v4.13.2

labring/FastGPTv4.13.2Oct 21, 2025by c121914yu

AI Summary

Adds HTTP tool manual creation mode, OpenAPI framework integration, and APIKey validation. It also optimizes workflow canvas performance and introduces several new plugins.

Key Highlights

  • Manual creation mode for HTTP tools
  • Introduction of OpenAPI framework
  • APIKey validity check endpoint
  • Export logs now include global variables.

New Features

  • HTTP manual creation
  • OpenAPI framework
  • APIKey validation
  • Export logs with global variables
  • Audit log visibility restriction
  • S3 for app avatars
  • Workflow canvas performance
  • Fix for LLM vision defaults
  • Mongo replica watch fix
  • Text chunking fix
  • Variable validation fix
  • Complex loop/parallel fix

Full Release Notes

## 🚀 新增内容

1. HTTP 工具集支持手动创建模式。 @newfish-cmyk 
2. 项目 OpenAPI 框架引入。 @xqvvu 
3. APIKey 有效性检测接口。 @c121914yu 
4. 导出对话日志,末尾跟随当前版本全局变量。 @c121914yu 

## ⚙️ 优化

1. 非管理员无法看到团队审计日志。@c121914yu 
2. 引入 S3 用于存储应用头像。 @xavierxcn 
3. 工作流画布性能。@c121914yu 

## 🐛 修复

1. LLM 模型默认支持图片,导致请求错误。@c121914yu 
2. Mongo 多副本切换时候,watch 未重新触发。@c121914yu 
3. 文本分块,所有策略用完后,未处理 LastText 数据。@c121914yu 
4. 变量输入框,number=0 时,无法通过校验。@c121914yu 
5. 工作流复杂循环并行判断异常。@c121914yu 

## 🔨 插件更新

1. 新增:Perplexity search 工具。
2. 新增:Base64转文件工具。
3. 新增:MiniMax TTS 文件生成工具。
4. 新增:Openrouter nano banana 绘图工具。
5. 新增:Redis 缓存操作工具。
6. 新增:Tavily search 工具。
7. 新增:硅基流动 qwen-image 和 qwen-image-edit 工具。
8. 新增:飞书多维表格操作套件。
9. 新增:Youtube 字幕提取。
10. 新增:阿里百炼 qwen image edit。
11. 新增:Markdown 转 PPT 工具。
12. 新增:whisper 语音转文字工具。
13. 系统工具支持配置是否需要在 Worker 中运行。

## What's Changed
* deploy doc by @c121914yu in https://github.com/labring/FastGPT/pull/5729
* doc by @c121914yu in https://github.com/labring/FastGPT/pull/5730
* fix: docker-compose pg_url removal; depends on pg -> vectorDB by @FinleyGe in https://github.com/labring/FastGPT/pull/5733
* fix: usage repeat by @c121914yu in https://github.com/labring/FastGPT/pull/5735
* hide audit by @c121914yu in https://github.com/labring/FastGPT/pull/5740
* update dockerfile (#105) by @c121914yu in https://github.com/labring/FastGPT/pull/5749
* Fixing Display Image Error Issues by @lizhq in https://github.com/labring/FastGPT/pull/5745
* dockerfile by @c121914yu in https://github.com/labring/FastGPT/pull/5750
* add user active tracks by @newfish-cmyk in https://github.com/labring/FastGPT/pull/5754
* fix: set vision default false by @c121914yu in https://github.com/labring/FastGPT/pull/5758
* Update 4132.mdx by @c121914yu in https://github.com/labring/FastGPT/pull/5766
* feat: add health check to MongoDB service in Docker Compose templates by @FinleyGe in https://github.com/labring/FastGPT/pull/5776
* chore(deps): bump mammoth from 1.9.0 to 1.11.0 by @dependabot[bot] in https://github.com/labring/FastGPT/pull/5781
* add 10-minute auto-refresh for token login by @newfish-cmyk in https://github.com/labring/FastGPT/pull/5788
* fix: resolve MCP service modal checkbox double-click event issue by @FinleyGe in https://github.com/labring/FastGPT/pull/5790
* V4.13.2 features by @c121914yu in https://github.com/labring/FastGPT/pull/5792
* fix: start node check by @c121914yu in https://github.com/labring/FastGPT/pull/5794
* perf: init s3 by @c121914yu in https://github.com/labring/FastGPT/pull/5795

## New Contributors
* @lizhq made their first contribution in https://github.com/labring/FastGPT/pull/5745

**Full Changelog**: https://github.com/labring/FastGPT/compare/v4.13.1...v4.13.2