Skip to content

AstrBot

v4.26.7 Breaking

This release includes breaking changes for platform teams planning a safe upgrade.

Published 8d AI Agents & Assistants
✓ 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

ReleasePort's take

Light signal
editorial:auto 8d

Release v4.26.7 introduces ChatUI inline interactive GenUI support and adds streaming agent statistics after each LLM call.

Why it matters: Feature additions (ChatUI, LLM stats) provide new interactivity tools; bugfixes improve reliability with higher‑severity severity 40 patches for context limits and dashboard stability.

Summary

AI summary

Updates 修复, 新增, and 变更 across a mixed release.

Changes in this release

Feature Low

Added ChatUI inline interactive GenUI support.

Added ChatUI inline interactive GenUI support.

Source: llm_adapter@2026-07-18

Confidence: high

 —
Feature Low

Added streaming agent statistics after each LLM call.

Added streaming agent statistics after each LLM call.

Source: llm_adapter@2026-07-18

Confidence: high

 —
Feature Low

Added a rerank provider for Text Embeddings Inference (TEI).

Added a rerank provider for Text Embeddings Inference (TEI).

Source: llm_adapter@2026-07-18

Confidence: high

 —
Feature Low

Added configurable embedding dimension send modes.

Added configurable embedding dimension send modes.

Source: llm_adapter@2026-07-18

Confidence: high

 —
Performance Low

Made configuration snapshot saves asynchronous and revision-aware to avoid blocking event loops and overwriting newer state.

Made configuration snapshot saves asynchronous and revision-aware to avoid blocking event loops and overwriting newer state.

Source: granite4.1:30b@2026-07-18-audit

Confidence: low

 —
Performance Low

Optimized repeated tool call detection by comparing tool names and arguments.

Optimized repeated tool call detection by comparing tool names and arguments.

Source: granite4.1:30b@2026-07-18-audit

Confidence: low

 —
Bugfix Medium

Prioritized the configured context limit when one is available.

Prioritized the configured context limit when one is available.

Source: llm_adapter@2026-07-18

Confidence: high

 —
Bugfix Medium

Removed unsaved provider sources locally when they are deleted.

Removed unsaved provider sources locally when they are deleted.

Source: llm_adapter@2026-07-18

Confidence: high

 —
Bugfix Medium

Corrected Skills download archive filenames for versioned skill names.

Corrected Skills download archive filenames for versioned skill names.

Source: llm_adapter@2026-07-18

Confidence: high

 —
Bugfix Medium

Added a catch‑all exception handler for dashboard API errors.

Added a catch‑all exception handler for dashboard API errors.

Source: llm_adapter@2026-07-18

Confidence: high

 —
Bugfix Medium

Compensated for partial knowledge base upload failures.

Compensated for partial knowledge base upload failures.

Source: llm_adapter@2026-07-18

Confidence: high

 —
Bugfix Medium

Removed duplicate platform logs from the dashboard.

Removed duplicate platform logs from the dashboard.

Source: llm_adapter@2026-07-18

Confidence: high

 —
Bugfix Low

Restored code block copying on insecure HTTP origins.

Restored code block copying on insecure HTTP origins.

Source: granite4.1:30b@2026-07-18-audit

Confidence: low

 —
Bugfix Low

Handled ChatUI follow‑up messages correctly.

Handled ChatUI follow‑up messages correctly.

Source: granite4.1:30b@2026-07-18-audit

Confidence: low

 —
Bugfix Low

Avoided a python-ripgrep crash on Python 3.14.

Avoided a python-ripgrep crash on Python 3.14.

Source: granite4.1:30b@2026-07-18-audit

Confidence: low

 —
Bugfix Low

Prevented purpose explanations from appearing before every tool call.

Prevented purpose explanations from appearing before every tool call.

Source: granite4.1:30b@2026-07-18-audit

Confidence: low

 —
Bugfix Low

Hid the command tooltip while the suggestion panel is open.

Hid the command tooltip while the suggestion panel is open.

Source: granite4.1:30b@2026-07-18-audit

Confidence: low

 —
Bugfix Low

Stopped matching plugin repository URLs as plugin names.

Stopped matching plugin repository URLs as plugin names.

Source: granite4.1:30b@2026-07-18-audit

Confidence: low

 —
Bugfix Low

Accepted UTF-8 BOM markers in plugin schemas.

Accepted UTF-8 BOM markers in plugin schemas.

Source: granite4.1:30b@2026-07-18-audit

Confidence: low

 —
Bugfix Low

Made plugin handler binding idempotent to prevent duplicate `self` arguments.

Made plugin handler binding idempotent to prevent duplicate `self` arguments.

Source: granite4.1:30b@2026-07-18-audit

Confidence: low

 —
Refactor Low

Streamlined and simplified the WebUI sidebar.

Streamlined and simplified the WebUI sidebar.

Source: granite4.1:30b@2026-07-18-audit

Confidence: low

 —
Refactor Low

Translated core logs into English.

Translated core logs into English.

Source: granite4.1:30b@2026-07-18-audit

Confidence: low

 —
Full changelog

4.26.7 - 2026-07-18

What can be shown cannot be said.

能够被呈现的，不必诉诸言语。

Added

  • Added ChatUI inline interactive GenUI support. (#8712)
  • Added streaming agent statistics after each LLM call. (#9260)
  • Added a rerank provider for Text Embeddings Inference (TEI). (#9274)
  • Added configurable embedding dimension send modes. (#9245)

Changed

  • Streamlined and simplified the WebUI sidebar. (#9233, #9313)
  • Made configuration snapshot saves asynchronous and revision-aware to avoid blocking event loops and overwriting newer state. (#9300)
  • Optimized repeated tool call detection by comparing tool names and arguments. (#9311)
  • Translated core logs into English. (#9318)

Fixed

  • Prioritized the configured context limit when one is available. (#9263)
  • Removed unsaved provider sources locally when they are deleted. (#9264)
  • Corrected Skills download archive filenames for versioned skill names. (#9270)
  • Added a catch-all exception handler for dashboard API errors. (#9271)
  • Compensated for partial knowledge base upload failures. (#9007, #9246)
  • Removed duplicate platform logs from the dashboard. (#9291)
  • Restored code block copying on insecure HTTP origins. (#9267)
  • Handled ChatUI follow-up messages correctly. (#9309)
  • Avoided a python-ripgrep crash on Python 3.14. (#9244)
  • Prevented purpose explanations from appearing before every tool call.
  • Hid the command tooltip while the suggestion panel is open. (#9312)
  • Stopped matching plugin repository URLs as plugin names. (#9314)
  • Accepted UTF-8 BOM markers in plugin schemas. (#9223)
  • Made plugin handler binding idempotent to prevent duplicate self arguments. (#9316)

中文

新增

  • ChatUI 支持内联可交互生成式 UI。(#8712)
  • 支持在每次 LLM 调用后流式推送 Agent 统计信息。 (#9260)
  • 新增 Text Embeddings Inference（TEI）重排序提供商。 (#9274)
  • 新增可配置的嵌入维度发送模式。 (#9245)

变更

  • 精简并简化 WebUI 侧边栏。 (#9233, #9313)
  • 配置快照保存改为异步且具备版本感知，避免阻塞事件循环或覆盖较新的状态。 (#9300)
  • 通过比较工具名称和参数，优化重复工具调用检测。 (#9311)
  • 将核心日志翻译为英文。 (#9318)

修复

  • 配置上下文上限后优先使用该值。 (#9263)
  • 删除未保存的提供商来源时，同步从本地状态移除。 (#9264)
  • 修正带版本号的 Skill 下载归档文件名。 (#9270)
  • 补充 Dashboard API 兜底异常处理。 (#9271)
  • 为知识库部分上传失败增加补偿处理。 (#9007, #9246)
  • 移除 Dashboard 中重复的平台日志。 (#9291)
  • 恢复非安全 HTTP 来源下的代码块复制功能。 (#9267)
  • 正确处理 ChatUI 后续消息。 (#9309)
  • 避免 python-ripgrep 在 Python 3.14 上崩溃。 (#9244)
  • 避免在每次工具调用前都输出用途说明。
  • 在建议面板打开时隐藏命令提示。 (#9312)
  • 避免将插件仓库 URL 误匹配为插件名称。 (#9314)
  • 支持解析带 UTF-8 BOM 标记的插件 Schema。 (#9223)
  • 使插件处理器绑定具备幂等性，避免重复传入 self 参数。 (#9316)
View diff on GitHub

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

Share on X Share on Bluesky

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]