Documentation
¶
Overview ¶
Package metaagent provides a generic framework for building AI agents.
The framework is fully generic over three type parameters:
- Req: The request type (must implement promptbuilder.Bindable)
- Resp: The structured response type returned by the agent
- CB: The callbacks type providing tool implementations
This design allows agents to be composed with any combination of tools from the toolcall package (worktree tools, finding tools, custom tools).
Model Support ¶
The framework supports both Claude and Gemini models:
- Models starting with "gemini-" use Google's Generative AI SDK
- Models starting with "claude-" use Anthropic's SDK via Vertex AI
Usage ¶
Define your callback type by composing tool callbacks:
type MyCallbacks = toolcall.FindingTools[toolcall.WorktreeTools[toolcall.EmptyTools]]
Create the corresponding tool provider:
tools := toolcall.NewFindingToolsProvider[*Result, toolcall.WorktreeTools[toolcall.EmptyTools]](
toolcall.NewWorktreeToolsProvider[*Result, toolcall.EmptyTools](
toolcall.NewEmptyToolsProvider[*Result](),
),
)
Configure and create the agent:
config := metaagent.Config[*Result, MyCallbacks]{
SystemInstructions: systemPrompt,
UserPrompt: userPrompt,
Tools: tools,
}
agent, err := metaagent.New[*Request, *Result, MyCallbacks](ctx, projectID, region, model, config)
result, err := agent.Execute(ctx, request, callbacks)
The agent uses the submit_result tool to return structured results. The Resp type's JSON tags define the schema for the tool's payload.
Index ¶
Examples ¶
Constants ¶
This section is empty.
Variables ¶
This section is empty.
Functions ¶
This section is empty.
Types ¶
type Agent ¶
type Agent[Req promptbuilder.Bindable, Resp, CB any] interface { // Execute runs the agent with the given request and tool callbacks. Execute(ctx context.Context, request Req, callbacks CB) (Resp, error) }
Agent is the interface for a configured meta-agent.
- Req must implement promptbuilder.Bindable.
- Resp is the structured response type.
- CB is the type providing all tool callbacks.
func New ¶
func New[Req promptbuilder.Bindable, Resp, CB any]( ctx context.Context, projectID, region, model string, config Config[Resp, CB], ) (Agent[Req, Resp, CB], error)
New creates a new meta-agent with the given configuration. The model parameter determines which provider implementation is used:
- Models starting with "gemini-" use Google's Generative AI SDK (native)
- Models starting with "claude-" use Anthropic's SDK via Vertex AI (native)
- Models in "publisher/model" format use Vertex AI's OpenAI-compatible endpoint
Example ¶
ExampleNew demonstrates creating a new meta-agent with model selection. New selects the provider implementation based on the model name prefix: "gemini-" uses Google's Generative AI SDK, "claude-" uses Anthropic via Vertex AI.
package main
import (
"context"
"fmt"
"chainguard.dev/driftlessaf/agents/metaagent"
"chainguard.dev/driftlessaf/agents/promptbuilder"
"chainguard.dev/driftlessaf/agents/toolcall"
)
// request is an example request type that implements promptbuilder.Bindable.
type request struct {
Query string
}
func (r *request) Bind(p *promptbuilder.Prompt) (*promptbuilder.Prompt, error) {
return p.BindXML("query", struct {
XMLName struct{} `xml:"query"`
Content string `xml:",chardata"`
}{
Content: r.Query,
})
}
// response is an example structured response type.
type response struct {
Answer string `json:"answer"`
}
func main() {
ctx := context.Background()
tools := toolcall.NewEmptyToolsProvider[*response]()
config := metaagent.Config[*response, toolcall.EmptyTools]{
Tools: tools,
}
// An unsupported model prefix returns an error.
_, err := metaagent.New[*request](ctx, "my-project", "us-central1", "unknown-model", config)
if err != nil {
fmt.Println("error:", err)
}
}
Output: error: unsupported model: unknown-model (expected gemini-*, claude-*, or publisher/model format)
type Config ¶
type Config[Resp, CB any] struct { // SystemInstructions is the system prompt that defines the agent's role and behavior. SystemInstructions *promptbuilder.Prompt // UserPrompt is the template for formatting the user's request. // The Req type is bound to this template via its Bind method. UserPrompt *promptbuilder.Prompt // Tools provides all tool definitions for this agent. // Compose providers using toolcall.NewFindingToolsProvider, // toolcall.NewWorktreeToolsProvider, and toolcall.NewEmptyToolsProvider. Tools toolcall.ToolProvider[Resp, CB] // MaxTurns sets the maximum number of conversation turns (LLM round-trips) // before the executor aborts. Zero means use the executor's default. MaxTurns int }
Config defines the configuration for a meta-agent instance.
- Resp is the structured response type returned by the agent.
- CB is the type providing all tool callbacks.
Source Files