6b29f659e5
1. 修复 mention_router 中的 IDOR 越权安全漏洞，加入 thread 归属权校验，定义强类型 Pydantic Schema。 2. 修复 mention_search_service 中 ensure_thread_dirs 的 GET 副作用、空 Query 扫描和 MAX_SEARCH_DEPTH 深度问题，使用标准 Base64 编解码。 3. 增加前端 mention_api.js 参数的安全兜底。 4. 重构 AgentPanel 自动展开策略，彻底解决大仓库克隆时的卡死问题： - 将 fetchThreadFiles 改为 recursive=false 避免递归大目录。 - 重构为只有在发生显性的物理文件写入（用户上传附件成功、用户保存交付件到工作区成功）的回调中才精准触发侧边栏自动展开，完美契合用户心智模型与性能诉求。 5. 精简 roadmap.md 文档，更新相关单元测试。 |
||
|---|---|---|
| .github | ||
| backend | ||
| docker | ||
| docs | ||
| scripts | ||
| web | ||
| .dockerignore | ||
| .env.template | ||
| .gitignore | ||
| AGENTS.md | ||
| ARCHITECTURE.md | ||
| CLAUDE.md | ||
| CONTRIBUTING.md | ||
| docker-compose.prod.yml | ||
| docker-compose.yml | ||
| LICENSE | ||
| Makefile | ||
| README.en.md | ||
| README.md | ||
*Image generated by GPT-Image-2.
Core Features
- Agent development: Built on LangGraph, with support for sub-agents, Skills, MCPs, Tools, and middleware.
- Knowledge base (RAG): Multi-format document parsing, Embedding / Rerank configuration, and knowledge base evaluation.
- Knowledge graph: Graph construction and visualization based on LightRAG, with property graph support for agent reasoning.
- Platform and engineering: Vue + FastAPI architecture with dark mode, Docker-based development, and production-oriented deployment.
Quick Start
Clone the repository and initialize the project:
git clone --branch v0.6.2 --depth 1 https://github.com/xerrors/Yuxi.git
cd Yuxi
# Linux/macOS
./scripts/init.sh
# Windows PowerShell
.\scripts\init.ps1
Start the project with Docker:
docker compose up --build
After the services are ready, open http://localhost:5173.
Examples and Demo
Home |
Dashboard Statistics |
Agent Configuration |
Knowledge Base Invocation |
|
Create Knowledge Base |
Knowledge Base Management |
|
Knowledge Graph Visualization |
Project Documentation |
Extension Management (Skills) |
Extension Management (MCPs) |
|
User / Department Permission Management |
Model Provider Configuration |
Acknowledgements
Yuxi references and builds on the following excellent open-source projects:
- LightRAG - Used as the foundation for graph construction and retrieval.
- DeepAgents - Used as the deep agent framework.
- DeerFlow - Referenced for Sandbox agent architecture ideas.
- RAGflow - Referenced for document text chunking strategies.
- LangGraph - Multi-agent orchestration framework and the core architectural foundation of this project.
- QwenPaw - Referenced for model configuration and personal file area design.
Contributing
Thanks to all contributors for supporting this project!
Star History
📄 License
This project is licensed under the MIT License. See LICENSE for details.
If this project helps you, please give us a ⭐️.