github AstrBotDevs/AstrBot v4.21.0

6 hours ago

What's Changed

新增

  • 为插件市场新增分类筛选并优化界面组件。(#6762
  • 新增 Kimi Coding Plan Provider(兼容 Anthropic API)。(#6559
  • 统一并重命名 skill.md 文件为 SKILL.md。(#6757
  • 新增 Ollama 关闭思考模式开关。(#5941
  • 新增小米 MiMo TTS 与 STT Provider。(#6643
  • 新增多模态上下文 token 计数能力(图片、音频与思维链)。(#6596
  • 新增按元信息名称安装插件并校验可导入标识符。(#6530

优化

  • 降低 kook_typeStrEnum(str, Enum) 以兼容旧版本 Python。(#6512
  • 优化 WebChat 消息处理:提前保存消息并增强流式补全。(#6698
  • 优化 Dashboard 中移动端 persona 选择器布局。(#5907
  • 优化 Dashboard,减少 MDI icon font 范围并自托管 Google Fonts。(#6532
  • 使用 Pydantic 重构 KOOK 适配器数据模型以提升消息结构解析与校验性能。(#5719
  • 调整文档术语与表达(“消息平台”改为“机器人”等)并优化更新说明文字。(#6568

修复

  • 修复 web search tools 中被禁用系统函数时未正确生效的问题。(#6584
  • 跳过空的知识库嵌入批次,避免不必要计算。(#6106
  • 修复 Feishu opus 文件在 Whisper API STT 场景下未正确转换的问题。(#6078
  • 修复 Lark 在工具调用中断时卡片创建与重续流程。(#6743
  • 修复 Windows 环境下 skill 文件编码兼容问题。(#6058
  • 修复 WebChat 单独渲染的 HTML 回复被错误显示的问题。(#6074
  • 修复 Gemini 数组 schema 缺少 items 字段的问题。(#6051
  • 修复 skills 使用硬编码工作区路径的问题,改为使用缓存中的真实沙箱路径。(#6331
  • 修复 subagent 工具调用超时传递,修正 tool_call_timeout 并将默认超时从 60 秒提升到 120 秒。(#6713
  • 修复 skills-like 下缺失 extra_user_content_parts 时未注入图片说明的问题。(#6710
  • 修复 /stop 后继续处理后续 follow-up 消息的问题。(#6704
  • 修复核心流程在 stop 时中断子代理工具等待的行为。(#5850
  • 修复 Windows 平台 stdio MCP 服务 PATHEXT 丢失的问题。(#5822
  • 修复 Telegram 轮询重启机制,失败时自动恢复循环。(#6648
  • 修复 /stop 后 follow-up 状态未清理导致后续触发继续运行的问题。(#6656
  • 修复 OpenAI 配置日志,改进代理与 API Base 的可读性与排障能力。(#6669
  • 修复长工具调用中截断逻辑误删唯一 user 消息的问题。(#6198
  • 修复截断器移除唯一用户消息导致部分 provider 返回 400 的问题。(#6581
  • 修复 ID 白名单为空时提示文案不清晰的问题。(#6611
  • 修复 MoonshotAI 官方 API 下 OpenAI token usage 缺失问题。(#6618
  • 提升 Wecom AI Bot 流式可读性与速度(限流处理),改善卡顿与显示体验。(#6610
  • 修复 Wecom 长连接回复消失的问题。(#6606
  • 修复 Windows 打包运行时 pip/native 构建环境配置问题。(#6575
  • 修复仅在显式配置时传递 embedding dimensions,避免无效参数干扰。(#6432
  • 修复 register_agent 装饰器导致的 NameError。(#5765
  • 修复默认 persona 场景下的 subagent 查询失败问题。(#5672
  • 修复 Windows 下 skill 读取失败问题。(#6490
  • 修复 SKILL.md 多行 frontmatter 解析问题。(#6460
  • 修复 SQLite database is locked 问题,新增繁忙超时处理。(#6474
  • 修复工作流限制仅允许上游仓库触发的报错场景。(#6531

What's Changed (EN)

New Features

  • Added category filtering for market plugins and enhanced UI components.
  • Normalized and renamed skill.md files to SKILL.md.
  • Added a toggle to disable thinking mode in Ollama.
  • Added Xiaomi MiMo TTS & STT providers.
  • Added Kimi Coding Plan provider with Anthropic API compatibility.
  • Added context token counting support for multimodal content (images, audio, and chain-of-thought).
  • Added plugin installation by metadata name and validated importable identifiers.

Improvements

  • Refactored StrEnum to (str, Enum) in kook_type for backward compatibility.
  • Enhanced WebChat message handling with proactive saving and streaming completion.
  • Simplified dashboard persona selector layout for mobile screens.
  • Subset MDI icon font and self-hosted Google Fonts in dashboard.
  • Implemented Pydantic data models for KOOK adapter for better retrieval and schema validation.
  • Updated documentation wording for incomplete updates terminology.

Bug Fixes

  • Fixed disabled system functions in web search tools.
  • Skipped empty knowledge-base embedding batches.
  • Converted Feishu opus files for Whisper API STT.
  • Deferred Lark card creation and renewal on tool call break.
  • Added fallback for Windows skill file encodings.
  • Rendered standalone HTML replies as code in WebChat.
  • Ensured Gemini array schemas always include items.
  • Fixed skills path resolution to use cached sandbox path instead of hardcoded workspace root.
  • Passed tool_call_timeout to subagent handsoff/cron/background tasks and increased default timeout to 120 seconds.
  • Fixed skills-like re-query missing extra_user_content_parts causing image caption not injected.
  • Rejected follow-up messages after /stop request.
  • Interrupted subagent tool waits on stop.
  • Preserved PATHEXT for stdio MCP servers on Windows.
  • Added automatic restart for Telegram polling loop on failure.
  • Fixed follow-up persistence logic after /stop trigger.
  • Improved OpenAI proxy/API base logging.
  • Prevented truncation logic from removing the only user message in long tool-calling conversations.
  • Fixed truncation removing the only user message and returning 400 for some providers.
  • Updated ID whitelist empty-configuration hint wording.
  • Fixed token usage with MoonshotAI official API.
  • Improved Wecom AI Bot streaming readability and speed via throttling.
  • Prevented Wecom AI Bot long connection replies from disappearing.
  • Set packaged Windows runtime build env for pip native builds.
  • Only pass embedding dimensions when explicitly configured.
  • Fixed register_agent decorator NameError.
  • Fixed subagent lookup failure when using default persona.
  • Fixed reading skills on Windows.
  • Fixed multiline frontmatter parsing in SKILL.md.
  • Fixed SQLite database is locked with busy timeout.
  • Restricted workflows to upstream repo.

Don't miss a new AstrBot release

NewReleases is sending notifications on new releases.