mirror of
https://github.com/AstrBotDevs/AstrBot
synced 2026-07-16 09:40:30 +08:00
* Add legacy session waiter compatibility * Expand legacy astrbot package compatibility * Tighten external legacy plugin compatibility smoke tests * Consolidate controlled legacy facade compatibility * docs: clarify compat package boundaries * test: align runtime fixtures with maintained samples * fix: preserve unicode sample fixtures in runtime tests * Implement legacy hook and tool compat runtime * Refactor legacy runtime execution boundary * 增强旧版兼容性,添加多个旧路径入口和相关功能 * 增强旧版兼容性,添加适配器边界的启动和关闭钩子支持 * Refactor legacy API and LLM compatibility logic - Moved legacy LLM and tool compatibility logic from `_legacy_api.py` to a new module `_legacy_llm.py` for better organization and separation of concerns. - Updated `_legacy_api.py` to import necessary components from `_legacy_llm.py`, removing redundant code. - Enhanced database client functionality by adding support for batch read/write operations and change event subscriptions. - Improved documentation in the database client and capability router to reflect new features. - Refined environment management process in the loader to better handle plugin grouping and virtual environment management. * 补充插件分组环境测试覆盖 * feat: Enhance CLI and testing capabilities - Added a new script entry point `astrbot-sdk` in `pyproject.toml`. - Introduced `has_waiter` method in `SessionWaiterManager` to check for existing waiters. - Updated `cli.py` to improve error handling and added context to error messages. - Implemented local development support in `cli.py` with a new `dev` command for running plugins against a mock core. - Created a new testing module `astrbot_sdk.testing` with utilities for local development and plugin testing. - Added comprehensive tests for the new testing module and CLI commands. - Improved compatibility and error messaging for plugin loading failures. * feat: 添加插件初始化、验证和构建命令,增强 CLI 功能 * feat: add platform client documentation and examples - Introduced platform client documentation in `docs/v4/clients/platform.md` detailing methods for sending messages, images, and managing group members. - Added example plugins for LLM chat and database functionalities in `docs/v4/examples/README.md`, `docs/v4/examples/llm-chat/README.md`, and `docs/v4/examples/database/README.md`. - Enhanced quickstart guide with links to new documentation and example plugins. - Implemented runtime contract tests to ensure compatibility of public capabilities and hooks. * Refactor legacy runtime handling and improve plugin loading - Updated `handler_dispatcher.py` to streamline legacy runtime preparation and dispatching results. - Enhanced `loader.py` to simplify legacy plugin detection and manifest building. - Added tests for new HTTPClient and MetadataClient functionalities. - Introduced tests for legacy context metadata methods and legacy loader helpers. - Improved legacy runtime tests to cover new functionality and edge cases. * refactor: 更新兼容层和导入路径,优化文档描述 * Support grouped plugin workers in shared environments - add group metadata driven worker startup for shared env plans - track per-plugin handler and capability ownership inside grouped workers - update runtime and smoke tests for grouped worker session behavior * Add v4 compat layer and legacy shims - Introduce private v4 compatibility surface using _legacy_api.py, _legacy_runtime.py, _legacy_loader.py plus new _legacy_context.py and _legacy_star.py to centralize legacy adapters while keeping public APIs thin. - Extend InitializeOutput to carry protocol_version for negotiated protocol, enabling runtime to adapt to the chosen v4 version. - Add lightweight legacy support for Star/Context via new LegacyStar and LegacyContext shims and expose legacy API through the aggregate _legacy_api entry point. - Ensure legacy loader preserves class declaration order by iterating module.__dict__ instead of relying on alphabetical sorting. - Add tests: protocol_version handling in InitializeOutput, legacy main component order preservation, and embedded-newline framing in transport tests. * Add architecture doc and refine API compat - Add PROJECT_ARCHITECTURE.md documenting architecture, compat surface, and testing notes. - Update astrbot_sdk.api.__init__ to clarify it is a compatibility implementation layer, not a simple facade, and list migration targets. - Normalize platform in AstrMessageEvent.to_payload to emit a string id by using get_platform_id(). * Potential fix for pull request finding Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> * delete old sdk * delete old sdk (#7) Co-authored-by: whatevertogo <whatevertogo@users.noreply.github.com> * feat(cli): normalize plugin init skeletons Add interactive plugin init prompts and normalize generated plugin names to the astrbot_plugin_ convention. Update CLI tests for the new skeleton layout and ignore generated plugin directories in git and coverage tooling. Also include related runtime logging adjustments from the current worktree. * Create lint.yml * Update lint.yml * clean it * feat: Enhance handler and capability dispatchers with improved error handling - Updated HandlerDispatcher to raise TypeError for uninjectable required parameters, logging errors appropriately. - Refactored CapabilityDispatcher to raise TypeError for missing required parameters during capability execution. - Renamed _load_plugin_config to load_plugin_config for clarity and consistency. - Introduced _sync_plugin_registry method in SupervisorRuntime to manage plugin capabilities more effectively. - Enhanced capability registration logic to handle naming conflicts with better logging and automatic renaming. - Added tests for handler and capability dispatchers to ensure proper error handling and functionality. - Implemented new HTTP and metadata capabilities with corresponding tests for registration and retrieval. - Improved MemoryClient methods with additional tests for save_with_ttl, get_many, delete_many, and stats. - Added tests for the testing module to ensure proper import and functionality of PluginHarness. * feat: 更新 SDK 描述,重构插件调用上下文,移除插件 ID 传递,增强能力路由和 HTTP 客户端的插件身份管理 * refactor: 更新文档和代码注释,优化兼容性描述,增强可读性 * feat: 添加插件热重载功能,支持文件变更时自动重新加载插件 * feat: 增强错误处理,添加上下文信息,优化插件组件加载和参数注入校验 * feat: 添加 hello_plugin 示例,包含插件结构、命令处理和测试用例 * refactor: 删除过时的架构文档、变更日志和兼容矩阵文件 * refactor: 更新兼容层弃用通知,优化文档结构和可读性 * refactor: 更新项目架构文档,增强能力客户端和执行边界的描述,移除兼容层设计章节 * feat(errors): Enhance AstrBotError with detailed documentation and examples feat(events): Expand MessageEvent with reply capabilities and detailed docstrings fix(loader): Ensure plugin path is correctly managed in sys.path feat(star): Improve Star class documentation and lifecycle method descriptions feat(testing): Add plugin metadata handling in MockContext and enhance PluginHarness feat(hello): Refactor HelloPlugin to utilize new reply methods and structured capabilities test(decorators): Add tests for input/output model support in provide_capability test(events): Implement tests for reply_image and reply_chain methods in MessageEvent test(http): Validate API registration with capability handler references and error handling test(tests): Enhance tests for plugin harness and directory handling in dev commands * feat(runtime): add configurable msgpack wire codec support * fix(runtime): align msgpack framing with transport defaults * fix(runtime): preserve json transport compatibility * fix(cli): scope worker wire codec option * feat: 添加 AGENTS.md 文档,描述 v4 架构约束和开发命令 refactor: 更新 HandlerDispatcher 和 WorkerSession,增强参数处理和结果汇总逻辑 * fix(test): 更新 init_plugin 测试以匹配新的目录命名规范 CLI 的 _normalize_init_plugin_name 函数现在自动添加 astrbot_plugin_ 前缀, 测试期望的目录名从 demo_plugin 更新为 astrbot_plugin_demo_plugin。 * Refactor worker initialization and remove unused codec parameters; add schedule and session waiter modules - Simplified `GroupWorkerRuntime` and `PluginWorkerRuntime` constructors by removing the codec parameter and related logic. - Introduced `schedule.py` to define `ScheduleContext` for managing scheduled tasks with a clear structure and payload handling. - Added `session_waiter.py` for session-based conversational flow management, including `SessionController` and `SessionWaiterManager` for handling multi-turn dialogues. - Enhanced testing utilities in `testing.py` by removing unused classes and streamlining the structure. - Created `types.py` to introduce `GreedyStr` for improved command parameter parsing. * feat: 添加 LLM 工具管理和会话级别状态管理能力 - 新增 llm/ 模块,包含 LLMToolSpec、ProviderRequest、AgentSpec 等实体 - 新增 LLMToolManager 用于管理 LLM 工具注册和激活状态 - 新增 SessionPluginManager 用于会话级别的插件启用状态管理 - 新增 SessionServiceManager 用于会话级别的 LLM/TTS 服务状态管理 - 新增 RegistryClient 用于查询 handler 元数据和设置白名单 - 扩展 CapabilityRouter 内置能力,支持 session.* 和 registry.* 命名空间 - 增强描述符和装饰器以支持新的 trigger 类型 * feat: 大幅增强 SDK 核心功能和文档 新增模块: - clients/files.py: 文件上传/下载客户端 - clients/managers.py: 会话/LLM/Provider 管理器 - clients/provider.py: LLM Provider 客户端 - conversation.py: 对话上下文管理 - plugin_kv.py: 插件 KV 存储辅助 - runtime/limiter.py: 限流器 - star_tools.py: Star 工具函数 - docs/: 完整的 SDK 使用文档 (01-05) 功能增强: - Context 大幅扩展,增加 reply/send_image/typing 等便捷方法 - 装饰器增强,支持 on_llm_request/on_provider_request 等 - 内置 schemas 扩展,覆盖更多 capability 定义 - capability_router_builtins 大幅扩展内置能力实现 - handler_dispatcher 增强参数注入和错误处理 - Star 基类增加生命周期钩子和工具方法 * Add comprehensive API documentation for types and utilities in AstrBot SDK - Introduced `types.md` detailing type aliases, generics, and Pydantic models used in the SDK. - Added `utils.md` covering utility classes and functions including CancelToken, MessageSession, command groups, and session management. - Included usage examples and detailed descriptions for each component to enhance developer understanding and ease of use. * feat: 添加高级方法和辅助函数文档,增强消息组件和事件处理功能 * feat: 增强过滤器类型和能力路由文档,添加 Provider 和会话管理功能 * change location * delete no need thing * delete again * feat: add Star plugin base class and StarTools utility class - Introduced `Star` class as a base for v4 native plugins, providing lifecycle methods and context management. - Added `StarTools` class for accessing runtime context and managing LLM tools. - Implemented `PluginHarness` for local development and testing of plugins, allowing for message dispatching and lifecycle management. - Created `GreedyStr` type for enhanced command parameter parsing, enabling the capture of remaining command text as a single argument. - Added testing utilities and mock capabilities for plugin development. * delete: remove hello_plugin example and its related files * Remove obsolete test files for testing module, top-level modules, transport, and wire codecs - Deleted `test_testing_module.py` as it is no longer needed. - Removed `test_top_level_modules.py` which had no content. - Eliminated `test_transport.py` due to redundancy. - Cleared out `test_wire_codecs.py` as part of the cleanup. * fix(runtime): avoid creating Star instance in on_error fallback * fix(runtime): avoid virtual dispatch in Star.on_error fallback * refactor(runtime): unify command matching logic (#25) * refactor(testing): share command matching with handler dispatcher * fix:添加公共函数文件 * fix: simplify register_task completion handling (#27) * fix: simplify register_task completion handling Remove duplicated cancellation logging in Context.register_task while keeping Future inputs compatible with asyncio.create_task semantics. Add regression coverage for coroutine, Future, cancellation, and failure paths. * fix: prioritize local src in tests_v4 Ensure tests_v4 always imports the working tree package by moving src to sys.path[0] even when another checkout or installed copy is already present. * chore: sync subtree from AstrBot * feat: replay non-sdk changes on clean sdk subtree baseline * feat(sdk): add merged provider config capability support Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * feat(sdk): add merged provider config bridge and client Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * feat(sdk): add merged provider config capability support Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * fix(sdk): tighten bridge cast typing Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * feat(sdk): add merged provider config bridge and client Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * test(sdk): cover merged provider config parity Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * feat: 完善 memory 向量检索与索引统计 (#28) Co-authored-by: united_pooh <united_pooh@outlook.com> * feat(tests): 添加测试用例以验证 register_task 的行为并更新测试运行说明 * Merge commit 'e45bade147ff44b43860ecff12067309e59c151a' into feat/sdk-integration * Squashed 'astrbot-sdk/' changes from 7dda6077..85342f1485342f14feat(tests): 添加测试用例以验证 register_task 的行为并更新测试运行说明fdffc09bMerge pull request #26 from united-pooh/fix/fix-star-on-error-fallback3b09747cfeat: 完善 memory 向量检索与索引统计 (#28)665c9c69fix(runtime): avoid virtual dispatch in Star.on_error fallback200559a5fix(runtime): avoid creating Star instance in on_error fallback git-subtree-dir: astrbot-sdk git-subtree-split:85342f149b* feat(tests): 添加测试用例以验证平台和消息类型过滤器的冲突处理 * docs: remove redundant testing instructions from AGENTS.md * docs: remove redundant testing instructions from AGENTS.md * docs: remove redundant testing instructions from AGENTS.md * Merge commit '5ac9401852ddb46f337da6bcc0f9b66eed265da9' into feat/sdk-integration * Squashed 'astrbot-sdk/' changes from 85342f14..09beabeb09beabebfeat(tests): 添加测试用例以验证平台和消息类型过滤器的冲突处理 git-subtree-dir: astrbot-sdk git-subtree-split:09beabeb62* feat: enhance SDK plugin configuration handling and logging * feat: enhance SDK plugin configuration handling and logging * feat: enhance SDK plugin configuration handling and logging * feat: 增强装饰器功能,添加会话命令支持及相关权限和限流装饰器 * feat: 增强装饰器功能,添加会话命令支持及相关权限和限流装饰器 * feat: 增强装饰器功能,添加会话命令支持及相关权限和限流装饰器 * feat: 更新文档以反映SDK负载的JSON可序列化要求和延迟导入设计约束 * feat: add conversation.get_current capability and related schemas - Introduced CONVERSATION_GET_CURRENT_INPUT_SCHEMA and CONVERSATION_GET_CURRENT_OUTPUT_SCHEMA for handling current conversation requests. - Implemented _conversation_get_current method in BuiltinCapabilityRouterMixin to manage current conversation retrieval and creation. - Registered the new capability in CoreCapabilityBridge. - Enhanced HandlerDispatcher to inject provider request, LLM response, and event result payloads into the event handling process. - Updated tests to validate the new functionality and ensure proper payload handling. * feat: add conversation.get_current capability and related schemas - Introduced CONVERSATION_GET_CURRENT_INPUT_SCHEMA and CONVERSATION_GET_CURRENT_OUTPUT_SCHEMA for handling current conversation requests. - Implemented _conversation_get_current method in BuiltinCapabilityRouterMixin to manage current conversation retrieval and creation. - Registered the new capability in CoreCapabilityBridge. - Enhanced HandlerDispatcher to inject provider request, LLM response, and event result payloads into the event handling process. - Updated tests to validate the new functionality and ensure proper payload handling. * feat: add conversation.get_current capability and related schemas - Introduced CONVERSATION_GET_CURRENT_INPUT_SCHEMA and CONVERSATION_GET_CURRENT_OUTPUT_SCHEMA for handling current conversation requests. - Implemented _conversation_get_current method in BuiltinCapabilityRouterMixin to manage current conversation retrieval and creation. - Registered the new capability in CoreCapabilityBridge. - Enhanced HandlerDispatcher to inject provider request, LLM response, and event result payloads into the event handling process. - Updated tests to validate the new functionality and ensure proper payload handling. * Refactor tool call handling in SdkPluginBridge - Introduced a dictionary to map tool call IDs to tool names for better clarity and efficiency. - Enhanced the extraction of tool call information from raw results, ensuring compatibility with both dictionary and object formats. - Updated the logic to retrieve tool names based on tool call IDs, improving the robustness of the tool calls result processing. * Refactor tool call handling in SdkPluginBridge - Introduced a dictionary to map tool call IDs to tool names for better clarity and efficiency. - Enhanced the extraction of tool call information from raw results, ensuring compatibility with both dictionary and object formats. - Updated the logic to retrieve tool names based on tool call IDs, improving the robustness of the tool calls result processing. * Refactor tool call handling in SdkPluginBridge - Introduced a dictionary to map tool call IDs to tool names for better clarity and efficiency. - Enhanced the extraction of tool call information from raw results, ensuring compatibility with both dictionary and object formats. - Updated the logic to retrieve tool names based on tool call IDs, improving the robustness of the tool calls result processing. * feat: add session and system capabilities for plugin management and event handling - Implemented SessionCapabilityMixin with methods to manage session-level plugin states and handlers. - Added SystemCapabilityMixin to handle system-level functionalities including file management, event handling, and dynamic command registration. - Introduced methods for enabling/disabling plugins, filtering handlers, and managing LLM and TTS service states. - Registered various system capabilities for data directory access, HTML rendering, and event streaming. * feat: add session and system capabilities for plugin management and event handling - Implemented SessionCapabilityMixin with methods to manage session-level plugin states and handlers. - Added SystemCapabilityMixin to handle system-level functionalities including file management, event handling, and dynamic command registration. - Introduced methods for enabling/disabling plugins, filtering handlers, and managing LLM and TTS service states. - Registered various system capabilities for data directory access, HTML rendering, and event streaming. * Squashed 'astrbot-sdk/' changes from 09beabeb..3204c9db3204c9dbMerge sdk-remote dev into feat/sdk-integration3a2d715eRefactor tool call handling in SdkPluginBridgeed1b9665feat: add conversation.get_current capability and related schemase74123bbfeat: 增强装饰器功能,添加会话命令支持及相关权限和限流装饰器bb361cf9feat: 增强装饰器功能,添加会话命令支持及相关权限和限流装饰器c6237f52Merge sdk-remote/dev into astrbot-sdk subtreee12029fffeat: enhance SDK plugin configuration handling and logging5e54bbb3feat: enhance SDK plugin configuration handling and loggingf48e2041Merge commit '5ac9401852ddb46f337da6bcc0f9b66eed265da9' into feat/sdk-integration619672e6Merge commit '5ac9401852ddb46f337da6bcc0f9b66eed265da9' into feat/sdk-integrationd5a3796ddocs: remove redundant testing instructions from AGENTS.md323e3f4ddocs: remove redundant testing instructions from AGENTS.mdf8438a7bMerge commit 'e45bade147ff44b43860ecff12067309e59c151a' into feat/sdk-integration96d1df85Merge commit 'e45bade147ff44b43860ecff12067309e59c151a' into feat/sdk-integrationf8a7e253feat(sdk): add merged provider config bridge and client752dc6cffeat(sdk): add merged provider config capability support git-subtree-dir: astrbot-sdk git-subtree-split:3204c9db9f* Implement feature X to enhance user experience and optimize performance * Implement feature X to enhance user experience and optimize performance * chore(sdk): stop tracking uv.lock * feat(sdk): add merged provider config capability support Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * feat(sdk): add merged provider config bridge and client Ultraworked with [Sisyphus](https://github.com/code-yeongyu/oh-my-openagent) Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> * feat(tests): 添加测试用例以验证 register_task 的行为并更新测试运行说明 * feat(tests): 添加测试用例以验证平台和消息类型过滤器的冲突处理 * docs: remove redundant testing instructions from AGENTS.md * feat: enhance SDK plugin configuration handling and logging * feat: 增强装饰器功能,添加会话命令支持及相关权限和限流装饰器 * feat: add conversation.get_current capability and related schemas - Introduced CONVERSATION_GET_CURRENT_INPUT_SCHEMA and CONVERSATION_GET_CURRENT_OUTPUT_SCHEMA for handling current conversation requests. - Implemented _conversation_get_current method in BuiltinCapabilityRouterMixin to manage current conversation retrieval and creation. - Registered the new capability in CoreCapabilityBridge. - Enhanced HandlerDispatcher to inject provider request, LLM response, and event result payloads into the event handling process. - Updated tests to validate the new functionality and ensure proper payload handling. * Refactor tool call handling in SdkPluginBridge - Introduced a dictionary to map tool call IDs to tool names for better clarity and efficiency. - Enhanced the extraction of tool call information from raw results, ensuring compatibility with both dictionary and object formats. - Updated the logic to retrieve tool names based on tool call IDs, improving the robustness of the tool calls result processing. * feat: add session and system capabilities for plugin management and event handling - Implemented SessionCapabilityMixin with methods to manage session-level plugin states and handlers. - Added SystemCapabilityMixin to handle system-level functionalities including file management, event handling, and dynamic command registration. - Introduced methods for enabling/disabling plugins, filtering handlers, and managing LLM and TTS service states. - Registered various system capabilities for data directory access, HTML rendering, and event streaming. * fix(runtime): avoid creating Star instance in on_error fallback * fix(runtime): avoid virtual dispatch in Star.on_error fallback * feat: refactor injected parameter handling and introduce is_framework_injected_parameter utility * Squashed 'astrbot-sdk/' changes from 027c15b4..d078e510d078e510feat: refactor injected parameter handling and introduce is_framework_injected_parameter utility461f7276Merge branch 'dev' of https://github.com/united-pooh/astrbot-sdk into dev5ead59c4fix(runtime): avoid virtual dispatch in Star.on_error fallbackd2382858fix(runtime): avoid creating Star instance in on_error fallbacke961e361feat: add session and system capabilities for plugin management and event handling5a46321aRefactor tool call handling in SdkPluginBridge47698448feat: add conversation.get_current capability and related schemas9b35bec8feat: 增强装饰器功能,添加会话命令支持及相关权限和限流装饰器48a20240feat: enhance SDK plugin configuration handling and loggingcb593a53docs: remove redundant testing instructions from AGENTS.mdf4942076feat(tests): 添加测试用例以验证平台和消息类型过滤器的冲突处理b0f8b2d6feat(tests): 添加测试用例以验证 register_task 的行为并更新测试运行说明6e417c6dfeat(sdk): add merged provider config bridge and client659eabcefeat(sdk): add merged provider config capability support REVERT:027c15b4Implement feature X to enhance user experience and optimize performance REVERT:c272661fchore: pull sdk subtree from dev (resolve delete/modify conflict) REVERT:0a2a3592feat: add session and system capabilities for plugin management and event handling REVERT:3204c9dbMerge sdk-remote dev into feat/sdk-integration REVERT:36443f1dRefactor tool call handling in SdkPluginBridge REVERT:3a2d715eRefactor tool call handling in SdkPluginBridge REVERT:b93c2c2bfeat: add conversation.get_current capability and related schemas REVERT:ed1b9665feat: add conversation.get_current capability and related schemas REVERT:e74123bbfeat: 增强装饰器功能,添加会话命令支持及相关权限和限流装饰器 REVERT:bb361cf9feat: 增强装饰器功能,添加会话命令支持及相关权限和限流装饰器 REVERT:c6237f52Merge sdk-remote/dev into astrbot-sdk subtree REVERT:e12029fffeat: enhance SDK plugin configuration handling and logging REVERT:5e54bbb3feat: enhance SDK plugin configuration handling and logging REVERT:f48e2041Merge commit '5ac9401852ddb46f337da6bcc0f9b66eed265da9' into feat/sdk-integration REVERT:619672e6Merge commit '5ac9401852ddb46f337da6bcc0f9b66eed265da9' into feat/sdk-integration REVERT:d5a3796ddocs: remove redundant testing instructions from AGENTS.md REVERT:323e3f4ddocs: remove redundant testing instructions from AGENTS.md REVERT:f8438a7bMerge commit 'e45bade147ff44b43860ecff12067309e59c151a' into feat/sdk-integration REVERT:96d1df85Merge commit 'e45bade147ff44b43860ecff12067309e59c151a' into feat/sdk-integration REVERT:f8a7e253feat(sdk): add merged provider config bridge and client REVERT:752dc6cffeat(sdk): add merged provider config capability support git-subtree-dir: astrbot-sdk git-subtree-split:d078e51051* refactor: reorganize imports and enhance type hints in sdk_bridge modules * refactor: update import paths to use Path for better compatibility * refactor(injection): centralize legacy injected parameter filtering * fix(testing): use public session waiter probe in PluginHarness * docs: add TODO for documentation content in _command_model.py * feat: add memory management capabilities to CoreCapabilityBridge and implement unit tests * feat: enhance memory search functionality and improve metadata retrieval in SDK * feat: add memory management attributes and typed provider method to CapabilityMixinHost * Implement feature X to enhance user experience and optimize performance * Refactor memory utility functions and enhance memory capability mixin - Added new utility functions for memory management in _memory_utils.py. - Refactored memory capability mixin methods to utilize the new utility functions for better readability and maintainability. - Updated PROJECT_ARCHITECTURE.md to reflect changes in documentation and structure. * Squashed 'astrbot-sdk/' changes from d078e510..208bc591208bc591Merge pull request #30 from united-pooh/refactor/unify-legacy-injected-paramsd86534a2docs: add TODO for documentation content in _command_model.py090724a7refactor(injection): centralize legacy injected parameter filtering git-subtree-dir: astrbot-sdk git-subtree-split:208bc591dd* Initial plan * docs: fix path, Python version, and client API table in PROJECT_ARCHITECTURE.md Co-authored-by: whatevertogo <149563971+whatevertogo@users.noreply.github.com> * Squashed 'astrbot-sdk/' changes from 208bc591..ad5e8d13ad5e8d13Merge pull request #37 from united-pooh/sdk/whatevertogo5751701fMerge pull request #38 from united-pooh/copilot/sub-pr-37e21acba5docs: fix path, Python version, and client API table in PROJECT_ARCHITECTURE.mdee67cab4Initial plan7d921570Refactor memory utility functions and enhance memory capability mixin git-subtree-dir: astrbot-sdk git-subtree-split:ad5e8d1397* docs: fix TODO comment formatting in _command_model.py * 集成SDK命令候选项,优化Telegram和Discord平台适配器的命令收集逻辑 * 删除AI女友插件的单元测试文件 * 更新文档,添加Telegram和Discord原生命令菜单的注册说明 * Squashed 'astrbot-sdk/' changes from ad5e8d13..5003da585003da58Merge pull request #40 from united-pooh/sdk/whatevertogob5084c44Merge branch 'sdk/whatevertogo' of https://github.com/united-pooh/astrbot-sdk into sdk/whatevertogo7559edf7docs: fix TODO comment formatting in _command_model.py git-subtree-dir: astrbot-sdk git-subtree-split:5003da58f5* fix(testing): route session waiter followups through dispatcher (#33) * fix(testing): route session waiter followups through dispatcher * fix(testing): preserve waiter context and completion state * fix(runtime): preserve session waiter plugin identity * fix(runtime): scope session waiters by plugin * fix(testing): isolate waiter replacement and followup drains * fix(runtime): normalize waiter routing inputs * fix(cli): route protocol stdout at command entry (#41) * 添加内存后端支持,优化插件内存管理逻辑 * feat(memory): enhance memory schemas and add namespace support - Updated MEMORY_SEARCH_INPUT_SCHEMA to include `namespace` and `include_descendants`. - Modified MEMORY_SEARCH_OUTPUT_SCHEMA to allow nullable `namespace`. - Added `namespace` to MEMORY_GET_INPUT_SCHEMA, MEMORY_DELETE_INPUT_SCHEMA, MEMORY_SAVE_WITH_TTL_INPUT_SCHEMA, MEMORY_GET_MANY_INPUT_SCHEMA, and MEMORY_DELETE_MANY_INPUT_SCHEMA. - Enhanced MEMORY_STATS_INPUT_SCHEMA to support `namespace` and `include_descendants`. - Updated MEMORY_GET_OUTPUT_SCHEMA and MEMORY_STATS_OUTPUT_SCHEMA to include `namespace` and `namespace_count`. - Introduced `_memory_backends` in CapabilityRouterHost and CapabilityRouterBridgeBase for better memory management. - Refactored MemoryCapabilityMixin to utilize memory backends for plugin-specific memory operations. - Improved memory search functionality to respect namespaces and include descendants based on input parameters. - Added tests to validate memory operations across different namespaces and ensure persistence across restarts. - Implemented error handling in the handler dispatcher to manage exceptions gracefully. * fix: guard session_waiter blocking usage * fix(runtime): preserve request-scoped system event overlays * test(runtime): lock peer initialization and transport failure semantics * test(loader): cover plugin reload and import isolation regressions * refactor(supervisor): clarify plugin registry sync phases * test(clients): cover provider lifecycle regressions * feat(cli): improve astr init defaults * feat(plugin): add plugin ID validation and data directory resolution - Implemented `validate_plugin_id` to ensure safe plugin identifiers. - Added `resolve_plugin_data_dir` to resolve plugin data directories securely. - Updated memory and system capabilities to utilize new plugin ID validation. - Refactored session waiter management to simplify plugin ID handling. - Enhanced tests for plugin ID validation and data directory resolution. * fix(cli): exit cleanly on init abort * feat(memory): enhance namespace handling and add tests for memory client * feat(agent): add tool status message handling and improve SDK command integration * Refactor SDK structure for backward compatibility - Moved message result and session classes to internal modules while preserving legacy import paths for compatibility. - Updated imports across the SDK to reflect the new internal structure. - Enhanced session waiter management to support multiple plugins and improve error handling. - Added tests to ensure LLM tool registration and session waiter functionality align with dispatcher expectations. - Cleaned up code and improved documentation for clarity and maintainability. * 增强异步下载功能,更新组件导入方式,并添加相关测试用例 * 添加任务重入锁以支持会话等待器的嵌套清理,并更新相关测试用例以验证后续消息的序列化处理 * 添加 .astrbot_sdk_testing 到 .gitignore 文件 * Add unit tests for provider management and tool capabilities - Introduced new test suite for provider platform management in `test_sdk_provider_platform_management.py`, covering scenarios for merged provider configurations, reserved plugin checks, and provider management functionalities. - Added tests for tool capabilities and provider queries in `test_sdk_provider_tool_platform_capabilities.py`, validating interactions with LLM tools and specialized proxies. - Removed obsolete `test_sdk_transport.py` as it contained outdated tests for transport layer functionality. * 添加多个模块和测试用例,增强SDK功能并支持单元测试 * fix(bridge): add missing capability registrations for db/memory/http/metadata Register methods for db, memory, http, and metadata capabilities exist in BasicCapabilityMixin but were never called in CoreCapabilityBridge.__init__. This caused SDK plugins using ctx.memory, ctx.db, ctx.http to fail with "LookupError: capability not found". * feat(kb): enhance knowledge base capabilities with document management and serialization * 添加知识库文档管理功能,包括文档上传、列表、获取、删除和刷新能力,更新相关的能力路由和协议模式 * feat(conversation): add ability to unset conversation persona and update related methods * 添加对话管理和元数据管理功能,包括清空对话人格和保存插件配置的能力 * feat(conversation): add test for unsetting conversation persona and verify state * feat(plugin): add save_plugin_config method and related tests for plugin configuration persistence * 优化插件配置保存方法的代码格式 * feat(sdk): enhance handler metadata with descriptions, priority, kind, and admin requirements * 添加描述、优先级和其他元数据到处理程序元数据和描述符中,优化相关功能 * feat(sdk): enhance SDK integration with local extras handling and message payloads * 添加对 MessageEvent 的额外字段支持,优化事件处理器的参数注入,增强 SDK 本地临时数据的管理能力 * 增强插件日志记录功能,添加控制台输出格式化和路径标签支持,新增单元测试以验证日志格式 * feat: Enhance command and tool management in dashboard - Refactor CommandRoute to utilize AstrBotCoreLifecycle for improved command handling. - Introduce command_key for commands to streamline toggling, renaming, and permission updates. - Implement support for SDK commands in the dashboard, marking them as read-only. - Update ToolTable and CommandTable components to use new command_key and tool_key properties. - Add runtime_kind and plugin_id to tools for better management. - Enhance API tests to cover SDK commands and tools, ensuring proper functionality and error handling. - Update localization files to include new messages related to SDK commands. * 优化插件日志记录和能力代理模块,增强异常处理,确保优先级参数为整数 * feat: 增强LLM能力,添加聊天提供者协议和异常处理,更新单元测试以验证提供者有效性 * feat: Implement SDK skill management capabilities - Added SkillCapabilityMixin to handle skill registration, unregistration, and listing. - Integrated skill management into the CoreCapabilityBridge. - Enhanced SkillManager to support SDK-registered skills, including loading, saving, and syncing skills. - Updated computer_client to utilize SkillManager for skill synchronization with sandboxes. - Refactored skill export functionality in SkillsRoute to accommodate new skill management structure. - Introduced tests for SDK skill registration, unregistration, and syncing to ensure functionality. - Improved skill handling in the dashboard and test suite to reflect changes in skill management. * 添加技能注册功能,包含技能注册、注销和列出能力的实现,增强插件能力管理 * 删除CLAUDE.md文档,移除过时的已知问题描述 * 删除 AGENTS.md 文档,移除过时的架构约束和开发命令说明 * 更新测试用例,修复插件发现失败时的错误信息,确保使用正确的运行时字段 * 修复错误处理和权限检查,新增单元测试以验证功能 * format * 增强命名空间管理,优化数据库操作,添加 HTTP 路由验证,新增并发隔离测试,完善命令模型解析单元测试 * 增强 HTTP 路由功能,添加 HTTP 方法注销逻辑的单元测试 * 格式化日志输出,优化批量插入时无内容提供的调试信息 * fix: add uv dependency for plugin environment groups * 删除代码审查文档 CODE_REVIEW_ISSUES.md * 添加消息历史管理功能,包括消息记录的增删查改,完善相关能力混合类和测试用例 * 实现 SDK 消息历史管理功能,包括记录的增删查改操作 * Add unit tests for MCP contract and capabilities in SDK - Implemented `_mcp_contract.py` to test local MCP server functionalities including listing, enabling, and disabling servers. - Created `test_sdk_mcp_capabilities.py` to cover various aspects of the CoreCapabilityBridge and SdkPluginBridge, including session management and global MCP server operations. - Introduced fake classes to simulate MCP server behavior and manage tool configurations for testing. - Ensured comprehensive coverage of MCP session lifecycle, including opening, listing tools, calling tools, and closing sessions. * feat(mcp): Implement local and global MCP server management capabilities - Added MCP management client to the context for local/global MCP service management. - Introduced decorators to acknowledge global MCP risk for plugins. - Defined schemas for MCP server operations including get, list, enable, disable, and session management. - Created MCP capability mixin to handle local and global MCP server operations. - Enhanced provider capabilities to include active local MCP tool names. - Updated capability router to support MCP functionalities and maintain session state. - Added tests for MCP functionalities, ensuring proper behavior and risk acknowledgment. --------- Co-authored-by: whatevertogo <149563971+whatevertogo@users.noreply.github.com> Co-authored-by: whatevertogo <whatevertogo@users.noreply.github.com> Co-authored-by: letr <letr007@foxmail.com> Co-authored-by: united_pooh <united_pooh@outlook.com> Co-authored-by: Copilot Autofix powered by AI <175728472+Copilot@users.noreply.github.com> Co-authored-by: united_pooh <united_pooh@icloud.com> Co-authored-by: Lishiling <m18384519631@163.com> Co-authored-by: Li-shi-ling <114913764+Li-shi-ling@users.noreply.github.com> Co-authored-by: letr <123731298+letr007@users.noreply.github.com> Co-authored-by: Sisyphus <clio-agent@sisyphuslabs.ai> Co-authored-by: copilot-swe-agent[bot] <198982749+Copilot@users.noreply.github.com> Co-authored-by: catDforD <3276453835@qq.com> Co-authored-by: united_pooh <united_pooh@MBP-F6H6T2CYVV-2219.local>
637 lines
21 KiB
Python
637 lines
21 KiB
Python
from __future__ import annotations
|
|
|
|
import json
|
|
import os
|
|
import shutil
|
|
import uuid
|
|
from pathlib import Path
|
|
from typing import TYPE_CHECKING
|
|
|
|
from astrbot.api import logger
|
|
from astrbot.core.skills.skill_manager import SANDBOX_SKILLS_ROOT, SkillManager
|
|
from astrbot.core.star.context import Context
|
|
from astrbot.core.utils.astrbot_path import (
|
|
get_astrbot_skills_path,
|
|
get_astrbot_temp_path,
|
|
)
|
|
|
|
from .booters.base import ComputerBooter
|
|
from .booters.constants import BOOTER_BOXLITE, BOOTER_SHIPYARD, BOOTER_SHIPYARD_NEO
|
|
from .booters.local import LocalBooter
|
|
|
|
if TYPE_CHECKING:
|
|
from astrbot.core.agent.tool import FunctionTool
|
|
|
|
session_booter: dict[str, ComputerBooter] = {}
|
|
local_booter: ComputerBooter | None = None
|
|
_MANAGED_SKILLS_FILE = ".astrbot_managed_skills.json"
|
|
|
|
|
|
def _discover_bay_credentials(endpoint: str) -> str:
|
|
"""Try to auto-discover Bay API key from credentials.json.
|
|
|
|
Search order:
|
|
1. BAY_DATA_DIR env var
|
|
2. Mono-repo relative path: ../pkgs/bay/ (dev layout)
|
|
3. Current working directory
|
|
|
|
Returns:
|
|
API key string, or empty string if not found.
|
|
"""
|
|
candidates: list[Path] = []
|
|
|
|
# 1. BAY_DATA_DIR env var
|
|
bay_data_dir = os.environ.get("BAY_DATA_DIR")
|
|
if bay_data_dir:
|
|
candidates.append(Path(bay_data_dir) / "credentials.json")
|
|
|
|
# 2. Mono-repo layout: AstrBot/../pkgs/bay/credentials.json
|
|
astrbot_root = Path(__file__).resolve().parents[3] # astrbot/core/computer/ → root
|
|
candidates.append(astrbot_root.parent / "pkgs" / "bay" / "credentials.json")
|
|
|
|
# 3. Current working directory
|
|
candidates.append(Path.cwd() / "credentials.json")
|
|
|
|
for cred_path in candidates:
|
|
if not cred_path.is_file():
|
|
continue
|
|
try:
|
|
data = json.loads(cred_path.read_text())
|
|
api_key = data.get("api_key", "")
|
|
if api_key:
|
|
# Optionally verify endpoint matches
|
|
cred_endpoint = data.get("endpoint", "")
|
|
if (
|
|
cred_endpoint
|
|
and endpoint
|
|
and cred_endpoint.rstrip("/") != endpoint.rstrip("/")
|
|
):
|
|
logger.warning(
|
|
"[Computer] bay_credentials_mismatch file_endpoint=%s configured_endpoint=%s action=use_key",
|
|
cred_endpoint,
|
|
endpoint,
|
|
)
|
|
masked_key = f"{api_key[:4]}..." if len(api_key) >= 6 else "redacted"
|
|
logger.info(
|
|
"[Computer] bay_credentials_lookup status=found path=%s key_prefix=%s",
|
|
cred_path,
|
|
masked_key,
|
|
)
|
|
return api_key
|
|
except (json.JSONDecodeError, OSError) as exc:
|
|
logger.debug(
|
|
"[Computer] bay_credentials_read_failed path=%s error=%s",
|
|
cred_path,
|
|
exc,
|
|
)
|
|
|
|
logger.debug("[Computer] bay_credentials_lookup status=not_found")
|
|
return ""
|
|
|
|
|
|
def _build_python_exec_command(script: str) -> str:
|
|
return (
|
|
"if command -v python3 >/dev/null 2>&1; then PYBIN=python3; "
|
|
"elif command -v python >/dev/null 2>&1; then PYBIN=python; "
|
|
"else echo 'python not found in sandbox' >&2; exit 127; fi; "
|
|
"$PYBIN - <<'PY'\n"
|
|
f"{script}\n"
|
|
"PY"
|
|
)
|
|
|
|
|
|
def _build_apply_sync_command() -> str:
|
|
"""Build shell command for sync stage only.
|
|
|
|
This stage mutates sandbox files (managed skill replacement) but does not scan
|
|
metadata. Keeping it separate allows callers to preserve old behavior while
|
|
reusing the apply step independently.
|
|
"""
|
|
script = f"""
|
|
import json
|
|
import shutil
|
|
import zipfile
|
|
from pathlib import Path
|
|
|
|
root = Path({SANDBOX_SKILLS_ROOT!r})
|
|
zip_path = root / "skills.zip"
|
|
tmp_extract = Path(f"{{root}}_tmp_extract")
|
|
managed_file = root / {_MANAGED_SKILLS_FILE!r}
|
|
|
|
|
|
def remove_tree(path: Path) -> None:
|
|
if not path.exists():
|
|
return
|
|
if path.is_dir():
|
|
shutil.rmtree(path, ignore_errors=True)
|
|
else:
|
|
path.unlink(missing_ok=True)
|
|
|
|
|
|
def load_managed_skills() -> list[str]:
|
|
if not managed_file.exists():
|
|
return []
|
|
try:
|
|
payload = json.loads(managed_file.read_text(encoding="utf-8"))
|
|
except Exception:
|
|
return []
|
|
if not isinstance(payload, dict):
|
|
return []
|
|
items = payload.get("managed_skills", [])
|
|
if not isinstance(items, list):
|
|
return []
|
|
result: list[str] = []
|
|
for item in items:
|
|
if isinstance(item, str) and item.strip():
|
|
result.append(item.strip())
|
|
return result
|
|
|
|
|
|
root.mkdir(parents=True, exist_ok=True)
|
|
for managed_name in load_managed_skills():
|
|
remove_tree(root / managed_name)
|
|
|
|
current_managed: list[str] = []
|
|
if zip_path.exists():
|
|
remove_tree(tmp_extract)
|
|
tmp_extract.mkdir(parents=True, exist_ok=True)
|
|
with zipfile.ZipFile(zip_path) as zf:
|
|
zf.extractall(tmp_extract)
|
|
for entry in sorted(tmp_extract.iterdir()):
|
|
if not entry.is_dir():
|
|
continue
|
|
target = root / entry.name
|
|
remove_tree(target)
|
|
shutil.copytree(entry, target)
|
|
current_managed.append(entry.name)
|
|
|
|
remove_tree(tmp_extract)
|
|
remove_tree(zip_path)
|
|
managed_file.write_text(
|
|
json.dumps({{"managed_skills": current_managed}}, ensure_ascii=False, indent=2),
|
|
encoding="utf-8",
|
|
)
|
|
print(json.dumps({{"managed_skills": current_managed}}, ensure_ascii=False))
|
|
""".strip()
|
|
return _build_python_exec_command(script)
|
|
|
|
|
|
def _build_scan_command() -> str:
|
|
"""Build shell command for scan stage only.
|
|
|
|
This stage is read-oriented: it scans SKILL.md metadata and returns the
|
|
historical payload shape consumed by cache update logic.
|
|
|
|
The scan resolves the absolute path of the skills root at runtime so
|
|
that the LLM can reliably ``cat`` skill files regardless of cwd.
|
|
Only the ``description`` field is extracted from frontmatter.
|
|
"""
|
|
script = f"""
|
|
import json
|
|
from pathlib import Path
|
|
|
|
root = Path({SANDBOX_SKILLS_ROOT!r})
|
|
managed_file = root / {_MANAGED_SKILLS_FILE!r}
|
|
|
|
# Resolve absolute path at runtime so prompts always have a reliable path
|
|
root_abs = str(root.resolve())
|
|
|
|
|
|
# NOTE: This parser mirrors skill_manager._parse_frontmatter_description.
|
|
# Keep the two implementations in sync when changing parsing logic.
|
|
def parse_description(text: str) -> str:
|
|
if not text.startswith("---"):
|
|
return ""
|
|
lines = text.splitlines()
|
|
if not lines or lines[0].strip() != "---":
|
|
return ""
|
|
end_idx = None
|
|
for i in range(1, len(lines)):
|
|
if lines[i].strip() == "---":
|
|
end_idx = i
|
|
break
|
|
if end_idx is None:
|
|
return ""
|
|
|
|
frontmatter = "\\n".join(lines[1:end_idx])
|
|
try:
|
|
import yaml
|
|
except ImportError:
|
|
return ""
|
|
|
|
try:
|
|
payload = yaml.safe_load(frontmatter) or dict()
|
|
except yaml.YAMLError:
|
|
return ""
|
|
if not isinstance(payload, dict):
|
|
return ""
|
|
|
|
description = payload.get("description", "")
|
|
if not isinstance(description, str):
|
|
return ""
|
|
return description.strip()
|
|
|
|
|
|
def load_managed_skills() -> list[str]:
|
|
if not managed_file.exists():
|
|
return []
|
|
try:
|
|
payload = json.loads(managed_file.read_text(encoding="utf-8"))
|
|
except Exception:
|
|
return []
|
|
if not isinstance(payload, dict):
|
|
return []
|
|
items = payload.get("managed_skills", [])
|
|
if not isinstance(items, list):
|
|
return []
|
|
result: list[str] = []
|
|
for item in items:
|
|
if isinstance(item, str) and item.strip():
|
|
result.append(item.strip())
|
|
return result
|
|
|
|
|
|
def collect_skills() -> list[dict[str, str]]:
|
|
skills: list[dict[str, str]] = []
|
|
if not root.exists():
|
|
return skills
|
|
for skill_dir in sorted(root.iterdir()):
|
|
if not skill_dir.is_dir():
|
|
continue
|
|
skill_md = skill_dir / "SKILL.md"
|
|
if not skill_md.is_file():
|
|
continue
|
|
description = ""
|
|
try:
|
|
text = skill_md.read_text(encoding="utf-8")
|
|
description = parse_description(text)
|
|
except Exception:
|
|
description = ""
|
|
skills.append(
|
|
{{
|
|
"name": skill_dir.name,
|
|
"description": description,
|
|
"path": f"{{root_abs}}/{{skill_dir.name}}/SKILL.md",
|
|
}}
|
|
)
|
|
return skills
|
|
|
|
|
|
print(
|
|
json.dumps(
|
|
{{
|
|
"managed_skills": load_managed_skills(),
|
|
"skills": collect_skills(),
|
|
}},
|
|
ensure_ascii=False,
|
|
)
|
|
)
|
|
""".strip()
|
|
return _build_python_exec_command(script)
|
|
|
|
|
|
def _shell_exec_succeeded(result: dict) -> bool:
|
|
if "success" in result:
|
|
return bool(result.get("success"))
|
|
exit_code = result.get("exit_code")
|
|
return exit_code in (0, None)
|
|
|
|
|
|
def _format_exec_error_detail(result: dict) -> str:
|
|
"""Format shell execution details for better observability.
|
|
|
|
Keep the message compact while still surfacing exit code and stderr/stdout.
|
|
"""
|
|
exit_code = result.get("exit_code")
|
|
stderr = str(result.get("stderr", "") or "").strip()
|
|
stdout = str(result.get("stdout", "") or "").strip()
|
|
stderr_text = stderr[:500]
|
|
stdout_text = stdout[:300]
|
|
return f"exit_code={exit_code}, stderr={stderr_text!r}, stdout_tail={stdout_text!r}"
|
|
|
|
|
|
def _decode_sync_payload(stdout: str) -> dict | None:
|
|
text = stdout.strip()
|
|
if not text:
|
|
return None
|
|
candidates = [text]
|
|
candidates.extend([line.strip() for line in text.splitlines() if line.strip()])
|
|
for candidate in reversed(candidates):
|
|
try:
|
|
payload = json.loads(candidate)
|
|
except Exception:
|
|
continue
|
|
if isinstance(payload, dict):
|
|
return payload
|
|
return None
|
|
|
|
|
|
def _update_sandbox_skills_cache(payload: dict | None) -> None:
|
|
if not isinstance(payload, dict):
|
|
return
|
|
skills = payload.get("skills", [])
|
|
if not isinstance(skills, list):
|
|
return
|
|
SkillManager().set_sandbox_skills_cache(skills)
|
|
|
|
|
|
async def _apply_skills_to_sandbox(booter: ComputerBooter) -> None:
|
|
"""Apply local skill bundle to sandbox filesystem only.
|
|
|
|
This function is intentionally limited to file mutation. Metadata scanning is
|
|
executed in a separate phase to keep failure domains clear.
|
|
"""
|
|
logger.info("[Computer] sandbox_sync phase=apply status=start")
|
|
apply_result = await booter.shell.exec(_build_apply_sync_command())
|
|
if not _shell_exec_succeeded(apply_result):
|
|
detail = _format_exec_error_detail(apply_result)
|
|
logger.error(
|
|
"[Computer] sandbox_sync phase=apply status=failed detail=%s", detail
|
|
)
|
|
raise RuntimeError(f"Failed to apply sandbox skill sync strategy: {detail}")
|
|
logger.info("[Computer] sandbox_sync phase=apply status=done")
|
|
|
|
|
|
async def _scan_sandbox_skills(booter: ComputerBooter) -> dict | None:
|
|
"""Scan sandbox skills and return normalized payload for cache update."""
|
|
logger.info("[Computer] sandbox_sync phase=scan status=start")
|
|
scan_result = await booter.shell.exec(_build_scan_command())
|
|
if not _shell_exec_succeeded(scan_result):
|
|
detail = _format_exec_error_detail(scan_result)
|
|
logger.error(
|
|
"[Computer] sandbox_sync phase=scan status=failed detail=%s", detail
|
|
)
|
|
raise RuntimeError(f"Failed to scan sandbox skills after sync: {detail}")
|
|
|
|
payload = _decode_sync_payload(str(scan_result.get("stdout", "") or ""))
|
|
if payload is None:
|
|
logger.warning("[Computer] sandbox_sync phase=scan status=empty_payload")
|
|
else:
|
|
logger.info("[Computer] sandbox_sync phase=scan status=done")
|
|
return payload
|
|
|
|
|
|
async def _sync_skills_to_sandbox(booter: ComputerBooter) -> None:
|
|
"""Sync local skills to sandbox and refresh cache.
|
|
|
|
Backward-compatible orchestrator: keep historical behavior while internally
|
|
splitting into `apply` and `scan` phases.
|
|
"""
|
|
import anyio
|
|
|
|
skills_root = anyio.Path(get_astrbot_skills_path())
|
|
if not await skills_root.is_dir():
|
|
return
|
|
local_skill_dirs = _list_local_skill_dirs(Path(skills_root))
|
|
|
|
temp_dir = anyio.Path(get_astrbot_temp_path())
|
|
await temp_dir.mkdir(parents=True, exist_ok=True)
|
|
zip_base = temp_dir / "skills_bundle"
|
|
zip_path = zip_base.with_suffix(".zip")
|
|
bundle_dir = temp_dir / f"skills_bundle_{uuid.uuid4().hex}"
|
|
|
|
try:
|
|
if local_skill_dirs:
|
|
if await zip_path.exists():
|
|
await zip_path.unlink()
|
|
shutil.make_archive(str(zip_base), "zip", str(skills_root))
|
|
remote_zip = anyio.Path(SANDBOX_SKILLS_ROOT) / "skills.zip"
|
|
logger.info("[Computer] sandbox_sync phase=upload status=start")
|
|
await booter.shell.exec(f"mkdir -p {SANDBOX_SKILLS_ROOT}")
|
|
upload_result = await booter.upload_file(str(zip_path), str(remote_zip))
|
|
if not upload_result.get("success", False):
|
|
logger.error("[Computer] sandbox_sync phase=upload status=failed")
|
|
raise RuntimeError("Failed to upload skills bundle to sandbox.")
|
|
logger.info("[Computer] sandbox_sync phase=upload status=done")
|
|
else:
|
|
logger.info(
|
|
"[Computer] sandbox_sync phase=upload status=skipped reason=no_local_skills"
|
|
)
|
|
await booter.shell.exec(f"rm -f {SANDBOX_SKILLS_ROOT}/skills.zip")
|
|
|
|
# Keep backward-compatible behavior while splitting lifecycle into two
|
|
# observable phases: apply (filesystem mutation) + scan (metadata read).
|
|
await _apply_skills_to_sandbox(booter)
|
|
payload = await _scan_sandbox_skills(booter)
|
|
_update_sandbox_skills_cache(payload)
|
|
managed = payload.get("managed_skills", []) if isinstance(payload, dict) else []
|
|
logger.info(
|
|
"[Computer] sandbox_sync phase=overall status=done managed=%d",
|
|
len(managed),
|
|
)
|
|
finally:
|
|
if bundle_dir.exists():
|
|
shutil.rmtree(bundle_dir, ignore_errors=True)
|
|
if zip_path.exists():
|
|
try:
|
|
zip_path.unlink()
|
|
except Exception:
|
|
logger.warning(
|
|
"[Computer] sandbox_sync phase=cleanup status=failed path=%s",
|
|
zip_path,
|
|
)
|
|
|
|
|
|
async def get_booter(
|
|
context: Context,
|
|
session_id: str,
|
|
) -> ComputerBooter:
|
|
config = context.get_config(umo=session_id)
|
|
|
|
runtime = config.get("provider_settings", {}).get("computer_use_runtime", "local")
|
|
if runtime == "local":
|
|
return get_local_booter()
|
|
elif runtime == "none":
|
|
raise RuntimeError("Sandbox runtime is disabled by configuration.")
|
|
|
|
sandbox_cfg = config.get("provider_settings", {}).get("sandbox", {})
|
|
booter_type = sandbox_cfg.get("booter", "shipyard_neo")
|
|
|
|
if session_id in session_booter:
|
|
booter = session_booter[session_id]
|
|
if not await booter.available():
|
|
# rebuild
|
|
session_booter.pop(session_id, None)
|
|
if session_id not in session_booter:
|
|
uuid_str = uuid.uuid5(uuid.NAMESPACE_DNS, session_id).hex
|
|
logger.info(
|
|
"[Computer] booter_init booter=%s session=%s",
|
|
booter_type,
|
|
session_id,
|
|
)
|
|
if booter_type == "shipyard":
|
|
from .booters.shipyard import ShipyardBooter
|
|
|
|
ep = sandbox_cfg.get("shipyard_endpoint", "")
|
|
token = sandbox_cfg.get("shipyard_access_token", "")
|
|
ttl = sandbox_cfg.get("shipyard_ttl", 3600)
|
|
max_sessions = sandbox_cfg.get("shipyard_max_sessions", 10)
|
|
|
|
client = ShipyardBooter(
|
|
endpoint_url=ep, access_token=token, ttl=ttl, session_num=max_sessions
|
|
)
|
|
elif booter_type == "shipyard_neo":
|
|
from .booters.shipyard_neo import ShipyardNeoBooter
|
|
|
|
ep = sandbox_cfg.get("shipyard_neo_endpoint", "")
|
|
token = sandbox_cfg.get("shipyard_neo_access_token", "")
|
|
ttl = sandbox_cfg.get("shipyard_neo_ttl", 3600)
|
|
profile = sandbox_cfg.get("shipyard_neo_profile", "python-default")
|
|
|
|
# Auto-discover token from Bay's credentials.json if not configured
|
|
if not token:
|
|
token = _discover_bay_credentials(ep)
|
|
|
|
logger.info(
|
|
f"[Computer] Shipyard Neo config: endpoint={ep}, profile={profile}, ttl={ttl}"
|
|
)
|
|
client = ShipyardNeoBooter(
|
|
endpoint_url=ep,
|
|
access_token=token,
|
|
profile=profile,
|
|
ttl=ttl,
|
|
)
|
|
elif booter_type == "boxlite":
|
|
from .booters.boxlite import BoxliteBooter
|
|
|
|
client = BoxliteBooter()
|
|
else:
|
|
raise ValueError(f"Unknown booter type: {booter_type}")
|
|
|
|
try:
|
|
await client.boot(uuid_str)
|
|
logger.info(
|
|
"[Computer] booter_ready booter=%s session=%s",
|
|
booter_type,
|
|
session_id,
|
|
)
|
|
await _sync_skills_to_sandbox(client)
|
|
except Exception:
|
|
logger.exception(
|
|
"[Computer] booter_init_failed booter=%s session=%s",
|
|
booter_type,
|
|
session_id,
|
|
)
|
|
raise
|
|
|
|
session_booter[session_id] = client
|
|
return session_booter[session_id]
|
|
|
|
|
|
async def sync_skills_to_active_sandboxes() -> None:
|
|
"""Best-effort skills synchronization for all active sandbox sessions."""
|
|
logger.info(
|
|
"[Computer] sandbox_sync scope=active sessions=%d",
|
|
len(session_booter),
|
|
)
|
|
for session_id, booter in list(session_booter.items()):
|
|
try:
|
|
if not await booter.available():
|
|
continue
|
|
await _sync_skills_to_sandbox(booter)
|
|
except Exception:
|
|
logger.exception(
|
|
"[Computer] sandbox_sync_failed session=%s booter=%s",
|
|
session_id,
|
|
booter.__class__.__name__,
|
|
)
|
|
|
|
|
|
def get_local_booter() -> ComputerBooter:
|
|
global local_booter
|
|
if local_booter is None:
|
|
local_booter = LocalBooter()
|
|
return local_booter
|
|
|
|
|
|
# ---------------------------------------------------------------------------
|
|
# Unified query API — used by ComputerToolProvider and subagent tool exec
|
|
# ---------------------------------------------------------------------------
|
|
|
|
|
|
def _get_booter_class(booter_type: str) -> type[ComputerBooter] | None:
|
|
"""Map booter_type string to class (lazy import)."""
|
|
if booter_type == BOOTER_SHIPYARD:
|
|
from .booters.shipyard import ShipyardBooter
|
|
|
|
return ShipyardBooter
|
|
elif booter_type == BOOTER_SHIPYARD_NEO:
|
|
from .booters.shipyard_neo import ShipyardNeoBooter
|
|
|
|
return ShipyardNeoBooter
|
|
elif booter_type == BOOTER_BOXLITE:
|
|
from .booters.boxlite import BoxliteBooter
|
|
|
|
return BoxliteBooter
|
|
logger.warning(
|
|
"[Computer] booter_class_lookup booter=%s found=false",
|
|
booter_type,
|
|
)
|
|
return None
|
|
|
|
|
|
def get_sandbox_tools(session_id: str) -> list[FunctionTool]:
|
|
"""Return precise tool list from a booted session, or [] if not booted."""
|
|
booter = session_booter.get(session_id)
|
|
if booter is None:
|
|
logger.debug(
|
|
"[Computer] sandbox_tools source=booted session=%s booter=none tools=0 capabilities=none",
|
|
session_id,
|
|
)
|
|
return []
|
|
tools = booter.get_tools()
|
|
caps = getattr(booter, "capabilities", None)
|
|
logger.debug(
|
|
"[Computer] sandbox_tools source=booted session=%s booter=%s tools=%d capabilities=%s",
|
|
session_id,
|
|
booter.__class__.__name__,
|
|
len(tools),
|
|
list(caps) if caps is not None else None,
|
|
)
|
|
return tools
|
|
|
|
|
|
def get_sandbox_capabilities(session_id: str) -> tuple[str, ...] | None:
|
|
"""Return capability tuple from a booted session, or None if unavailable."""
|
|
booter = session_booter.get(session_id)
|
|
if booter is None:
|
|
logger.debug(
|
|
"[Computer] sandbox_capabilities session=%s booter=none capabilities=none",
|
|
session_id,
|
|
)
|
|
return None
|
|
caps = getattr(booter, "capabilities", None)
|
|
logger.debug(
|
|
"[Computer] sandbox_capabilities session=%s booter=%s capabilities=%s",
|
|
session_id,
|
|
booter.__class__.__name__,
|
|
list(caps) if caps is not None else None,
|
|
)
|
|
return caps
|
|
|
|
|
|
def get_default_sandbox_tools(sandbox_cfg: dict) -> list[FunctionTool]:
|
|
"""Return conservative (pre-boot) tool list based on config. No instance needed."""
|
|
booter_type = sandbox_cfg.get("booter", BOOTER_SHIPYARD_NEO)
|
|
cls = _get_booter_class(booter_type)
|
|
tools = cls.get_default_tools() if cls else []
|
|
logger.debug(
|
|
"[Computer] sandbox_tools source=default booter=%s tools=%d capabilities=unknown",
|
|
booter_type,
|
|
len(tools),
|
|
)
|
|
return tools
|
|
|
|
|
|
def get_sandbox_prompt_parts(sandbox_cfg: dict) -> list[str]:
|
|
"""Return booter-specific system prompt fragments based on config."""
|
|
booter_type = sandbox_cfg.get("booter", BOOTER_SHIPYARD_NEO)
|
|
cls = _get_booter_class(booter_type)
|
|
prompt_parts = cls.get_system_prompt_parts() if cls else []
|
|
logger.debug(
|
|
"[Computer] sandbox_prompts booter=%s parts=%d",
|
|
booter_type,
|
|
len(prompt_parts),
|
|
)
|
|
return prompt_parts
|