feat(skills): add Agent Skills management system by fdc310 · Pull Request #1917 · langbot-app/LangBot

fdc310 · 2026-01-13T07:00:32Z

Implement comprehensive skills management feature inspired by agentskills spec:

Backend:

Add Skill and SkillPipelineBinding database entities
Add database migration (dbm018) for skills tables
Implement SkillManager for skill loading, matching, and resolution
Implement SkillService for CRUD operations
Add skills API endpoints for skill and pipeline binding management
Integrate skill index injection into pipeline preprocessor
Add skill activation detection in LocalAgentRunner

Frontend:

Add Skills page with listing, search, and type filter
Add SkillDetailDialog for create/edit with preview
Add SkillCard and SkillForm components
Add skills API methods to BackendClient
Add skills entry to sidebar navigation
Add i18n translations (en-US, zh-Hans)

Features:

Support skill and workflow types
Sub-skill composition via {{INVOKE_SKILL: name}} syntax
Progressive disclosure (index in prompt, full instructions on activation)
Pipeline-specific skill bindings with priority

概述 / Overview

请在此部分填写你实现/解决/优化的内容:
Summary of what you implemented/solved/optimized:

更改前后对比截图 / Screenshots

请在此部分粘贴更改前后对比截图（可以是界面截图、控制台输出、对话截图等）:
Please paste the screenshots of changes before and after here (can be interface screenshots, console output, conversation screenshots, etc.):

修改前 / Before:

修改后 / After:

检查清单 / Checklist

PR 作者完成 / For PR author

请在方括号间写x以打勾 / Please tick the box with x

阅读仓库贡献指引了吗？ / Have you read the contribution guide?
与项目所有者沟通过了吗？ / Have you communicated with the project maintainer?
我确定已自行测试所作的更改，确保功能符合预期。 / I have tested the changes and ensured they work as expected.

项目维护者完成 / For project maintainer

相关 issues 链接了吗？ / Have you linked the related issues?
配置项写好了吗？迁移写好了吗？生效了吗？ / Have you written the configuration items? Have you written the migration? Has it taken effect?
依赖加到 pyproject.toml 和 core/bootutils/deps.py 了吗 / Have you added the dependencies to pyproject.toml and core/bootutils/deps.py?
文档编写了吗？ / Have you written the documentation?

huanghuoguoguo · 2026-03-22T08:20:15Z

Update: package-backed skills + sandbox execution

在初始 commit (a6f1a28b) 的基础上做了一轮设计调整和补充实现。

初始 commit 做了什么

初始版本实现了 Skills 管理系统的基础框架：Skill/SkillPipelineBinding 数据模型、SkillManager（加载/匹配/激活）、API + 前端 CRUD、pipeline preprocessor 中注入 skill index、LocalAgentRunner 中的 [ACTIVATE_SKILL] 检测与 prompt 注入。

此时 skill 还是纯 prompt 驱动的——激活后只是往对话里注入一段 instructions，没有确定性执行能力。

后续做了什么改动

核心变化是让 skill 从"纯 prompt 引导"升级为"package-backed + sandbox 执行"：

数据模型扩展：Skill 新增 source_type（inline/package）、package_root、entry_file、skill_tools 字段，兼容已有 inline skill
Package skill 加载：SkillManager 支持从本地目录读取 SKILL.md 作为 instructions
Skill tool 分发：ToolManager 新增第四层 SkillToolLoader（native → plugin → mcp → skill），query 级隔离，tool 名称自动命名空间化为 skill__{skill}__{tool}
Sandbox 执行：BoxService.execute_skill_tool() 将 package_root 只读挂载到 /workspace，根据 entry 后缀自动拼装命令，参数通过环境变量传入
LocalAgent 动态注入：skill 激活后，将其 skill_tools 转为 LLMTool 追加到 query.use_funcs，第二轮 LLM 请求即可调用
安全校验：package_root allowlist 校验、entry 路径防逃逸、默认 network=off、前端不暴露 raw command

后续计划

Skill 目前放在 pkg/skill/ 下作为独立模块。后续计划将其移动到与 MCP 同级的位置（pkg/provider/tools/ 体系下），原因：

Skill tool 本质上是 ToolManager 的第四类 tool source，和 native/plugin/mcp 是同层概念
当前 skill 的 activation 逻辑嵌在 LocalAgentRunner 里，长期应抽象为 provider 层的统一能力
与 MCP 对齐后，skill 可以复用 tool discovery、binding、pipeline config 等已有基础设施

这样 skills 就不再是一个游离的独立模块，而是融入 LangBot 的 provider 体系中。

Implement comprehensive skills management feature inspired by agentskills spec: Backend: - Add Skill and SkillPipelineBinding database entities - Add database migration (dbm018) for skills tables - Implement SkillManager for skill loading, matching, and resolution - Implement SkillService for CRUD operations - Add skills API endpoints for skill and pipeline binding management - Integrate skill index injection into pipeline preprocessor - Add skill activation detection in LocalAgentRunner Frontend: - Add Skills page with listing, search, and type filter - Add SkillDetailDialog for create/edit with preview - Add SkillCard and SkillForm components - Add skills API methods to BackendClient - Add skills entry to sidebar navigation - Add i18n translations (en-US, zh-Hans) Features: - Support skill and workflow types - Sub-skill composition via {{INVOKE_SKILL: name}} syntax - Progressive disclosure (index in prompt, full instructions on activation) - Pipeline-specific skill bindings with priority

- Remove non-existent external_kb service import - Add skill_mgr mock to localagent sandbox_exec tests - Keep database version at 24 (sandbox branch's latest)

Evolve the skills system from pure prompt-based to package-backed with sandbox tool execution support: - Add source_type/package_root/entry_file/skill_tools fields to Skill entity - SkillManager loads SKILL.md from local package directories - SkillToolLoader as 4th dispatch layer in ToolManager (query-scoped) - LocalAgent injects skill tools into use_funcs on skill activation - BoxService.execute_skill_tool() runs scripts in sandbox (ro mount, env params) - Skill tool names auto-namespaced as skill__{skill}__{tool} - API validation for package_root allowlist and entry path traversal - Frontend source_type toggle, package_root input, skill_tools editor - Migration renumbered to 025 with ALTER TABLE fallback for existing DBs - Fix unclosed limitation section in i18n files - Fix skills API methods misplaced outside BackendClient class

…tooling - skills 从 inline/package 双轨收敛成 package-first - instructions 改为写入并读取 SKILL.md - 新增本地目录扫描和 GitHub 安装 skill - 前端把 skills 整合进 plugins 页，新增 SkillsComponent 和 GitHub 导入弹窗 - skill form 去掉 source_type / type 筛选，改成目录扫描驱动 - Box skill tool 挂载模式从 ro 改成 rw - 测试和中英文文案同步更新

management

After the architecture settled on always using an independent Box Runtime service, several pieces of compatibility code and design shortcuts were left behind. This commit cleans them up: - Remove `LocalBoxRuntimeClient` and `create_box_runtime_client` from production code (moved to test-only helper). - Remove unused `_clip_bytes` method from backend. - Remove `__langbot_session_placeholder__` hack by making `BoxSpec.cmd` default to empty and validating non-empty only in `runtime.execute()`. - Extract `get_box_config()` helper to eliminate 5× duplicated config access boilerplate. - Remove `session_id`/`host_path`/`host_path_mode` from the LLM-facing tool schema to enforce request-scoped session isolation. - Fix dual shutdown path: `NativeToolLoader.shutdown()` no longer calls `box_service.shutdown()` (handled by `Application.dispose()`). - Simplify `_assert_session_compatible` with a loop. - Inline client creation in `BoxRuntimeConnector`. - Remove redundant `BOX__RUNTIME_URL` env var from docker-compose (auto-detected by code). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com>

… dep install, security ## Summary When Podman/Docker is available, all stdio-mode MCP servers now automatically run inside Box containers with dependency installation, path rewriting, and lifecycle management. When no container runtime exists, LangBot starts normally and stdio MCP falls back to host-direct execution. ## What changed ### MCP stdio → Box integration (mcp.py) - Add `MCPServerBoxConfig` pydantic model for structured box configuration with validation and defaults (network, host_path_mode, timeouts, resources) - Auto-infer `host_path` from command/args with venv detection: recognizes `.venv/bin/python` patterns and walks up to the project root - Rewrite host paths to container `/workspace` paths transparently - Replace venv python commands with container-native `python` - Auto-detect `pyproject.toml`/`setup.py`/`requirements.txt` and run `pip install` inside the container before starting the MCP server - Copy project to `/tmp` before install to handle read-only mounts - Add retry with exponential backoff (3 retries, 2s/4s/8s delays) - Add Box managed process health monitoring (poll every 5s) - Fix session leak: `_cleanup_box_stdio_session()` now runs in `finally` block of `_lifecycle_loop`, covering all exit paths - Fix retry logic: `_ready_event` is only set after all retries exhaust or on success, not on first failure - Enhance `get_runtime_info_dict()` with `box_session_id` and `box_enabled` ### Box security (security.py — new) - `validate_sandbox_security()` blocks dangerous host paths: `/etc`, `/proc`, `/sys`, `/dev`, `/root`, `/boot`, `/run`, docker.sock, podman socket - Called at the start of `CLISandboxBackend.start_session()` ### Box models (models.py) - Add `BoxHostMountMode.NONE` — skips volume mount entirely - Adjust `validate_host_mount_consistency` to allow arbitrary workdir when `host_path_mode=NONE` ### Box backend (backend.py) - Add `validate_sandbox_security()` call in `start_session()` - Add `langbot.box.config_hash` label on containers for drift detection - Handle `BoxHostMountMode.NONE` — skip `-v` mount arg - Add `cleanup_orphaned_containers()` to base class (no-op default) and CLI implementation (single batched `rm -f` command) ### Box runtime (runtime.py) - Call `cleanup_orphaned_containers()` during `initialize()` to remove lingering containers from previous runs ### Box service (service.py) - Graceful degradation: `initialize()` catches runtime errors and sets `available=False` instead of crashing LangBot startup - Add `available` property and guard on `execute_sandbox_tool()` - Add `skip_host_mount_validation` parameter to `build_spec()` and `create_session()` — MCP paths are admin-configured and trusted, bypassing `allowed_host_mount_roots` restrictions meant for LLM-generated sandbox_exec commands ### Default behavior - stdio MCP servers automatically use Box when `box_service.available` is True (Podman/Docker detected); no explicit `box` config needed - When no container runtime exists, falls back to host-direct stdio - MCP Box defaults: `network=on` (for pip install), `read_only_rootfs=false` (for site-packages), `host_path_mode=ro`, `startup_timeout=120s` ### Tests - `test_box_security.py`: blocked paths, safe paths, subpath rejection - `test_mcp_box_integration.py`: config model, path rewriting, venv unwrap, host_path inference, payload building, runtime info, box availability check - `test_box_service.py`: `BoxHostMountMode.NONE` validation tests

…ession API, and integration tests ## Changes ### Precise orphan container cleanup - Runtime generates a unique instance_id on startup - Every container gets a `langbot.box.instance_id` label - `cleanup_orphaned_containers()` only removes containers from previous instances, preserving containers owned by the current one - Containers from older versions (no label) are also cleaned up - `cleanup_orphaned_containers` added to `BaseSandboxBackend` as a no-op default method, removing hasattr duck-typing ### Fine-grained MCP error classification - New `MCPSessionErrorPhase` enum with 7 phases: session_create, dep_install, process_start, relay_connect, mcp_init, runtime, tool_call - Each phase in `_init_box_stdio_server()` sets the error phase before re-raising, enabling precise failure diagnosis - `retry_count` tracked across retry attempts - `get_runtime_info_dict()` exposes `error_phase` and `retry_count` ### GET /v1/sessions/{id} API - `BoxRuntime.get_session()` returns session details including managed process info when present - `handle_get_session` HTTP handler + route in server.py - `BoxRuntimeClient.get_session()` abstract method + remote impl ### stdio defaults to Box when runtime is available - `_uses_box_stdio()` checks `box_service.available` instead of requiring explicit `box` key in server_config - `BoxService.initialize()` catches runtime errors gracefully, sets `available=False` instead of crashing LangBot startup - When no container runtime exists, stdio MCP falls back to host-direct execution ### Code quality (from /simplify review) - Extracted `_VENV_DIRS` / `_VENV_BIN_DIRS` module-level constants - Removed dead `_box_network_mode()` method and unused `bc` variable - Fixed broken import `from ....box.models` → `from ...box.models` - Cached `_resolve_host_path()` result — computed once, passed through - Config hash now includes `host_path` field - Batched orphan cleanup into single `rm -f` command ### Session leak fix - `_cleanup_box_stdio_session()` now runs in `_lifecycle_loop`'s finally block, covering all exit paths (normal shutdown, error, retry, final failure) ### Integration tests - 6 end-to-end tests covering managed process lifecycle, WebSocket stdio bidirectional IO, session cleanup verification, single session query, process exit detection, and orphan cleanup safety

- Fix O(n²) stderr trimming in runtime.py with running length tracker - Remove dead code: RESERVED_CONTAINER_PATHS, _subprocess_wait_task, unused config_hash computation, unused imports - Deduplicate connection callback in BoxRuntimeConnector, parse URL once - Use enum comparison instead of stringly-typed spec.network.value check - Replace manual _result_to_dict/_session_to_dict with model_dump() - Cache NativeToolLoader tool definition and sandbox system guidance - Extract _is_path_under() helper to eliminate duplicated path checks - Import SANDBOX_EXEC_TOOL_NAME from native.py instead of redefining - Add JSON startswith guard in logging_utils to skip futile json.loads - Fix ruff lint errors (F401 unused imports, F841 unused variables)

- Move sandbox system-prompt guidance from LocalAgentRunner into BoxService.get_system_guidance() so all box domain knowledge stays in the box module. - Remove standalone logging_utils.py; merge format_result_log() into MessageHandler base class alongside cut_str(). - Strip sandbox-specific JSON parsing from log formatting; tool results now use generic truncation. - Revert TYPE_CHECKING changes in stage.py and runner.py that were unrelated to this feature. - Skip two test files affected by a pre-existing circular import (runner ↔ app) until the import cycle is resolved in a separate PR.

Extract self-contained box runtime modules (actions, backend, client, errors, models, runtime, security, server) to langbot-plugin-sdk and update all imports to use `langbot_plugin.box.*`. Keep only service and connector in LangBot core as they depend on the Application context. - Update docker-compose to use `langbot_plugin.box.server` entry point - Update pyproject.toml to use local SDK via `tool.uv.sources` - Remove migrated source files and their unit/integration tests - Update remaining test imports to match new module paths

…hive

- Fix sidebar skill icon - Add skills route and error page component - Refactor plugin GitHub install from dialog modal to inline card - Add skill install dropdown menu (create/upload/github) in sidebar - Wire sidebar → skills page communication via pendingSkillInstallAction context - Add i18n keys for error page and skill install actions

Sections opened via sub-item navigation now retain their expanded state when the user switches to a different section, instead of collapsing because the isActive fallback becomes false.

* feat(skills): add Agent Skills management system Implement comprehensive skills management feature inspired by agentskills spec: Backend: - Add Skill and SkillPipelineBinding database entities - Add database migration (dbm018) for skills tables - Implement SkillManager for skill loading, matching, and resolution - Implement SkillService for CRUD operations - Add skills API endpoints for skill and pipeline binding management - Integrate skill index injection into pipeline preprocessor - Add skill activation detection in LocalAgentRunner Frontend: - Add Skills page with listing, search, and type filter - Add SkillDetailDialog for create/edit with preview - Add SkillCard and SkillForm components - Add skills API methods to BackendClient - Add skills entry to sidebar navigation - Add i18n translations (en-US, zh-Hans) Features: - Support skill and workflow types - Sub-skill composition via {{INVOKE_SKILL: name}} syntax - Progressive disclosure (index in prompt, full instructions on activation) - Pipeline-specific skill bindings with priority * fix: resolve cherry-pick conflicts for agentskills onto sandbox - Remove non-existent external_kb service import - Add skill_mgr mock to localagent sandbox_exec tests - Keep database version at 24 (sandbox branch's latest) * feat(skills): upgrade to package-backed skills with sandbox execution Evolve the skills system from pure prompt-based to package-backed with sandbox tool execution support: - Add source_type/package_root/entry_file/skill_tools fields to Skill entity - SkillManager loads SKILL.md from local package directories - SkillToolLoader as 4th dispatch layer in ToolManager (query-scoped) - LocalAgent injects skill tools into use_funcs on skill activation - BoxService.execute_skill_tool() runs scripts in sandbox (ro mount, env params) - Skill tool names auto-namespaced as skill__{skill}__{tool} - API validation for package_root allowlist and entry path traversal - Frontend source_type toggle, package_root input, skill_tools editor - Migration renumbered to 025 with ALTER TABLE fallback for existing DBs - Fix unclosed limitation section in i18n files - Fix skills API methods misplaced outside BackendClient class * fix: test info * feat(skills): switch skills to package-backed storage and add import tooling - skills 从 inline/package 双轨收敛成 package-first - instructions 改为写入并读取 SKILL.md - 新增本地目录扫描和 GitHub 安装 skill - 前端把 skills 整合进 plugins 页，新增 SkillsComponent 和 GitHub 导入弹窗 - skill form 去掉 source_type / type 筛选，改成目录扫描驱动 - Box skill tool 挂载模式从 ro 改成 rw - 测试和中英文文案同步更新 * feat: simplify langbot skill create and import * refactor(skills): clean up legacy skill API and harden activation flow * refactor(skills): remove skill dependency expansion and add skill_get * fix: lint * fix: delete * fix(skills): align tool manager loader initialization * refactor: remove sandbox execute skill * fix(skills): hide activation markers and isolate skill activation flow * refactor(skills): switch skill model to filesystem-backed packages * refactor(skills): switch skill model to filesystem-backed packages * refactor(skills): unify runtime skill access around filesystem paths * refactor(skills): unify runtime skill access around filesystem paths * feat(skills): align rw package design and fix skill activation, visibility, and lint issues * refactor(skills): replace rich authoring API with import/reload flow and update Box design doc * feat(box): add sandbox_exec tool loop for local-agent calculations * feat(box): add host workspace mounting and sandbox_exec guidance * feat(box): add BoxProfile with resource limits and improved output truncation - Implement head+tail output truncation (60/40 split) so LLM sees both beginning and final results; add streaming byte-limited reads in backend to prevent unbounded memory usage (_MAX_RAW_OUTPUT_BYTES = 1MB) - Define BoxProfile model with locked fields and max_timeout_sec clamping - Add four built-in profiles: default, offline_readonly, network_basic, network_extended with differentiated resource and security constraints - Add resource limit fields to BoxSpec (cpus, memory_mb, pids_limit, read_only_rootfs) and pass corresponding container CLI flags (--cpus, --memory, --pids-limit, --read-only, --tmpfs) - Profile loaded from config (box.profile), applied in service layer before BoxSpec validation; locked fields cannot be overridden by tool-call parameters * feat(box): add obs * refactor(box): unify box service lifecycle and local runtime management * refactor(box): remove legacy in-process runtime code and clean up smells After the architecture settled on always using an independent Box Runtime service, several pieces of compatibility code and design shortcuts were left behind. This commit cleans them up: - Remove `LocalBoxRuntimeClient` and `create_box_runtime_client` from production code (moved to test-only helper). - Remove unused `_clip_bytes` method from backend. - Remove `__langbot_session_placeholder__` hack by making `BoxSpec.cmd` default to empty and validating non-empty only in `runtime.execute()`. - Extract `get_box_config()` helper to eliminate 5× duplicated config access boilerplate. - Remove `session_id`/`host_path`/`host_path_mode` from the LLM-facing tool schema to enforce request-scoped session isolation. - Fix dual shutdown path: `NativeToolLoader.shutdown()` no longer calls `box_service.shutdown()` (handled by `Application.dispose()`). - Simplify `_assert_session_compatible` with a loop. - Inline client creation in `BoxRuntimeConnector`. - Remove redundant `BOX__RUNTIME_URL` env var from docker-compose (auto-detected by code). Co-Authored-By: Claude Opus 4.6 (1M context) <noreply@anthropic.com> * feat(box/mcp): integrate MCP stdio with Box sandbox — auto-isolation, dep install, security ## Summary When Podman/Docker is available, all stdio-mode MCP servers now automatically run inside Box containers with dependency installation, path rewriting, and lifecycle management. When no container runtime exists, LangBot starts normally and stdio MCP falls back to host-direct execution. ## What changed ### MCP stdio → Box integration (mcp.py) - Add `MCPServerBoxConfig` pydantic model for structured box configuration with validation and defaults (network, host_path_mode, timeouts, resources) - Auto-infer `host_path` from command/args with venv detection: recognizes `.venv/bin/python` patterns and walks up to the project root - Rewrite host paths to container `/workspace` paths transparently - Replace venv python commands with container-native `python` - Auto-detect `pyproject.toml`/`setup.py`/`requirements.txt` and run `pip install` inside the container before starting the MCP server - Copy project to `/tmp` before install to handle read-only mounts - Add retry with exponential backoff (3 retries, 2s/4s/8s delays) - Add Box managed process health monitoring (poll every 5s) - Fix session leak: `_cleanup_box_stdio_session()` now runs in `finally` block of `_lifecycle_loop`, covering all exit paths - Fix retry logic: `_ready_event` is only set after all retries exhaust or on success, not on first failure - Enhance `get_runtime_info_dict()` with `box_session_id` and `box_enabled` ### Box security (security.py — new) - `validate_sandbox_security()` blocks dangerous host paths: `/etc`, `/proc`, `/sys`, `/dev`, `/root`, `/boot`, `/run`, docker.sock, podman socket - Called at the start of `CLISandboxBackend.start_session()` ### Box models (models.py) - Add `BoxHostMountMode.NONE` — skips volume mount entirely - Adjust `validate_host_mount_consistency` to allow arbitrary workdir when `host_path_mode=NONE` ### Box backend (backend.py) - Add `validate_sandbox_security()` call in `start_session()` - Add `langbot.box.config_hash` label on containers for drift detection - Handle `BoxHostMountMode.NONE` — skip `-v` mount arg - Add `cleanup_orphaned_containers()` to base class (no-op default) and CLI implementation (single batched `rm -f` command) ### Box runtime (runtime.py) - Call `cleanup_orphaned_containers()` during `initialize()` to remove lingering containers from previous runs ### Box service (service.py) - Graceful degradation: `initialize()` catches runtime errors and sets `available=False` instead of crashing LangBot startup - Add `available` property and guard on `execute_sandbox_tool()` - Add `skip_host_mount_validation` parameter to `build_spec()` and `create_session()` — MCP paths are admin-configured and trusted, bypassing `allowed_host_mount_roots` restrictions meant for LLM-generated sandbox_exec commands ### Default behavior - stdio MCP servers automatically use Box when `box_service.available` is True (Podman/Docker detected); no explicit `box` config needed - When no container runtime exists, falls back to host-direct stdio - MCP Box defaults: `network=on` (for pip install), `read_only_rootfs=false` (for site-packages), `host_path_mode=ro`, `startup_timeout=120s` ### Tests - `test_box_security.py`: blocked paths, safe paths, subpath rejection - `test_mcp_box_integration.py`: config model, path rewriting, venv unwrap, host_path inference, payload building, runtime info, box availability check - `test_box_service.py`: `BoxHostMountMode.NONE` validation tests * feat(box/mcp): instance-based orphan cleanup, error classification, session API, and integration tests ## Changes ### Precise orphan container cleanup - Runtime generates a unique instance_id on startup - Every container gets a `langbot.box.instance_id` label - `cleanup_orphaned_containers()` only removes containers from previous instances, preserving containers owned by the current one - Containers from older versions (no label) are also cleaned up - `cleanup_orphaned_containers` added to `BaseSandboxBackend` as a no-op default method, removing hasattr duck-typing ### Fine-grained MCP error classification - New `MCPSessionErrorPhase` enum with 7 phases: session_create, dep_install, process_start, relay_connect, mcp_init, runtime, tool_call - Each phase in `_init_box_stdio_server()` sets the error phase before re-raising, enabling precise failure diagnosis - `retry_count` tracked across retry attempts - `get_runtime_info_dict()` exposes `error_phase` and `retry_count` ### GET /v1/sessions/{id} API - `BoxRuntime.get_session()` returns session details including managed process info when present - `handle_get_session` HTTP handler + route in server.py - `BoxRuntimeClient.get_session()` abstract method + remote impl ### stdio defaults to Box when runtime is available - `_uses_box_stdio()` checks `box_service.available` instead of requiring explicit `box` key in server_config - `BoxService.initialize()` catches runtime errors gracefully, sets `available=False` instead of crashing LangBot startup - When no container runtime exists, stdio MCP falls back to host-direct execution ### Code quality (from /simplify review) - Extracted `_VENV_DIRS` / `_VENV_BIN_DIRS` module-level constants - Removed dead `_box_network_mode()` method and unused `bc` variable - Fixed broken import `from ....box.models` → `from ...box.models` - Cached `_resolve_host_path()` result — computed once, passed through - Config hash now includes `host_path` field - Batched orphan cleanup into single `rm -f` command ### Session leak fix - `_cleanup_box_stdio_session()` now runs in `_lifecycle_loop`'s finally block, covering all exit paths (normal shutdown, error, retry, final failure) ### Integration tests - 6 end-to-end tests covering managed process lifecycle, WebSocket stdio bidirectional IO, session cleanup verification, single session query, process exit detection, and orphan cleanup safety * refactor: use rpc * fix: import * refactor(box): clean up sandbox subsystem code quality and efficiency - Fix O(n²) stderr trimming in runtime.py with running length tracker - Remove dead code: RESERVED_CONTAINER_PATHS, _subprocess_wait_task, unused config_hash computation, unused imports - Deduplicate connection callback in BoxRuntimeConnector, parse URL once - Use enum comparison instead of stringly-typed spec.network.value check - Replace manual _result_to_dict/_session_to_dict with model_dump() - Cache NativeToolLoader tool definition and sandbox system guidance - Extract _is_path_under() helper to eliminate duplicated path checks - Import SANDBOX_EXEC_TOOL_NAME from native.py instead of redefining - Add JSON startswith guard in logging_utils to skip futile json.loads - Fix ruff lint errors (F401 unused imports, F841 unused variables) * fix: ruff * refactor(sandbox): keep box logic out of pipeline and localagent - Move sandbox system-prompt guidance from LocalAgentRunner into BoxService.get_system_guidance() so all box domain knowledge stays in the box module. - Remove standalone logging_utils.py; merge format_result_log() into MessageHandler base class alongside cut_str(). - Strip sandbox-specific JSON parsing from log formatting; tool results now use generic truncation. - Revert TYPE_CHECKING changes in stage.py and runner.py that were unrelated to this feature. - Skip two test files affected by a pre-existing circular import (runner ↔ app) until the import cycle is resolved in a separate PR. * refactor(box): move box runtime to langbot-plugin-sdk Extract self-contained box runtime modules (actions, backend, client, errors, models, runtime, security, server) to langbot-plugin-sdk and update all imports to use `langbot_plugin.box.*`. Keep only service and connector in LangBot core as they depend on the Application context. - Update docker-compose to use `langbot_plugin.box.server` entry point - Update pyproject.toml to use local SDK via `tool.uv.sources` - Remove migrated source files and their unit/integration tests - Update remaining test imports to match new module paths * fix: ruff * fix(box): tighten sandbox exposure and restore box integration coverage * refactor(types): remove quoted annotations under postponed evaluation * chore(sandbox): move MCP loader changes to follow-up branch * refactor(plugins): simplify GitHub install flow to default master archive * revert(api): restore plugin GitHub import flow in plugins controller * Improve data-root handling and skill install previews * Add managed skill authoring tools for local agents * Refactor the skills UI around sidebar detail pages * Document why managed skill authoring tools bypass box * fix: lint * feat(web): refactor plugin/skill install flows and fix skills page - Fix sidebar skill icon - Add skills route and error page component - Refactor plugin GitHub install from dialog modal to inline card - Add skill install dropdown menu (create/upload/github) in sidebar - Wire sidebar → skills page communication via pendingSkillInstallAction context - Add i18n keys for error page and skill install actions * fix(web): persist sidebar collapsible section open state on navigation Sections opened via sub-item navigation now retain their expanded state when the user switches to a different section, instead of collapsing because the isActive fallback becomes false. --------- Co-authored-by: youhuanghe <1051233107@qq.com> Co-authored-by: Claude Opus 4.6 (1M context) <noreply@anthropic.com> Co-authored-by: Junyan Qin <rockchinq@gmail.com>

huanghuoguoguo force-pushed the feat/agentskills branch from 070f9b7 to 39aea83 Compare March 22, 2026 08:10

huanghuoguoguo changed the base branch from master to feat/sandbox March 22, 2026 08:15

huanghuoguoguo force-pushed the feat/agentskills branch 4 times, most recently from e788306 to 1368337 Compare March 26, 2026 06:04

huanghuoguoguo force-pushed the feat/sandbox branch from 8f111a5 to 6007b79 Compare March 27, 2026 02:27

huanghuoguoguo force-pushed the feat/agentskills branch from 1368337 to 221e1f7 Compare March 27, 2026 03:10

huanghuoguoguo force-pushed the feat/sandbox branch from 6007b79 to 726da24 Compare March 28, 2026 01:11

RockChinQ force-pushed the feat/agentskills branch from 15aaf16 to 505ff0d Compare April 4, 2026 02:13

huanghuoguoguo force-pushed the feat/sandbox branch from 726da24 to 1f958e8 Compare April 8, 2026 01:52

fdc310 and others added 13 commits April 8, 2026 01:59

fix: resolve cherry-pick conflicts for agentskills onto sandbox

a71c793

- Remove non-existent external_kb service import - Add skill_mgr mock to localagent sandbox_exec tests - Keep database version at 24 (sandbox branch's latest)

fix: test info

e6e53e2

feat: simplify langbot skill create and import

cc6317d

refactor(skills): clean up legacy skill API and harden activation flow

50b21e1

refactor(skills): remove skill dependency expansion and add skill_get

8381088

fix: lint

3ec3297

fix: delete

2bab663

fix(skills): align tool manager loader initialization

8cb7edc

refactor: remove sandbox execute skill

0066abb

fix(skills): hide activation markers and isolate skill activation flow

12e0f2f

huanghuoguoguo and others added 23 commits April 8, 2026 01:59

feat(box): add obs

5a8ea4f

refactor(box): unify box service lifecycle and local runtime

729a54a

management

refactor: use rpc

45ede51

fix: import

5a87728

fix: ruff

0ae9d3c

fix: ruff

c4a3588

fix(box): tighten sandbox exposure and restore box integration coverage

ff1c795

refactor(types): remove quoted annotations under postponed evaluation

2374231

chore(sandbox): move MCP loader changes to follow-up branch

21f14ec

refactor(plugins): simplify GitHub install flow to default master arc…

461ea21

…hive

revert(api): restore plugin GitHub import flow in plugins controller

fbdcf9e

Improve data-root handling and skill install previews

3b57f9a

Add managed skill authoring tools for local agents

be5a62e

Refactor the skills UI around sidebar detail pages

f41fa56

Document why managed skill authoring tools bypass box

d68b20c

fix: lint

9a97e96

huanghuoguoguo force-pushed the feat/agentskills branch from 211df8a to f6b8843 Compare April 8, 2026 02:02

fix(web): persist sidebar collapsible section open state on navigation

916257f

Sections opened via sub-item navigation now retain their expanded state when the user switches to a different section, instead of collapsing because the isActive fallback becomes false.

huanghuoguoguo merged commit f73a1ee into feat/sandbox Apr 8, 2026
1 of 6 checks passed

huanghuoguoguo deleted the feat/agentskills branch April 8, 2026 09:07

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

feat(skills): add Agent Skills management system#1917

feat(skills): add Agent Skills management system#1917
huanghuoguoguo merged 46 commits intofeat/sandboxfrom
feat/agentskills

fdc310 commented Jan 13, 2026

Uh oh!

huanghuoguoguo commented Mar 22, 2026

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants

Conversation

fdc310 commented Jan 13, 2026

概述 / Overview

更改前后对比截图 / Screenshots

检查清单 / Checklist

PR 作者完成 / For PR author

项目维护者完成 / For project maintainer

Uh oh!

huanghuoguoguo commented Mar 22, 2026

Update: package-backed skills + sandbox execution

初始 commit 做了什么

后续做了什么改动

后续计划

Uh oh!

Uh oh!

Reviewers

Assignees

Labels

Projects

Milestone

Development

Uh oh!

3 participants