350f5a20fd
独立模块 cmd/picoclaw-voice，实现端到端语音对话链路（ASR → LLM → TTS）。 协议层基于 xiaozhi WebSocket 协议，做了适当扩展。 - 流式 ASR：豆包 / FunASR（本地） - 流式 TTS：豆包 / Fish Speech（本地） - Docker Compose 一键部署本地 ASR + TTS 服务 - Python demo 客户端用于联调
23 lines
595 B
Go
23 lines
595 B
Go
// PicoClaw - Ultra-lightweight personal AI agent
|
|
// License: MIT
|
|
//
|
|
// Copyright (c) 2026 PicoClaw contributors
|
|
|
|
package providers
|
|
|
|
import "context"
|
|
|
|
// StreamingProvider extends LLMProvider with streaming capability.
|
|
// Text tokens are delivered via onToken as they arrive from the API.
|
|
// Tool calls are accumulated internally and returned in the final *LLMResponse.
|
|
type StreamingProvider interface {
|
|
LLMProvider
|
|
ChatStream(
|
|
ctx context.Context,
|
|
messages []Message,
|
|
tools []ToolDefinition,
|
|
model string,
|
|
options map[string]any,
|
|
onToken func(string),
|
|
) (*LLMResponse, error)
|
|
}
|