项目文件夹

文件
T
Asim Aslam 1bb25d6e7f Add agent platform showcase and refactor project structure (#2884)
* feat: add agent platform showcase and blog post

Add a complete platform example (Users, Posts, Comments, Mail) that
mirrors micro/blog, demonstrating how existing microservices become
AI-accessible through MCP with zero code changes.

Includes blog post "Your Microservices Are Already an AI Platform"
walking through real agent workflows: signup, content creation,
commenting, tagging, and cross-service messaging.

https://claude.ai/code/session_01GkduEhcrqcG45rdfYh8dAc

* refactor: rename handler types to drop redundant Service suffix

UserService → Users, PostService → Posts, CommentService → Comments,
MailService → Mail. Matches micro/blog naming convention.

https://claude.ai/code/session_01GkduEhcrqcG45rdfYh8dAc

* refactor: consolidate top-level directories, reduce framework bloat

Move internal/non-public packages behind internal/ or into their
parent packages where they belong:

- deploy/ → gateway/mcp/deploy/ (Helm charts belong with the gateway)
- profile/ → service/profile/ (preset plugin profiles are a service concern)
- scripts/ → internal/scripts/ (install script is not public API)
- test/ → internal/test/ (test harness is not public API)
- util/ → internal/util/ (internal helpers shouldn't be imported externally)

Also fixes CLAUDE.md merge conflict markers and updates project
structure documentation.

All import paths updated. Build and tests pass.

https://claude.ai/code/session_01GkduEhcrqcG45rdfYh8dAc

* refactor: redesign model package to match framework conventions

Rename model.Database interface to model.Model (consistent with
client.Client, server.Server, store.Store). Remove generics in
favor of interface{}-based API with reflection.

Key changes:
- model.Model interface: Register once, CRUD infers table from type
- DefaultModel + NewModel() + package-level convenience functions
- Schema registered via Register(&User{}), no per-call schema passing
- Memory implementation as default (in model package, like store)
- memory/sqlite/postgres backends updated for new interface
- protoc-gen-micro generates RegisterXModel() instead of generic factory
- All docs, blog, and README updated

https://claude.ai/code/session_01GkduEhcrqcG45rdfYh8dAc

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-03-05 11:21:41 +00:00

5.9 KiB

CLAUDE.md - Go Micro Project Guide

Project Overview

Go Micro is a framework for distributed systems development in Go. It provides pluggable abstractions for service discovery, RPC, pub/sub, config, auth, storage, and more.

The framework is evolving into an AI-native platform where every microservice is automatically accessible to AI agents via the Model Context Protocol (MCP).

Build & Test

# Run all tests
make test

# Run tests for a specific package
go test ./gateway/mcp/...
go test ./ai/...
go test ./model/...

# Lint
make lint

# Format
make fmt

# Build CLI
go build -o micro ./cmd/micro

# Run locally with hot reload
micro run

Project Structure

go-micro/
├── ai/             # AI model providers (Anthropic, OpenAI)
├── auth/           # Authentication (JWT, no-op)
├── broker/         # Message broker (NATS, RabbitMQ)
├── cache/          # Caching (Redis)
├── client/         # RPC client (gRPC)
├── cmd/micro/      # CLI tool (run, deploy, mcp, build, server)
├── codec/          # Message codecs (JSON, Proto)
├── config/         # Dynamic config (env, file, etcd, NATS)
├── errors/         # Error handling
├── events/         # Event system (NATS JetStream)
├── gateway/
│   ├── api/        # REST API gateway
│   └── mcp/        # MCP gateway (core AI integration)
│       └── deploy/ # Helm charts for MCP gateway
├── health/         # Health checking
├── logger/         # Logging
├── metadata/       # Context metadata
├── model/          # Typed data models (CRUD, queries, schemas)
├── registry/       # Service discovery (mDNS, Consul, etcd)
├── selector/       # Client-side load balancing
├── server/         # RPC server
├── service/        # Service interface + profiles
├── store/          # Data persistence (Postgres, NATS KV)
├── transport/      # Network transport
├── wrapper/        # Middleware (auth, trace, metrics)
├── examples/       # Working examples
└── internal/       # Non-public: docs, utils, test harness

Key Architectural Decisions

  • Plugin architecture: All abstractions use Go interfaces. Defaults work out of the box, everything is swappable.
  • Progressive complexity: Zero-config for development, full control for production.
  • AI-native by default: Every service is automatically an MCP tool. No extra code needed.
  • In-repo plugins: Plugins live in the main repo to avoid version compatibility issues.
  • Reflection-based registration: Handlers are registered via reflection for minimal boilerplate.

Code Conventions

  • Standard Go conventions (gofmt, golint)
  • Functional options pattern for configuration (WithX() functions)
  • Interface-first design: define the interface, then implement
  • Tests alongside code (not in separate test directories)
  • Commit messages: imperative mood, concise summary line

Current Focus & Priorities (March 2026)

Status

  • Q1 2026 (MCP Foundation): COMPLETE
  • Q2 2026 (Agent DX): COMPLETE (100%)
  • Q3 2026 (Production): 50% complete (ahead of schedule)

Priority 1: Agent Showcase & Examples

Build compelling demos showing agents interacting with go-micro services in realistic scenarios.

Priority 2: Additional Protocol Support

  • gRPC reflection-based MCP
  • HTTP/3 support

Priority 3: Kubernetes & Deployment

  • Helm Charts for MCP gateway
  • Kubernetes Operator with CRDs

Recently Completed

  • micro new MCP Templates - Scaffolds MCP-enabled services with doc comments, @example tags, WithMCP(). --no-mcp to opt out.
  • CRUD Example - Contact book service with 6 operations, rich agent docs (examples/mcp/crud/)
  • Migration Guide - "Add MCP to Existing Services" guide with 3 approaches
  • Troubleshooting Guide - Common MCP issues and solutions
  • Error Handling Guide - Patterns for agent-friendly error responses
  • Documentation Guides - Six guides: AI-native services, MCP security, tool descriptions, agent patterns, error handling, troubleshooting
  • WithMCP Option - One-line MCP setup (gateway/mcp/option.go)
  • Agent Playground Redesign - Chat-focused UI with collapsible tool calls
  • Standalone Gateway Binary - micro-mcp-gateway with Docker support
  • WebSocket Transport - Bidirectional JSON-RPC 2.0 streaming (gateway/mcp/websocket.go)
  • OpenTelemetry Integration - Full span instrumentation with W3C trace context (gateway/mcp/otel.go)
  • LlamaIndex SDK - Python package with RAG examples (contrib/go-micro-llamaindex/)

Key Files

Purpose File
MCP Gateway gateway/mcp/mcp.go
MCP Docs gateway/mcp/DOCUMENTATION.md
AI Interface ai/model.go
Model Layer model/model.go
CLI Entry cmd/micro/main.go
MCP CLI cmd/micro/mcp/
Server (run/server) cmd/micro/server/server.go
Roadmap internal/docs/ROADMAP_2026.md
Status internal/docs/CURRENT_STATUS_SUMMARY.md
Changelog CHANGELOG.md
Docs Site internal/website/docs/

Roadmap & Status Documents

Contributing

See CONTRIBUTING.md for full guidelines. Key points:

  • Open an issue before large changes
  • Include tests for new features
  • Run make test and make lint before submitting
  • Follow commit message format: type: description (e.g., feat: add WebSocket transport)