🚀 快速安装
复制以下命令并运行,立即安装此 Skill:
npx @anthropic-ai/skills install github/awesome-copilot/copilot-sdk
💡 提示:需要 Node.js 和 NPM
GitHub Copilot SDK
在任何应用中使用 Python、TypeScript、Go 或 .NET 嵌入 Copilot 的代理工作流。
概述
GitHub Copilot SDK 公开了 Copilot CLI 背后的相同引擎:一个经过生产测试的代理运行时,您可以通过编程方式调用它。无需构建自己的编排——您定义代理行为,Copilot 负责规划、工具调用、文件编辑等。
先决条件
- 已安装并验证 GitHub Copilot CLI (安装指南)
- 语言运行时:Node.js 18+、Python 3.8+、Go 1.21+ 或 .NET 8.0+
验证 CLI: copilot --version
安装
Node.js/TypeScript
mkdir copilot-demo && cd copilot-demo
npm init -y --init-type module
npm install @github/copilot-sdk tsx
Python
pip install github-copilot-sdk
Go
mkdir copilot-demo && cd copilot-demo
go mod init copilot-demo
go get github.com/github/copilot-sdk/go
.NET
dotnet new console -n CopilotDemo && cd CopilotDemo
dotnet add package GitHub.Copilot.SDK
快速开始
TypeScript
import { CopilotClient } from "@github/copilot-sdk";
const client = new CopilotClient();
const session = await client.createSession({ model: "gpt-4.1" });
const response = await session.sendAndWait({ prompt: "What is 2 + 2?" });
console.log(response?.data.content);
await client.stop();
process.exit(0);
运行: npx tsx index.ts
Python
import asyncio
from copilot import CopilotClient
async def main():
client = CopilotClient()
await client.start()
session = await client.create_session({"model": "gpt-4.1"})
response = await session.send_and_wait({"prompt": "What is 2 + 2?"})
print(response.data.content)
await client.stop()
asyncio.run(main())
Go
package main
import (
"fmt"
"log"
"os"
copilot "github.com/github/copilot-sdk/go"
)
func main() {
client := copilot.NewClient(nil)
if err := client.Start(); err != nil {
log.Fatal(err)
}
defer client.Stop()
session, err := client.CreateSession(&copilot.SessionConfig{Model: "gpt-4.1"})
if err != nil {
log.Fatal(err)
}
response, err := session.SendAndWait(copilot.MessageOptions{Prompt: "What is 2 + 2?"}, 0)
if err != nil {
log.Fatal(err)
}
fmt.Println(*response.Data.Content)
os.Exit(0)
}
.NET (C#)
using GitHub.Copilot.SDK;
await using var client = new CopilotClient();
await using var session = await client.CreateSessionAsync(new SessionConfig { Model = "gpt-4.1" });
var response = await session.SendAndWaitAsync(new MessageOptions { Prompt = "What is 2 + 2?" });
Console.WriteLine(response?.Data.Content);
运行: dotnet run
流式响应
启用实时输出以获得更好的用户体验:
TypeScript
import { CopilotClient, SessionEvent } from "@github/copilot-sdk";
const client = new CopilotClient();
const session = await client.createSession({
model: "gpt-4.1",
streaming: true,
});
session.on((event: SessionEvent) => {
if (event.type === "assistant.message_delta") {
process.stdout.write(event.data.deltaContent);
}
if (event.type === "session.idle") {
console.log(); // 完成时换行
}
});
await session.sendAndWait({ prompt: "Tell me a short joke" });
await client.stop();
process.exit(0);
Python
import asyncio
import sys
from copilot import CopilotClient
from copilot.generated.session_events import SessionEventType
async def main():
client = CopilotClient()
await client.start()
session = await client.create_session({
"model": "gpt-4.1",
"streaming": True,
})
def handle_event(event):
if event.type == SessionEventType.ASSISTANT_MESSAGE_DELTA:
sys.stdout.write(event.data.delta_content)
sys.stdout.flush()
if event.type == SessionEventType.SESSION_IDLE:
print()
session.on(handle_event)
await session.send_and_wait({"prompt": "Tell me a short joke"})
await client.stop()
asyncio.run(main())
Go
session, err := client.CreateSession(&copilot.SessionConfig{
Model: "gpt-4.1",
Streaming: true,
})
session.On(func(event copilot.SessionEvent) {
if event.Type == "assistant.message_delta" {
fmt.Print(*event.Data.DeltaContent)
}
if event.Type == "session.idle" {
fmt.Println()
}
})
_, err = session.SendAndWait(copilot.MessageOptions{Prompt: "Tell me a short joke"}, 0)
.NET
await using var session = await client.CreateSessionAsync(new SessionConfig
{
Model = "gpt-4.1",
Streaming = true,
});
session.On(ev =>
{
if (ev is AssistantMessageDeltaEvent deltaEvent)
Console.Write(deltaEvent.Data.DeltaContent);
if (ev is SessionIdleEvent)
Console.WriteLine();
});
await session.SendAndWaitAsync(new MessageOptions { Prompt = "Tell me a short joke" });
自定义工具
定义 Copilot 在推理过程中可以调用的工具。当您定义工具时,您告诉 Copilot:
- 该工具做什么(描述)
- 它需要哪些参数(模式)
- 要运行什么代码(处理程序)
TypeScript (JSON Schema)
import { CopilotClient, defineTool, SessionEvent } from "@github/copilot-sdk";
const getWeather = defineTool("get_weather", {
description: "获取指定城市的当前天气", // 翻译
parameters: {
type: "object",
properties: {
city: { type: "string", description: "城市名称" }, // 翻译
},
required: ["city"],
},
handler: async (args: { city: string }) => {
const { city } = args;
// 在实际应用中,这里调用天气API
const conditions = ["sunny", "cloudy", "rainy", "partly cloudy"];
const temp = Math.floor(Math.random() * 30) + 50;
const condition = conditions[Math.floor(Math.random() * conditions.length)];
return { city, temperature: `${temp}°F`, condition };
},
});
const client = new CopilotClient();
const session = await client.createSession({
model: "gpt-4.1",
streaming: true,
tools: [getWeather],
});
session.on((event: SessionEvent) => {
if (event.type === "assistant.message_delta") {
process.stdout.write(event.data.deltaContent);
}
});
await session.sendAndWait({
prompt: "What's the weather like in Seattle and Tokyo?",
});
await client.stop();
process.exit(0);
Python (Pydantic)
import asyncio
import random
import sys
from copilot import CopilotClient
from copilot.tools import define_tool
from copilot.generated.session_events import SessionEventType
from pydantic import BaseModel, Field
class GetWeatherParams(BaseModel):
city: str = Field(description="要获取天气的城市名称") # 翻译
@define_tool(description="获取指定城市的当前天气") # 翻译
async def get_weather(params: GetWeatherParams) -> dict:
city = params.city
conditions = ["sunny", "cloudy", "rainy", "partly cloudy"]
temp = random.randint(50, 80)
condition = random.choice(conditions)
return {"city": city, "temperature": f"{temp}°F", "condition": condition}
async def main():
client = CopilotClient()
await client.start()
session = await client.create_session({
"model": "gpt-4.1",
"streaming": True,
"tools": [get_weather],
})
def handle_event(event):
if event.type == SessionEventType.ASSISTANT_MESSAGE_DELTA:
sys.stdout.write(event.data.delta_content)
sys.stdout.flush()
session.on(handle_event)
await session.send_and_wait({
"prompt": "What's the weather like in Seattle and Tokyo?"
})
await client.stop()
asyncio.run(main())
Go
type WeatherParams struct {
City string `json:"city" jsonschema:"城市名称"` // 翻译
}
type WeatherResult struct {
City string `json:"city"`
Temperature string `json:"temperature"`
Condition string `json:"condition"`
}
getWeather := copilot.DefineTool(
"get_weather",
"获取指定城市的当前天气", // 翻译
func(params WeatherParams, inv copilot.ToolInvocation) (WeatherResult, error) {
conditions := []string{"sunny", "cloudy", "rainy", "partly cloudy"}
temp := rand.Intn(30) + 50
condition := conditions[rand.Intn(len(conditions))]
return WeatherResult{
City: params.City,
Temperature: fmt.Sprintf("%d°F", temp),
Condition: condition,
}, nil
},
)
session, _ := client.CreateSession(&copilot.SessionConfig{
Model: "gpt-4.1",
Streaming: true,
Tools: []copilot.Tool{getWeather},
})
.NET (Microsoft.Extensions.AI)
using GitHub.Copilot.SDK;
using Microsoft.Extensions.AI;
using System.ComponentModel;
var getWeather = AIFunctionFactory.Create(
([Description("城市名称")] string city) => // 翻译
{
var conditions = new[] { "sunny", "cloudy", "rainy", "partly cloudy" };
var temp = Random.Shared.Next(50, 80);
var condition = conditions[Random.Shared.Next(conditions.Length)];
return new { city, temperature = $"{temp}°F", condition };
},
"get_weather",
"获取指定城市的当前天气" // 翻译
);
await using var session = await client.CreateSessionAsync(new SessionConfig
{
Model = "gpt-4.1",
Streaming = true,
Tools = [getWeather],
});
工具工作原理
当 Copilot 决定调用您的工具时:
- Copilot 发送带有参数的工具调用请求
- SDK 运行您的处理程序函数
- 结果被发送回 Copilot
- Copilot 将结果整合到其响应中
Copilot 根据用户的问题和您工具的描述来决定何时调用您的工具。
交互式 CLI 助手
构建一个完整的交互式助手:
TypeScript
import { CopilotClient, defineTool, SessionEvent } from "@github/copilot-sdk";
import * as readline from "readline";
const getWeather = defineTool("get_weather", {
description: "获取指定城市的当前天气", // 翻译
parameters: {
type: "object",
properties: {
city: { type: "string", description: "城市名称" }, // 翻译
},
required: ["city"],
},
handler: async ({ city }) => {
const conditions = ["sunny", "cloudy", "rainy", "partly cloudy"];
const temp = Math.floor(Math.random() * 30) + 50;
const condition = conditions[Math.floor(Math.random() * conditions.length)];
return { city, temperature: `${temp}°F`, condition };
},
});
const client = new CopilotClient();
const session = await client.createSession({
model: "gpt-4.1",
streaming: true,
tools: [getWeather],
});
session.on((event: SessionEvent) => {
if (event.type === "assistant.message_delta") {
process.stdout.write(event.data.deltaContent);
}
});
const rl = readline.createInterface({
input: process.stdin,
output: process.stdout,
});
console.log("天气助手 (输入 'exit' 退出)"); // 翻译
console.log("试试: 'What's the weather in Paris?'\n");
const prompt = () => {
rl.question("You: ", async (input) => {
if (input.toLowerCase() === "exit") {
await client.stop();
rl.close();
return;
}
process.stdout.write("Assistant: ");
await session.sendAndWait({ prompt: input });
console.log("\n");
prompt();
});
};
prompt();
Python
import asyncio
import random
import sys
from copilot import CopilotClient
from copilot.tools import define_tool
from copilot.generated.session_events import SessionEventType
from pydantic import BaseModel, Field
class GetWeatherParams(BaseModel):
city: str = Field(description="要获取天气的城市名称") # 翻译
@define_tool(description="获取指定城市的当前天气") # 翻译
async def get_weather(params: GetWeatherParams) -> dict:
conditions = ["sunny", "cloudy", "rainy", "partly cloudy"]
temp = random.randint(50, 80)
condition = random.choice(conditions)
return {"city": params.city, "temperature": f"{temp}°F", "condition": condition}
async def main():
client = CopilotClient()
await client.start()
session = await client.create_session({
"model": "gpt-4.1",
"streaming": True,
"tools": [get_weather],
})
def handle_event(event):
if event.type == SessionEventType.ASSISTANT_MESSAGE_DELTA:
sys.stdout.write(event.data.delta_content)
sys.stdout.flush()
session.on(handle_event)
print("天气助手 (输入 'exit' 退出)") # 翻译
print("试试: 'What's the weather in Paris?'\n")
while True:
try:
user_input = input("You: ")
except EOFError:
break
if user_input.lower() == "exit":
break
sys.stdout.write("Assistant: ")
await session.send_and_wait({"prompt": user_input})
print("\n")
await client.stop()
asyncio.run(main())
MCP 服务器集成
连接到 MCP(模型上下文协议)服务器以使用预构建的工具。连接到 GitHub 的 MCP 服务器以访问仓库、议题和 PR:
TypeScript
const session = await client.createSession({
model: "gpt-4.1",
mcpServers: {
github: {
type: "http",
url: "https://api.githubcopilot.com/mcp/",
},
},
});
Python
session = await client.create_session({
"model": "gpt-4.1",
"mcp_servers": {
"github": {
"type": "http",
"url": "https://api.githubcopilot.com/mcp/",
},
},
})
Go
session, _ := client.CreateSession(&copilot.SessionConfig{
Model: "gpt-4.1",
MCPServers: map[string]copilot.MCPServerConfig{
"github": {
Type: "http",
URL: "https://api.githubcopilot.com/mcp/",
},
},
})
.NET
await using var session = await client.CreateSessionAsync(new SessionConfig
{
Model = "gpt-4.1",
McpServers = new Dictionary<string, McpServerConfig>
{
["github"] = new McpServerConfig
{
Type = "http",
Url = "https://api.githubcopilot.com/mcp/",
},
},
});
自定义代理
为特定任务定义专门的 AI 角色:
TypeScript
const session = await client.createSession({
model: "gpt-4.1",
customAgents: [{
name: "pr-reviewer",
displayName: "PR 审查员", // 翻译
description: "根据最佳实践审查拉取请求", // 翻译
prompt: "你是一名代码审查专家。关注安全性、性能和可维护性。", // 翻译
}],
});
Python
session = await client.create_session({
"model": "gpt-4.1",
"custom_agents": [{
"name": "pr-reviewer",
"display_name": "PR 审查员", # 翻译
"description": "根据最佳实践审查拉取请求", # 翻译
"prompt": "你是一名代码审查专家。关注安全性、性能和可维护性。", # 翻译
}],
})
系统消息
自定义 AI 的行为和个性:
TypeScript
const session = await client.createSession({
model: "gpt-4.1",
systemMessage: {
content: "你是我工程团队的得力助手。务必保持简洁。", // 翻译
},
});
Python
session = await client.create_session({
"model": "gpt-4.1",
"system_message": {
"content": "你是我工程团队的得力助手。务必保持简洁。", # 翻译
},
})
外部 CLI 服务器
单独以服务器模式运行 CLI,并将 SDK 连接到它。便于调试、资源共享或自定义环境。
以服务器模式启动 CLI
copilot --server --port 4321
连接 SDK 到外部服务器
TypeScript
const client = new CopilotClient({
cliUrl: "localhost:4321"
});
const session = await client.createSession({ model: "gpt-4.1" });
Python
client = CopilotClient({
"cli_url": "localhost:4321"
})
await client.start()
session = await client.create_session({"model": "gpt-4.1"})
Go
client := copilot.NewClient(&copilot.ClientOptions{
CLIUrl: "localhost:4321",
})
if err := client.Start(); err != nil {
log.Fatal(err)
}
session, _ := client.CreateSession(&copilot.SessionConfig{Model: "gpt-4.1"})
.NET
using var client = new CopilotClient(new CopilotClientOptions
{
CliUrl = "localhost:4321"
});
await using var session = await client.CreateSessionAsync(new SessionConfig { Model = "gpt-4.1" });
注意: 当提供 cliUrl 时,SDK 不会生成或管理 CLI 进程——它仅连接到现有服务器。
事件类型
| 事件 | 描述 |
|---|---|
user.message |
已添加用户输入 |
assistant.message |
完整模型响应 |
assistant.message_delta |
流式响应片段 |
assistant.reasoning |
模型推理(取决于模型) |
assistant.reasoning_delta |
流式推理片段 |
tool.execution_start |
工具调用已开始 |
tool.execution_complete |
工具执行已完成 |
session.idle |
无活动处理 |
session.error |
发生错误 |
客户端配置
| 选项 | 描述 | 默认值 |
|---|---|---|
cliPath |
Copilot CLI 可执行文件的路径 | 系统 PATH |
cliUrl |
连接到现有服务器(例如 “localhost:4321″) | 无 |
port |
服务器通信端口 | 随机 |
useStdio |
使用 stdio 传输而非 TCP | true |
logLevel |
日志详细程度 | “info” |
autoStart |
自动启动服务器 | true |
autoRestart |
崩溃时重启 | true |
cwd |
CLI 进程的工作目录 | 继承 |
会话配置
| 选项 | 描述 |
|---|---|
model |
要使用的 LLM(”gpt-4.1″、”claude-sonnet-4.5″ 等) |
sessionId |
自定义会话标识符 |
tools |
自定义工具定义 |
mcpServers |
MCP 服务器连接 |
customAgents |
自定义代理角色 |
systemMessage |
覆盖默认系统提示 |
streaming |
启用增量响应片段 |
availableTools |
允许的工具白名单 |
excludedTools |
禁用的工具黑名单 |
会话持久化
在重启之间保存和恢复对话:
使用自定义 ID 创建
const session = await client.createSession({
sessionId: "user-123-conversation",
model: "gpt-4.1"
});
恢复会话
const session = await client.resumeSession("user-123-conversation");
await session.send({ prompt: "What did we discuss earlier?" });
列出和删除会话
const sessions = await client.listSessions();
await client.deleteSession("old-session-id");
错误处理
try {
const client = new CopilotClient();
const session = await client.createSession({ model: "gpt-4.1" });
const response = await session.sendAndWait(
{ prompt: "Hello!" },
30000 // 超时时间(毫秒)
);
} catch (error) {
if (error.code === "ENOENT") {
console.error("未安装 Copilot CLI"); // 翻译
} else if (error.code === "ECONNREFUSED") {
console.error("无法连接到 Copilot 服务器"); // 翻译
} else {
console.error("错误:", error.message); // 翻译
}
} finally {
await client.stop();
}
优雅关闭
process.on("SIGINT", async () => {
console.log("正在关闭..."); // 翻译
await client.stop();
process.exit(0);
});
常见模式
多轮对话
const session = await client.createSession({ model: "gpt-4.1" });
await session.sendAndWait({ prompt: "My name is Alice" });
await session.sendAndWait({ prompt: "What's my name?" });
// 响应: "Your name is Alice"
文件附件
await session.send({
prompt: "分析这个文件", // 翻译
attachments: [{
type: "file",
path: "./data.csv",
displayName: "销售数据" // 翻译
}]
});
中止长时间操作
const timeoutId = setTimeout(() => {
session.abort();
}, 60000);
session.on((event) => {
if (event.type === "session.idle") {
clearTimeout(timeoutId);
}
});
可用模型
在运行时查询可用模型:
const models = await client.getModels();
// 返回: ["gpt-4.1", "gpt-4o", "claude-sonnet-4.5", ...]
最佳实践
- 始终清理资源:使用
try-finally或defer确保调用client.stop() - 设置超时:对长时间操作使用带超时的
sendAndWait - 处理事件:订阅错误事件以实现稳健的错误处理
- 使用流式:在长响应上启用流式以获得更好的用户体验
- 持久化会话:对多轮对话使用自定义会话 ID
- 定义清晰的工具:编写描述性的工具名称和描述
架构
您的应用程序
|
SDK 客户端
| JSON-RPC
Copilot CLI (服务器模式)
|
GitHub (模型、认证)
SDK 自动管理 CLI 进程的生命周期。所有通信通过基于 stdio 或 TCP 的 JSON-RPC 进行。
资源
- GitHub 仓库:https://github.com/github/copilot-sdk
- 入门教程:https://github.com/github/copilot-sdk/blob/main/docs/tutorials/first-app.md
- GitHub MCP 服务器:https://github.com/github/github-mcp-server
- MCP 服务器目录:https://github.com/modelcontextprotocol/servers
- 菜谱:https://github.com/github/copilot-sdk/tree/main/cookbook
- 示例:https://github.com/github/copilot-sdk/tree/main/samples
状态
此 SDK 处于技术预览版,可能会有重大更改。尚不建议用于生产环境。
📄 原始文档
完整文档(英文):
https://skills.sh/github/awesome-copilot/copilot-sdk
💡 提示:点击上方链接查看 skills.sh 原始英文文档,方便对照翻译。

评论(0)