Skip to content

Releases: lujoai/Lujo-MCP

Lujo-MCP v0.5.0

Choose a tag to compare

@Ljj041120 Ljj041120 released this 13 Aug 00:49

Highlights

  • DebugContext Schema Alignment — Pydantic model expanded from 7 to 20 fields, aligned with build_debug_context() output
  • Runtime Debug Context Integrationbuild_debug_context() now returns DebugContext | None (Pydantic model) instead of plain dict
  • MCP Tool Category Metadata — All 17 MCP tools tagged with category (agent/sdk) and experimental fields in tools/list response
  • Prompt Injection Protection — LLM analyzer and Agent layer hardened with evidence wrapping (<debug_evidence> XML tags) and injection guard
  • API Schema Validation/verify and /verify/ui endpoints now use Pydantic models (VerifyRequest/VerifyUiRequest) with extra="ignore"
  • Session Security Hardening — Session limit (10,000) with LRU eviction, /internal/health IP-based access control

Compatibility

  • MCP Protocol unchanged (2024-11-05)
  • Existing MCP clients compatible (new category/experimental fields are optional, ignored by old clients)
  • No breaking changes — all new fields are Optional with defaults
  • DebugContext JSON structure unchanged (model_dump() produces equivalent output)

Not included

The following features are not implemented in v0.5.0:

  • Repair Loop — planned for v0.5.2
  • Auto Patch — planned for v0.5.2
  • Automatic Code Repair — planned for v0.5.2
  • Source Map parsing — planned for v0.5.1
  • Browser SDK enhancements — planned for v0.5.1

Test Results

992 passed, 6 skipped, 0 failed

Lujo-MCP v0.4.1-beta

Lujo-MCP v0.4.1-beta Pre-release
Pre-release

Choose a tag to compare

@Ljj041120 Ljj041120 released this 11 Aug 05:40

Lujo-MCP 是面向 AI Agent 的运行时调试上下文基础设施。

目标:让 AI Agent 不仅读取代码,还能够理解真实 Bug 运行现场。

What's New

Runtime Debug Context

  • 采集:runtime events、exceptions、stacktrace、network trace、UI events、git context、spec context

Debug Experience RAG

  • 通过历史 Debug Experience 增强 Agent 分析能力
  • retrieve_debug_experience() 三层检索:L1 fingerprint 精确 → L2 message normalize → L3 vector(默认关闭)
  • 种子知识库 + KB 验证写回

MCP Debug Context Observability(Phase 3 D5)

  • DebugContextTrace:记录 request_id / Runtime Context 可用性与大小 / Debug Experience 开关与命中数 / Context 构建耗时 / Tool 响应耗时
  • stdio + HTTP 传输层记录 tool 响应耗时/大小(仅日志,不打印敏感负载)
  • Server(...) 传入 version=0.4.1-beta 对齐 serverInfo 版本

Quality Benchmark Framework(Phase 3 D6)

  • benchmark/BenchmarkCase / EvaluationMetrics + 5 个手写 Debug Case(api_500 / frontend_blank / db_error / auth_403 / perf_slow)
  • runner.py CLI:list / show / quality 旁证
  • 验证 MCP Debug Context 是否提升外部 AI Debug 能力(与 QualityScorer 两个体系分离)

npm 开箱即用分发

  • npm install -g @lujoai/lujo-mcp 一条命令,三平台二进制(win32-x64 / linux-x64 / osx-arm64)自动安装
  • 版本统一 0.4.1-beta(app / npm / README / CHANGELOG / serverInfo / git tag)

Architecture

External MCP Client
       ↓
    MCP Server(stdio / HTTP)
       ↓
  Runtime Debug Context
       ↓
Debug Experience RAG
       ↓
     Agent
       ↓
    Verifier

Validation

测试:927 passed / 6 skipped / 0 failed(含 D5 MCP Observability 16 项 + D6 Benchmark 框架 19 项 + stacktrace 工具与存储工厂边界 17 项)

MCP Client 接入验证:stdio + HTTP 双传输 initialize / tools/list(17 工具)/ tools/call 全通过。

说明:无回归。

Architecture Rules

  • Runtime 保持纯净(不依赖 RAG / Agent / LLM / MCP)
  • RAG 独立(不反向依赖 Agent / Runtime / LLM / MCP)
  • Agent 消费 RAG(允许方向:Agent → RAG)

Limitations

当前版本:

  • 不包含自动修复
  • 不包含 Patch 生成
  • 不包含 Repair Loop

Roadmap

未来:

  • More Debug Experience
  • Better Context Collection
  • Enterprise Integration

Lujo-MCP v0.4.0

Choose a tag to compare

@Ljj041120 Ljj041120 released this 09 Aug 15:24

正式版 v0.4.0 — AI 智能调试,开箱即用

🏆 最大亮点:npm 一键安装

告别 Python 环境配置,小白用户也能直接用:

npm install -g @lujoai/lujo-mcp

✨ 核心能力

  • Runtime Debug Context(真实运行现场采集)
  • Debug Experience RAG(历史调试经验检索增强)
  • AI Debug Agent(自动修复 + 多 Agent DAG 协同)
  • Browser SDK V2-V6(网络请求捕获 / 静默失败检测)
  • 矢量检索 RAG(in-process + Qdrant 双后端)

✅ 质量验证

  • 单元测试:891 passed / 6 skipped / 0 failed
  • CI 构建:Windows/Linux/macOS 三平台全通过
  • npm 发布:3 平台二进制 + 元包全部上线

🔧 MCP 客户端配置示例

{
  "mcpServers": {
    "lujo-mcp": {
      "command": "lujo-mcp-server"
    }
  }
}

📝 变更摘要

相比 v0.3.0,本版本新增:

  • MCP Streamable HTTP 传输
  • AI Debug Agent Phase 1 + Phase 2
  • Dashboard SSE 实时推送
  • 安全加固(RBAC/LFI/SSRF 防护)
  • npm 跨平台分发

Lujo-MCP v0.4.0-beta

Lujo-MCP v0.4.0-beta Pre-release
Pre-release

Choose a tag to compare

@Ljj041120 Ljj041120 released this 07 Aug 14:47

Lujo-MCP v0.4.0-beta

Overview

Lujo-MCP 是面向 AI Agent 的运行时调试上下文基础设施。

目标:让 AI Agent 不仅读取代码,还能够理解真实 Bug 运行现场。

What's New

Runtime Debug Context

采集:

  • runtime events
  • exceptions
  • logs
  • user behavior context

Debug Experience RAG

通过历史 Debug Experience 增强 Agent 分析能力:

  • DebugExperienceRecord 输出 DTO/View(纯 View,不建存储、不替代 DebugCase)
  • retrieve_debug_experience() 三层检索:L1 fingerprint 精确 → L2 message normalize → L3 vector(默认关闭)

Context Assembly

Agent 上下文构建与 RAG 解耦:

  • _safe_debug_experience_recall() 集成于 assemble() 输出(可选字段,默认 None)
  • debug_experience_enabled 默认 False,关闭状态零调用、零耗时

Verification Foundation

提供验证能力基础(Verifier / assert engine / spec store)。

Architecture

Runtime
    ↓
Debug Context
    ↓
Debug Experience RAG
    ↓
Agent
    ↓
Verifier

Validation

测试:874 passed / 6 skipped / 0 failed

说明:无回归。

Architecture Rules

  • Runtime 保持纯净(不依赖 RAG / Agent / LLM / MCP)
  • RAG 独立(不反向依赖 Agent / Runtime / LLM / MCP)
  • Agent 消费 RAG(允许方向:Agent → RAG)

Limitations

当前版本:

  • 不包含自动修复
  • 不包含 Patch 生成
  • 不包含 Repair Loop

Roadmap

未来:

  • Debug Experience Quality Evaluation
  • Benchmark Dataset
  • Repair Loop Research
  • Human Approval Workflow