项目文件夹

文件
T
Asim Aslam 9dae4e34b7 Enhance README with sponsorship CTA and improve agent architecture (#2961)
* docs: add 'become a sponsor' call-to-action linking to Discord

Now that there are a couple of sponsors, invite more: a short CTA under
the Sponsors section in the README and on the landing page, pointing to
the Discord to get in touch.

* fix(health): remove duplicate RegistryCheck declaration

Two PRs (#2957 and #2958) each added a RegistryCheck to the health
package, leaving the package uncompilable on master (RegistryCheck
redeclared: health/registry.go vs health/health.go). Keep the
health.go implementation — it honors the check's context timeout so a
hung registry (e.g. an unreachable etcd) reports down instead of
blocking the probe — and remove the duplicate registry.go and its test.
registry_check_test.go already covers healthy/down/nil/timeout/not-ready.

* feat(agent): pluggable memory and custom tools

Make agents compose the way services do — pluggable pieces with working
defaults — by adding the two abstractions an agent needs beyond the model:

- Memory: a pluggable interface for conversation memory. The default is
  store-backed and durable across restarts (the previous hardcoded
  behavior, now behind an interface); supply your own with WithMemory
  (in-memory, database, semantic store). NewMemory / NewInMemory provided.
- Custom tools: WithTool registers any function as a tool the agent can
  call, so agents are no longer limited to orchestrating RPC services.

Both exposed at the micro package (AgentMemory, AgentTool, NewMemory,
NewInMemory). Behavior-preserving refactor of the agent's history into
the default Memory; tests cover persistence, in-memory, clear, custom
tool dispatch and errors. README + AGENT_DESIGN document the pluggable
composition (model / memory / tools / guardrails).

* blog: 'Doubling Down on Agents' (#20)

The vision post for making agents a first-class framework the way
services were: opinionated, batteries-included, pluggable. Frames an
agent as a composition of model + memory + tools + guardrails with
working defaults; introduces the new pluggable memory and custom tools;
makes the microagents argument (an agent for everything, distributed
like microservices); and lays out the three primitives — services,
agents, workflows — as one substrate, with an honest list of the gaps
still to fill (knowledge/retrieval, streaming, explicit loop).

---------

Co-authored-by: Claude <noreply@anthropic.com>
2026-06-10 11:04:23 +01:00

159 行
4.4 KiB
Go

package agent
import (
"context"
"go-micro.dev/v5/ai"
"go-micro.dev/v5/client"
"go-micro.dev/v5/registry"
"go-micro.dev/v5/store"
)
// Option configures an Agent.
type Option func(*Options)
// ApproveFunc decides whether an agent may execute a tool call before it
// runs. Returning false blocks the call; the reason is shown to the
// model so it can adapt. Use it for human-in-the-loop approval or policy
// checks. It is called for actions (service tools and delegate), not for
// the internal plan tool.
type ApproveFunc func(tool string, input map[string]any) (approved bool, reason string)
// ToolFunc handles a custom tool call. Return the result as a string
// (often JSON); return an error to report failure back to the model.
type ToolFunc func(ctx context.Context, input map[string]any) (string, error)
// customTool is a developer-registered tool beyond the agent's services.
type customTool struct {
def ai.Tool
handler ToolFunc
}
// Options holds agent configuration.
type Options struct {
Name string
Services []string
Prompt string
Provider string
Model string
APIKey string
Registry registry.Registry
Client client.Client
Store store.Store
HistoryLimit int
// Memory is the agent's conversation memory. Nil = the default
// store-backed memory (durable across restarts).
Memory Memory
// MaxSteps bounds the number of tool executions per Ask (0 =
// unbounded). Once exceeded, further tool calls are refused and the
// model is told to stop and summarize. A stopping condition.
MaxSteps int
// Approve gates each action before it runs. Nil = allow all.
Approve ApproveFunc
// tools are developer-registered custom tools (see WithTool).
tools []customTool
}
func newOptions(opts ...Option) Options {
o := Options{
Registry: registry.DefaultRegistry,
Client: client.DefaultClient,
Store: store.DefaultStore,
HistoryLimit: 50,
}
for _, opt := range opts {
opt(&o)
}
return o
}
// Name sets the agent name.
func Name(n string) Option {
return func(o *Options) { o.Name = n }
}
// Services sets which services this agent manages.
func Services(names ...string) Option {
return func(o *Options) { o.Services = names }
}
// Prompt sets the system prompt.
func Prompt(p string) Option {
return func(o *Options) { o.Prompt = p }
}
// Provider sets the LLM provider.
func Provider(p string) Option {
return func(o *Options) { o.Provider = p }
}
// Model sets the LLM model name.
func Model(m string) Option {
return func(o *Options) { o.Model = m }
}
// APIKey sets the API key for the LLM provider.
func APIKey(k string) Option {
return func(o *Options) { o.APIKey = k }
}
// WithRegistry sets the service registry.
func WithRegistry(r registry.Registry) Option {
return func(o *Options) { o.Registry = r }
}
// WithClient sets the RPC client.
func WithClient(c client.Client) Option {
return func(o *Options) { o.Client = c }
}
// WithStore sets the store for agent memory.
func WithStore(s store.Store) Option {
return func(o *Options) { o.Store = s }
}
// HistoryLimit sets the max conversation messages to retain.
func HistoryLimit(n int) Option {
return func(o *Options) { o.HistoryLimit = n }
}
// MaxSteps bounds tool executions per Ask (0 = unbounded). A stopping
// condition: beyond the limit, tool calls are refused and the model is
// told to stop and summarize.
func MaxSteps(n int) Option {
return func(o *Options) { o.MaxSteps = n }
}
// ApproveTool sets a human-in-the-loop / policy hook called before each
// action (service tools and delegate). Returning false blocks the call.
func ApproveTool(fn ApproveFunc) Option {
return func(o *Options) { o.Approve = fn }
}
// WithMemory sets the agent's conversation memory. The default is
// store-backed memory keyed by agent name; supply your own to use an
// in-process, database, or semantic store.
func WithMemory(m Memory) Option {
return func(o *Options) { o.Memory = m }
}
// WithTool registers a custom tool the agent can call, beyond the
// services it discovers — a local function, an external API, anything.
// properties is the JSON-schema map for the tool's parameters.
func WithTool(name, description string, properties map[string]any, handler ToolFunc) Option {
return func(o *Options) {
o.tools = append(o.tools, customTool{
def: ai.Tool{
Name: name,
OriginalName: name,
Description: description,
Properties: properties,
},
handler: handler,
})
}
}