(session, snapshot, preserve_existing=True)
+            await self._apply_workspaces(session, snapshot, accounts_by_uuid=accounts_by_uuid)
+            active_workspace_count = await self._enforce_active_workspace_capacity(session)
+            await session.flush()
+
+        await self._update_entitlement_workspace_activity(
+            snapshot.workspaces,
+            requested_workspace_uuids=requested,
+        )
+        self._publish_runtime_execution_projection(
+            snapshot.workspaces,
+            affected_workspace_uuids=requested,
+        )
+        self._request_model_catalog_sync()
+        self._record_batch_cardinality(
+            active_workspaces=active_workspace_count,
+            workspaces=workspace_count,
+            memberships=membership_count,
+        )
+
+    async def _sync_once(self) -> None:
        cursor = self._consumer_cursor
        if cursor is None:
-            await self.initialize()
+            await self._refresh_snapshot()
            return
        batch = await self.provider.fetch_events(
            self.instance_uuid,
@@ -708,7 +794,13 @@ class DirectoryProjectionService:
        for row in inbox_rows:
            row.applied_at = now

-    async def _apply_accounts(self, session: Any, snapshot: DirectorySnapshot) -> dict[str, User]:
+    async def _apply_accounts(
+        self,
+        session: Any,
+        snapshot: DirectorySnapshot,
+        *,
+        preserve_existing: bool = False,
+    ) -> dict[str, User]:
        selected: dict[str, DirectoryMember] = {}
        emails: dict[str, str] = {}
        for workspace in snapshot.workspaces:
@@ -773,6 +865,12 @@ class DirectoryProjectionService:
                continue
            if account.source != AccountSource.CLOUD_PROJECTION.value:
                raise DirectoryProjectionUnavailableError('Directory account UUID collides with a local Core account')
+            if preserve_existing:
+                # A targeted Workspace fetch has no independently monotonic
+                # Account revision. It may create a missing runtime shadow, but
+                # ordered event/snapshot projection remains the only updater of
+                # existing Account identity and status fields.
+                continue
            if account.projection_revision > snapshot.cursor:
                raise DirectoryProjectionUnavailableError('Directory account revision rolled back')
            projected_account = self._account_projection(member)
@@ -43,6 +43,7 @@ from . import entities as core_entities
 from ..rag.knowledge import kbmgr as rag_mgr
 from ..rag.service import RAGRuntimeService
 from ..vector import mgr as vectordb_mgr
+from ..skill import repository as skill_repository
 from ..telemetry import telemetry as telemetry_module
 from ..survey import manager as survey_module
 from ..skill import manager as skill_mgr
@@ -84,6 +85,7 @@ class Application:
    # TODO move to pipeline
    tool_mgr: llm_tool_mgr.ToolManager = None
    box_service: box_service_module.BoxService = None
+    skill_repository: skill_repository.SkillRepository = None

    # ======= Config manager =======

@@ -635,9 +637,9 @@ class Application:
        frontend_path = paths.get_frontend_path()

        if not os.path.exists(frontend_path):
-            self.logger.warning('WebUI 文件缺失，请根据文档部署：https://docs.langbot.app/zh')
+            self.logger.warning('WebUI 文件缺失，请根据文档部署：https://langbot.app/docs/zh')
            self.logger.warning(
-                'WebUI files are missing, please deploy according to the documentation: https://docs.langbot.app/en'
+                'WebUI files are missing, please deploy according to the documentation: https://langbot.app/docs/en'
            )
            return

@@ -26,6 +26,7 @@ from ...api.http.service import knowledge as knowledge_service
 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 ...skill import repository as skill_repository
 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
@@ -127,6 +128,7 @@ class BuildAppStage(stage.BootingStage):
        webhook_service_inst = webhook_service.WebhookService(ap)
        ap.webhook_service = webhook_service_inst

+        ap.skill_repository = skill_repository.SkillRepository(ap)
        skill_service_inst = skill_service.SkillService(ap)
        ap.skill_service = skill_service_inst

@@ -328,6 +328,8 @@ class PreProcessor(stage.PipelineStage):
        #      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:
+            available_tool_names = {tool.name for tool in query.use_funcs}
+            query.variables['_skill_execution_available'] = 'exec' in available_tool_names
            skill_execution_context = get_query_execution_context(query)
            await self.ap.skill_mgr.ensure_loaded(skill_execution_context)
            pipeline_data = await self.ap.pipeline_service.get_pipeline(
@@ -349,7 +351,7 @@ class PreProcessor(stage.PipelineStage):
                skill_execution_context,
                bound_skills=bound_skills,
            )
-            if skill_addition:
+            if skill_addition and 'activate' in available_tool_names:
                self._append_to_system_prompt(query.prompt.messages, skill_addition)
                self.ap.logger.debug(
                    f'Skill index injected into system prompt: '
@@ -357,7 +359,7 @@ class PreProcessor(stage.PipelineStage):
                    f'bound_skills={bound_skills or "all"} '
                    f'loaded_skills={len(self.ap.skill_mgr.get_skills(skill_execution_context))}'
                )
-            else:
+            elif 'activate' in available_tool_names:
                self.ap.logger.debug(
                    f'No skills available for prompt injection: '
                    f'pipeline={query.pipeline_uuid} '
@@ -15,9 +15,9 @@ spec:
  categories:
    - protocol
  help_links:
-    zh: https://link.langbot.app/zh/platforms/aiocqhttp
-    en: https://link.langbot.app/en/platforms/aiocqhttp
-    ja: https://link.langbot.app/ja/platforms/aiocqhttp
+    zh: https://langbot.app/docs/zh/usage/platforms/qq/aiocqhttp/napcat
+    en: https://langbot.app/docs/en/usage/platforms/qq/aiocqhttp/napcat
+    ja: https://langbot.app/docs/ja/usage/platforms/qq/aiocqhttp/napcat
  config:
    - name: host
      label:
@@ -15,9 +15,9 @@ spec:
  categories:
    - china
  help_links:
-    zh: https://link.langbot.app/zh/platforms/dingtalk
-    en: https://link.langbot.app/en/platforms/dingtalk
-    ja: https://link.langbot.app/ja/platforms/dingtalk
+    zh: https://langbot.app/docs/zh/usage/platforms/dingtalk
+    en: https://langbot.app/docs/en/usage/platforms/dingtalk
+    ja: https://langbot.app/docs/ja/usage/platforms/dingtalk
  config:
    - name: one-click-create
      label:
@@ -24,9 +24,9 @@ spec:
    - popular
    - global
  help_links:
-    zh: https://link.langbot.app/zh/platforms/discord
-    en: https://link.langbot.app/en/platforms/discord
-    ja: https://link.langbot.app/ja/platforms/discord
+    zh: https://langbot.app/docs/zh/usage/platforms/discord
+    en: https://langbot.app/docs/en/usage/platforms/discord
+    ja: https://langbot.app/docs/ja/usage/platforms/discord
  config:
    - name: client_id
      label:
@@ -18,9 +18,9 @@ spec:
    - popular
    - global
  help_links:
-    zh: https://docs.langbot.app/zh/platforms/http-bot
-    en: https://docs.langbot.app/en/platforms/http-bot
-    ja: https://docs.langbot.app/ja/platforms/http-bot
+    zh: https://langbot.app/docs/zh/platforms/http-bot
+    en: https://langbot.app/docs/en/platforms/http-bot
+    ja: https://langbot.app/docs/ja/platforms/http-bot
  config:
    - name: webhook_url
      label:
@@ -15,9 +15,9 @@ spec:
  categories:
    - china
  help_links:
-    zh: https://link.langbot.app/zh/platforms/kook
-    en: https://link.langbot.app/en/platforms/kook
-    ja: https://link.langbot.app/ja/platforms/kook
+    zh: https://langbot.app/docs/zh/usage/platforms/kook
+    en: https://langbot.app/docs/en/usage/platforms/kook
+    ja: https://langbot.app/docs/ja/usage/platforms/kook
  config:
    - name: token
      label:
@@ -160,6 +160,29 @@ def _lark_should_update_stream_element(
    return not resume_from and not form_data and (msg_seq % 8 == 0 or is_final)


+def _lark_final_layout_texts(
+    *,
+    resume_from: bool,
+    text_message: str,
+    pre_pause_cached: str | None,
+    resume_cached: str,
+) -> tuple[str, str]:
+    """Return (main_text, resume_placeholder_text) for the final card update.
+
+    Non-resume round: the full reply belongs in the main streaming element
+    only — also rendering the resume placeholder duplicates the reply, since
+    both hold the same accumulated text. Resume round (Dify HITL): keep the
+    pre-pause text in the main element and the resumed text in the
+    placeholder, as they are distinct segments.
+    """
+    if resume_from:
+        # An empty pre-pause cache is valid (Dify paused before emitting any
+        # text); only a missing entry (None) falls back to the full text.
+        main_text = text_message if pre_pause_cached is None else pre_pause_cached
+        return main_text, resume_cached
+    return text_message, ''
+
+
 def _lark_display_input_value(field: dict, value: typing.Any) -> str:
    field_type = _dify_field_type(field)
    if field_type == 'file':
@@ -2358,16 +2381,21 @@ class LarkAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                    self.card_form_input_defs[card_id] = _lark_form_input_defs(form_data)
                    self.card_form_inputs[card_id] = dict(form_data.get('inputs') or {})
            else:
-                # Normal finish: keep pre-pause + resume content visible,
-                # remove buttons/notice, drop the resume placeholder.
+                # Normal finish: remove buttons/notice and finalize the card.
+                main_text, resume_text = _lark_final_layout_texts(
+                    resume_from=resume_from,
+                    text_message=text_message,
+                    pre_pause_cached=self.card_pre_pause_text.get(card_id),
+                    resume_cached=resume_cached,
+                )
                await self._update_card_layout(
                    card_id=card_id,
                    message_source=message_source,
-                    text_message=pre_pause,
+                    text_message=main_text,
                    sequence=final_seq,
                    form_data=None,
                    notice_text=selected_notice if resume_from else '',
-                    resume_placeholder_text=resume_cached,
+                    resume_placeholder_text=resume_text,
                )
                self._drop_card_state(card_id)
            self.card_id_dict.pop(message_id, None)
@@ -19,9 +19,9 @@ spec:
    - china
    - global
  help_links:
-    zh: https://link.langbot.app/zh/platforms/lark
-    en: https://link.langbot.app/en/platforms/lark
-    ja: https://link.langbot.app/ja/platforms/lark
+    zh: https://langbot.app/docs/zh/usage/platforms/lark
+    en: https://langbot.app/docs/en/usage/platforms/lark
+    ja: https://langbot.app/docs/ja/usage/platforms/lark
  config:
    - name: domain
      label:
@@ -22,9 +22,9 @@ spec:
  categories:
    - global
  help_links:
-    zh: https://link.langbot.app/zh/platforms/line
-    en: https://link.langbot.app/en/platforms/line
-    ja: https://link.langbot.app/ja/platforms/line
+    zh: https://langbot.app/docs/zh/usage/platforms/line
+    en: https://langbot.app/docs/en/usage/platforms/line
+    ja: https://langbot.app/docs/ja/usage/platforms/line
  config:
    - name: webhook_url
      label:
@@ -15,9 +15,9 @@ spec:
  categories:
    - china
  help_links:
-    zh: https://link.langbot.app/zh/platforms/officialaccount
-    en: https://link.langbot.app/en/platforms/officialaccount
-    ja: https://link.langbot.app/ja/platforms/officialaccount
+    zh: https://langbot.app/docs/zh/usage/platforms/wxoa
+    en: https://langbot.app/docs/en/usage/platforms/wxoa
+    ja: https://langbot.app/docs/ja/usage/platforms/wxoa
  config:
    - name: webhook_url
      label:
@@ -16,9 +16,9 @@ spec:
    - popular
    - china
  help_links:
-    zh: https://link.langbot.app/zh/platforms/openclaw_weixin
-    en: https://link.langbot.app/en/platforms/openclaw_weixin
-    ja: https://link.langbot.app/ja/platforms/openclaw_weixin
+    zh: https://langbot.app/docs/zh/usage/platforms/wechat/weixin
+    en: https://langbot.app/docs/en/usage/platforms/readme
+    ja: https://langbot.app/docs/ja/usage/platforms/readme
  config:
    - name: base_url
      label:
@@ -205,7 +205,7 @@ class QQOfficialAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter
        bot = QQOfficialClient(
            app_id=config['appid'],
            secret=config['secret'],
-            token=config['token'],
+            token=config.get('token', ''),
            logger=logger,
            unified_mode=enable_webhook,
        )
@@ -15,9 +15,9 @@ spec:
  categories:
    - china
  help_links:
-    zh: https://link.langbot.app/zh/platforms/qqofficial
-    en: https://link.langbot.app/en/platforms/qqofficial
-    ja: https://link.langbot.app/ja/platforms/qqofficial
+    zh: https://langbot.app/docs/zh/usage/platforms/qq/official_webhook
+    en: https://langbot.app/docs/en/usage/platforms/qq/official_webhook
+    ja: https://langbot.app/docs/ja/usage/platforms/qq/official_webhook
  config:
    - name: __system.outbound_ips
      label:
@@ -21,9 +21,9 @@ spec:
  categories:
    - protocol
  help_links:
-    zh: https://link.langbot.app/zh/platforms/satori
-    en: https://link.langbot.app/en/platforms/satori
-    ja: https://link.langbot.app/ja/platforms/satori
+    zh: https://langbot.app/docs/zh/usage/platforms/readme
+    en: https://langbot.app/docs/en/usage/platforms/readme
+    ja: https://langbot.app/docs/ja/usage/platforms/readme
  config:
    - name: platform
      label:
@@ -24,9 +24,9 @@ spec:
    - popular
    - global
  help_links:
-    zh: https://link.langbot.app/zh/platforms/slack
-    en: https://link.langbot.app/en/platforms/slack
-    ja: https://link.langbot.app/ja/platforms/slack
+    zh: https://langbot.app/docs/zh/usage/platforms/slack
+    en: https://langbot.app/docs/en/usage/platforms/slack
+    ja: https://langbot.app/docs/ja/usage/platforms/slack
  config:
    - name: webhook_url
      label:
@@ -24,9 +24,9 @@ spec:
    - popular
    - global
  help_links:
-    zh: https://link.langbot.app/zh/platforms/telegram
-    en: https://link.langbot.app/en/platforms/telegram
-    ja: https://link.langbot.app/ja/platforms/telegram
+    zh: https://langbot.app/docs/zh/usage/platforms/telegram
+    en: https://langbot.app/docs/en/usage/platforms/telegram
+    ja: https://langbot.app/docs/ja/usage/platforms/telegram
  config:
    - name: token
      label:
@@ -15,9 +15,9 @@ spec:
  categories:
    - china
  help_links:
-    zh: https://link.langbot.app/zh/platforms/wechatpad
-    en: https://link.langbot.app/en/platforms/wechatpad
-    ja: https://link.langbot.app/ja/platforms/wechatpad
+    zh: https://langbot.app/docs/zh/usage/platforms/wechat/wechatpad
+    en: https://langbot.app/docs/en/usage/platforms/readme
+    ja: https://langbot.app/docs/ja/usage/platforms/readme
  config:
    - name: wechatpad_url
      label:
@@ -274,11 +274,11 @@ class WecomAdapter(abstract_platform_adapter.AbstractMessagePlatformAdapter):
                if content['type'] == 'text':
                    await self.bot.send_private_msg(user_id, agent_id, content['content'])
                if content['type'] == 'image':
-                    await self.bot.send_image(user_id, agent_id, content['media'])
+                    await self.bot.send_image(user_id, agent_id, content['media_id'])
                if content['type'] == 'voice':
-                    await self.bot.send_voice(user_id, agent_id, content['media'])
+                    await self.bot.send_voice(user_id, agent_id, content['media_id'])
                if content['type'] == 'file':
-                    await self.bot.send_file(user_id, agent_id, content['media'])
+                    await self.bot.send_file(user_id, agent_id, content['media_id'])

    def register_listener(
        self,
@@ -16,9 +16,9 @@ spec:
    - popular
    - china
  help_links:
-    zh: https://link.langbot.app/zh/platforms/wecom
-    en: https://link.langbot.app/en/platforms/wecom
-    ja: https://link.langbot.app/ja/platforms/wecom
+    zh: https://langbot.app/docs/zh/usage/platforms/wecom/wecom
+    en: https://langbot.app/docs/en/usage/platforms/wecom/wecom
+    ja: https://langbot.app/docs/ja/usage/platforms/wecom/wecom
  config:
    - name: webhook_url
      label:
@@ -15,9 +15,9 @@ spec:
  categories:
    - china
  help_links:
-    zh: https://link.langbot.app/zh/platforms/wecombot
-    en: https://link.langbot.app/en/platforms/wecombot
-    ja: https://link.langbot.app/ja/platforms/wecombot
+    zh: https://langbot.app/docs/zh/usage/platforms/wecom/wecombot
+    en: https://langbot.app/docs/en/usage/platforms/wecom/wecombot
+    ja: https://langbot.app/docs/ja/usage/platforms/wecom/wecombot
  config:
    - name: one-click-create
      label:
@@ -15,9 +15,9 @@ spec:
  categories:
    - china
  help_links:
-    zh: https://link.langbot.app/zh/platforms/wecomcs
-    en: https://link.langbot.app/en/platforms/wecomcs
-    ja: https://link.langbot.app/ja/platforms/wecomcs
+    zh: https://langbot.app/docs/zh/usage/platforms/wecom/wecomcs
+    en: https://langbot.app/docs/en/usage/platforms/wecom/wecomcs
+    ja: https://langbot.app/docs/ja/usage/platforms/wecom/wecomcs
  config:
    - name: webhook_url
      label:
@@ -573,7 +573,7 @@ class LiteLLMRequester(requester.ProviderAPIRequester):
            levels = ['provider_default', 'disabled', 'enabled']
        elif family == 'doubao':
            levels = ['provider_default', 'disabled', 'low', 'medium', 'high']
-        elif family == 'ollama':
+        elif family in ('ollama', 'ollama_chat'):
            levels = ['provider_default']
            levels.append('disabled')
            if normalized_name.startswith('gpt-oss') or '/gpt-oss' in normalized_name:
@@ -1345,7 +1345,14 @@ class LiteLLMRequester(requester.ProviderAPIRequester):
        extra_args: dict[str, typing.Any] = {},
    ) -> tuple[list[list[float]], dict]:
        """Invoke embedding and return vectors with usage info."""
-        model_name = self._build_litellm_model_name(model.model_entity.name)
+        # litellm's embedding routing has no "ollama_chat" branch (that provider
+        # exists only for /api/chat completions) — embeddings still go through
+        # the plain "ollama" provider. Requesters configured for ollama_chat
+        # (to get native tool-calling on the chat path) must fall back to
+        # "ollama" here specifically, or embedding calls raise "Unmapped LLM
+        # provider for this endpoint".
+        embedding_provider = 'ollama' if self._get_custom_llm_provider() == 'ollama_chat' else None
+        model_name = self._build_litellm_model_name(model.model_entity.name, embedding_provider)
        api_key = model.provider.token_mgr.get_token()

        args = {
@@ -1541,6 +1548,12 @@ class LiteLLMRequester(requester.ProviderAPIRequester):
                event_hooks=httpclient.httpx_response_limit_hooks(),
            ) as client:
                response = await client.get(models_url, headers=headers)
+                if response.status_code == 404 and not base_url.rstrip('/').endswith('/v1'):
+                    # Some OpenAI-compatible servers (notably a bare Ollama host,
+                    # e.g. http://host:11434) expose the model list under /v1/models
+                    # rather than /models. Providers whose configured base_url
+                    # already ends in /v1 keep their original (working) URL.
+                    response = await client.get(f'{base_url}/v1/models', headers=headers)
                response.raise_for_status()
                payload = await httpclient.parse_json_response(response)

@@ -7,7 +7,7 @@ metadata:
    zh_Hans: Ollama
  icon: ollama.svg
 spec:
-  litellm_provider: ollama
+  litellm_provider: ollama_chat
  config:
  - name: base_url
    label:
@@ -39,6 +39,9 @@ class N8nServiceAPIRunner(runner.RequestRunner):

        # 获取输出键名，默认为response
        self.output_key = self.pipeline_config['ai']['n8n-service-api'].get('output-key', 'response')
+        self.response_handling = self.pipeline_config['ai']['n8n-service-api'].get('response-handling', 'reply')
+        if self.response_handling not in {'reply', 'ignore'}:
+            raise ValueError(f'Invalid n8n response-handling: {self.response_handling}')

        # 获取认证类型，默认为none
        self.auth_type = self.pipeline_config['ai']['n8n-service-api'].get('auth-type', 'none')
@@ -262,7 +265,11 @@ class N8nServiceAPIRunner(runner.RequestRunner):
            async with session.post(
                self.webhook_url, json=payload, headers=headers, auth=auth, timeout=self.timeout
            ) as response:
-                if response.status != 200:
+                if self.response_handling == 'ignore':
+                    status_ok = 200 <= response.status < 300
+                else:
+                    status_ok = response.status == 200
+                if not status_ok:
                    error_text = (
                        await httpclient.read_limited(
                            response,
@@ -272,6 +279,11 @@ class N8nServiceAPIRunner(runner.RequestRunner):
                    self.ap.logger.error(f'n8n webhook call failed: {response.status}, {error_text}')
                    raise Exception(f'n8n webhook call failed: {response.status}, {error_text}')

+                if self.response_handling == 'ignore':
+                    response.release()
+                    self.ap.logger.debug('n8n async webhook accepted; response body ignored')
+                    return
+
                async for chunk in self._process_response(response):
                    if is_stream:
                        yield chunk
@@ -18,12 +18,11 @@ from ....box.workspace import (
    BoxWorkspaceSession,
    classify_python_workspace,
    infer_workspace_host_path,
-    normalize_host_path,
    rewrite_mounted_path,
    rewrite_venv_command,
    unwrap_venv_path,
-    wrap_python_command_with_env,
 )
+from ....utils.python_workspace import normalize_host_path, wrap_python_command_with_env

 if TYPE_CHECKING:
    from .mcp import RuntimeMCPSession
@@ -32,7 +32,7 @@ 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}
+SANDBOX_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'}
@@ -222,6 +222,7 @@ class NativeToolLoader(loader.ToolLoader):
            self.ap.logger.warning(
                'Native sandbox tools (exec/read/write/edit/glob/grep) are NOT available. '
                'No sandbox backend (Docker/nsjail/E2B) is ready. '
+                'Trusted local development may explicitly select box.backend=host. '
                'The LLM will not have access to code execution or file operation tools.'
            )

@@ -259,7 +260,11 @@ class NativeToolLoader(loader.ToolLoader):
        return list(self._tools)

    async def has_tool(self, name: str) -> bool:
-        return name in _ALL_TOOL_NAMES and await self._is_sandbox_available()
+        return name in SANDBOX_TOOL_NAMES and await self._is_sandbox_available()
+
+    @staticmethod
+    def recognizes_tool(name: str) -> bool:
+        return name in SANDBOX_TOOL_NAMES

    async def invoke_tool(self, name: str, parameters: dict, query: pipeline_query.Query):
        require_sandbox = getattr(
@@ -324,20 +329,11 @@ class NativeToolLoader(loader.ToolLoader):
            if not package_root:
                raise ValueError(f'Activated skill "{selected_skill_name}" has no package_root.')

-            # Pass only the logical name across the authenticated Core→Runtime
-            # boundary. In Cloud mode the shared Box Runtime resolves the
-            # Workspace-scoped package root and constructs the read-only mount;
-            # Core host paths are never accepted as mount authority.
            # 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}'
            python_project = selected_skill.get('python_project') is True
-            if 'python_project' not in selected_skill and bool(
-                getattr(self.ap.box_service, 'shares_filesystem_with_box', False)
-            ):
-                # Backward compatibility for a same-process OSS Runtime that
-                # predates trusted Box metadata. Never probe a path reported by
-                # an external Runtime from the Core filesystem.
+            if 'python_project' not in selected_skill:
                python_project = skill_loader.should_prepare_skill_python_env(package_root)
            if python_project:
                parameters = dict(parameters)
@@ -353,12 +349,9 @@ class NativeToolLoader(loader.ToolLoader):
        result = await self.ap.box_service.execute_tool(
            parameters,
            query,
-            skill_name=selected_skill_name,
+            read_only_mounts=skill_loader.build_execution_mounts(self.ap, query),
        )
        result = self._normalize_exec_result(result)
-
-        if selected_skill is not None:
-            self._refresh_skill_from_disk(query, selected_skill)
        return result

    def _resolve_host_location(
@@ -380,10 +373,7 @@ class NativeToolLoader(loader.ToolLoader):
        box_service = self.ap.box_service
        if selected_skill is not None:
            if not self._can_interpret_skill_host_paths():
-                raise ValueError(
-                    'Skill package paths are owned by the Box Runtime; '
-                    'this operation requires a Runtime skill-file API.'
-                )
+                raise ValueError('Secure Core host file operations are unavailable on this platform.')
            host_root = selected_skill.get('package_root')
            workspace_anchor = None
        else:
@@ -421,11 +411,9 @@ class NativeToolLoader(loader.ToolLoader):
        return selected_skill, relative

    def _can_interpret_skill_host_paths(self) -> bool:
-        """Require an explicitly proven shared Core/Runtime filesystem view."""
+        """Return whether Core can use its no-follow host file primitives."""

-        return _SECURE_HOST_FILE_OPS_AVAILABLE and bool(
-            getattr(self.ap.box_service, 'shares_filesystem_with_box', False)
-        )
+        return _SECURE_HOST_FILE_OPS_AVAILABLE

    def _should_use_box_workspace_files(self, selected_skill: dict | None) -> bool:
        if selected_skill is not None:
@@ -1122,20 +1110,11 @@ else:
            include_visible=True,
            include_activated=True,
        )
-        if skill_request is not None and hasattr(self.ap.box_service, 'read_skill_file'):
+        skill_repository = getattr(self.ap, 'skill_repository', None)
+        if skill_request is not None and skill_repository is not None:
            selected_skill, relative = skill_request
-            if self._can_interpret_skill_host_paths():
-                host_location = self._resolve_skill_host_location(selected_skill, relative)
-            else:
-                host_location = None
-            if host_location is not None:
-                try:
-                    return await asyncio.to_thread(self._read_host_location, host_location, parameters)
-                except FileNotFoundError:
-                    pass
-
            try:
-                result = await self.ap.box_service.read_skill_file(
+                result = await skill_repository.read_skill_file(
                    self._execution_context(query),
                    selected_skill['name'],
                    relative,
@@ -1143,7 +1122,7 @@ else:
                return self._build_read_result_from_text(str(result.get('content', '')), parameters)
            except Exception:
                try:
-                    result = await self.ap.box_service.list_skill_files(
+                    result = await skill_repository.list_skill_files(
                        self._execution_context(query),
                        selected_skill['name'],
                        relative,
@@ -1177,12 +1156,13 @@ else:
            include_visible=False,
            include_activated=True,
        )
-        if skill_request is not None and hasattr(self.ap.box_service, 'write_skill_file'):
+        skill_repository = getattr(self.ap, 'skill_repository', None)
+        if skill_request is not None and skill_repository is not None:
            if encoding != 'text':
                return {'ok': False, 'error': 'base64 writes to skill packages are not supported.'}
            selected_skill, relative = skill_request
            execution_context = self._execution_context(query)
-            await self.ap.box_service.write_skill_file(execution_context, selected_skill['name'], relative, content)
+            await skill_repository.write_skill_file(execution_context, selected_skill['name'], relative, content)
            await self.ap.skill_mgr.reload_skills(execution_context)
            return {'ok': True, 'path': path}

@@ -1215,14 +1195,10 @@ else:
            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')
-        ):
+        if skill_request is not None and getattr(self.ap, 'skill_repository', None) is not None:
            selected_skill, relative = skill_request
            try:
-                result = await self.ap.box_service.read_skill_file(
+                result = await self.ap.skill_repository.read_skill_file(
                    self._execution_context(query),
                    selected_skill['name'],
                    relative,
@@ -1237,7 +1213,7 @@ else:
                return {'ok': False, 'error': f'old_string matches {count} locations; provide a more unique string.'}
            new_content = content.replace(old_string, new_string, 1)
            execution_context = self._execution_context(query)
-            await self.ap.box_service.write_skill_file(
+            await self.ap.skill_repository.write_skill_file(
                execution_context,
                selected_skill['name'],
                relative,
@@ -1,10 +1,14 @@
 from __future__ import annotations

+import os
 import re
 import typing

-from ....box import workspace as box_workspace
 from ....api.http.context import ExecutionContext
+from ....utils.python_workspace import (
+    should_prepare_python_env,
+    wrap_python_command_with_env,
+)

 if typing.TYPE_CHECKING:
    from ....core import app
@@ -57,6 +61,30 @@ def get_visible_skill(ap: app.Application, query: pipeline_query.Query, skill_na
    return get_visible_skills(ap, query).get(skill_name)


+def build_execution_mounts(ap: app.Application, query: pipeline_query.Query) -> list[dict]:
+    """Translate visible Core-owned packages into generic read-only mounts."""
+
+    mounts: list[dict] = []
+    for skill_name, skill_data in get_visible_skills(ap, query).items():
+        package_root = str(skill_data.get('package_root', '') or '').strip()
+        if not package_root:
+            continue
+        if not os.path.isdir(package_root):
+            ap.logger.warning(
+                f'Skill "{skill_name}" package_root missing on the Core filesystem '
+                f'({package_root}); skipping its execution mount. Reload the skill catalog.'
+            )
+            continue
+        mounts.append(
+            {
+                'host_path': package_root,
+                'mount_path': get_virtual_skill_mount_path(skill_name),
+                'mode': 'ro',
+            }
+        )
+    return mounts
+
+
 def get_activated_skills(query: pipeline_query.Query) -> dict[str, dict]:
    if query.variables is None:
        return {}
@@ -198,7 +226,7 @@ def build_skill_session_id(skill_data: dict, query: pipeline_query.Query) -> str


 def should_prepare_skill_python_env(package_root: str | None) -> bool:
-    return box_workspace.should_prepare_python_env(package_root)
+    return should_prepare_python_env(package_root)


 def wrap_skill_command_with_python_env(
@@ -207,7 +235,7 @@ def wrap_skill_command_with_python_env(
    mount_path: str = '/workspace',
    state_path: str | None = None,
 ) -> str:
-    return box_workspace.wrap_python_command_with_env(
+    return wrap_python_command_with_env(
        command,
        mount_path=mount_path,
        state_path=state_path,
@@ -6,7 +6,6 @@ import typing
 import langbot_plugin.api.entities.builtin.resource.tool as resource_tool

 from .. import loader
-from .availability import is_box_backend_available
 from ....api.http.context import ExecutionContext

 # Align with Claude Code's Skill tool design:
@@ -15,12 +14,23 @@ from ....api.http.context import ExecutionContext
 # - This protects KV Cache and follows industry standard

 ACTIVATE_SKILL_TOOL_NAME = 'activate'
+LIST_SKILL_RESOURCES_TOOL_NAME = 'list_skill_resources'
+READ_SKILL_RESOURCE_TOOL_NAME = 'read_skill_resource'
 REGISTER_SKILL_TOOL_NAME = 'register_skill'

-SKILL_TOOL_NAMES = {
+READ_ONLY_SKILL_TOOL_NAMES = {
    ACTIVATE_SKILL_TOOL_NAME,
+    LIST_SKILL_RESOURCES_TOOL_NAME,
+    READ_SKILL_RESOURCE_TOOL_NAME,
+}
+SANDBOX_SKILL_TOOL_NAMES = {
    REGISTER_SKILL_TOOL_NAME,
 }
+SKILL_TOOL_NAMES = READ_ONLY_SKILL_TOOL_NAMES | SANDBOX_SKILL_TOOL_NAMES
+_SKILL_EXECUTION_AVAILABLE_KEY = '_skill_execution_available'
+_SKILL_RESOURCE_BYTES_READ_KEY = '_skill_resource_bytes_read'
+_MAX_SKILL_RESOURCE_FILE_BYTES = 256 * 1024
+_MAX_SKILL_RESOURCE_RUN_BYTES = 1024 * 1024


 class SkillToolLoader(loader.ToolLoader):
@@ -28,61 +38,73 @@ class SkillToolLoader(loader.ToolLoader):

    def __init__(self, ap):
        super().__init__(ap)
-        self._tools: list[resource_tool.LLMTool] = []
-        self._sandbox_available: bool = False
+        self._read_only_tools: list[resource_tool.LLMTool] = []
+        self._sandbox_tools: list[resource_tool.LLMTool] = []

    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 = [
+        if self._is_available():
+            self._read_only_tools = [
                self._build_activate_skill_tool(),
-                self._build_register_skill_tool(),
+                self._build_list_skill_resources_tool(),
+                self._build_read_skill_resource_tool(),
            ]
+            self._sandbox_tools = [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.'
-            )
+            self.ap.logger.info('Skill tools are unavailable because the Core SkillRepository is not initialized.')

-    async def _check_sandbox_available(self) -> bool:
-        """Check if the box backend is truly available (not just the runtime)."""
-        return await is_box_backend_available(self.ap)
-
-    async def get_tools(self, bound_plugins: list[str] | None = None) -> list[resource_tool.LLMTool]:
-        if not await self._is_available():
+    async def get_tools(
+        self,
+        bound_plugins: list[str] | None = None,
+        *,
+        sandbox_available: bool | None = None,
+    ) -> list[resource_tool.LLMTool]:
+        if not self._is_available():
            return []
-        if not self._tools:
-            self._tools = [
-                self._build_activate_skill_tool(),
-                self._build_register_skill_tool(),
-            ]
-        return list(self._tools)
+        if not self._read_only_tools:
+            await self.initialize()
+        tools = list(self._read_only_tools)
+        if sandbox_available:
+            tools.extend(self._sandbox_tools)
+        return tools

-    async def has_tool(self, name: str) -> bool:
-        return await self._is_available() and name in SKILL_TOOL_NAMES
+    async def get_tool(self, name: str, *, sandbox_available: bool | None = None):
+        for tool in await self.get_tools(sandbox_available=sandbox_available):
+            if tool.name == name:
+                return tool
+        return None

-    async def _is_available(self) -> bool:
-        """Check if skill tools should be available.
-
-        Skill tools require both a skill manager and a sandbox backend.
-        """
-        if not self._has_skill_manager():
+    async def has_tool(self, name: str, *, sandbox_available: bool | None = None) -> bool:
+        if not self._is_available() or name not in SKILL_TOOL_NAMES:
            return False
-        self._sandbox_available = await self._check_sandbox_available()
-        return self._sandbox_available
+        return name in READ_ONLY_SKILL_TOOL_NAMES or bool(sandbox_available)
+
+    @staticmethod
+    def is_sandbox_tool(name: str) -> bool:
+        return name in SANDBOX_SKILL_TOOL_NAMES
+
+    @staticmethod
+    def recognizes_tool(name: str) -> bool:
+        return name in SKILL_TOOL_NAMES
+
+    def _is_available(self) -> bool:
+        return self._has_skill_manager() and getattr(self.ap, 'skill_repository', None) is not None

    async def invoke_tool(self, name: str, parameters: dict, query) -> typing.Any:
-        require_sandbox = getattr(
-            getattr(self.ap, 'box_service', None),
-            'require_workspace_sandbox',
-            None,
-        )
-        if callable(require_sandbox):
-            await require_sandbox(self._execution_context(query))
        if name == ACTIVATE_SKILL_TOOL_NAME:
            return await self._invoke_activate_skill(parameters, query)
+        if name == LIST_SKILL_RESOURCES_TOOL_NAME:
+            return await self._invoke_list_skill_resources(parameters, query)
+        if name == READ_SKILL_RESOURCE_TOOL_NAME:
+            return await self._invoke_read_skill_resource(parameters, query)
        if name == REGISTER_SKILL_TOOL_NAME:
+            require_sandbox = getattr(
+                getattr(self.ap, 'box_service', None),
+                'require_workspace_sandbox',
+                None,
+            )
+            if not callable(require_sandbox):
+                return self._sandbox_unavailable_result(name)
+            await require_sandbox(self._execution_context(query))
            return await self._invoke_register_skill(parameters, query)
        raise ValueError(f'Unknown skill tool: {name}')

@@ -107,6 +129,27 @@ class SkillToolLoader(loader.ToolLoader):
    def _has_skill_manager(self) -> bool:
        return getattr(self.ap, 'skill_mgr', None) is not None

+    @staticmethod
+    def _sandbox_unavailable_result(name: str) -> dict:
+        return {
+            'ok': False,
+            'code': 'sandbox_unavailable',
+            'tool': name,
+            'message': 'This operation requires Box execution, but Box is not configured or available.',
+        }
+
+    async def _execution_available(self, query) -> bool:
+        variables = getattr(query, 'variables', None)
+        if isinstance(variables, dict) and _SKILL_EXECUTION_AVAILABLE_KEY in variables:
+            return bool(variables[_SKILL_EXECUTION_AVAILABLE_KEY])
+        checker = getattr(getattr(self.ap, 'box_service', None), 'is_workspace_sandbox_available', None)
+        if not callable(checker):
+            return False
+        try:
+            return bool(await checker(self._execution_context(query)))
+        except Exception:
+            return False
+
    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()
@@ -115,42 +158,111 @@ class SkillToolLoader(loader.ToolLoader):

        from . import skill as skill_loader

-        skill_data = skill_loader.get_visible_skill(self.ap, query, skill_name)
-        if skill_data is None:
+        visible_skill = skill_loader.get_visible_skill(self.ap, query, skill_name)
+        if visible_skill is None:
            visible_skills = skill_loader.get_visible_skills(self.ap, query)
            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
+        skill_data = await self.ap.skill_repository.get_skill(
+            self._execution_context(query),
+            skill_name,
+            snapshot=True,
+        )
+        if skill_data is None:
+            raise ValueError(f'Skill "{skill_name}" is no longer available; reload the skill catalog.')
+
        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)
+        revision = str(skill_data.get('revision', '') or '')
+        execution_available = await self._execution_available(query)
+        mount_path = skill_loader.get_virtual_skill_mount_path(skill_name) if execution_available else None

-        # 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'<revision>{revision}</revision>\n'
+        result_content += '<resources-readable>true</resources-readable>\n'
+        result_content += f'<execution-available>{str(execution_available).lower()}</execution-available>\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 += '- Use `list_skill_resources` and `read_skill_resource` for read-only package resources.\n'
+        if execution_available:
+            result_content += (
+                f'- Box execution is available; executable package files will be mounted at {mount_path}.\n'
+            )
+        else:
+            result_content += (
+                '- Box execution is unavailable. Do not attempt to run scripts or modify Workspace files.\n'
+            )
        result_content += '</skill-activation>\n'

        return {
            'activated': True,
            'skill_name': skill_name,
            'mount_path': mount_path,
+            'revision': revision,
+            'capabilities': {
+                'instructions_readable': True,
+                'resources_readable': True,
+                'execution_available': execution_available,
+            },
            'activated_skill_names': skill_loader.get_activated_skill_names(query),
            'content': result_content,
        }

+    @staticmethod
+    def _activated_skill(parameters: dict, query) -> dict:
+        from . import skill as skill_loader
+
+        skill_name = str(parameters.get('skill_name', '') or '').strip()
+        if not skill_name:
+            raise ValueError('skill_name is required')
+        skill_data = skill_loader.get_activated_skill(query, skill_name)
+        if skill_data is None:
+            raise ValueError(f'Skill "{skill_name}" must be activated before its resources can be read.')
+        requested_revision = str(parameters.get('revision', '') or '').strip()
+        activated_revision = str(skill_data.get('revision', '') or '').strip()
+        if requested_revision and requested_revision != activated_revision:
+            raise ValueError('revision must match the activated skill revision')
+        return skill_data
+
+    async def _invoke_list_skill_resources(self, parameters: dict, query) -> dict:
+        skill_data = self._activated_skill(parameters, query)
+        return await self.ap.skill_repository.list_skill_resources(
+            self._execution_context(query),
+            skill_data['name'],
+            str(parameters.get('path', '.') or '.'),
+            expected_revision=skill_data.get('revision'),
+        )
+
+    async def _invoke_read_skill_resource(self, parameters: dict, query) -> dict:
+        skill_data = self._activated_skill(parameters, query)
+        path = str(parameters.get('path', '') or '').strip()
+        if not path:
+            raise ValueError('path is required')
+        result = await self.ap.skill_repository.read_skill_resource(
+            self._execution_context(query),
+            skill_data['name'],
+            path,
+            expected_revision=skill_data.get('revision'),
+        )
+        content = str(result.get('content', ''))
+        size = len(content.encode('utf-8'))
+        if size > _MAX_SKILL_RESOURCE_FILE_BYTES:
+            raise ValueError('Skill resource exceeds the per-file read limit')
+        variables = getattr(query, 'variables', None)
+        if not isinstance(variables, dict):
+            variables = {}
+            query.variables = variables
+        total = int(variables.get(_SKILL_RESOURCE_BYTES_READ_KEY, 0) or 0) + size
+        if total > _MAX_SKILL_RESOURCE_RUN_BYTES:
+            raise ValueError('Skill resource reads exceed the per-run limit')
+        variables[_SKILL_RESOURCE_BYTES_READ_KEY] = total
+        result['size'] = size
+        return result
+
    async def _invoke_register_skill(self, parameters: dict, query) -> typing.Any:
        """Register a skill from sandbox directory to data/skills/."""
        sandbox_path = str(parameters.get('path', '') or '').strip()
@@ -175,14 +287,14 @@ class SkillToolLoader(loader.ToolLoader):
            raise ValueError('skill name is required')

        # Create the skill
-        created = await skill_service.create_skill(
+        created = await skill_service.import_skill_directory(
            execution_context,
+            host_path,
            {
                '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,
            },
        )

@@ -248,6 +360,42 @@ class SkillToolLoader(loader.ToolLoader):
            func=lambda parameters: parameters,
        )

+    def _build_list_skill_resources_tool(self) -> resource_tool.LLMTool:
+        return resource_tool.LLMTool(
+            name=LIST_SKILL_RESOURCES_TOOL_NAME,
+            human_desc='List activated skill resources',
+            description='List read-only files in an activated skill package without starting a sandbox.',
+            parameters={
+                'type': 'object',
+                'properties': {
+                    'skill_name': {'type': 'string', 'description': 'The activated skill name.'},
+                    'path': {'type': 'string', 'description': 'Relative directory path. Defaults to the package root.'},
+                    'revision': {'type': 'string', 'description': 'Optional revision returned by activate.'},
+                },
+                'required': ['skill_name'],
+                'additionalProperties': False,
+            },
+            func=lambda parameters: parameters,
+        )
+
+    def _build_read_skill_resource_tool(self) -> resource_tool.LLMTool:
+        return resource_tool.LLMTool(
+            name=READ_SKILL_RESOURCE_TOOL_NAME,
+            human_desc='Read an activated skill resource',
+            description='Read a UTF-8 text resource from an activated skill package without starting a sandbox.',
+            parameters={
+                'type': 'object',
+                'properties': {
+                    'skill_name': {'type': 'string', 'description': 'The activated skill name.'},
+                    'path': {'type': 'string', 'description': 'File path relative to the skill package root.'},
+                    'revision': {'type': 'string', 'description': 'Optional revision returned by activate.'},
+                },
+                'required': ['skill_name', 'path'],
+                'additionalProperties': False,
+            },
+            func=lambda parameters: parameters,
+        )
+
    def _build_register_skill_tool(self) -> resource_tool.LLMTool:
        return resource_tool.LLMTool(
            name=REGISTER_SKILL_TOOL_NAME,
@@ -66,6 +66,15 @@ class ToolManager:
        except Exception:
            return False

+    @staticmethod
+    def _sandbox_unavailable_result(name: str) -> dict[str, typing.Any]:
+        return {
+            'ok': False,
+            'code': 'sandbox_unavailable',
+            'tool': name,
+            'message': 'This operation requires Box execution, but Box is not configured or available.',
+        }
+
    async def initialize(self):
        from langbot.pkg.utils import importutil
        from langbot.pkg.provider.tools import loaders
@@ -102,8 +111,8 @@ class ToolManager:
        sandbox_available = await self._workspace_sandbox_available(context)
        if sandbox_available:
            all_functions.extend(await self.native_tool_loader.get_tools())
-        if include_skill_authoring and sandbox_available:
-            all_functions.extend(await self.skill_tool_loader.get_tools())
+        if include_skill_authoring:
+            all_functions.extend(await self.skill_tool_loader.get_tools(sandbox_available=sandbox_available))
        all_functions.extend(await self.plugin_tool_loader.get_tools(bound_plugins))
        all_functions.extend(
            await self.mcp_tool_loader.get_tools(
@@ -142,8 +151,12 @@ class ToolManager:
        sandbox_available = await self._workspace_sandbox_available(context)
        if sandbox_available:
            append_tools('builtin', 'LangBot', await self.native_tool_loader.get_tools())
-        if include_skill_authoring and sandbox_available:
-            append_tools('skill', 'LangBot', await self.skill_tool_loader.get_tools())
+        if include_skill_authoring:
+            append_tools(
+                'skill',
+                'LangBot',
+                await self.skill_tool_loader.get_tools(sandbox_available=sandbox_available),
+            )
        catalog.extend(await self.plugin_tool_loader.get_tool_catalog(bound_plugins))

        if self.mcp_tool_loader:
@@ -168,10 +181,9 @@ class ToolManager:
            tool = await active_loader.get_tool(name)
            if tool:
                return tool
-        if sandbox_available:
-            tool = await self.skill_tool_loader.get_tool(name)
-            if tool:
-                return tool
+        tool = await self.skill_tool_loader.get_tool(name, sandbox_available=sandbox_available)
+        if tool:
+            return tool

        return await self.mcp_tool_loader.get_tool(context, name)

@@ -310,7 +322,10 @@ class ToolManager:
                query=query,
                invoke=lambda: self.mcp_tool_loader.invoke_tool(name, parameters, query),
            )
-        if sandbox_available and await self.skill_tool_loader.has_tool(name):
+        if await self.skill_tool_loader.has_tool(name, sandbox_available=sandbox_available):
+            variables = getattr(query, 'variables', None)
+            if isinstance(variables, dict):
+                variables['_skill_execution_available'] = sandbox_available
            telemetry_features.increment(query, 'tool_calls', 'skill')
            return await self._invoke_tool_with_monitoring(
                source='skill',
@@ -319,6 +334,13 @@ class ToolManager:
                query=query,
                invoke=lambda: self.skill_tool_loader.invoke_tool(name, parameters, query),
            )
+        recognizes_native = getattr(self.native_tool_loader, 'recognizes_tool', None)
+        is_sandbox_skill_tool = getattr(self.skill_tool_loader, 'is_sandbox_tool', None)
+        if not sandbox_available and (
+            (callable(recognizes_native) and recognizes_native(name) is True)
+            or (callable(is_sandbox_skill_tool) and is_sandbox_skill_tool(name) is True)
+        ):
+            return self._sandbox_unavailable_result(name)
        raise ToolNotFoundError(name)

    async def shutdown(self):
@@ -1,3 +1,5 @@
 from .manager import SkillManager
+from .repository import SkillRepository

-__all__ = ['SkillManager']
+
+__all__ = ['SkillManager', 'SkillRepository']
@@ -1,14 +1,12 @@
 from __future__ import annotations

-import os
-
 from ..api.http.context import ExecutionContext
 from ..api.http.service.tenant import TenantContext, require_workspace_uuid
 from ..core import app


 class SkillManager:
-    """Workspace-scoped in-memory view of Box-managed skill packages."""
+    """Workspace-scoped in-memory view of Core-managed skill packages."""

    ap: app.Application

@@ -63,33 +61,20 @@ class SkillManager:
                self._skills_by_scope.pop(existing_key, None)
        self._skills_by_scope[key] = {}

-        box_service = getattr(self.ap, 'box_service', None)
-        if box_service is None or not getattr(box_service, 'available', False):
-            self.ap.logger.info(
-                f'Box runtime unavailable; skill cache is empty for Workspace {execution_context.workspace_uuid}.'
-            )
+        repository = getattr(self.ap, 'skill_repository', None)
+        if repository is None:
+            self.ap.logger.info('Skill repository unavailable; skill cache will remain empty.')
            return

-        validate_locally = bool(getattr(box_service, 'shares_filesystem_with_box', False))
        try:
-            dropped = 0
            skills: dict[str, dict] = {}
-            for skill_data in await box_service.list_skills(execution_context):
+            for skill_data in await repository.list_skills(execution_context):
                skill_name = skill_data.get('name')
                if not skill_name:
                    continue
-                package_root = str(skill_data.get('package_root', '') or '').strip()
-                if validate_locally and package_root and not os.path.isdir(package_root):
-                    self.ap.logger.warning(
-                        f'Skill "{skill_name}" reported by Box runtime but package_root '
-                        f'missing on LangBot filesystem ({package_root}); dropping from cache.'
-                    )
-                    dropped += 1
-                    continue
                skills[skill_name] = skill_data
            self._skills_by_scope[key] = skills
-            suffix = f' ({dropped} dropped due to missing package_root)' if dropped else ''
-            self.ap.logger.info(f'Loaded {len(skills)} skills for Workspace {execution_context.workspace_uuid}{suffix}')
+            self.ap.logger.info(f'Loaded {len(skills)} skills for Workspace {execution_context.workspace_uuid}')
        except Exception as exc:
            self.ap.logger.warning(f'Failed to load skills for Workspace {execution_context.workspace_uuid}: {exc}')

@@ -0,0 +1,199 @@
+from __future__ import annotations
+
+import asyncio
+import os
+
+from langbot_plugin.skill_store import (
+    SkillRevisionMismatchError,
+    SkillStore,
+    skill_namespace,
+)
+
+from ..api.http.context import ExecutionContext
+from ..api.http.service.tenant import TenantContext, require_workspace_uuid
+from ..utils.bounded_executor import blocking_work_scope, run_blocking_atomic
+
+
+class SkillRepository:
+    """Async, Workspace-scoped adapter around the SDK SkillStore."""
+
+    def __init__(self, ap) -> None:
+        self.ap = ap
+        config = getattr(getattr(ap, 'instance_config', None), 'data', {}) or {}
+        self._local_config = (config.get('box') or {}).get('local') or {}
+        self._skills_config = config.get('skills') or {}
+        self._store = SkillStore(self._skills_root())
+        self._lock = asyncio.Lock()
+
+    def _host_root(self) -> str:
+        configured = str(self._local_config.get('host_root') or './data/box').strip()
+        return os.path.realpath(os.path.abspath(os.path.expanduser(configured)))
+
+    def _skills_root(self) -> str:
+        configured = str(self._skills_config.get('root') or '').strip()
+        if not configured:
+            # Online-upgrade bridge for installations whose persisted config
+            # predates the standalone Skill domain.
+            # TODO(next-major): remove box.local.skills_root fallback.
+            legacy = str(self._local_config.get('skills_root') or '').strip()
+            configured = legacy or 'skills'
+            if not os.path.isabs(configured):
+                configured = os.path.join(self._host_root(), configured)
+        return os.path.realpath(os.path.abspath(os.path.expanduser(configured)))
+
+    def _default_workspace(self) -> str:
+        configured = str(self._local_config.get('default_workspace') or '').strip()
+        if not configured:
+            configured = os.path.join(self._host_root(), 'default')
+        elif not os.path.isabs(configured):
+            configured = os.path.join(self._host_root(), configured)
+        return os.path.realpath(os.path.abspath(os.path.expanduser(configured)))
+
+    @staticmethod
+    def _execution_context(context: TenantContext) -> ExecutionContext:
+        workspace_uuid = require_workspace_uuid(context)
+        instance_uuid = str(getattr(context, 'instance_uuid', '') or '').strip()
+        generation = getattr(context, 'placement_generation', None)
+        if not instance_uuid:
+            raise ValueError('Skill operations require an explicit instance UUID')
+        if isinstance(generation, bool) or not isinstance(generation, int) or generation <= 0:
+            raise ValueError('Skill operations require a positive placement generation')
+        return ExecutionContext(
+            instance_uuid=instance_uuid,
+            workspace_uuid=workspace_uuid,
+            placement_generation=generation,
+            bot_uuid=getattr(context, 'bot_uuid', None),
+            pipeline_uuid=getattr(context, 'pipeline_uuid', None),
+            query_uuid=getattr(context, 'query_uuid', None),
+            entitlement_revision=getattr(context, 'entitlement_revision', 0),
+        )
+
+    @classmethod
+    def _namespace(cls, context: TenantContext) -> str:
+        execution_context = cls._execution_context(context)
+        return skill_namespace(
+            execution_context.instance_uuid,
+            execution_context.workspace_uuid,
+        )
+
+    async def _validated_execution_context(self, context: TenantContext) -> ExecutionContext:
+        execution_context = self._execution_context(context)
+        binding = await self.ap.workspace_service.get_execution_binding(
+            execution_context.workspace_uuid,
+            expected_generation=execution_context.placement_generation,
+        )
+        if (
+            binding.instance_uuid != execution_context.instance_uuid
+            or str(getattr(binding, 'workspace_uuid', '') or '') != execution_context.workspace_uuid
+            or getattr(binding, 'placement_generation', None) != execution_context.placement_generation
+        ):
+            raise ValueError('Skill execution context belongs to a stale Workspace placement')
+        return execution_context
+
+    def _workspace_root(self, namespace: str) -> str:
+        return os.path.join(self._default_workspace(), 'tenants', namespace)
+
+    async def _call(self, context: TenantContext, method_name: str, *args, **kwargs):
+        execution_context = await self._validated_execution_context(context)
+        namespace = self._namespace(execution_context)
+
+        def invoke():
+            method = getattr(self._store.scoped(namespace), method_name)
+            return method(*args, **kwargs)
+
+        async with self._lock:
+            with blocking_work_scope(f'skill:{namespace}'):
+                return await run_blocking_atomic(invoke)
+
+    async def list_skills(self, context: TenantContext) -> list[dict]:
+        return await self._call(context, 'list_skills')
+
+    async def get_skill(self, context: TenantContext, name: str, *, snapshot: bool = False) -> dict | None:
+        return await self._call(context, 'get_skill_snapshot' if snapshot else 'get_skill', name)
+
+    async def create_skill(self, context: TenantContext, skill: dict) -> dict:
+        return await self._call(context, 'create_skill', skill)
+
+    async def import_skill_directory(self, context: TenantContext, path: str, skill: dict) -> dict:
+        namespace = self._namespace(context)
+        return await self._call(
+            context,
+            'import_skill_directory',
+            path,
+            skill,
+            source_root=self._workspace_root(namespace),
+        )
+
+    async def update_skill(self, context: TenantContext, name: str, skill: dict) -> dict:
+        return await self._call(context, 'update_skill', name, skill)
+
+    async def delete_skill(self, context: TenantContext, name: str) -> None:
+        await self._call(context, 'delete_skill', name)
+
+    async def scan_skill_directory(self, context: TenantContext, path: str) -> dict:
+        namespace = self._namespace(context)
+        return await self._call(
+            context,
+            'scan_import_directory',
+            path,
+            source_root=self._workspace_root(namespace),
+        )
+
+    async def list_skill_files(
+        self,
+        context: TenantContext,
+        name: str,
+        path: str = '.',
+        include_hidden: bool = False,
+        max_entries: int = 200,
+    ) -> dict:
+        return await self._call(context, 'list_skill_files', name, path, include_hidden, max_entries)
+
+    async def read_skill_file(self, context: TenantContext, name: str, path: str) -> dict:
+        return await self._call(context, 'read_skill_file', name, path)
+
+    async def list_skill_resources(
+        self,
+        context: TenantContext,
+        name: str,
+        path: str = '.',
+        *,
+        expected_revision: str | None = None,
+    ) -> dict:
+        return await self._call(
+            context,
+            'list_skill_resources',
+            name,
+            path,
+            False,
+            200,
+            expected_revision=expected_revision,
+        )
+
+    async def read_skill_resource(
+        self,
+        context: TenantContext,
+        name: str,
+        path: str,
+        *,
+        expected_revision: str | None = None,
+    ) -> dict:
+        return await self._call(
+            context,
+            'read_skill_resource',
+            name,
+            path,
+            expected_revision=expected_revision,
+        )
+
+    async def write_skill_file(self, context: TenantContext, name: str, path: str, content: str) -> dict:
+        return await self._call(context, 'write_skill_file', name, path, content)
+
+    async def preview_skill_zip(self, context: TenantContext, file_bytes: bytes, filename: str, **kwargs) -> list[dict]:
+        return await self._call(context, 'preview_zip_upload', file_bytes=file_bytes, filename=filename, **kwargs)
+
+    async def install_skill_zip(self, context: TenantContext, file_bytes: bytes, filename: str, **kwargs) -> list[dict]:
+        return await self._call(context, 'install_zip_upload', file_bytes=file_bytes, filename=filename, **kwargs)
+
+
+__all__ = ['SkillRepository', 'SkillRevisionMismatchError']
@@ -198,7 +198,7 @@ async def build_heartbeat_payload(
    except Exception:
        features['plugin_count'] = -1

-    # Skill count (from Box runtime via skill manager)
+    # Skill count (from the Core SkillRepository cache)
    try:
        skill_mgr = getattr(ap, 'skill_mgr', None)
        if skill_mgr is not None:
@@ -0,0 +1,191 @@
+"""Python project detection and sandbox-local environment bootstrap helpers."""
+
+from __future__ import annotations
+
+import os
+import textwrap
+
+
+PYTHON_MANIFEST_FILES = (
+    'requirements.txt',
+    'pyproject.toml',
+    'setup.py',
+    'setup.cfg',
+)
+
+
+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 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 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',
+    state_path: str | None = None,
+) -> str:
+    """Wrap a command with a reusable sandbox-local Python env bootstrap."""
+
+    writable_state_path = state_path or mount_path
+    bootstrap = textwrap.dedent(
+        f"""
+        set -e
+
+        _LB_VENV_DIR="{writable_state_path}/.venv"
+        _LB_META_DIR="{writable_state_path}/.langbot"
+        _LB_META_FILE="$_LB_META_DIR/python-env.json"
+        _LB_LOCK_DIR="$_LB_META_DIR/python-env.lock"
+        _LB_TMP_DIR="{writable_state_path}/.tmp"
+        _LB_PIP_CACHE_DIR="{writable_state_path}/.cache/pip"
+
+        mkdir -p "$_LB_META_DIR" "$_LB_TMP_DIR" "$_LB_PIP_CACHE_DIR"
+        _LB_SYSTEM_PYTHON="$(command -v python3 || command -v python || true)"
+        if [ -z "$_LB_SYSTEM_PYTHON" ]; then
+          echo "python3 or python is required to prepare the workspace Python environment" >&2
+          exit 127
+        fi
+
+        export TMPDIR="$_LB_TMP_DIR"
+        export TEMP="$_LB_TMP_DIR"
+        export TMP="$_LB_TMP_DIR"
+        export PIP_CACHE_DIR="$_LB_PIP_CACHE_DIR"
+
+        _lb_python_meta() {{
+          "$_LB_SYSTEM_PYTHON" - <<'PY'
+        import hashlib
+        import json
+        import os
+        import sys
+
+        root = "{mount_path}"
+        max_manifest_bytes = 10 * 1024 * 1024
+        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
+            if os.path.getsize(path) > max_manifest_bytes:
+                raise RuntimeError(
+                    f"Python project manifest exceeds {{max_manifest_bytes}} bytes: {{rel}}"
+                )
+            manifest_files.append(rel)
+            with open(path, "rb") as handle:
+                digest.update(rel.encode("utf-8"))
+                digest.update(b"\0")
+                while chunk := handle.read(1024 * 1024):
+                    digest.update(chunk)
+                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 [ "$_LB_LOCK_WAIT" -ge 120 ]; then
+              _LB_LOCK_OWNER="$(cat "$_LB_LOCK_DIR/pid" 2>/dev/null || true)"
+              if [ -n "$_LB_LOCK_OWNER" ] && kill -0 "$_LB_LOCK_OWNER" 2>/dev/null; then
+                echo "Timed out waiting for active Python environment lock: $_LB_LOCK_DIR" >&2
+                exit 1
+              fi
+              echo "Timed out waiting for Python environment lock, clearing stale lock: $_LB_LOCK_DIR" >&2
+              rm -rf "$_LB_LOCK_DIR" 2>/dev/null || true
+              if mkdir "$_LB_LOCK_DIR" 2>/dev/null; then
+                break
+              fi
+              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
+          printf '%s\n' "$$" > "$_LB_LOCK_DIR/pid" 2>/dev/null || true
+
+          _lb_cleanup_lock() {{
+            rm -rf "$_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"
+            "$_LB_SYSTEM_PYTHON" -m venv "$_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'
+
+
+__all__ = [
+    'PYTHON_MANIFEST_FILES',
+    'list_python_manifest_files',
+    'normalize_host_path',
+    'should_prepare_python_env',
+    'wrap_python_command_with_env',
+]
@@ -83,7 +83,7 @@ class VersionManager:
        try:
            if await self.is_new_version_available():
                return (
-                    'New version available. Update guide: https://link.langbot.app/en/docs/update',
+                    'New version available. Update guide: https://langbot.app/docs/en/deploy/update',
                    logging.INFO,
                )
        except Exception as e:
@@ -269,7 +269,7 @@ class InvitationDeliveryService:
        <table role="presentation" width="100%" cellspacing="0" cellpadding="0" border="0" style="width:100%;max-width:600px;">
          <tr>
            <td style="padding:0 4px 20px;">
-              <img src="https://docs.langbot.app/langbot-logo.png" alt="LangBot" width="34" height="34" style="display:inline-block;width:34px;height:34px;border:0;vertical-align:middle;">
+              <img src="https://langbot.app/docs/langbot-logo.png" alt="LangBot" width="34" height="34" style="display:inline-block;width:34px;height:34px;border:0;vertical-align:middle;">
              <span style="display:inline-block;margin-left:10px;vertical-align:middle;font-size:18px;font-weight:700;letter-spacing:-.01em;">LangBot</span>
            </td>
          </tr>
@@ -323,15 +323,25 @@ monitoring:
        # Prevent one large Workspace backlog from monopolizing PostgreSQL.
        # Supports MONITORING__AUTO_CLEANUP__MAX_BATCHES_PER_TABLE_PER_RUN.
        max_batches_per_table_per_run: 4
+skills:
+    # Core-owned SkillStore. Skill discovery, activation, resources, CRUD and
+    # revisions remain available when Box is disabled.
+    # TODO(next-major): change the fresh-install default to './data/skills'
+    # after the online-upgrade window for the historical Box path closes.
+    root: './data/box/skills'
+
 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.
+    # subprocess. Disabling Box disables execution-backed features: native
+    # sandbox tools (exec/read/write/edit/glob/grep), agent-side skill
+    # registration, and stdio-mode MCP servers. Skill management, activation,
+    # and read-only package resources remain available without Box.
    enabled: true
-    backend: 'local'  # 'local' (Docker/nsjail), 'docker', 'nsjail', or 'e2b'. Can be written via BOX__BACKEND.
+    # 'host' runs commands directly as the Box Runtime user without sandbox
+    # isolation. It is never auto-selected and is only for trusted local
+    # development. Can be written via BOX__BACKEND.
+    backend: 'local'  # 'local' (Docker/nsjail), 'docker', 'nsjail', 'e2b', or explicit unsafe 'host'.
    runtime:
        # LANGBOT_BOX_CONTROL_TOKEN is optional for OSS external WebSocket
        # runtimes. To protect an exposed endpoint, set the same strong secret
@@ -375,7 +385,6 @@ box:
        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'
@@ -80,7 +80,8 @@
            "header-name": "",
            "header-value": "",
            "timeout": 120,
-            "output-key": "response"
+            "output-key": "response",
+            "response-handling": "reply"
        },
        "langflow-api": {
            "base-url": "http://localhost:7860",
@@ -642,9 +642,10 @@
              .replace(/\s+/g, " ")
              .trim();
            if (
-              prevContent === content ||
-              prevContent.indexOf(content) >= 0 ||
-              content.indexOf(prevContent) >= 0
+              prevContent &&
+              (prevContent === content ||
+                prevContent.indexOf(content) >= 0 ||
+                content.indexOf(prevContent) >= 0)
            )
              return;
          }
@@ -475,6 +475,25 @@ stages:
        type: string
        required: false
        default: 'response'
+      - name: response-handling
+        label:
+          en_US: Webhook Response Handling
+          zh_Hans: Webhook 响应处理方式
+        description:
+          en_US: Choose whether LangBot forwards the n8n webhook response to the chat user. Ignore mode requires the n8n Webhook node to use Respond Immediately.
+          zh_Hans: 选择是否将 n8n Webhook 响应转发给聊天用户。忽略模式要求 n8n Webhook 节点使用“立即响应”。
+        type: select
+        required: false
+        default: 'reply'
+        options:
+          - name: reply
+            label:
+              en_US: Forward as chat reply
+              zh_Hans: 转发为聊天回复
+          - name: ignore
+            label:
+              en_US: Ignore response body (asynchronous workflow)
+              zh_Hans: 忽略响应正文（异步工作流）
  - name: coze-api
    label:
      en_US: coze API
@@ -242,6 +242,22 @@ class TestMonitoringSessionsEndpoint:

        assert response.status_code == 200

+    @pytest.mark.asyncio
+    async def test_get_sessions_forwards_user_search_and_page_window(self, quart_test_client, fake_monitoring_app):
+        fake_monitoring_app.monitoring_service.get_sessions.reset_mock()
+
+        response = await quart_test_client.get(
+            '/api/v1/monitoring/sessions?botId=bot-1&userQuery=alice&limit=20&offset=40',
+            headers={'Authorization': 'Bearer test_token'},
+        )
+
+        assert response.status_code == 200
+        kwargs = fake_monitoring_app.monitoring_service.get_sessions.await_args.kwargs
+        assert kwargs['bot_ids'] == ['bot-1']
+        assert kwargs['user_query'] == 'alice'
+        assert kwargs['limit'] == 20
+        assert kwargs['offset'] == 40
+

@pytest.mark.usefixtures('mock_circular_import_chain')
 class TestMonitoringErrorsEndpoint:
@@ -278,13 +294,19 @@ class TestMonitoringDetailsEndpoints:
    """Tests for detail endpoints."""

    @pytest.mark.asyncio
-    async def test_get_session_analysis(self, quart_test_client):
+    async def test_get_session_analysis(self, quart_test_client, fake_monitoring_app):
        """GET /api/v1/monitoring/sessions/{id}/analysis."""
        response = await quart_test_client.get(
-            '/api/v1/monitoring/sessions/sess-1/analysis', headers={'Authorization': 'Bearer test_token'}
+            '/api/v1/monitoring/sessions/sess-1/analysis'
+            '?startTime=2026-08-31T16%3A00%3A00.000Z'
+            '&endTime=2026-09-01T15%3A59%3A59.999Z',
+            headers={'Authorization': 'Bearer test_token'},
        )

        assert response.status_code == 200
+        kwargs = fake_monitoring_app.monitoring_service.get_session_analysis.await_args.kwargs
+        assert kwargs['start_time'].isoformat() == '2026-08-31T16:00:00'
+        assert kwargs['end_time'].isoformat() == '2026-09-01T15:59:59.999000'

    @pytest.mark.asyncio
    async def test_get_message_details(self, quart_test_client):
@@ -1,4 +1,4 @@
-"""Skills API behavior when a workspace plan has no managed sandbox."""
+"""Skills API behavior is independent from managed sandbox entitlement."""

 from __future__ import annotations

@@ -9,10 +9,7 @@ import pytest
 import quart

 from langbot.pkg.api.http.controller.groups.skills import SkillsRouterGroup
-from langbot.pkg.cloud.entitlements import (
-    EntitlementFeatureUnavailableError,
-    EntitlementUnavailableError,
-)
+from langbot.pkg.cloud.entitlements import EntitlementUnavailableError

 pytestmark = pytest.mark.integration
 WORKSPACE_UUID = '11111111-1111-4111-8111-111111111111'
@@ -32,10 +29,7 @@ async def skills_api():
    application.user_service.get_authenticated_account = AsyncMock(return_value=account)
    application.workspace_collaboration_service.resolve_account_workspace = AsyncMock(return_value=access)
    application.skill_service.list_skills = AsyncMock(
-        side_effect=EntitlementFeatureUnavailableError(
-            'managed_sandbox',
-            entitlement_revision=1,
-        )
+        return_value=[{'name': 'docs-only', 'description': 'No execution required'}]
    )

    quart_app = quart.Quart(__name__)
@@ -45,7 +39,7 @@ async def skills_api():


@pytest.mark.asyncio
-async def test_list_skills_is_empty_when_plan_has_no_managed_sandbox(skills_api):
+async def test_list_skills_remains_available_without_managed_sandbox(skills_api):
    application, client = skills_api
    response = await client.get(
        '/api/v1/skills',
@@ -57,7 +51,7 @@ async def test_list_skills_is_empty_when_plan_has_no_managed_sandbox(skills_api)

    assert response.status_code == 200
    payload = await response.get_json()
-    assert payload['data'] == {'skills': []}
+    assert payload['data'] == {'skills': [{'name': 'docs-only', 'description': 'No execution required'}]}
    application.skill_service.list_skills.assert_awaited_once()


@@ -27,7 +27,8 @@ async def space_oauth_api():
        execution=SimpleNamespace(instance_uuid='instance-a', placement_generation=1),
    )
    application = Mock()
-    application.deployment = SimpleNamespace(multi_workspace_enabled=False)
+    application.deployment = SimpleNamespace(multi_workspace_enabled=False, mode='oss')
+    application.directory_projection_service = None
    application.persistence_mgr = None
    application.user_service.get_authenticated_account = AsyncMock(return_value=account)
    application.user_service.issue_space_oauth_state = AsyncMock(
@@ -125,6 +126,26 @@ async def test_cloud_launch_state_is_server_issued_and_workspace_bound(space_oau
    )


+@pytest.mark.asyncio
+async def test_cloud_login_entry_uses_normal_stateful_oauth(space_oauth_api):
+    application, client = space_oauth_api
+    application.deployment.mode = 'cloud'
+
+    response = await client.get(
+        '/api/v1/user/space/authorize-url',
+        query_string={
+            'redirect_uri': 'http://localhost/auth/space/callback',
+            'cloud_entry': '1',
+        },
+        headers={'Origin': 'http://localhost'},
+    )
+
+    assert response.status_code == 200
+    authorize_url = (await response.get_json())['data']['authorize_url']
+    assert authorize_url.startswith('https://space.example/authorize?state=')
+    application.user_service.issue_space_oauth_state.assert_awaited_once_with('login')
+
+
@pytest.mark.asyncio
 async def test_public_login_rejects_caller_supplied_state(space_oauth_api):
    application, client = space_oauth_api
@@ -249,10 +270,14 @@ async def test_server_side_webhook_origin_supports_bundled_ui(space_oauth_api):
 async def test_login_callback_requires_and_consumes_server_state(space_oauth_api):
    application, client = space_oauth_api

-    missing = await client.post('/api/v1/user/space/callback', json={'code': 'oauth-code'})
+    missing = await client.post('/api/v1/user/space/callback', json={'code': 'v4_oauth-code'})
    response = await client.post(
        '/api/v1/user/space/callback',
-        json={'code': 'oauth-code', 'state': 'opaque-login-state'},
+        json={
+            'code': 'v4_oauth-code',
+            'state': 'opaque-login-state',
+            'redirect_uri': 'https://oss.example/auth/space/callback',
+        },
    )

    assert (await missing.get_json())['code'] == 1
@@ -260,12 +285,146 @@ async def test_login_callback_requires_and_consumes_server_state(space_oauth_api
    assert (await response.get_json())['data']['token'] == 'space-login-token'
    application.user_service.consume_space_oauth_state_details.assert_awaited_once_with('opaque-login-state', 'login')
    application.space_service.exchange_oauth_code.assert_awaited_once_with(
-        'oauth-code',
+        'v4_oauth-code',
        [WORKSPACE_UUID],
        {WORKSPACE_UUID: int(WORKSPACE_CREATED_AT.timestamp())},
+        redirect_uri='https://oss.example/auth/space/callback',
    )


+@pytest.mark.asyncio
+async def test_login_callback_rejects_downgraded_legacy_code(space_oauth_api):
+    application, client = space_oauth_api
+
+    response = await client.post(
+        '/api/v1/user/space/callback',
+        json={'code': 'v2_legacy-code', 'state': 'opaque-login-state'},
+    )
+
+    payload = await response.get_json()
+    assert response.status_code == 200
+    assert payload['code'] == 1
+    assert 'code contract' in payload['msg']
+    application.space_service.exchange_oauth_code.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_cloud_login_callback_reconciles_authorized_workspace_before_local_authentication(space_oauth_api):
+    application, client = space_oauth_api
+    application.deployment.mode = 'cloud'
+    calls: list[str] = []
+    application.directory_projection_service = SimpleNamespace(
+        reconcile_workspaces=AsyncMock(side_effect=lambda _workspace_uuids: calls.append('reconcile'))
+    )
+    application.space_service.exchange_oauth_code.return_value = {
+        'access_token': 'space-access-token',
+        'refresh_token': 'space-refresh-token',
+        'expires_in': 3600,
+        'cloud_workspace_uuid': WORKSPACE_UUID,
+    }
+
+    authenticated_account = application.user_service.authenticate_space_user.return_value[1]
+
+    async def authenticate(*_args):
+        calls.append('authenticate')
+        return 'space-login-token', authenticated_account
+
+    application.user_service.authenticate_space_user.side_effect = authenticate
+
+    response = await client.post(
+        '/api/v1/user/space/callback',
+        json={'code': 'v4_oauth-code', 'state': 'opaque-login-state'},
+    )
+
+    assert response.status_code == 200
+    assert (await response.get_json())['data']['workspace_uuid'] == WORKSPACE_UUID
+    assert calls == ['reconcile', 'authenticate']
+    application.directory_projection_service.reconcile_workspaces.assert_awaited_once_with((WORKSPACE_UUID,))
+
+
+@pytest.mark.asyncio
+async def test_cloud_login_callback_fails_closed_without_workspace_binding(space_oauth_api):
+    application, client = space_oauth_api
+    application.deployment.mode = 'cloud'
+    application.directory_projection_service = SimpleNamespace(reconcile_workspaces=AsyncMock())
+
+    response = await client.post(
+        '/api/v1/user/space/callback',
+        json={'code': 'v4_oauth-code', 'state': 'opaque-login-state'},
+    )
+
+    payload = await response.get_json()
+    assert response.status_code == 200
+    assert payload['code'] == 1
+    assert 'Cloud Workspace binding' in payload['msg']
+    application.directory_projection_service.reconcile_workspaces.assert_not_awaited()
+    application.user_service.authenticate_space_user.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_cloud_login_callback_requires_code_binding_for_launch_state(space_oauth_api):
+    application, client = space_oauth_api
+    application.deployment.mode = 'cloud'
+    application.directory_projection_service = SimpleNamespace(reconcile_workspaces=AsyncMock())
+    application.user_service.consume_space_oauth_state_details.return_value = SimpleNamespace(
+        launch_workspace_uuid=WORKSPACE_UUID
+    )
+
+    response = await client.post(
+        '/api/v1/user/space/callback',
+        json={'code': 'v4_oauth-code', 'state': 'opaque-login-state'},
+    )
+
+    payload = await response.get_json()
+    assert response.status_code == 200
+    assert payload['code'] == 1
+    assert 'Workspace binding' in payload['msg']
+    application.directory_projection_service.reconcile_workspaces.assert_not_awaited()
+    application.user_service.authenticate_space_user.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_cloud_login_callback_rejects_conflicting_state_and_code_workspace_bindings(space_oauth_api):
+    application, client = space_oauth_api
+    application.deployment.mode = 'cloud'
+    application.directory_projection_service = SimpleNamespace(reconcile_workspaces=AsyncMock())
+    application.user_service.consume_space_oauth_state_details.return_value = SimpleNamespace(
+        launch_workspace_uuid=WORKSPACE_UUID
+    )
+    application.space_service.exchange_oauth_code.return_value = {
+        'access_token': 'space-access-token',
+        'refresh_token': 'space-refresh-token',
+        'expires_in': 3600,
+        'cloud_workspace_uuid': 'workspace-from-another-flow',
+    }
+
+    response = await client.post(
+        '/api/v1/user/space/callback',
+        json={'code': 'v4_oauth-code', 'state': 'opaque-login-state'},
+    )
+
+    payload = await response.get_json()
+    assert response.status_code == 200
+    assert payload['code'] == 1
+    assert 'Workspace binding' in payload['msg']
+    application.directory_projection_service.reconcile_workspaces.assert_not_awaited()
+    application.user_service.authenticate_space_user.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_oss_login_callback_does_not_request_cloud_reconciliation(space_oauth_api):
+    application, client = space_oauth_api
+    application.directory_projection_service = SimpleNamespace(reconcile_workspaces=AsyncMock())
+
+    response = await client.post(
+        '/api/v1/user/space/callback',
+        json={'code': 'v4_oauth-code', 'state': 'opaque-login-state'},
+    )
+
+    assert response.status_code == 200
+    application.directory_projection_service.reconcile_workspaces.assert_not_awaited()
+
+
@pytest.mark.asyncio
 async def test_login_callback_launch_state_selects_asserted_workspace(space_oauth_api):
    application, client = space_oauth_api
@@ -276,7 +435,7 @@ async def test_login_callback_launch_state_selects_asserted_workspace(space_oaut

    response = await client.post(
        '/api/v1/user/space/callback',
-        json={'code': 'oauth-code', 'state': 'opaque-login-state'},
+        json={'code': 'v4_oauth-code', 'state': 'opaque-login-state'},
    )

    assert response.status_code == 200
@@ -375,18 +534,22 @@ async def test_bind_callback_uses_opaque_state_and_never_treats_it_as_jwt(space_

    rejected = await client.post(
        '/api/v1/user/bind-space',
-        json={'code': 'attacker-code', 'state': 'jwt.must-not-be-used'},
+        json={'code': 'v4_attacker-code', 'state': 'jwt.must-not-be-used'},
    )
    response = await client.post(
        '/api/v1/user/bind-space',
-        json={'code': 'oauth-code', 'state': 'opaque-bind-state'},
+        json={'code': 'v4_oauth-code', 'state': 'opaque-bind-state'},
    )

    assert rejected.status_code == 401
    assert response.status_code == 200
    assert (await response.get_json())['data']['token'] == 'rotated-account-token'
    application.user_service.verify_jwt_token.assert_not_awaited()
-    application.user_service.bind_space_account.assert_awaited_once_with('owner@example.com', 'oauth-code')
+    application.user_service.bind_space_account.assert_awaited_once_with(
+        'owner@example.com',
+        'v4_oauth-code',
+        redirect_uri='http://localhost/auth/space/callback?mode=bind',
+    )


@pytest.mark.asyncio
@@ -394,6 +557,7 @@ async def test_direct_launch_assertion_does_not_consume_normal_oauth_state(space
    application, client = space_oauth_api
    application.user_service.consume_space_oauth_state.reset_mock()
    application.space_service.exchange_oauth_code.reset_mock()
+    application.directory_projection_service = SimpleNamespace(reconcile_workspaces=AsyncMock())

    response = await client.post(
        '/api/v1/user/space/callback',
@@ -414,3 +578,29 @@ async def test_direct_launch_assertion_does_not_consume_normal_oauth_state(space
    )
    application.user_service.consume_space_oauth_state.assert_not_awaited()
    application.space_service.exchange_oauth_code.assert_not_awaited()
+
+
+@pytest.mark.asyncio
+async def test_direct_launch_reconciles_exact_workspace_before_resolving_access(space_oauth_api):
+    application, client = space_oauth_api
+    projected_account = SimpleNamespace(
+        uuid='account-a',
+        user='owner@example.com',
+        account_type='space',
+        status='active',
+    )
+    application.user_service.get_user_by_uuid = AsyncMock(return_value=projected_account)
+    application.directory_projection_service = SimpleNamespace(reconcile_workspaces=AsyncMock())
+
+    response = await client.post(
+        '/api/v1/user/space/callback',
+        json={
+            'workspace_uuid': WORKSPACE_UUID,
+            'launch_assertion': 'signed-launch-token',
+        },
+    )
+
+    assert response.status_code == 200
+    assert (await response.get_json())['data']['workspace_uuid'] == WORKSPACE_UUID
+    application.directory_projection_service.reconcile_workspaces.assert_awaited_once_with((WORKSPACE_UUID,))
+    application.user_service.get_user_by_uuid.assert_awaited_once_with('account-a')
@@ -29,6 +29,9 @@ from langbot.pkg.cloud.entitlements import (
    EntitlementSnapshot,
    EntitlementUnavailableError,
 )
+from langbot.pkg.skill.manager import SkillManager
+from langbot.pkg.skill.repository import SkillRepository
+from langbot.pkg.provider.tools.loaders import skill as skill_loader


 pytestmark = pytest.mark.integration
@@ -54,7 +57,7 @@ class _AdmissionBackend(BaseSandboxBackend):
            'mount_isolation': True,
            'network_isolation': True,
            'hard_workspace_quota': True,
-            'hard_skill_storage_quota': True,
+            'hard_read_only_mount_quota': True,
            'bounded_ephemeral_storage': True,
            'inode_quota': True,
        }
@@ -230,9 +233,18 @@ async def _stack(tmp_path):
        deployment=SimpleNamespace(multi_workspace_enabled=True),
        entitlement_resolver=EntitlementResolver('instance-a', entitlements),
        workspace_service=workspace_service,
-        instance_config=SimpleNamespace(data={'box': box_config, 'system': {'limitation': {}}}),
+        instance_config=SimpleNamespace(
+            data={
+                'skills': {'root': str(shared_root / 'skills')},
+                'box': box_config,
+                'system': {'limitation': {}},
+            }
+        ),
    )
+    app.skill_repository = SkillRepository(app)
+    app.skill_mgr = SkillManager(app)
    service = BoxService(app, client=client)
+    app.box_service = service
    await service.initialize()
    return service, runtime, backend, entitlements, server_task, client_task

@@ -312,7 +324,7 @@ async def test_two_workspaces_get_isolated_physical_sessions_and_paths(tmp_path)


@pytest.mark.asyncio
-async def test_cloud_skills_reject_host_paths_and_require_managed_entitlement(tmp_path):
+async def test_cloud_core_skills_mount_generically_and_do_not_require_box_entitlement(tmp_path):
    service, runtime, backend, entitlements, server_task, client_task = await _stack(tmp_path)
    first = _context('workspace-a')
    second = _context('workspace-b')
@@ -324,32 +336,35 @@ async def test_cloud_skills_reject_host_paths_and_require_managed_entitlement(tm
        managed=False,
    )
    try:
-        private = await service.create_skill(
+        repository = service.ap.skill_repository
+        await repository.create_skill(
            second,
            {
                'name': 'private',
                'instructions': 'workspace-b secret',
            },
        )
-        own_skill = await service.create_skill(
+        own_skill = await repository.create_skill(
            first,
            {
                'name': 'runner',
                'instructions': 'Run scripts/main.py',
            },
        )
-        await service.write_skill_file(first, 'runner', 'scripts/main.py', "print('ok')")
-        await service.write_skill_file(first, 'runner', 'requirements.txt', 'requests==2.32.0\n')
-        refreshed_skill = await service.get_skill(first, 'runner')
+        await repository.write_skill_file(first, 'runner', 'scripts/main.py', "print('ok')")
+        await repository.write_skill_file(first, 'runner', 'requirements.txt', 'requests==2.32.0\n')
+        refreshed_skill = await repository.get_skill(first, 'runner')
        assert refreshed_skill is not None
        assert refreshed_skill['python_project'] is True
+        await service.ap.skill_mgr.reload_skills(first)
+        query = _query(first, 91)
        await service.execute_tool(
            {
                'command': 'python /workspace/.skills/runner/scripts/main.py',
                'workdir': '/workspace/.skills/runner',
            },
-            _query(first, 91),
-            skill_name='runner',
+            query,
+            read_only_mounts=skill_loader.build_execution_mounts(service.ap, query),
        )

        mounted_spec = backend.started_specs[-1]
@@ -358,20 +373,14 @@ async def test_cloud_skills_reject_host_paths_and_require_managed_entitlement(tm
        assert mounted_spec.extra_mounts[0].mount_path == '/workspace/.skills/runner'
        assert mounted_spec.extra_mounts[0].mode.value == 'ro'

-        with pytest.raises(BoxAdmissionError, match='Scanning arbitrary host'):
-            await service.scan_skill_directory(first, private['package_root'])
-        with pytest.raises(BoxAdmissionError, match='package_root is runtime-owned'):
-            await service.create_skill(
-                first,
-                {
-                    'name': 'stolen',
-                    'package_root': private['package_root'],
-                },
-            )
-
-        assert await service.get_skill(first, 'private') is None
+        assert await repository.get_skill(first, 'private') is None
+        await repository.create_skill(
+            ineligible,
+            {'name': 'docs-only', 'instructions': 'Read this without Box.'},
+        )
+        assert [skill['name'] for skill in await repository.list_skills(ineligible)] == ['docs-only']
        with pytest.raises(EntitlementUnavailableError):
-            await service.list_skills(ineligible)
+            await service.execute_tool({'command': 'true'}, _query(ineligible, 92))
    finally:
        server_task.cancel()
        client_task.cancel()
@@ -12,6 +12,7 @@ import pytest
 from unittest.mock import AsyncMock, MagicMock, Mock, patch
 from types import SimpleNamespace
 import json
+import sqlalchemy
 import uuid

 from langbot.pkg.api.http.service.bot import BotService
@@ -449,10 +450,58 @@ class TestBotServiceCreateBot:
        insert_statement = ap.persistence_mgr.execute_async.await_args_list[1].args[0]
        insert_values = insert_statement.compile().params
        assert insert_values['workspace_uuid'] == WORKSPACE_UUID
-        assert insert_values['use_pipeline_uuid'] == 'default-pipeline-uuid'
-        assert insert_values['use_pipeline_name'] == 'Default Pipeline'
        assert bot_uuid is not None  # Verify UUID was returned

+    async def test_create_bot_rolls_back_insert_when_load_bot_fails(self):
+        """Deletes the inserted row when the adapter fails to load.
+
+        Regression: a failing adapter constructor (e.g. KeyError on a missing
+        optional credential key) used to leave a permanently disabled orphan
+        bot in the DB — the insert was already committed and the HTTP layer
+        surfaced a 500 without any cleanup.
+        """
+        # Setup
+        ap = SimpleNamespace()
+        ap.persistence_mgr = SimpleNamespace()
+        ap.instance_config = SimpleNamespace()
+        ap.instance_config.data = {'system': {'limitation': {'max_bots': -1}}}
+        ap.platform_mgr = SimpleNamespace()
+        ap.platform_mgr.load_bot = AsyncMock(side_effect=KeyError('token'))
+
+        pipeline_result = Mock()
+        pipeline_result.first = Mock(return_value=None)
+        bot_result = Mock()
+        bot_result.first = Mock(return_value=_create_mock_bot())
+
+        executed_statements = []
+
+        async def mock_execute(query):
+            executed_statements.append(query)
+            if len(executed_statements) <= 2:
+                return pipeline_result  # 1: limitation bots query, 2: pipeline query
+            if len(executed_statements) == 3:
+                return Mock()  # insert
+            return bot_result  # get_bot after insert
+
+        ap.persistence_mgr.execute_async = AsyncMock(side_effect=mock_execute)
+        ap.persistence_mgr.serialize_model = Mock(return_value={'uuid': 'new-uuid', 'name': 'New Bot'})
+
+        service = BotService(ap)
+
+        # Execute & Verify: the adapter error propagates
+        with pytest.raises(KeyError, match='token'):
+            await service.create_bot(
+                WORKSPACE_UUID, {'name': 'New Bot', 'adapter': 'telegram', 'adapter_config': {}}
+            )
+
+        # And the inserted row is rolled back via a DELETE on the new uuid
+        # (no limitation query runs because max_bots=-1)
+        assert len(executed_statements) == 4  # pipeline select, insert, bot select, delete
+        delete_statement = executed_statements[-1]
+        assert isinstance(delete_statement, sqlalchemy.sql.dml.Delete)
+        compiled = delete_statement.compile()
+        assert compiled.params['uuid_1'] is not None
+

 class TestBotServiceUpdateBot:
    """Tests for update_bot method."""
@@ -138,6 +138,39 @@ async def test_same_session_and_resource_ids_do_not_collide(service):
    assert (await service.get_message_details(context_a, message_b))['found'] is False


+async def test_session_search_matches_user_id_or_name_within_workspace(service):
+    context_a = _context(WORKSPACE_A)
+    context_b = _context(WORKSPACE_B)
+    fixtures = [
+        (context_a, 'session-id-match', 'customer-42', 'Alice'),
+        (context_a, 'session-name-match', 'customer-99', 'Bob Alice Cooper'),
+        (context_a, 'session-no-match', 'customer-7', 'Bob'),
+        (context_b, 'session-other-workspace', 'customer-42', 'Alice'),
+    ]
+    for context, session_id, user_id, user_name in fixtures:
+        await service.record_session_start(
+            context,
+            session_id=session_id,
+            bot_id='same-bot',
+            bot_name='Same Bot',
+            pipeline_id='same-pipeline',
+            pipeline_name='Same Pipeline',
+            user_id=user_id,
+            user_name=user_name,
+        )
+
+    by_id, id_total = await service.get_sessions(context_a, user_query='customer-42')
+    by_name, name_total = await service.get_sessions(context_a, user_query='alice')
+
+    assert id_total == 1
+    assert [session['session_id'] for session in by_id] == ['session-id-match']
+    assert name_total == 2
+    assert {session['session_id'] for session in by_name} == {
+        'session-id-match',
+        'session-name-match',
+    }
+
+
 async def test_tool_call_inherits_context_from_connection_message_row(service):
    context = _context(WORKSPACE_A)
    message_id = await _record_message(service, context, 'tool context')
@@ -95,7 +95,9 @@ class TestSpaceServiceGetOAuthAuthorizeUrl:
        result = service.get_oauth_authorize_url('http://localhost/callback')

        # Verify
-        assert parse_qs(urlsplit(result).query)['redirect_uri'] == ['http://localhost/callback']
+        query = parse_qs(urlsplit(result).query)
+        assert query['redirect_uri'] == ['http://localhost/callback']
+        assert query['code_contract'] == ['redirect-v1']
        assert 'https://space.langbot.app/auth/authorize' in result

    def test_get_oauth_authorize_url_with_state(self):
@@ -578,12 +580,14 @@ class TestSpaceServiceExchangeOAuthCode:
                'auth_code',
                ['workspace-1'],
                {'workspace-1': 1_700_000_000},
+                redirect_uri='https://oss.example/auth/space/callback',
            )

        # Verify
        assert result['access_token'] == 'new_access_token'
        assert mock_session_obj.post.call_args.kwargs['json'] == {
            'code': 'auth_code',
+            'redirect_uri': 'https://oss.example/auth/space/callback',
            'instance_id': constants.instance_id,
            'workspace_uuids': ['workspace-1'],
            'workspace_created_ats': {'workspace-1': 1_700_000_000},
@@ -846,10 +850,7 @@ class TestSpaceServiceGetModelSelection:
        if response_shape == 'models-envelope':
            data = {'models': models}
        elif response_shape == 'availability-wrapper':
-            data = [
-                {'model': model, 'latency_ms': index + 10, 'http_code': 200}
-                for index, model in enumerate(models)
-            ]
+            data = [{'model': model, 'latency_ms': index + 10, 'http_code': 200} for index, model in enumerate(models)]
        else:
            data = models
        payload = {'code': 0, 'data': data}
@@ -41,6 +41,7 @@ from langbot_plugin.box.security import (
 from langbot_plugin.entities.io.context import ActionContext
 from langbot.pkg.api.http.context import ExecutionContext
 from langbot.pkg.box.service import BoxService
+from langbot.pkg.provider.tools.loaders import skill as skill_loader

 _UTC = dt.timezone.utc
 _CONTEXT = ExecutionContext(
@@ -301,7 +302,7 @@ class TestSharesFilesystemWithBox:
    - stdio (local child process) → shared filesystem → True
    - WebSocket (Docker / sidecar / --standalone-box / remote) → separated → False

-    This drives whether LangBot validates Box-reported skill paths locally.
+    This drives whether LangBot can safely perform local workspace operations.
    Getting it wrong silently drops every skill in separated deployments.
    """

@@ -338,7 +339,7 @@ class TestSharesFilesystemWithBox:

    def test_false_when_client_injected_without_connector(self):
        # Injected client (no connector) → unknown topology → conservative False
-        # so LangBot never wrongly drops Box-reported skills.
+        # so LangBot does not assume a shared local filesystem.
        service = BoxService(make_app(Mock()), client=Mock(spec=BoxRuntimeClient))

        assert service._runtime_connector is None
@@ -552,7 +553,6 @@ async def test_box_service_reconnect_restores_workspace_and_runs_cleanup(
    monkeypatch: pytest.MonkeyPatch,
 ):
    app = make_app(Mock())
-    app.skill_mgr = SimpleNamespace(reload_skills=AsyncMock())
    service = BoxService(app, client=Mock(spec=BoxRuntimeClient))
    connector = Mock()
    connector.reconnect = AsyncMock()
@@ -565,16 +565,14 @@ async def test_box_service_reconnect_restores_workspace_and_runs_cleanup(
    connector.reconnect.assert_awaited_once()
    service._ensure_default_workspace.assert_called_once()
    service._purge_attachment_dirs.assert_awaited_once()
-    app.skill_mgr.reload_skills.assert_awaited_once()
    assert service.available is True


@pytest.mark.asyncio
-async def test_cloud_box_service_reconnect_does_not_reload_unscoped_skills(
+async def test_cloud_box_service_reconnect_restores_runtime_only(
    monkeypatch: pytest.MonkeyPatch,
 ):
    app = make_app(Mock())
-    app.skill_mgr = SimpleNamespace(reload_skills=AsyncMock())
    service = BoxService(app, client=Mock(spec=BoxRuntimeClient))
    service._cloud_managed = True
    connector = Mock()
@@ -587,7 +585,6 @@ async def test_cloud_box_service_reconnect_does_not_reload_unscoped_skills(

    connector.reconnect.assert_awaited_once()
    service._verify_cloud_runtime.assert_awaited_once()
-    app.skill_mgr.reload_skills.assert_not_awaited()
    assert service.available is True


@@ -1941,7 +1938,7 @@ def test_disconnect_callback_does_not_schedule_without_running_event_loop():
    assert service._reconnecting is False


-class TestBuildSkillExtraMounts:
+class TestBuildSkillExecutionMounts:
    """Robustness of skill mount construction against a stale skill cache.

    The three sandbox backends behave inconsistently when a skill's
@@ -1951,16 +1948,10 @@ class TestBuildSkillExtraMounts:
    the backend never sees a bad mount.
    """

-    def _make_service(self, logger, skills, *, shares_filesystem=True):
+    def _make_app(self, logger, skills):
        app = make_app(logger)
        app.skill_mgr = SimpleNamespace(skills=skills, get_skills=Mock(return_value=skills))
-        client = Mock(spec=BoxRuntimeClient)
-        service = BoxService(app, client=client)
-        # Tests construct BoxService with an injected client (no connector), so
-        # set the topology explicitly. Most cases exercise the shared-fs (local
-        # stdio) path where local package_root validation applies.
-        service._shares_filesystem_with_box_override = shares_filesystem
-        return service
+        return app

    def test_skips_skill_with_missing_package_root(self):
        logger = Mock()
@@ -1969,16 +1960,16 @@ class TestBuildSkillExtraMounts:
                'alive': {'name': 'alive', 'package_root': live_dir},
                'ghost': {'name': 'ghost', 'package_root': '/nonexistent/path/should/never/exist'},
            }
-            service = self._make_service(logger, skills)
+            app = self._make_app(logger, skills)
            query = make_query()

-            mounts = service.build_skill_extra_mounts(query)
+            mounts = skill_loader.build_execution_mounts(app, query)

            assert mounts == [
                {
                    'host_path': live_dir,
                    'mount_path': '/workspace/.skills/alive',
-                    'mode': 'rw',
+                    'mode': 'ro',
                }
            ]
            # Warning logged so operators can see what was dropped
@@ -1987,27 +1978,19 @@ class TestBuildSkillExtraMounts:
                for call in logger.warning.call_args_list
            )

-    def test_trusts_box_paths_when_filesystem_not_shared(self):
-        """In separated deployments (Docker Compose, k8s sidecar,
-        --standalone-box, remote endpoint) the Box runtime owns its own
-        filesystem. package_root values it reports are NOT resolvable on the
-        LangBot side, so LangBot must trust them rather than dropping every
-        skill via a local isdir() check."""
+    def test_rejects_missing_core_paths_when_filesystem_not_shared(self):
+        """Core owns package paths even when Box is a separate process."""
        logger = Mock()
        skills = {
            'a': {'name': 'a', 'package_root': '/box/skills/a'},
            'b': {'name': 'b', 'package_root': '/box/skills/b'},
        }
-        service = self._make_service(logger, skills, shares_filesystem=False)
+        app = self._make_app(logger, skills)

-        mounts = service.build_skill_extra_mounts(make_query())
+        mounts = skill_loader.build_execution_mounts(app, make_query())

-        assert mounts == [
-            {'host_path': '/box/skills/a', 'mount_path': '/workspace/.skills/a', 'mode': 'rw'},
-            {'host_path': '/box/skills/b', 'mount_path': '/workspace/.skills/b', 'mode': 'rw'},
-        ]
-        # No skill is dropped, so no "missing" warning should be logged.
-        assert not any('package_root missing' in str(call.args[0]) for call in logger.warning.call_args_list)
+        assert mounts == []
+        assert len(logger.warning.call_args_list) == 2

    def test_skips_skill_with_empty_package_root(self):
        logger = Mock()
@@ -2015,25 +1998,23 @@ class TestBuildSkillExtraMounts:
            'no_root': {'name': 'no_root', 'package_root': ''},
            'whitespace': {'name': 'whitespace', 'package_root': '   '},
        }
-        service = self._make_service(logger, skills)
+        app = self._make_app(logger, skills)

-        assert service.build_skill_extra_mounts(make_query()) == []
+        assert skill_loader.build_execution_mounts(app, make_query()) == []

    def test_empty_package_root_skipped_even_when_not_shared(self):
        """An empty package_root is always invalid regardless of topology."""
        logger = Mock()
        skills = {'no_root': {'name': 'no_root', 'package_root': ''}}
-        service = self._make_service(logger, skills, shares_filesystem=False)
+        app = self._make_app(logger, skills)

-        assert service.build_skill_extra_mounts(make_query()) == []
+        assert skill_loader.build_execution_mounts(app, make_query()) == []

    def test_returns_empty_when_no_skill_manager(self):
        logger = Mock()
        app = make_app(logger)
        # no skill_mgr attribute
-        service = BoxService(app, client=Mock(spec=BoxRuntimeClient))
-
-        assert service.build_skill_extra_mounts(make_query()) == []
+        assert skill_loader.build_execution_mounts(app, make_query()) == []


 # ── Attachment passthrough (inbound / outbound) ─────────────────────────────
@@ -13,8 +13,8 @@ from langbot.pkg.box.workspace import (
    classify_python_workspace,
    infer_workspace_host_path,
    rewrite_mounted_path,
-    wrap_python_command_with_env,
 )
+from langbot.pkg.utils.python_workspace import wrap_python_command_with_env


 _CONTEXT = ExecutionContext(
@@ -1,9 +1,10 @@
 from __future__ import annotations

+import asyncio
 import datetime
 import logging
 from types import SimpleNamespace
-from unittest.mock import Mock
+from unittest.mock import AsyncMock, Mock

 import pytest
 import sqlalchemy
@@ -214,6 +215,88 @@ async def test_directory_delta_requests_model_catalog_sync_after_commit(projecti
    request_sync.assert_called_once_with()


+async def test_targeted_reconciliation_projects_new_workspace_without_advancing_event_cursor(projection_context):
+    application, session_factory = projection_context
+    provider = _Provider(
+        [_snapshot(7, workspaces=[])],
+        deltas=[_delta(workspaces=[_workspace(revision=8, name='JIT Workspace')])],
+    )
+    service = DirectoryProjectionService(application, provider, INSTANCE_UUID)
+    await service.initialize()
+
+    await service.reconcile_workspaces((WORKSPACE_UUID,))
+
+    async with session_factory() as session:
+        account = await session.scalar(sqlalchemy.select(User).where(User.uuid == ACCOUNT_UUID))
+        workspace = await session.get(Workspace, WORKSPACE_UUID)
+        membership = await session.scalar(
+            sqlalchemy.select(WorkspaceMembership).where(
+                WorkspaceMembership.workspace_uuid == WORKSPACE_UUID,
+                WorkspaceMembership.account_uuid == ACCOUNT_UUID,
+            )
+        )
+        state = await session.get(DirectoryProjectionState, INSTANCE_UUID)
+    assert account is not None
+    assert workspace is not None and workspace.name == 'JIT Workspace'
+    assert membership is not None and membership.status == 'active'
+    assert state is not None and state.cursor == 7
+    assert provider.delta_calls == 1
+    assert provider.after_cursors == []
+
+
+async def test_targeted_reconciliation_preserves_existing_account_until_ordered_event_projection(projection_context):
+    application, session_factory = projection_context
+    targeted_workspace = _workspace(revision=8, name='Renamed Workspace').model_copy(
+        update={
+            'members': [
+                _member(revision=8).model_copy(update={'display_name': 'Changed Account Name'})
+            ]
+        }
+    )
+    provider = _Provider(
+        [_snapshot(7)],
+        deltas=[_delta(workspaces=[targeted_workspace])],
+    )
+    service = DirectoryProjectionService(application, provider, INSTANCE_UUID)
+    await service.initialize()
+
+    await service.reconcile_workspaces((WORKSPACE_UUID,))
+
+    async with session_factory() as session:
+        account = await session.scalar(sqlalchemy.select(User).where(User.uuid == ACCOUNT_UUID))
+        workspace = await session.get(Workspace, WORKSPACE_UUID)
+        state = await session.get(DirectoryProjectionState, INSTANCE_UUID)
+    assert account is not None and account.user == 'Workspace Owner'
+    assert account.projection_revision == 7
+    assert workspace is not None and workspace.name == 'Renamed Workspace'
+    assert state is not None and state.cursor == 7
+
+
+async def test_targeted_reconciliation_only_updates_requested_workspace_side_effects(projection_context):
+    application, _session_factory = projection_context
+    provider = _Provider(
+        [_snapshot(7, workspaces=[])],
+        deltas=[_delta(workspaces=[_workspace(revision=8, name='JIT Workspace')])],
+    )
+    service = DirectoryProjectionService(application, provider, INSTANCE_UUID)
+    await service.initialize()
+    service._reconcile_entitlement_snapshot_set = AsyncMock()
+    service._update_entitlement_workspace_activity = AsyncMock()
+    service._publish_runtime_execution_projection = Mock()
+
+    await service.reconcile_workspaces((WORKSPACE_UUID,))
+
+    service._reconcile_entitlement_snapshot_set.assert_not_awaited()
+    service._update_entitlement_workspace_activity.assert_awaited_once()
+    assert service._update_entitlement_workspace_activity.await_args.kwargs == {
+        'requested_workspace_uuids': {WORKSPACE_UUID},
+    }
+    service._publish_runtime_execution_projection.assert_called_once()
+    assert service._publish_runtime_execution_projection.call_args.kwargs == {
+        'affected_workspace_uuids': {WORKSPACE_UUID},
+    }
+
+
 async def test_initial_snapshot_projects_core_owned_rows(projection_context):
    application, session_factory = projection_context
    reconcile_execution_projection = Mock()
@@ -735,6 +818,72 @@ async def test_each_replica_consumes_events_with_its_own_cursor(projection_conte
    assert second_provider.after_cursors == [1, 2]


+async def test_concurrent_sync_once_calls_are_serialized_per_service(projection_context):
+    application, _session_factory = projection_context
+
+    class _ConcurrentProvider(_Provider):
+        def __init__(self) -> None:
+            super().__init__([_snapshot(1)])
+            self.first_fetch_started = asyncio.Event()
+            self.release_first_fetch = asyncio.Event()
+            self.active_fetches = 0
+            self.max_active_fetches = 0
+
+        async def fetch_events(
+            self,
+            instance_uuid: str,
+            after_cursor: int,
+            limit: int,
+        ) -> DirectoryEventBatch:
+            assert instance_uuid == INSTANCE_UUID
+            assert limit == 100
+            self.after_cursors.append(after_cursor)
+            self.active_fetches += 1
+            self.max_active_fetches = max(self.max_active_fetches, self.active_fetches)
+            try:
+                if len(self.after_cursors) == 1:
+                    self.first_fetch_started.set()
+                    await self.release_first_fetch.wait()
+                cursor = after_cursor + 1
+                return DirectoryEventBatch(
+                    instance_uuid=instance_uuid,
+                    after_cursor=after_cursor,
+                    cursor=cursor,
+                    high_water_cursor=cursor,
+                    events=(
+                        DirectoryEvent(
+                            cursor=cursor,
+                            uuid=f'40000000-0000-4000-8000-{cursor:012d}',
+                            aggregate_uuid=WORKSPACE_UUID,
+                            event_type='entitlement.changed',
+                            revision=cursor,
+                            payload={
+                                'workspace_uuid': WORKSPACE_UUID,
+                                'entitlement_revision': cursor,
+                            },
+                            created_at=datetime.datetime(2026, 7, 24, 12, cursor, tzinfo=datetime.UTC),
+                        ),
+                    ),
+                )
+            finally:
+                self.active_fetches -= 1
+
+    provider = _ConcurrentProvider()
+    service = DirectoryProjectionService(application, provider, INSTANCE_UUID)
+    await service.initialize()
+
+    first = asyncio.create_task(service.sync_once())
+    await provider.first_fetch_started.wait()
+    second = asyncio.create_task(service.sync_once())
+    await asyncio.sleep(0)
+    provider.release_first_fetch.set()
+    await asyncio.gather(first, second)
+
+    assert provider.max_active_fetches == 1
+    assert provider.after_cursors == [1, 2]
+    assert service._consumer_cursor == 3
+
+
 async def test_snapshot_coverage_allows_lagging_replica_to_replay_receipts(projection_context):
    application, session_factory = projection_context
    event_two = DirectoryEvent(
@@ -55,7 +55,7 @@ finally:
 # ---------------------------------------------------------------------------


-def make_runner(output_key: str = 'response') -> N8nServiceAPIRunner:
+def make_runner(output_key: str = 'response', response_handling: str = 'reply') -> N8nServiceAPIRunner:
    ap = Mock()
    ap.logger = Mock()
    pipeline_config = {
@@ -63,6 +63,7 @@ def make_runner(output_key: str = 'response') -> N8nServiceAPIRunner:
            'n8n-service-api': {
                'webhook-url': 'http://test-n8n/webhook',
                'output-key': output_key,
+                'response-handling': response_handling,
                'auth-type': 'none',
            }
        }
@@ -287,6 +288,7 @@ def make_http_session_mock(response_bytes: bytes, status: int = 200):
    """Mock httpclient.get_session() returning a session whose post() yields response_bytes."""
    mock_response = make_mock_response([response_bytes], status=status)
    mock_response.status = status
+    mock_response.headers = {}

    mock_cm = AsyncMock()
    mock_cm.__aenter__ = AsyncMock(return_value=mock_response)
@@ -314,6 +316,91 @@ async def test_call_webhook_nonstream_adapter_plain_json():
    assert results[0].content == 'result text'


+@pytest.mark.asyncio
+@pytest.mark.parametrize('status', [200, 201, 202, 204])
+@pytest.mark.parametrize(
+    'response_body',
+    [
+        b'{"message":"Workflow was started"}',
+        b'{"response":"must not be forwarded"}',
+        b'plain acknowledgement',
+    ],
+)
+async def test_call_webhook_ignore_response_body(response_body: bytes, status: int):
+    """Ignore mode accepts any HTTP 2xx response without emitting chat output."""
+    runner = make_runner(response_handling='ignore')
+    query = make_query(is_stream=False)
+    http_session = make_http_session_mock(response_body, status=status)
+
+    with patch('langbot.pkg.provider.runners.n8nsvapi.httpclient.get_session', return_value=http_session):
+        results = []
+        async for message in runner._call_webhook(query):
+            results.append(message)
+
+    assert results == []
+
+
+@pytest.mark.asyncio
+async def test_call_webhook_ignore_releases_without_reading_response_body():
+    """Ignore mode returns after the success status without waiting for the body."""
+    runner = make_runner(response_handling='ignore')
+    query = make_query(is_stream=False)
+    mock_response = make_mock_response([], status=202)
+    mock_response.headers = {}
+    mock_response.release = Mock()
+
+    async def fail_if_read(_size):
+        raise AssertionError('ignore mode must not read the response body')
+        yield b''
+
+    mock_response.content.iter_chunked = fail_if_read
+    mock_cm = AsyncMock()
+    mock_cm.__aenter__ = AsyncMock(return_value=mock_response)
+    mock_cm.__aexit__ = AsyncMock(return_value=False)
+    mock_session = Mock()
+    mock_session.post = Mock(return_value=mock_cm)
+
+    with patch('langbot.pkg.provider.runners.n8nsvapi.httpclient.get_session', return_value=mock_session):
+        results = [message async for message in runner._call_webhook(query)]
+
+    assert results == []
+    mock_response.release.assert_called_once_with()
+
+
+@pytest.mark.asyncio
+@pytest.mark.parametrize('status', [201, 202, 204])
+async def test_call_webhook_reply_mode_preserves_http_200_contract(status: int):
+    """Reply mode remains backward compatible and rejects non-200 statuses."""
+    runner = make_runner(response_handling='reply')
+    query = make_query(is_stream=False)
+    http_session = make_http_session_mock(b'', status=status)
+
+    with patch('langbot.pkg.provider.runners.n8nsvapi.httpclient.get_session', return_value=http_session):
+        with pytest.raises(N8nAPIError, match=f'n8n webhook call failed: {status}'):
+            async for _ in runner._call_webhook(query):
+                pass
+
+
+@pytest.mark.asyncio
+async def test_call_webhook_ignore_mode_preserves_http_error():
+    """Ignore mode must not swallow a failed n8n webhook response."""
+    runner = make_runner(response_handling='ignore')
+    query = make_query(is_stream=False)
+    http_session = make_http_session_mock(b'{"error":"unavailable"}', status=500)
+
+    with patch('langbot.pkg.provider.runners.n8nsvapi.httpclient.get_session', return_value=http_session):
+        with pytest.raises(N8nAPIError, match='n8n webhook call exception'):
+            async for _ in runner._call_webhook(query):
+                pass
+
+
+@pytest.mark.asyncio
+async def test_invalid_response_handling_is_rejected():
+    """Configuration errors should fail fast instead of silently changing reply behavior."""
+    with pytest.raises(ValueError, match='Invalid n8n response-handling'):
+        make_runner(response_handling='unexpected')
+
+
@pytest.mark.asyncio
 async def test_call_webhook_stream_adapter_stream_format():
    """Stream adapter + stream format → MessageChunks, last is_final."""
@@ -1,8 +1,11 @@
 """Tests for DingTalk API payload helpers."""

 import json
+from contextlib import asynccontextmanager
+from unittest.mock import AsyncMock

-from langbot.libs.dingtalk_api.api import _stringify_card_param_map
+from langbot.libs.dingtalk_api.api import DingTalkClient, _stringify_card_param_map
+from langbot.pkg.utils import httpclient


 def test_dingtalk_card_param_map_stringifies_select_component_arrays():
@@ -40,3 +43,41 @@ def test_dingtalk_card_param_map_stringifies_unregistered_structures():

    assert params['other'] == '["A"]'
    assert params['empty'] == ''
+
+
+async def test_create_card_embeds_layout_config_as_template_parameter(monkeypatch):
+    response = type('Response', (), {'status_code': 200})()
+    post = AsyncMock(return_value=response)
+
+    @asynccontextmanager
+    async def client_context():
+        yield type('HttpClient', (), {'post': post})()
+
+    client = object.__new__(DingTalkClient)
+    client.access_token = 'access-token'
+    client.robot_code = 'robot-code'
+    client.key = 'client-id'
+    client.logger = None
+    client.check_access_token = AsyncMock(return_value=True)
+    client._http_client_context = client_context
+    monkeypatch.setattr(httpclient, 'response_text', AsyncMock(return_value='{}'))
+
+    original_params = {'content': 'hello'}
+    delivered = await client.create_and_deliver_card(
+        card_template_id='template-id',
+        out_track_id='track-id',
+        open_space_id='dtv1.card//IM_ROBOT.user-id',
+        is_group=False,
+        card_param_map=original_params,
+        card_data_config={'autoLayout': True},
+    )
+
+    request_body = post.await_args.kwargs['json']
+    assert delivered is True
+    assert request_body['cardData'] == {
+        'cardParamMap': {
+            'content': 'hello',
+            'config': '{"autoLayout": true}',
+        }
+    }
+    assert original_params == {'content': 'hello'}
@@ -1,7 +1,7 @@
 """Tests for Lark adapter helper behavior."""

 import threading
-from unittest.mock import MagicMock
+from unittest.mock import AsyncMock, MagicMock

 import pytest

@@ -12,6 +12,7 @@ from langbot.pkg.platform.sources.lark import (
    _lark_completed_input_lines,
    _lark_current_input_defs,
    _lark_extract_action_form_inputs,
+    _lark_final_layout_texts,
    _lark_should_update_stream_element,
    _lark_visible_form_content,
 )
@@ -221,3 +222,121 @@ def test_lark_completed_input_lines_display_select_value_from_object():
    )

    assert lines == ['✅ xiala：B']
+
+
+def test_lark_final_layout_texts_normal_round_drops_resume_placeholder():
+    """Non-resume final chunk: the reply must land in the main element only.
+
+    Regression: rendering the resume placeholder too duplicated the reply,
+    because the accumulated streaming text equals the final text on a normal
+    round (e.g. 'It is Sep 1, 2026.\nIt is Sep 1, 2026.' in the card).
+    """
+    main_text, resume_text = _lark_final_layout_texts(
+        resume_from=False,
+        text_message='It is Sep 1, 2026, 15:09:15.',
+        pre_pause_cached=None,
+        resume_cached='It is Sep 1, 2026, 15:09:15.',
+    )
+
+    assert main_text == 'It is Sep 1, 2026, 15:09:15.'
+    assert resume_text == ''
+
+
+def test_lark_final_layout_texts_resume_round_keeps_both_segments():
+    """Dify HITL resume final chunk: pre-pause text and resumed text differ,
+    both segments stay visible."""
+    main_text, resume_text = _lark_final_layout_texts(
+        resume_from=True,
+        text_message='resumed answer',
+        pre_pause_cached='partial answer before pause',
+        resume_cached='resumed answer',
+    )
+
+    assert main_text == 'partial answer before pause'
+    assert resume_text == 'resumed answer'
+
+
+def test_lark_final_layout_texts_resume_round_without_pre_pause_falls_back():
+    main_text, resume_text = _lark_final_layout_texts(
+        resume_from=True,
+        text_message='answer',
+        pre_pause_cached=None,
+        resume_cached='answer',
+    )
+
+    assert main_text == 'answer'
+    assert resume_text == 'answer'
+
+
+def test_lark_final_layout_texts_resume_round_empty_pre_pause_kept_empty():
+    """Dify paused before emitting any text: the pre-pause cache is a valid
+    empty string and must NOT be treated as a cache miss.
+
+    Regression: `pre_pause_cached or text_message` fell back to the full
+    text, so the final card rendered ('resumed answer', 'resumed answer')
+    and duplicated the reply.
+    """
+    main_text, resume_text = _lark_final_layout_texts(
+        resume_from=True,
+        text_message='resumed answer',
+        pre_pause_cached='',
+        resume_cached='resumed answer',
+    )
+
+    assert main_text == ''
+    assert resume_text == 'resumed answer'
+
+
+def _build_resume_final_chunk_adapter(message_text: str):
+    """Build a LarkAdapter whose card state mimics a Dify HITL round that
+    paused before emitting any text, then resumed and completed."""
+    adapter = LarkAdapter.model_construct(
+        api_client=MagicMock(),
+        message_converter=MagicMock(yiri2target=AsyncMock(return_value=([[{'tag': 'text', 'text': message_text}]], []))),
+    )
+    adapter.config = {'app_type': 'self'}
+    LarkAdapter.get_app_access_token = lambda self: None
+    LarkAdapter.get_tenant_access_token = lambda self, tenant_key: None
+    adapter.card_id_dict = {'msg-1': 'card-1'}
+    adapter.card_streaming_text = {'card-1': message_text}
+    adapter.card_pre_pause_text = {'card-1': ''}
+    adapter.card_resume_transitioned = {'card-1'}
+    adapter.card_sequence_dict = {}
+    adapter.card_last_accessed = {}
+    adapter.card_cleanup_at = 0.0
+    adapter.card_id_to_source_ids = {}
+    adapter.reply_message_card_ids = {}
+    adapter.card_form_content = {}
+    adapter.card_form_input_defs = {}
+    adapter.card_form_inputs = {}
+    adapter._update_card_layout = AsyncMock()
+    return adapter
+
+
+@pytest.mark.asyncio
+async def test_reply_message_chunk_resume_final_with_empty_pre_pause_keeps_main_empty():
+    """End-to-end regression via reply_message_chunk: Dify paused before any
+    text, so the pre-pause cache is ''. The final card update must render the
+    resumed answer only once (empty main text + resume placeholder), not
+    twice as ('resumed answer', 'resumed answer')."""
+    adapter = _build_resume_final_chunk_adapter('resumed answer')
+
+    bot_message = MagicMock(
+        resp_message_id='msg-1',
+        msg_sequence=1,
+        spec=['resp_message_id', 'msg_sequence', '_resume_from_form'],
+    )
+    bot_message._resume_from_form = True
+    message_source = MagicMock(source_platform_object=None)
+
+    await adapter.reply_message_chunk(
+        message_source,
+        bot_message,
+        MagicMock(),
+        is_final=True,
+    )
+
+    adapter._update_card_layout.assert_awaited_once()
+    layout_kwargs = adapter._update_card_layout.await_args.kwargs
+    assert layout_kwargs['text_message'] == ''
+    assert layout_kwargs['resume_placeholder_text'] == 'resumed answer'
--- a/Show More
+++ b/Show More
Author	SHA1	Message	Date
huanghuoguoguo	cba842fbee	style: format core skill orchestration	2026-09-05 23:18:17 +08:00
huanghuoguoguo	a61b0f0068	refactor(skill): compose generic box mounts in core	2026-09-05 23:09:46 +08:00
huanghuoguoguo	c15f668126	feat(skill): use SDK store without box execution	2026-09-05 19:49:35 +08:00
Hyu	ec63978ecf	docs: replace legacy documentation shortlinks (#2510 ) * docs: replace legacy documentation shortlinks * style: format updated documentation URLs --------- Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-09-05 01:19:28 +08:00
Hyu	1cfe87186c	docs: update published documentation links (#2509 ) Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-09-05 00:55:18 +08:00
leonoxo	9794df0933	feat(n8n-runner): support async response handling (#2487 ) * feat(n8n-runner): support async response handling * fix(n8n-runner): expose response handling in form * fix(n8n-runner): preserve async response semantics --------- Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-09-04 22:36:40 +08:00
Hyu	a63808caa6	chore(release): prepare LangBot 4.10.10 (#2507 ) Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-09-04 21:47:31 +08:00
mintya	de3c0b00ad	fix(bot): roll back inserted bot row when adapter fails to load (#2497 ) create_bot inserts the Bot row first and only then instantiates the adapter via platform_mgr.load_bot. When the adapter constructor raises (e.g. KeyError on a missing credential key), the insert is already committed and nothing removes the row: the HTTP layer returns 500 but a permanently disabled orphan bot stays in the DB. Callers never receive the bot uuid, so they cannot compensate by deleting it, and load_bots_from_db skips enable=False bots, so the orphan is never loaded or surfaced anywhere. Wrap load_bot in try/except and delete the inserted row before re-raising. Add a regression test asserting the DELETE is issued when the adapter constructor fails.	2026-09-04 13:06:12 +08:00
mintya	cb45807b12	fix(qqofficial): tolerate missing optional token in adapter config (#2496 ) Since `b55f073e` the token field is optional in qqofficial.yaml ("the current adapter implementation does not use it either, so it can be safely left blank"), but the adapter constructor still reads it with config['token']. Creating a bot via QR binding (which only returns appid/secret) or with the token field left blank raises KeyError and the API returns 500. Read it with config.get('token', '') instead. The value is never used by QQOfficialClient beyond being stored, so an empty string default is safe.	2026-09-04 13:05:36 +08:00
Amir Fathi	d942bfe19a	fix(wecom): read media_id instead of media in send_message() (#2447 ) WecomMessageConverter.yiri2target() always emits {'media_id': ...} for image/voice/file parts (never 'media'), matching the correct usage already in reply_message(). send_message(), the entry point plugins use via PluginToRuntimeAction.SEND_MESSAGE, instead read content['media'], which is never set, so any image/voice/file part raises KeyError and aborts the send. Refs #1687 Signed-off-by: Amir Fathi <amirfathi.me@gmail.com>	2026-09-04 13:02:40 +08:00
Hyu	b44b8f474d	fix(cloud): provision login workspace just in time (#2505 ) * fix(cloud): provision login workspace just in time * fix(oauth): send callback URI during code exchange * fix(oauth): preserve callback URI through browser exchange * fix(oauth): negotiate redirect-bound codes --------- Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-09-03 23:14:44 +08:00
Hyu	ab52684a01	Revert "fix(cloud): request automatic Space launch (#2501 )" (#2503 ) This reverts commit `d50957fc4f`. Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-09-03 12:16:21 +08:00
Hyu	d50957fc4f	fix(cloud): request automatic Space launch (#2501 ) Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-09-03 11:44:32 +08:00
Hyu	c8d8b1aac4	fix(cloud): serialize directory catch-up (#2500 ) Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-09-02 21:57:53 +08:00
Hyu	018dd7a363	fix(cloud): launch newly registered accounts through Space (#2499 ) * fix(cloud): launch new accounts through Space * style: format Cloud entry URL * fix(cloud): wait for launch workspace projection --------- Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-09-02 21:41:35 +08:00
huanghuoguoguo	7b7d3f04e8	feat(box): support explicit host backend (#2498 )	2026-09-02 21:22:14 +08:00
CWT	601c6975ea	fix(ollama): use litellm's ollama_chat provider for native tool-calling (#2494 ) The Ollama requester declared litellm_provider: ollama, which routes every request through litellm's legacy /api/generate-based OllamaConfig. That config's get_supported_openai_params() does not include "tools"/"tool_choice" at all, so an Ollama-hosted model in a local-agent pipeline could never receive a structured tool definition or return a structured tool_calls response - it could only try to express a tool call as free text (typically inside its own <think> reasoning), which LangBot then has no way to execute. litellm's "ollama_chat" provider targets Ollama's modern /api/chat endpoint instead, which correctly forwards tools/tool_choice and correctly surfaces the model's native message.tool_calls field. Verified against a real local Ollama 0.33.2 instance with the exact system prompt, RAG-augmented user message, and tool set a live pipeline sends. Two follow-on fixes needed because the Ollama requester definition is shared by LLM and text-embedding models: - get_reasoning_capabilities: match family in ('ollama', 'ollama_chat') so the reasoning-level UI still works for this provider. - scan_models: retry {base_url}/v1/models on a 404 from {base_url}/models, since Ollama's base_url is a bare host (must not include /v1 - that would break OllamaChatConfig.get_complete_url, which appends /api/chat to it directly), unlike most other OpenAI-compatible providers whose base_url already ends in /v1. - invoke_embedding: litellm's embedding routing has no "ollama_chat" case, only "ollama". Build the embedding model name with an explicit custom_llm_provider="ollama" override when the requester is configured for ollama_chat, so embedding models (e.g. bge-m3) keep working. Co-authored-by: zx90316 <zx90316@users.noreply.github.com>	2026-09-01 22:36:35 +08:00
mintya	5ca30133a3	fix(lark): stop duplicating final reply text in streaming card (#2490 ) * fix(lark): stop duplicating final reply text in streaming card * fix(lark): stop duplicating final reply text in streaming card	2026-09-01 21:24:54 +08:00
Hyu	5c49cb60e3	fix(embed): preserve replies after empty assistant frames (#2492 ) Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-09-01 20:11:21 +08:00
Hyu	8cf0015502	fix(dingtalk): restore card auto layout (#2491 ) Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-09-01 17:56:02 +08:00
Hyu	bf8d418ad4	feat(monitoring): paginate sessions and messages (#2489 ) * feat(monitoring): paginate sessions and messages * fix(monitoring): align detail pages with local dates --------- Co-authored-by: dadachann <185672915+dadachann@users.noreply.github.com>	2026-09-01 15:14:29 +08:00