Skip to content

AstrBot

v4.26.4 Bugfix

This release fixes issues for SREs watching stability and regressions.

✓ No known CVEs patched
Read the diff → Tool health → What is this tool? →

✓ No known CVEs patched in this version

Topics

agent ai astrbot llm chatgpt discord
+9 more
docker gemini llama mcp openai python qq qqbot telegram

Summary

AI summary

Fixed astrbot_file_read_tool to return clear errors when given a directory path instead of misleading permission errors.

Full changelog

What's Changed

Fixes

  • Return clear errors when astrbot_file_read_tool receives a directory path instead of reporting a misleading permission error (#9088)
  • Reduce markdown streaming lag (#9097)
  • Resample and downmix WAV files for Tencent Silk encoding (#9100)
  • Guard desktop-managed core restart (#9098)
  • Update reboot logic (#9073)
  • Fix Discord adapter command registration regex being too strict (#9102)
  • Reject non-200 download responses (#9085)
  • Fix WeCom webhook adapter returning JSON instead of plain text (#9107)
  • Preserve raw webhook callback responses for unified webhook routes
  • Skip _unbind_plugin for inactive plugins during specified plugin reload (#9096)
  • Apply fallback chat models to background wakeups (#9094)

Chinese

修复

  • 修复企业微信、企业微信客服 Webhook、QQ 官方机器人 Webhook 无法正常校验的问题 (#9107)
  • astrbot_file_read_tool 读取目录路径时返回明确错误,避免误报权限不足 (#9088)
  • 降低 Markdown 流式输出延迟 (#9097)
  • 为腾讯系 IM Silk 编码重采样并下混 WAV 文件 (#9100)
  • 保护由桌面端管理的核心重启流程 (#9098)
  • 更新重启逻辑 (#9073)
  • 修复 Discord 适配器注册命令正则过于严格的问题 (#9102)
  • 拒绝非 200 状态码的下载响应 (#9085)
  • 指定插件重载时,对未启用插件跳过 _unbind_plugin (#9096)
  • 后台唤醒主 Agent 时应用 fallback chat models (#9094)

Weekly OSS security release digest.

The CVE patches and breaking changes that affected production tools this week. One email, every Sunday.

No spam, unsubscribe anytime.

Share this release

Track AstrBot

Get notified when new releases ship.

Sign up free

About AstrBot

All releases →

Related context

Earlier breaking changes

  • v4.25.3 Upgrades MiniMax Token Plan default model to M3.

Beta — feedback welcome: [email protected]