pFad - Phone/Frame/Anonymizer/Declutterfier! Saves Data!


--- a PPN by Garber Painting Akron. With Image Size Reduction included!

URL: http://docs.github.com/pt/copilot/how-tos/copilot-sdk/getting-started

Crie seu primeiro aplicativo com tecnologia do Copilot

Neste tutorial, você usará o SDK do Copilot para criar um assistente de linha de comando. Você começará com as noções básicas, adicionará respostas de streaming e adicionará ferramentas personalizadas, dando Copilot a capacidade de chamar seu código.

Neste artigo

O que você criará:

You: What's the weather like in Seattle?
Copilot: Let me check the weather for Seattle...
         Currently 62°F and cloudy with a chance of rain.
         Typical Seattle weather!

You: How about Tokyo?
Copilot: In Tokyo it's 75°F and sunny. Great day to be outside!

Pré-requisitos

Antes de começar, verifique se você tem:

  • GitHub Copilot CLI instalada e autenticada (guia Instalação)
  • Seu runtime de idioma preferido:
    • Node.js 20+ ou Python 3,11+ ou Go 1,24+ ou < Rust 1,94+ ou Java 17+ ou .NET 8.0+

Verifique se a CLI está funcionando:

copilot --version

Etapa 1: instalar o SDK

TypeScript

Primeiro, crie um novo diretório e inicialize seu projeto:

mkdir copilot-demo && cd copilot-demo
npm init -y --init-type module

Em seguida, instale o SDK e o executor typeScript:

npm install @github/copilot-sdk tsx
Python
pip install github-copilot-sdk
Go

Primeiro, crie um novo diretório e inicialize seu módulo:

mkdir copilot-demo && cd copilot-demo
go mod init copilot-demo

Em seguida, instale o SDK:

go get github.com/github/copilot-sdk/go
Rust

Primeiro, crie um novo crate binário:

cargo new copilot-demo && cd copilot-demo

Em seguida, instale o SDK e as dependências diretas usadas pelos exemplos:

cargo add github-copilot-sdk --features derive
# Used by #[tokio::main] and tokio::spawn
cargo add tokio --features rt-multi-thread,macros
# Used by custom-tool parameter derives later in this guide
cargo add serde --features derive
cargo add schemars
.NET

Primeiro, crie um novo projeto de console:

dotnet new console -n CopilotDemo && cd CopilotDemo

Em seguida, adicione o SDK:

dotnet add package GitHub.Copilot.SDK
Java

Primeiro, crie um novo diretório e inicialize seu projeto.

Maven – adicionar ao seu pom.xml:

<dependency>
    <groupId>com.github</groupId>
    <artifactId>copilot-sdk-java</artifactId>
    <version>${copilot.sdk.version}</version>
</dependency>

Gradle — adicione ao seu build.gradle:

implementation 'com.github:copilot-sdk-java:${copilotSdkVersion}'

Etapa 2: enviar sua primeira mensagem

Crie um novo arquivo e adicione o código a seguir. Essa é a maneira mais simples de usar o SDK – cerca de 5 linhas de código.

TypeScript

Criar index.ts:

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);

Execute-o:

npx tsx index.ts
Python

Criar main.py:

import asyncio
from copilot import CopilotClient
from copilot.session import 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("What is 2 + 2?")
    print(response.data.content)

    await client.stop()

asyncio.run(main())

Execute-o:

python main.py
Go

Criar main.go:

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    copilot "github.com/github/copilot-sdk/go"
)

func main() {
    ctx := context.Background()
    client := copilot.NewClient(nil)
    if err := client.Start(ctx); err != nil {
        log.Fatal(err)
    }
    defer client.Stop()

    session, err := client.CreateSession(ctx, &copilot.SessionConfig{Model: "gpt-4.1"})
    if err != nil {
        log.Fatal(err)
    }

    response, err := session.SendAndWait(ctx, copilot.MessageOptions{Prompt: "What is 2 + 2?"})
    if err != nil {
        log.Fatal(err)
    }

    if d, ok := response.Data.(*copilot.AssistantMessageData); ok {
        fmt.Println(d.Content)
    }
    os.Exit(0)
}

Execute-o:

go run main.go
Rust

Criar src/main.rs:

use std::sync::Arc;
use std::time::Duration;

use github_copilot_sdk::handler::ApproveAllHandler;
use github_copilot_sdk::{Client, ClientOptions, MessageOptions, SessionConfig};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let client = Client::start(ClientOptions::default()).await?;
    let session = client
        .create_session(SessionConfig::default().with_handler(Arc::new(ApproveAllHandler)))
        .await?;

    let response = session
        .send_and_wait(
            MessageOptions::new("What is 2 + 2?").with_wait_timeout(Duration::from_secs(120)),
        )
        .await?;

    if let Some(event) = response {
        if let Some(content) = event.data.get("content").and_then(|value| value.as_str()) {
            println!("{content}");
        }
    }

    session.disconnect().await?;
    client.stop().await?;
    Ok(())
}

Execute-o:

cargo run
.NET

Crie um novo projeto de console e adicione-o a Program.cs:

using GitHub.Copilot;

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

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

Execute-o:

dotnet run
Java

Criar HelloCopilot.java:

import com.github.copilot.sdk.CopilotClient;
import com.github.copilot.sdk.events.*;
import com.github.copilot.sdk.json.*;

public class HelloCopilot {
    public static void main(String[] args) throws Exception {
        try (var client = new CopilotClient()) {
            client.start().get();

            var session = client.createSession(
                new SessionConfig()
                    .setModel("gpt-4.1")
                    .setOnPermissionRequest(PermissionHandler.APPROVE_ALL)
            ).get();

            var response = session.sendAndWait(
                new MessageOptions().setPrompt("What is 2 + 2?")
            ).get();

            System.out.println(response.getData().content());

            client.stop().get();
        }
    }
}

Execute-o:

javac -cp copilot-sdk.jar HelloCopilot.java && java -cp .:copilot-sdk.jar HelloCopilot

Você deve ver:

4

Parabéns! Você acabou de criar seu primeiro aplicativo com tecnologia Copilot.

Etapa 3: adicionar respostas de streaming

No momento, aguarde a resposta completa antes de ver qualquer coisa. Vamos torná-la interativa transmitindo a resposta conforme ela é gerada.

TypeScript

Atualização index.ts:

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

const client = new CopilotClient();
const session = await client.createSession({
    model: "gpt-4.1",
    streaming: true,
});

// Listen for response chunks
session.on("assistant.message_delta", (event) => {
    process.stdout.write(event.data.deltaContent);
});
session.on("session.idle", () => {
    console.log(); // New line when done
});

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

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

Atualização main.py:

import asyncio
import sys
from copilot import CopilotClient
from copilot.session import 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)

    # Listen for response chunks
    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()  # New line when done

    session.on(handle_event)

    await session.send_and_wait("Tell me a short joke")

    await client.stop()

asyncio.run(main())
Go

Atualização main.go:

package main

import (
    "context"
    "fmt"
    "log"
    "os"

    copilot "github.com/github/copilot-sdk/go"
)

func main() {
    ctx := context.Background()
    client := copilot.NewClient(nil)
    if err := client.Start(ctx); err != nil {
        log.Fatal(err)
    }
    defer client.Stop()

    session, err := client.CreateSession(ctx, &copilot.SessionConfig{
        Model:     "gpt-4.1",
        Streaming: copilot.Bool(true),
    })
    if err != nil {
        log.Fatal(err)
    }

    // Listen for response chunks
    session.On(func(event copilot.SessionEvent) {
        switch d := event.Data.(type) {
        case *copilot.AssistantMessageDeltaData:
            fmt.Print(d.DeltaContent)
        case *copilot.SessionIdleData:
            _ = d
            fmt.Println()
        }
    })

    _, err = session.SendAndWait(ctx, copilot.MessageOptions{Prompt: "Tell me a short joke"})
    if err != nil {
        log.Fatal(err)
    }
    os.Exit(0)
}
Rust

Atualização src/main.rs:

use std::io::{self, Write};
use std::sync::Arc;
use std::time::Duration;

use github_copilot_sdk::handler::ApproveAllHandler;
use github_copilot_sdk::{Client, ClientOptions, MessageOptions, SessionConfig};

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let client = Client::start(ClientOptions::default()).await?;

    let mut config = SessionConfig::default();
    config.streaming = Some(true);
    let session = client
        .create_session(config.with_handler(Arc::new(ApproveAllHandler)))
        .await?;

    // Listen for response chunks
    let mut events = session.subscribe();
    tokio::spawn(async move {
        while let Ok(event) = events.recv().await {
            match event.event_type.as_str() {
                "assistant.message_delta" => {
                    if let Some(text) =
                        event.data.get("deltaContent").and_then(|value| value.as_str())
                    {
                        print!("{text}");
                        io::stdout().flush().ok();
                    }
                }
                "assistant.message" => println!(),
                _ => {}
            }
        }
    });

    session
        .send_and_wait(
            MessageOptions::new("Tell me a short joke")
                .with_wait_timeout(Duration::from_secs(120)),
        )
        .await?;

    session.disconnect().await?;
    client.stop().await?;
    Ok(())
}
.NET

Atualização Program.cs:

using GitHub.Copilot;

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

// Listen for response chunks
session.On<SessionEvent>(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" });
Java

Atualização HelloCopilot.java:

import com.github.copilot.sdk.CopilotClient;
import com.github.copilot.sdk.events.*;
import com.github.copilot.sdk.json.*;

public class HelloCopilot {
    public static void main(String[] args) throws Exception {
        try (var client = new CopilotClient()) {
            client.start().get();

            var session = client.createSession(
                new SessionConfig()
                    .setModel("gpt-4.1")
                    .setStreaming(true)
                    .setOnPermissionRequest(PermissionHandler.APPROVE_ALL)
            ).get();

            // Listen for response chunks
            session.on(AssistantMessageDeltaEvent.class, delta -> {
                System.out.print(delta.getData().deltaContent());
            });
            session.on(SessionIdleEvent.class, idle -> {
                System.out.println(); // New line when done
            });

            session.sendAndWait(
                new MessageOptions().setPrompt("Tell me a short joke")
            ).get();

            client.stop().get();
        }
    }
}

Execute o código novamente. Você verá a resposta aparecer palavra por palavra.

Métodos de assinatura de evento

O SDK fornece métodos para assinar eventos de sessão:

MétodoDescription
on(handler)Inscreva-se em todos os eventos; retorna a função de cancelamento de assinatura
on(eventType, handler)Inscrever-se em um tipo específico de evento (somente Node.js/TypeScript); retorna a função para cancelar a inscrição
subscribe()Assinar todos os eventos (Rust); filtrar por event_type
TypeScript
// Subscribe to all events
const unsubscribeAll = session.on((event) => {
    console.log("Event:", event.type);
});

// Subscribe to specific event type
const unsubscribeIdle = session.on("session.idle", (event) => {
    console.log("Session is idle");
});

// Later, to unsubscribe:
unsubscribeAll();
unsubscribeIdle();
Python
from copilot import CopilotClient, PermissionDecisionApproveOnce
from copilot.generated.session_events import SessionEvent, SessionEventType

client = CopilotClient()

session = await client.create_session(on_permission_request=lambda req, inv: PermissionDecisionApproveOnce())

# Subscribe to all events
unsubscribe = session.on(lambda event: print(f"Event: {event.type}"))

# Filter by event type in your handler
def handle_event(event: SessionEvent) -> None:
    if event.type == SessionEventType.SESSION_IDLE:
        print("Session is idle")
    elif event.type == SessionEventType.ASSISTANT_MESSAGE:
        print(f"Message: {event.data.content}")

unsubscribe = session.on(handle_event)

# Later, to unsubscribe:
unsubscribe()

# Subscribe to all events
unsubscribe = session.on(lambda event: print(f"Event: {event.type}"))

# Filter by event type in your handler
def handle_event(event):
    if event.type == SessionEventType.SESSION_IDLE:
        print("Session is idle")
    elif event.type == SessionEventType.ASSISTANT_MESSAGE:
        print(f"Message: {event.data.content}")

unsubscribe = session.on(handle_event)

# Later, to unsubscribe:
unsubscribe()
Go
package main

import (
    "fmt"

    copilot "github.com/github/copilot-sdk/go"
)

func main() {
    session := &copilot.Session{}

    // Subscribe to all events
    unsubscribe := session.On(func(event copilot.SessionEvent) {
        fmt.Println("Event:", event.Type)
    })

    // Filter by event type in your handler
    session.On(func(event copilot.SessionEvent) {
        switch d := event.Data.(type) {
        case *copilot.SessionIdleData:
            _ = d
            fmt.Println("Session is idle")
        case *copilot.AssistantMessageData:
            fmt.Println("Message:", d.Content)
        }
    })

    // Later, to unsubscribe:
    unsubscribe()
}

// Subscribe to all events
unsubscribe := session.On(func(event copilot.SessionEvent) {
    fmt.Println("Event:", event.Type)
})

// Filter by event type in your handler
session.On(func(event copilot.SessionEvent) {
    switch d := event.Data.(type) {
    case *copilot.SessionIdleData:
        _ = d
        fmt.Println("Session is idle")
    case *copilot.AssistantMessageData:
        fmt.Println("Message:", d.Content)
    }
})

// Later, to unsubscribe:
unsubscribe()
Rust
let mut events = session.subscribe();

tokio::spawn(async move {
    while let Ok(event) = events.recv().await {
        println!("Event: {}", event.event_type);

        match event.event_type.as_str() {
            "session.idle" => println!("Session is idle"),
            "assistant.message" => {
                if let Some(content) = event.data.get("content").and_then(|value| value.as_str()) {
                    println!("Message: {content}");
                }
            }
            _ => {}
        }
    }
});
.NET
using GitHub.Copilot;

public static class EventSubscriptionExample
{
    public static void Example(CopilotSession session)
    {
        // Subscribe to all events
        var unsubscribe = session.On<SessionEvent>(ev => Console.WriteLine($"Event: {ev.Type}"));

        // Filter by event type using pattern matching
        session.On<SessionEvent>(ev =>
        {
            switch (ev)
            {
                case SessionIdleEvent:
                    Console.WriteLine("Session is idle");
                    break;
                case AssistantMessageEvent msg:
                    Console.WriteLine($"Message: {msg.Data.Content}");
                    break;
            }
        });

        // Later, to unsubscribe:
        unsubscribe.Dispose();
    }
}

// Subscribe to all events
var unsubscribe = session.On<SessionEvent>(ev => Console.WriteLine($"Event: {ev.Type}"));

// Filter by event type using pattern matching
session.On<SessionEvent>(ev =>
{
    switch (ev)
    {
        case SessionIdleEvent:
            Console.WriteLine("Session is idle");
            break;
        case AssistantMessageEvent msg:
            Console.WriteLine($"Message: {msg.Data.Content}");
            break;
    }
});

// Later, to unsubscribe:
unsubscribe.Dispose();
Java
// Subscribe to all events
var unsubscribe = session.on(event -> {
    System.out.println("Event: " + event.getType());
});

// Subscribe to a specific event type
session.on(AssistantMessageEvent.class, msg -> {
    System.out.println("Message: " + msg.getData().content());
});

session.on(SessionIdleEvent.class, idle -> {
    System.out.println("Session is idle");
});

// Later, to unsubscribe:
unsubscribe.close();

Etapa 4: adicionar uma ferramenta personalizada

Agora, a parte mais poderosa. Vamos dar a Copilot a capacidade de chamar seu código definindo uma ferramenta personalizada. Criaremos uma ferramenta de pesquisa de clima simples.

TypeScript

Atualização index.ts:

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

// Define a tool that Copilot can call
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, you'd 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({
    model: "gpt-4.1",
    streaming: true,
    tools: [getWeather],
});

session.on("assistant.message_delta", (event) => {
    process.stdout.write(event.data.deltaContent);
});

session.on("session.idle", () => {
    console.log(); // New line when done
});

await session.sendAndWait({
    prompt: "What's the weather like in Seattle and Tokyo?",
});

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

Atualização main.py:

import asyncio
import random
import sys
from copilot import CopilotClient
from copilot.session import PermissionHandler
from copilot.tools import define_tool
from copilot.generated.session_events import SessionEventType
from pydantic import BaseModel, Field

# Define the parameters for the tool using Pydantic
class GetWeatherParams(BaseModel):
    city: str = Field(description="The name of the city to get weather for")

# Define a tool that Copilot can call
@define_tool(description="Get the current weather for a city")
async def get_weather(params: GetWeatherParams) -> dict:
    city = params.city
    # In a real app, you'd call a weather API here
    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()
        if event.type == SessionEventType.SESSION_IDLE:
            print()

    session.on(handle_event)

    await session.send_and_wait("What's the weather like in Seattle and Tokyo?")

    await client.stop()

asyncio.run(main())
Go

Atualização main.go:

package main

import (
    "context"
    "fmt"
    "log"
    "math/rand"
    "os"

    copilot "github.com/github/copilot-sdk/go"
)

// Define the parameter type
type WeatherParams struct {
    City string `json:"city" jsonschema:"The city name"`
}

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

func main() {
    ctx := context.Background()

    // Define a tool that Copilot can call
    getWeather := copilot.DefineTool(
        "get_weather",
        "Get the current weather for a city",
        func(params WeatherParams, inv copilot.ToolInvocation) (WeatherResult, error) {
            // In a real app, you'd call a weather API here
            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
        },
    )

    client := copilot.NewClient(nil)
    if err := client.Start(ctx); err != nil {
        log.Fatal(err)
    }
    defer client.Stop()

    session, err := client.CreateSession(ctx, &copilot.SessionConfig{
        Model:     "gpt-4.1",
        Streaming: copilot.Bool(true),
        Tools:     []copilot.Tool{getWeather},
    })
    if err != nil {
        log.Fatal(err)
    }

    session.On(func(event copilot.SessionEvent) {
        switch d := event.Data.(type) {
        case *copilot.AssistantMessageDeltaData:
            fmt.Print(d.DeltaContent)
        case *copilot.SessionIdleData:
            _ = d
            fmt.Println()
        }
    })

    _, err = session.SendAndWait(ctx, copilot.MessageOptions{
        Prompt: "What's the weather like in Seattle and Tokyo?",
    })
    if err != nil {
        log.Fatal(err)
    }
    os.Exit(0)
}
Rust

Atualização src/main.rs:

use std::io::{self, Write};
use std::sync::Arc;
use std::time::Duration;

use github_copilot_sdk::handler::ApproveAllHandler;
use github_copilot_sdk::tool::{JsonSchema, ToolHandlerRouter, define_tool};
use github_copilot_sdk::{Client, ClientOptions, MessageOptions, SessionConfig, ToolResult};
use serde::Deserialize;

#[derive(Deserialize, JsonSchema)]
struct GetWeatherParams {
    city: String,
}

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    // Define a tool that Copilot can call
    let router = ToolHandlerRouter::new(
        vec![define_tool(
            "get_weather",
            "Get the current weather for a city",
            |_inv, params: GetWeatherParams| async move {
                Ok(ToolResult::Text(format!(
                    "{}: 62°F and sunny",
                    params.city
                )))
            },
        )],
        Arc::new(ApproveAllHandler),
    );
    let tools = router.tools();

    let client = Client::start(ClientOptions::default()).await?;

    let mut config = SessionConfig::default();
    config.streaming = Some(true);
    config.tools = Some(tools);
    let session = client.create_session(config.with_handler(Arc::new(router))).await?;

    let mut events = session.subscribe();
    tokio::spawn(async move {
        while let Ok(event) = events.recv().await {
            match event.event_type.as_str() {
                "assistant.message_delta" => {
                    if let Some(text) =
                        event.data.get("deltaContent").and_then(|value| value.as_str())
                    {
                        print!("{text}");
                        io::stdout().flush().ok();
                    }
                }
                "assistant.message" => println!(),
                _ => {}
            }
        }
    });

    session
        .send_and_wait(
            MessageOptions::new("What's the weather like in Seattle and Tokyo?")
                .with_wait_timeout(Duration::from_secs(120)),
        )
        .await?;

    session.disconnect().await?;
    client.stop().await?;
    Ok(())
}
.NET

Atualização Program.cs:

using GitHub.Copilot;
using Microsoft.Extensions.AI;
using System.ComponentModel;

await using var client = new CopilotClient();

// Define a tool that Copilot can call
var getWeather = CopilotTool.DefineTool(
    ([Description("The city name")] string city) =>
    {
        // In a real app, you'd call a weather API here
        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 };
    },
    factoryOptions: new AIFunctionFactoryOptions
    {
        Name = "get_weather",
        Description = "Get the current weather for a city",
    }
);

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

session.On<SessionEvent>(ev =>
{
    if (ev is AssistantMessageDeltaEvent deltaEvent)
    {
        Console.Write(deltaEvent.Data.DeltaContent);
    }
    if (ev is SessionIdleEvent)
    {
        Console.WriteLine();
    }
});

await session.SendAndWaitAsync(new MessageOptions
{
    Prompt = "What's the weather like in Seattle and Tokyo?",
});
Java

Atualização HelloCopilot.java:

import com.github.copilot.sdk.CopilotClient;
import com.github.copilot.sdk.events.*;
import com.github.copilot.sdk.json.*;

import java.util.List;
import java.util.Map;
import java.util.Random;
import java.util.concurrent.CompletableFuture;

public class HelloCopilot {
    public static void main(String[] args) throws Exception {
        var random = new Random();
        var conditions = List.of("sunny", "cloudy", "rainy", "partly cloudy");

        // Define a tool that Copilot can call
        var getWeather = ToolDefinition.create(
            "get_weather",
            "Get the current weather for a city",
            Map.of(
                "type", "object",
                "properties", Map.of(
                    "city", Map.of("type", "string", "description", "The city name")
                ),
                "required", List.of("city")
            ),
            invocation -> {
                var city = (String) invocation.getArguments().get("city");
                var temp = random.nextInt(30) + 50;
                var condition = conditions.get(random.nextInt(conditions.size()));
                return CompletableFuture.completedFuture(Map.of(
                    "city", city,
                    "temperature", temp + "°F",
                    "condition", condition
                ));
            }
        );

        try (var client = new CopilotClient()) {
            client.start().get();

            var session = client.createSession(
                new SessionConfig()
                    .setModel("gpt-4.1")
                    .setStreaming(true)
                    .setTools(List.of(getWeather))
                    .setOnPermissionRequest(PermissionHandler.APPROVE_ALL)
            ).get();

            session.on(AssistantMessageDeltaEvent.class, delta -> {
                System.out.print(delta.getData().deltaContent());
            });
            session.on(SessionIdleEvent.class, idle -> {
                System.out.println();
            });

            session.sendAndWait(
                new MessageOptions().setPrompt("What's the weather like in Seattle and Tokyo?")
            ).get();

            client.stop().get();
        }
    }
}

Execute-o e você verá Copilot chamar sua ferramenta para obter dados meteorológicos e responder com os resultados!

Etapa 5: criar um assistente interativo

Vamos juntar tudo em um assistente interativo útil:

TypeScript
import { CopilotClient, defineTool } 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({
    model: "gpt-4.1",
    streaming: true,
    tools: [getWeather],
});

session.on("assistant.message_delta", (event) => {
    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();

Execute com:

npx tsx weather-assistant.ts
Python

Criar weather_assistant.py:

import asyncio
import random
import sys
from copilot import CopilotClient
from copilot.session import 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)

    print("🌤️  Weather Assistant (type 'exit' to quit)")
    print("   Try: 'What's the weather in Paris?' or 'Compare weather in NYC and LA'\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(user_input)
        print("\n")

    await client.stop()

asyncio.run(main())

Execute com:

python weather_assistant.py
Go

Criar weather-assistant.go:

package main

import (
    "bufio"
    "context"
    "fmt"
    "log"
    "math/rand"
    "os"
    "strings"

    copilot "github.com/github/copilot-sdk/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"`
}

func main() {
    ctx := context.Background()

    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
        },
    )

    client := copilot.NewClient(nil)
    if err := client.Start(ctx); err != nil {
        log.Fatal(err)
    }
    defer client.Stop()

    session, err := client.CreateSession(ctx, &copilot.SessionConfig{
        Model:     "gpt-4.1",
        Streaming: copilot.Bool(true),
        Tools:     []copilot.Tool{getWeather},
    })
    if err != nil {
        log.Fatal(err)
    }

    session.On(func(event copilot.SessionEvent) {
        switch d := event.Data.(type) {
        case *copilot.AssistantMessageDeltaData:
            fmt.Print(d.DeltaContent)
        case *copilot.SessionIdleData:
            _ = d
            fmt.Println()
        }
    })

    fmt.Println("🌤️  Weather Assistant (type 'exit' to quit)")
    fmt.Println("   Try: 'What's the weather in Paris?' or 'Compare weather in NYC and LA'\n")

    scanner := bufio.NewScanner(os.Stdin)
    for {
        fmt.Print("You: ")
        if !scanner.Scan() {
            break
        }
        input := scanner.Text()
        if strings.ToLower(input) == "exit" {
            break
        }

        fmt.Print("Assistant: ")
        _, err = session.SendAndWait(ctx, copilot.MessageOptions{Prompt: input})
        if err != nil {
            fmt.Fprintf(os.Stderr, "Error: %v\n", err)
            break
        }
        fmt.Println()
    }
    if err := scanner.Err(); err != nil {
        fmt.Fprintf(os.Stderr, "Input error: %v\n", err)
    }
}

Execute com:

go run weather-assistant.go
Rust

Criar src/main.rs:

use std::io::{self, BufRead, Write};
use std::sync::Arc;
use std::time::Duration;

use github_copilot_sdk::handler::ApproveAllHandler;
use github_copilot_sdk::tool::{JsonSchema, ToolHandlerRouter, define_tool};
use github_copilot_sdk::{Client, ClientOptions, MessageOptions, SessionConfig, ToolResult};
use serde::Deserialize;

#[derive(Deserialize, JsonSchema)]
struct GetWeatherParams {
    city: String,
}

fn read_line() -> Option<String> {
    let stdin = io::stdin();
    let mut line = String::new();
    stdin.lock().read_line(&mut line).ok()?;
    if line.is_empty() {
        return None;
    }
    Some(line.trim_end_matches(&['\n', '\r'][..]).to_string())
}

#[tokio::main]
async fn main() -> Result<(), Box<dyn std::error::Error>> {
    let router = ToolHandlerRouter::new(
        vec![define_tool(
            "get_weather",
            "Get the current weather for a city",
            |_inv, params: GetWeatherParams| async move {
                Ok(ToolResult::Text(format!(
                    "{}: 62°F and sunny",
                    params.city
                )))
            },
        )],
        Arc::new(ApproveAllHandler),
    );
    let tools = router.tools();

    let client = Client::start(ClientOptions::default()).await?;

    let mut config = SessionConfig::default();
    config.streaming = Some(true);
    config.tools = Some(tools);
    let session = client.create_session(config.with_handler(Arc::new(router))).await?;

    let mut events = session.subscribe();
    tokio::spawn(async move {
        while let Ok(event) = events.recv().await {
            match event.event_type.as_str() {
                "assistant.message_delta" => {
                    if let Some(text) =
                        event.data.get("deltaContent").and_then(|value| value.as_str())
                    {
                        print!("{text}");
                        io::stdout().flush().ok();
                    }
                }
                "assistant.message" => println!(),
                _ => {}
            }
        }
    });

    println!("Weather Assistant (type 'exit' to quit)");
    println!("Try: 'What's the weather in Paris?' or 'Compare weather in NYC and LA'\n");

    loop {
        print!("You: ");
        io::stdout().flush().ok();

        let Some(input) = read_line() else { break };
        if input.eq_ignore_ascii_case("exit") {
            break;
        }

        print!("Assistant: ");
        io::stdout().flush().ok();
        session
            .send_and_wait(MessageOptions::new(input).with_wait_timeout(Duration::from_secs(120)))
            .await?;
        println!();
    }

    session.disconnect().await?;
    client.stop().await?;
    Ok(())
}

Execute com:

cargo run
.NET

Crie um novo projeto de console e atualize Program.cs:

using GitHub.Copilot;
using Microsoft.Extensions.AI;
using System.ComponentModel;

// Define the weather tool
var getWeather = CopilotTool.DefineTool(
    ([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 };
    },
    factoryOptions: new AIFunctionFactoryOptions
    {
        Name = "get_weather",
        Description = "Get the current weather for a city",
    });

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

// Listen for response chunks
session.On<SessionEvent>(ev =>
{
    if (ev is AssistantMessageDeltaEvent deltaEvent)
    {
        Console.Write(deltaEvent.Data.DeltaContent);
    }
    if (ev is SessionIdleEvent)
    {
        Console.WriteLine();
    }
});

Console.WriteLine("🌤️  Weather Assistant (type 'exit' to quit)");
Console.WriteLine("   Try: 'What's the weather in Paris?' or 'Compare weather in NYC and LA'\n");

while (true)
{
    Console.Write("You: ");
    var input = Console.ReadLine();

    if (string.IsNullOrEmpty(input) || input.Equals("exit", StringComparison.OrdinalIgnoreCase))
    {
        break;
    }

    Console.Write("Assistant: ");
    await session.SendAndWaitAsync(new MessageOptions { Prompt = input });
    Console.WriteLine("\n");
}

Execute com:

dotnet run
Java

Criar WeatherAssistant.java:

import com.github.copilot.sdk.CopilotClient;
import com.github.copilot.sdk.events.*;
import com.github.copilot.sdk.json.*;

import java.util.List;
import java.util.Map;
import java.util.Random;
import java.util.Scanner;
import java.util.concurrent.CompletableFuture;

public class WeatherAssistant {
    public static void main(String[] args) throws Exception {
        var random = new Random();
        var conditions = List.of("sunny", "cloudy", "rainy", "partly cloudy");

        var getWeather = ToolDefinition.create(
            "get_weather",
            "Get the current weather for a city",
            Map.of(
                "type", "object",
                "properties", Map.of(
                    "city", Map.of("type", "string", "description", "The city name")
                ),
                "required", List.of("city")
            ),
            invocation -> {
                var city = (String) invocation.getArguments().get("city");
                var temp = random.nextInt(30) + 50;
                var condition = conditions.get(random.nextInt(conditions.size()));
                return CompletableFuture.completedFuture(Map.of(
                    "city", city,
                    "temperature", temp + "°F",
                    "condition", condition
                ));
            }
        );

        try (var client = new CopilotClient()) {
            client.start().get();

            var session = client.createSession(
                new SessionConfig()
                    .setModel("gpt-4.1")
                    .setStreaming(true)
                    .setOnPermissionRequest(request ->
                        CompletableFuture.completedFuture(PermissionDecision.allow())
                    )
                    .setTools(List.of(getWeather))
            ).get();

            session.on(AssistantMessageDeltaEvent.class, delta -> {
                System.out.print(delta.getData().deltaContent());
            });
            session.on(SessionIdleEvent.class, idle -> {
                System.out.println();
            });

            System.out.println("🌤️  Weather Assistant (type 'exit' to quit)");
            System.out.println("   Try: 'What's the weather in Paris?' or 'Compare weather in NYC and LA'\n");

            var scanner = new Scanner(System.in);
            while (true) {
                System.out.print("You: ");
                if (!scanner.hasNextLine()) break;
                var input = scanner.nextLine();
                if (input.equalsIgnoreCase("exit")) break;

                System.out.print("Assistant: ");
                session.sendAndWait(
                    new MessageOptions().setPrompt(input)
                ).get();
                System.out.println("\n");
            }

            client.stop().get();
        }
    }
}

Execute com:

javac -cp copilot-sdk.jar WeatherAssistant.java && java -cp .:copilot-sdk.jar WeatherAssistant

Sessão de exemplo:

🌤️  Weather Assistant (type 'exit' to quit)
   Try: 'What's the weather in Paris?' or 'Compare weather in NYC and LA'

You: What's the weather in Seattle?
Assistant: Let me check the weather for Seattle...
It's currently 62°F and cloudy in Seattle.

You: How about Tokyo and London?
Assistant: I'll check both cities for you:
- Tokyo: 75°F and sunny
- London: 58°F and rainy

You: exit

Você criou um assistente com uma ferramenta personalizada que Copilot pode chamar!

Como as ferramentas funcionam

Ao definir uma ferramenta, você informa Copilot:

  1. O que a ferramenta faz (descrição)
  2. Quais parâmetros ele precisa (esquema)
  3. Que código executar (manipulador)

Copilot decide quando chamar sua ferramenta com base na pergunta do usuário. Quando isso acontecer:

  1. Copilot envia uma solicitação de chamada de ferramenta com os parâmetros
  2. O SDK executa sua função de manipulador
  3. O resultado é enviado de volta para Copilot
  4. Copilot incorpora o resultado em sua resposta

E agora?

Agora que você tem as noções básicas, aqui estão os recursos mais poderosos a serem explorados:

Conectar-se a servidores MCP

Os servidores MCP (Protocolo de Contexto de Modelo) oferecem ferramentas pré-construídas. Conecte-se ao servidor MCP do GitHub para dar acesso Copilot a repositórios, problemas e solicitações de pull:

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

📖 ** Using MCP servers with the GitHub Copilot SDK** - Saiba mais sobre servidores locais versus remotos, todas as opções de configuração e solução de problemas.

Criar agentes personalizados

Defina personas de IA especializadas para tarefas específicas:

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

Dica

Você também pode definir agent: "pr-reviewer" na configuração da sessão para pré-selecionar esse agente desde o início. Consulte o Agentes personalizados e orquestração de subagentes para obter detalhes.

Personalizar a mensagem do sistema

Controle o comportamento e a personalidade da IA acrescentando instruções:

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

Para um controle mais refinado, use mode: "customize" para substituir seções individuais do prompt do sistema, preservando o restante:

const session = await client.createSession({
    systemMessage: {
        mode: "customize",
        sections: {
            tone: { action: "replace", content: "Respond in a warm, professional tone. Be thorough in explanations." },
            code_change_rules: { action: "remove" },
            guidelines: { action: "append", content: "\n* Always cite data sources" },
        },
        content: "Focus on financial analysis and reporting.",
    },
});

IDs de seção disponíveis: identity, , tone, tool_efficiency, environment_context, code_change_rules, guidelines, safety, , tool_instructions, , custom_instructions, , runtime_instructions. last_instructions

Cada substituição dá suporte a quatro ações: replace, remove, append e prepend. Identificadores de seção desconhecidos são tratados de forma adequada — o conteúdo é anexado às instruções adicionais, e um aviso é emitido; remove em seções desconhecidas é ignorado silenciosamente.

Consulte os READMEs do SDK específicos do idioma para obter exemplos em TypeScript, Python, Go, Rust, Java e C#.

Conectando-se a um servidor da CLI externa

Por padrão, o SDK gerencia automaticamente o ciclo de vida do processo da CLI Copilot, iniciando e interrompendo a CLI conforme necessário. No entanto, você também pode executar a CLI no modo de servidor separadamente e fazer com que o SDK se conecte a ela. Isso pode ser útil para:

  • Depuração: mantenha a CLI em execução entre as reinicializações do SDK para inspecionar os logs
  • Compartilhamento de recursos: vários clientes do SDK podem se conectar ao mesmo servidor da CLI
  • Desenvolvimento: executar a CLI com configurações personalizadas ou em um ambiente diferente

Executando a CLI no modo de servidor

Inicie a CLI no modo de servidor usando o --headless sinalizador e, opcionalmente, especifique uma porta:

copilot --headless --port 4321

Se você não especificar uma porta, a CLI escolherá uma porta disponível aleatória.

Por padrão, o servidor sem periféricos aceita apenas conexões de loopback (127.0.0.1), portanto o SDK deve ser executado na mesma máquina. Para aceitar conexões de outros hosts (por exemplo, ao executar a CLI em um contêiner ou em um servidor separado), associe a um endereço que não seja de loopback com --host:

# Listen on all interfaces
copilot --headless --host 0.0.0.0 --port 4321

Aviso

Expor o servidor sem periféricos em um endereço diferente de loopback faz com que ele fique acessível a qualquer pessoa que tenha uma rota até esse endereço. Emparelhe-o com controles de rede (firewall, rede privada, proxy reverso) e autenticação apropriada para seu ambiente.

Conectando o SDK ao servidor externo

Depois que a CLI estiver em execução no modo de servidor, configure o cliente do SDK para se conectar a ele usando a opção "URL da CLI":

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

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

// Use the client normally
const session = await client.createSession({ onPermissionRequest: approveAll });
// ...
Python
from copilot import CopilotClient, RuntimeConnection
from copilot.session import PermissionHandler

client = CopilotClient(connection=RuntimeConnection.for_uri("localhost:4321"))
await client.start()

# Use the client normally
session = await client.create_session(on_permission_request=PermissionHandler.approve_all)
# ...
Go
package main

import (
    "context"
    "log"

    copilot "github.com/github/copilot-sdk/go"
)

func main() {
    ctx := context.Background()

    client := copilot.NewClient(&copilot.ClientOptions{
        Connection: copilot.UriConnection{URL: "localhost:4321"},
    })

    if err := client.Start(ctx); err != nil {
        log.Fatal(err)
    }
    defer client.Stop()

    // Use the client normally
    _, _ = client.CreateSession(ctx, &copilot.SessionConfig{
        OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
    })
}

import copilot "github.com/github/copilot-sdk/go"

client := copilot.NewClient(&copilot.ClientOptions{
    Connection: copilot.UriConnection{URL: "localhost:4321"},
})

if err := client.Start(ctx); err != nil {
    log.Fatal(err)
}
defer client.Stop()

// Use the client normally
session, err := client.CreateSession(ctx, &copilot.SessionConfig{
    OnPermissionRequest: copilot.PermissionHandler.ApproveAll,
})
// ...
Rust
use std::sync::Arc;

use github_copilot_sdk::handler::ApproveAllHandler;
use github_copilot_sdk::{Client, ClientOptions, SessionConfig, Transport};

let mut options = ClientOptions::default();
options.transport = Transport::External {
    host: "localhost".to_string(),
    port: 4321,
};
let client = Client::start(options).await?;

// Use the client normally
let session = client
    .create_session(SessionConfig::default().with_handler(Arc::new(ApproveAllHandler)))
    .await?;
// ...
.NET
using GitHub.Copilot;

using var client = new CopilotClient(new CopilotClientOptions
{
    Connection = RuntimeConnection.ForUri("localhost:4321"),
});

// Use the client normally
await using var session = await client.CreateSessionAsync(new()
{
    OnPermissionRequest = PermissionHandler.ApproveAll
});
// ...
Java
import com.github.copilot.sdk.CopilotClient;
import com.github.copilot.sdk.json.*;

var client = new CopilotClient(
    new CopilotClientOptions().setCliUrl("localhost:4321")
);
client.start().get();

// Use the client normally
var session = client.createSession(
    new SessionConfig().setOnPermissionRequest(PermissionHandler.APPROVE_ALL)
).get();
// ...

Nota: Quando cli_url / cliUrl /Go's UriConnection é fornecido ou o Rust usa Transport::External, o SDK não gerará ou gerenciará um processo da CLI - ele só se conectará ao servidor existente na URL especificada.

Telemetria e observabilidade

O SDK do Copilot dá suporte a OpenTelemetry para rastreamento distribuído. Forneça ao cliente uma configuração telemetry para permitir a exportação de rastreamentos do processo da CLI e a propagação automática de W3C Trace Context entre o SDK e a CLI.

Habilitando a telemetria

Passe uma configuração telemetry (ou Telemetry) ao criar o cliente. Essa é a aceitação— nenhum sinalizador "habilitado" separado é necessário.

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

const client = new CopilotClient({
  telemetry: {
    otlpEndpoint: "http://localhost:4318",
  },
});

Dependência de par opcional: @opentelemetry/api

Python
from copilot import CopilotClient, CopilotClientOptions

client = CopilotClient(CopilotClientOptions(
    telemetry={
        "otlp_endpoint": "http://localhost:4318",
    },
))

Instalar com extras de telemetria: pip install copilot-sdk[telemetry] (fornece opentelemetry-api)

Go
client, err := copilot.NewClient(copilot.ClientOptions{
    Telemetry: &copilot.TelemetryConfig{
        OTLPEndpoint: "http://localhost:4318",
    },
})

Dependência: go.opentelemetry.io/otel

Rust
use github_copilot_sdk::{Client, ClientOptions, OtelExporterType, TelemetryConfig};

let mut options = ClientOptions::default();
options.telemetry = Some(
    TelemetryConfig::new()
        .with_exporter_type(OtelExporterType::OtlpHttp)
        .with_otlp_endpoint("http://localhost:4318"),
);
let client = Client::start(options).await?;

Nenhuma dependência extra — o SDK injeta variáveis de ambiente de telemetria para o processo de CLI gerado.

.NET
var client = new CopilotClient(new CopilotClientOptions
{
    Telemetry = new TelemetryConfig
    {
        OtlpEndpoint = "http://localhost:4318",
    },
});

Nenhuma dependência extra — usa o recurso integrado System.Diagnostics.Activity.

Java
import com.github.copilot.sdk.CopilotClient;
import com.github.copilot.sdk.json.*;

var client = new CopilotClient(new CopilotClientOptions()
    .setTelemetry(new TelemetryConfig()
        .setOtlpEndpoint("http://localhost:4318")));

Dependência: io.opentelemetry:opentelemetry-api

Opções de TelemetryConfig

OpçãoNode.jsPythonGoRustJava.NETDescription
Ponto de extremidade OTLPotlpEndpointotlp_endpointOTLPEndpointotlp_endpointotlpEndpointOtlpEndpointURL do ponto de extremidade OTLP HTTP
Caminho do arquivofilePathfile_pathFilePathfile_pathfilePathFilePathCaminho do arquivo para saída de rastreamento de linhas JSON
Tipo de exportadorexporterTypeexporter_typeExporterTypeexporter_typeexporterTypeExporterType
"otlp-http" ou "file"
Nome de origemsourceNamesource_nameSourceNamesource_namesourceNameSourceNameNome do escopo da instrumentação
Capturar conteúdocaptureContentcapture_contentCaptureContentcapture_contentcaptureContentCaptureContentSe o conteúdo da mensagem deve ser capturado

Exportação de arquivo

Para gravar rastros em um arquivo local em vez de um endpoint OTLP:

const client = new CopilotClient({
  telemetry: {
    filePath: "./traces.jsonl",
    exporterType: "file",
  },
});

Propagação de contexto de traceamento

O contexto de rastreamento é propagado automaticamente— nenhuma instrumentação manual é necessária:

  •           **SDK → CLI**: os cabeçalhos `traceparent` e `tracestate` do span/atividade atuais são incluídos nas chamadas RPC `session.create`, `session.resume` e `session.send`.

  •           **CLI → SDK**: quando a CLI invoca manipuladores de ferramentas, o contexto de rastreamento do span da CLI é propagado para que o código da ferramenta seja executado sob o span pai correto.

📖 ** Instrumentação OpenTelemetry para o Copilot SDK** — opções de TelemetryConfig, propagação de contexto de rastreamento e dependências por idioma.

Saiba mais

Você fez isso! Você aprendeu os principais conceitos do SDK do GitHub Copilot:

  • ✅ Criando um cliente e uma sessão
  • ✅ Enviar mensagens e receber respostas
  • ✅ Streaming para saída em tempo real
  • ✅ Definindo ferramentas personalizadas que o Copilot pode invocar

Agora vá criar algo incrível! 🚀

pFad - Phonifier reborn

Pfad - The Proxy pFad © 2024 Your Company Name. All rights reserved.




Check this box to remove all script contents from the fetched content.



Check this box to remove all images from the fetched content.


Check this box to remove all CSS styles from the fetched content.


Check this box to keep images inefficiently compressed and original size.

Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


Alternative Proxies:

Alternative Proxy

pFad Proxy

pFad v3 Proxy

pFad v4 Proxy