copilot-sdk

Name: copilot-sdk
Author: github

GitHub Copilot SDK

在任何應用程式中嵌入 Copilot 的代理工作流程，支援 Python、TypeScript、Go 或 .NET。

概覽

GitHub Copilot SDK 公開了 Copilot CLI 背後的相同引擎：一個經過生產測試的代理執行環境，您可以透過程式方式呼叫。無需自行建構編排邏輯——您定義代理行為，Copilot 負責規劃、工具呼叫、檔案編輯等。

先決條件

安裝並驗證 GitHub Copilot CLI（安裝指南）
語言執行環境：Node.js 18+、Python 3.8+、Go 1.21+ 或 .NET 8.0+

驗證 CLI：copilot --version

安裝

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

快速開始

TypeScript

import { CopilotClient, approveAll } from "@github/copilot-sdk";

const client = new CopilotClient();
const session = await client.createSession({
    onPermissionRequest: approveAll,
    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);

執行：npx tsx index.ts

Python

import asyncio
from copilot import CopilotClient, PermissionHandler

async def main():
    client = CopilotClient()
    await client.start()

    session = await client.create_session({
        "on_permission_request": PermissionHandler.approve_all,
        "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{
        OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
        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
{
    OnPermissionRequest = PermissionHandler.ApproveAll,
    Model = "gpt-4.1",
});

var response = await session.SendAndWaitAsync(new MessageOptions { Prompt = "What is 2 + 2?" });
Console.WriteLine(response?.Data.Content);

執行：dotnet run

串流回應

啟用即時輸出以獲得更好的使用者體驗：

TypeScript

import { CopilotClient, approveAll, SessionEvent } from "@github/copilot-sdk";

const client = new CopilotClient();
const session = await client.createSession({
    onPermissionRequest: approveAll,
    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(); // New line when done
    }
});

await session.sendAndWait({ prompt: "Tell me a short joke" });

await client.stop();
process.exit(0);

Python

import asyncio
import sys
from copilot import CopilotClient, PermissionHandler
from copilot.generated.session_events import SessionEventType

async def main():
    client = CopilotClient()
    await client.start()

    session = await client.create_session({
        "on_permission_request": PermissionHandler.approve_all,
        "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{
	OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
    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
{
    OnPermissionRequest = PermissionHandler.ApproveAll,
    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" });

自訂工具

定義 Copilot 在推理過程中可以呼叫的工具。當您定義工具時，您告訴 Copilot：

工具的功能（描述）
需要的參數（結構）
要執行的程式碼（處理器）

TypeScript (JSON Schema)

import { CopilotClient, approveAll, defineTool, SessionEvent } from "@github/copilot-sdk";

const getWeather = defineTool("get_weather", {
    description: "Get the current weather for a city",
    parameters: {
        type: "object",
        properties: {
            city: { type: "string", description: "The city name" },
        },
        required: ["city"],
    },
    handler: async (args: { city: string }) => {
        const { city } = args;
        // In a real app, call a weather API here
        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({
    onPermissionRequest: approveAll,
    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, PermissionHandler
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="The name of the city to get weather for")

@define_tool(description="Get the current weather for a city")
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({
        "on_permission_request": PermissionHandler.approve_all,
        "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:"The city name"`
}

type WeatherResult struct {
    City        string `json:"city"`
    Temperature string `json:"temperature"`
    Condition   string `json:"condition"`
}

getWeather := copilot.DefineTool(
    "get_weather",
    "Get the current weather for a city",
    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{
	OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
    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("The city name")] string city) =>
    {
        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",
    "Get the current weather for a city"
);

await using var session = await client.CreateSessionAsync(new SessionConfig
{
    OnPermissionRequest = PermissionHandler.ApproveAll,
    Model = "gpt-4.1",
    Streaming = true,
    Tools = [getWeather],
});

工具運作方式

當 Copilot 決定呼叫您的工具時：

Copilot 發送工具呼叫請求，包含參數
SDK 執行您的處理器函式
結果回傳給 Copilot
Copilot 將結果納入回應中

Copilot 會根據使用者的問題和工具的描述，決定何時呼叫您的工具。

互動式 CLI 助手

建立完整的互動式助手：

TypeScript

import { CopilotClient, approveAll, defineTool, SessionEvent } from "@github/copilot-sdk";
import * as readline from "readline";

const getWeather = defineTool("get_weather", {
    description: "Get the current weather for a city",
    parameters: {
        type: "object",
        properties: {
            city: { type: "string", description: "The city name" },
        },
        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({
    onPermissionRequest: approveAll,
    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("Weather Assistant (type 'exit' to quit)");
console.log("Try: '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, PermissionHandler
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="The name of the city to get weather for")

@define_tool(description="Get the current weather for a city")
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({
        "on_permission_request": PermissionHandler.approve_all,
        "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("Weather Assistant (type 'exit' to quit)")
    print("Try: '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 伺服器整合

連線至 MCP（模型上下文協定）伺服器以使用預建工具。連線至 GitHub 的 MCP 伺服器以存取儲存庫、議題和 PR：

TypeScript

const session = await client.createSession({
    onPermissionRequest: approveAll,
    model: "gpt-4.1",
    mcpServers: {
        github: {
            type: "http",
            url: "https://api.githubcopilot.com/mcp/",
        },
    },
});

Python

session = await client.create_session({
    "on_permission_request": PermissionHandler.approve_all,
    "model": "gpt-4.1",
    "mcp_servers": {
        "github": {
            "type": "http",
            "url": "https://api.githubcopilot.com/mcp/",
        },
    },
})

Go

session, _ := client.CreateSession(&copilot.SessionConfig{
	OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
    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
{
    OnPermissionRequest = PermissionHandler.ApproveAll,
    Model = "gpt-4.1",
    McpServers = new Dictionary<string, McpServerConfig>
    {
        ["github"] = new McpServerConfig
        {
            Type = "http",
            Url = "https://api.githubcopilot.com/mcp/",
        },
    },
});

自訂代理

為特定任務定義專門的 AI 角色：

TypeScript

const session = await client.createSession({
    onPermissionRequest: approveAll,
    model: "gpt-4.1",
    customAgents: [{
        name: "pr-reviewer",
        displayName: "PR Reviewer",
        description: "Reviews pull requests for best practices",
        prompt: "You are an expert code reviewer. Focus on security, performance, and maintainability.",
    }],
});

Python

session = await client.create_session({
    "on_permission_request": PermissionHandler.approve_all,
    "model": "gpt-4.1",
    "custom_agents": [{
        "name": "pr-reviewer",
        "display_name": "PR Reviewer",
        "description": "Reviews pull requests for best practices",
        "prompt": "You are an expert code reviewer. Focus on security, performance, and maintainability.",
    }],
})

系統訊息

自訂 AI 的行為和個性：

TypeScript

const session = await client.createSession({
    onPermissionRequest: approveAll,
    model: "gpt-4.1",
    systemMessage: {
        content: "You are a helpful assistant for our engineering team. Always be concise.",
    },
});

Python

session = await client.create_session({
    "on_permission_request": PermissionHandler.approve_all,
    "model": "gpt-4.1",
    "system_message": {
        "content": "You are a helpful assistant for our engineering team. Always be concise.",
    },
})

外部 CLI 伺服器

將 CLI 以伺服器模式單獨執行，並將 SDK 連線至該伺服器。適用於除錯、資源共享或自訂環境。

以伺服器模式啟動 CLI

copilot --server --port 4321

將 SDK 連線至外部伺服器

TypeScript

const client = new CopilotClient({
    cliUrl: "localhost:4321"
});

const session = await client.createSession({
    onPermissionRequest: approveAll,
    model: "gpt-4.1",
});

Python

client = CopilotClient({
    "cli_url": "localhost:4321"
})
await client.start()

session = await client.create_session({
    "on_permission_request": PermissionHandler.approve_all,
    "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{
	OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
	Model:               "gpt-4.1",
})

.NET

using var client = new CopilotClient(new CopilotClientOptions
{
    CliUrl = "localhost:4321"
});

await using var session = await client.CreateSessionAsync(new SessionConfig
{
    OnPermissionRequest = PermissionHandler.ApproveAll,
    Model = "gpt-4.1",
});

注意： 當提供 cliUrl 時，SDK 不會啟動或管理 CLI 程序——它只會連線至現有的伺服器。

事件類型

事件	描述
`user.message`	使用者輸入已新增
`assistant.message`	完整的模型回應
`assistant.message_delta`	串流回應區塊
`assistant.reasoning`	模型推理（依模型而定）
`assistant.reasoning_delta`	串流推理區塊
`tool.execution_start`	工具呼叫已開始
`tool.execution_complete`	工具執行已完成
`session.idle`	無進行中的處理
`session.error`	發生錯誤

用戶端設定

選項	描述	預設值
`cliPath`	Copilot CLI 可執行檔的路徑	系統 PATH
`cliUrl`	連線至現有伺服器（例如 "localhost:4321"）	無
`port`	伺服器通訊埠	隨機
`useStdio`	使用 stdio 傳輸而非 TCP	true
`logLevel`	記錄詳細程度	"info"
`autoStart`	自動啟動伺服器	true
`autoRestart`	當機時自動重新啟動	true
`cwd`	CLI 程序的工作目錄	繼承

工作階段設定

選項	描述
`model`	使用的 LLM（"gpt-4.1"、"claude-sonnet-4.5" 等）
`sessionId`	自訂工作階段識別碼
`tools`	自訂工具定義
`mcpServers`	MCP 伺服器連線
`customAgents`	自訂代理角色
`systemMessage`	覆寫預設系統提示
`streaming`	啟用增量回應區塊
`availableTools`	允許的工具白名單
`excludedTools`	停用的工具黑名單

工作階段持久化

在重新啟動之間儲存和恢復對話：

使用自訂 ID 建立

const session = await client.createSession({
    onPermissionRequest: approveAll,
    sessionId: "user-123-conversation",
    model: "gpt-4.1"
});

恢復工作階段

const session = await client.resumeSession("user-123-conversation", { onPermissionRequest: approveAll });
await session.send({ prompt: "What did we discuss earlier?" });

列出和刪除工作階段

const sessions = await client.listSessions();
await client.deleteSession("old-session-id");

錯誤處理

try {
    const client = new CopilotClient();
    const session = await client.createSession({
        onPermissionRequest: approveAll,
        model: "gpt-4.1",
    });
    const response = await session.sendAndWait(
        { prompt: "Hello!" },
        30000 // timeout in ms
    );
} catch (error) {
    if (error.code === "ENOENT") {
        console.error("Copilot CLI not installed");
    } else if (error.code === "ECONNREFUSED") {
        console.error("Cannot connect to Copilot server");
    } else {
        console.error("Error:", error.message);
    }
} finally {
    await client.stop();
}

優雅關閉

process.on("SIGINT", async () => {
    console.log("Shutting down...");
    await client.stop();
    process.exit(0);
});

常見模式

多輪對話

const session = await client.createSession({
    onPermissionRequest: approveAll,
    model: "gpt-4.1",
});

await session.sendAndWait({ prompt: "My name is Alice" });
await session.sendAndWait({ prompt: "What's my name?" });
// Response: "Your name is Alice"

檔案附件

await session.send({
    prompt: "Analyze this file",
    attachments: [{
        type: "file",
        path: "./data.csv",
        displayName: "Sales Data"
    }]
});

中止長時間操作

const timeoutId = setTimeout(() => {
    session.abort();
}, 60000);

session.on((event) => {
    if (event.type === "session.idle") {
        clearTimeout(timeoutId);
    }
});

可用模型

在執行時查詢可用模型：

const models = await client.getModels();
// Returns: ["gpt-4.1", "gpt-4o", "claude-sonnet-4.5", ...]

最佳實踐

務必清理：使用 try-finally 或 defer 確保 client.stop() 被呼叫
設定逾時：對長時間操作使用 sendAndWait 搭配逾時
處理事件：訂閱錯誤事件以實現穩健的錯誤處理
使用串流：啟用串流以獲得長時間回應的更好使用者體驗
持久化工作階段：對多輪對話使用自訂工作階段 ID
定義清晰工具：撰寫描述性的工具名稱和描述

架構

您的應用程式
       |
  SDK 用戶端
       | JSON-RPC
  Copilot CLI（伺服器模式）
       |
  GitHub（模型、驗證）

SDK 會自動管理 CLI 程序的生命週期。所有通訊透過 JSON-RPC 經由 stdio 或 TCP 進行。

資源

GitHub 儲存庫：https://github.com/github/copilot-sdk
入門教學：https://github.com/github/copilot-sdk/blob/main/docs/tutorials/first-app.md
GitHub MCP 伺服器：https://github.com/github/github-mcp-server
MCP 伺服器目錄：https://github.com/modelcontextprotocol/servers
食譜：https://github.com/github/copilot-sdk/tree/main/cookbook
範例：https://github.com/github/copilot-sdk/tree/main/samples

狀態

此 SDK 處於技術預覽階段，可能會有重大變更。目前不建議用於生產環境。

您可能也喜歡

ads-attribution

7.8Kmcp-integrations

審查跨平台歸因、轉換定義、報表時間窗口（Reporting Windows）、GA4、AdServices 與 AdAttributionKit、MMP、瀏覽器及伺服器端事件、離線轉換，以及平台間的數據對帳。適用於歸因審查、歸因模型分析、轉換窗口評估、合併或加總 Meta 與 Google 轉換數的請求、不相容報表窗口的數據加總、GA4 歸因、MMP 審查、AppsFlyer、Adjust、Branch、Singular，或處理跨平台數據差異等場景。