项目文件夹

文件
Asim Aslam 1bc886fa82 Introduce Agent abstraction and integrate with chat router (#2939)
* docs: Agent interface design sketch

Proposes Agent as a top-level abstraction alongside Service in the
micro package. Agent manages services — scoped tools, system prompt,
conversation memory, registry-discoverable.

Design only, no implementation.

https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd

* feat: Agent as a first-class abstraction

Introduce micro.NewAgent() alongside micro.New() — Agent is to
intelligence what Service is to capability.

Agent interface:
- Chat(ctx, message) (*Response, error) — core interaction method
- Run() — registers in registry, subscribes to broker, blocks
- Stop() — graceful shutdown
- Scoped tools — only sees endpoints of its assigned services
- Persistent memory — conversation history stored in store
- Agent-to-agent — communication via broker topics

Top-level API:
  agent := micro.NewAgent("task-mgr",
      micro.AgentServices("task"),
      micro.AgentPrompt("You manage tasks."),
      micro.AgentProvider("anthropic"),
  )
  agent.Run()

https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd

* feat: wire agents into chat router, add micro agent CLI, expose Flow

Three top-level abstractions:
  micro.New("task")              — Service (capability)
  micro.NewAgent("task-mgr")     — Agent (intelligence)
  micro.NewFlow("onboard-user")  — Flow (event-driven orchestration)

micro chat as router:
- Discovers agents from registry on startup
- Single agent: routes directly
- Multiple agents: LLM classifies intent, dispatches to right agent
  via route_to_agent tool
- No agents: falls back to current direct-service behaviour
- Banner shows discovered agents

micro agent CLI:
- micro agent list — shows registered agents and their services
- micro agent describe <name> — shows agent details from registry

https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd

* feat: move flow to top level, update docs for three abstractions

Package structure now consistent:
  service/   — Service (capability)
  agent/     — Agent (intelligence)
  flow/      — Flow (event-driven orchestration)

ai/flow/ kept as backward-compatible re-export.

Updated across all surfaces:
- CLAUDE.md: added agent/ and flow/ to project structure
- README: added "Building Agents" section with NewAgent() examples,
  updated features table (Agents, Flows, Chat router), CLI table
  (agent list, agent describe), docs links
- Website: features grid shows Services, Agents, Flows as the three
  pillars alongside generation, MCP, and pluggable architecture
- micro.go: Flow imported from top-level flow/ package

https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd

* docs: rewrite getting-started, fix ai-integration import paths

Getting started now covers all three abstractions:
- Service (write handlers, micro run, templates)
- Agent (micro.NewAgent, scoped tools, memory, CLI)
- Flow (event-driven LLM orchestration)
Leads with prompt-based generation, then manual service creation.

ai-integration.md: fixed flow import path from go-micro.dev/v5/ai/flow
to go-micro.dev/v5/flow, updated stack diagram to show agent/flow/chat.

https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd

* blog: Introducing micro.NewAgent()

Post 16 — announces Agent as a first-class abstraction. Shows the
API (NewAgent, AgentServices, AgentPrompt, AgentProvider), scoped
tools, persistent memory, multi-service agents, multi-agent systems,
and the three-abstraction comparison table (Service/Agent/Flow).

https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd

* feat: fix agent registration, blog post 16

Agent registration:
- Add node with address so mDNS can discover agents
- Store type and services in node metadata (mDNS requirement)
- Connect broker before subscribing, non-fatal if broker unavailable
- Print registration confirmation on Run()

Agent/chat discovery:
- Check both service-level and node-level metadata for type=agent
  (mDNS stores metadata on nodes, not services)

Blog post 16: "Introducing micro.NewAgent()" — announces the Agent
abstraction with code examples, comparison table, multi-agent patterns.

Tested end-to-end: micro run → micro agent list discovers the agent →
micro chat routes to it → agent calls service endpoints.

https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd

* feat: agents are proper services with RPC Chat endpoint

Refactored agent to use server.Server instead of fake registry entries.
An agent now:
- Creates a real RPC server with server.Name(agentName)
- Registers an Agent.Chat handler callable via standard RPC
- Sets server metadata type=agent, services=x,y for discovery
- No more fake addresses or broker hacks

micro chat calls agents via RPC (client.Call) instead of creating
local agent instances. The registry stays clean — agents are real
services with real endpoints.

Removed broker dependency from agent options. Agent-to-agent
communication is just RPC like everything else.

https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd

* feat: agent uses proto-defined RPC interface

Added agent/proto/agent.proto with Agent service definition:
  rpc Chat(ChatRequest) returns (ChatResponse)

Agent now implements the generated AgentHandler interface and
registers via pb.RegisterAgentHandler. The Chat endpoint is a
standard proto-based RPC callable by any go-micro client.

Renamed the programmatic API from Chat() to Ask() to avoid
collision with the proto handler method name.

micro chat calls agents via standard RPC with JSON-encoded
request/response — no special types needed on the caller side.

https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd

* feat: generate agent alongside services, update all docs

micro run --prompt now generates an agent binary that manages all
the generated services. The agent reads MICRO_AI_PROVIDER and
MICRO_AI_API_KEY from the environment. micro run propagates these
when started with --prompt.

Run banner shows services and agents separately.

Updated README, getting-started guide, and landing page to show
the complete flow: generate → services + agent start → micro chat
routes to agent → agent orchestrates services.

https://claude.ai/code/session_01QTp4SshuVmLAvvEGJe4TJd

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-06-05 10:25:14 +01:00

207 行
5.3 KiB
Go

package microcli
import (
"context"
"encoding/json"
"fmt"
"os"
"os/exec"
"github.com/urfave/cli/v2"
"go-micro.dev/v5/client"
"go-micro.dev/v5/cmd"
"go-micro.dev/v5/codec/bytes"
"go-micro.dev/v5/registry"
"go-micro.dev/v5/cmd/micro/cli/new"
"go-micro.dev/v5/cmd/micro/cli/util"
// Import packages that register commands via init()
_ "go-micro.dev/v5/cmd/micro/cli/agent"
_ "go-micro.dev/v5/cmd/micro/cli/build"
_ "go-micro.dev/v5/cmd/micro/cli/deploy"
_ "go-micro.dev/v5/cmd/micro/cli/init"
_ "go-micro.dev/v5/cmd/micro/cli/remote"
)
var (
// version is set by the release action
// this is the default for local builds
version = "5.0.0-dev"
)
func genProtoHandler(c *cli.Context) error {
cmd := exec.Command("find", ".", "-name", "*.proto", "-exec", "protoc", "--proto_path=.", "--micro_out=.", "--go_out=.", `{}`, `;`)
cmd.Stdout = os.Stdout
cmd.Stderr = os.Stderr
return cmd.Run()
}
func init() {
cmd.Register([]*cli.Command{
{
Name: "new",
Usage: "Create a new service",
ArgsUsage: "[name]",
UsageText: ` micro new helloworld # scaffold a single service
micro new --prompt "a todo list with tasks" # AI-design multiple services
micro new --prompt "add tags to the task service" # extend existing services`,
Action: new.Run,
Flags: []cli.Flag{
&cli.BoolFlag{
Name: "no-mcp",
Usage: "Disable MCP gateway integration in generated code",
},
&cli.StringFlag{
Name: "template",
Usage: "Service template: default, crud, pubsub, api",
},
&cli.StringFlag{
Name: "prompt",
Usage: "Describe the system to generate (uses AI to design & build services with real business logic)",
EnvVars: []string{"MICRO_NEW_PROMPT"},
},
&cli.StringFlag{
Name: "provider",
Usage: "AI provider for --prompt (anthropic, openai, gemini, atlascloud, groq, mistral, together)",
EnvVars: []string{"MICRO_AI_PROVIDER"},
},
&cli.StringFlag{
Name: "api_key",
Usage: "API key for --prompt (or set ANTHROPIC_API_KEY, OPENAI_API_KEY, etc.)",
EnvVars: []string{"MICRO_AI_API_KEY"},
},
},
},
{
Name: "gen",
Usage: "Generate various things",
Subcommands: []*cli.Command{
{
Name: "proto",
Usage: "Generate proto requires protoc and protoc-gen-micro",
Action: genProtoHandler,
},
},
},
{
Name: "services",
Usage: "List available services",
Action: func(ctx *cli.Context) error {
services, err := registry.ListServices()
if err != nil {
return err
}
for _, service := range services {
fmt.Println(service.Name)
}
return nil
},
},
{
Name: "call",
Usage: "Call a service",
Flags: []cli.Flag{
&cli.StringSliceFlag{
Name: "header",
Aliases: []string{"H"},
Usage: "Set request headers (can be used multiple times): --header 'Key:Value'",
},
&cli.StringSliceFlag{
Name: "metadata",
Aliases: []string{"m"},
Usage: "Set request metadata (can be used multiple times): --metadata 'Key:Value'",
},
},
Action: func(ctx *cli.Context) error {
args := ctx.Args()
if args.Len() < 2 {
return fmt.Errorf("Usage: [service] [endpoint] [request]")
}
service := args.Get(0)
endpoint := args.Get(1)
request := `{}`
if args.Len() == 3 {
request = args.Get(2)
}
// Create context with metadata if provided
// Note: This is for the direct 'micro call' command.
// Dynamic service calls (e.g., 'micro helloworld call') are handled in CallService.
callCtx := context.TODO()
callCtx = util.AddMetadataToContext(callCtx, ctx.StringSlice("metadata"))
callCtx = util.AddMetadataToContext(callCtx, ctx.StringSlice("header"))
req := client.NewRequest(service, endpoint, &bytes.Frame{Data: []byte(request)})
var rsp bytes.Frame
err := client.Call(callCtx, req, &rsp)
if err != nil {
return err
}
fmt.Print(string(rsp.Data))
return nil
},
},
{
Name: "describe",
Usage: "Describe a service",
Action: func(ctx *cli.Context) error {
args := ctx.Args()
if args.Len() != 1 {
return fmt.Errorf("Usage: [service]")
}
service := args.Get(0)
services, err := registry.GetService(service)
if err != nil {
return err
}
if len(services) == 0 {
return nil
}
b, _ := json.MarshalIndent(services[0], "", " ")
fmt.Println(string(b))
return nil
},
},
// Note: The following commands are registered in their respective packages:
// - status, logs, stop: remote/remote.go
// - build: build/build.go
// - deploy: deploy/deploy.go
// - init: init/init.go
}...)
cmd.App().Action = func(c *cli.Context) error {
if c.Args().Len() == 0 {
return nil
}
v, err := exec.LookPath("micro-" + c.Args().First())
if err == nil {
ce := exec.Command(v, c.Args().Slice()[1:]...)
ce.Stdout = os.Stdout
ce.Stderr = os.Stderr
return ce.Run()
}
command := c.Args().Get(0)
args := c.Args().Slice()
if srv, err := util.LookupService(command); err != nil {
return util.CliError(err)
} else if srv != nil && util.ShouldRenderHelp(args) {
return cli.Exit(util.FormatServiceUsage(srv, c), 0)
} else if srv != nil {
err := util.CallService(srv, args)
return util.CliError(err)
}
return nil
}
}