Copilot Sdk

GitHub Copilot SDK

Build applications that programmatically interact with GitHub Copilot. The SDK wraps the Copilot CLI via JSON-RPC, providing session management, custom tools, hooks, MCP server integration, and streaming across Node.js, Python, Go, and .NET.

Prerequisites

• GitHub Copilot CLI installed and authenticated (copilot --version to verify)
• GitHub Copilot subscription (Individual, Business, or Enterprise) — not required for BYOK
• Runtime: Node.js 18+ / Python 3.8+ / Go 1.21+ / .NET 8.0+

Installation

Core Pattern: Client → Session → Message

All SDK usage follows this pattern: create a client, create a session, send messages.

Node.js / 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();

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

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

session, _ := client.CreateSession(ctx, &copilot.SessionConfig{Model: "gpt-4.1"})
response, _ := session.SendAndWait(ctx, copilot.MessageOptions{Prompt: "What is 2 + 2?"})
fmt.Println(*response.Data.Content)

.NET

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);

Streaming Responses

Enable real-time output by setting streaming: true and subscribing to delta events.

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

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

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

Python equivalent:

from copilot.generated.session_events import SessionEventType

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()

session.on(handle_event)
await session.send_and_wait({"prompt": "Tell me a joke"})

Event Subscription

Custom Tools

Define tools that Copilot can call to extend its capabilities.

Node.js

import { CopilotClient, defineTool } 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 ({ city }) => ({ city, temperature: "72°F", condition: "sunny" }),
});

const session = await client.createSession({
    model: "gpt-4.1",
    tools: [getWeather],
});

Python

from copilot.tools import define_tool
from pydantic import BaseModel, Field

class GetWeatherParams(BaseModel):
    city: str = Field(description="The city name")

@define_tool(description="Get the current weather for a city")
async def get_weather(params: GetWeatherParams) -> dict:
    return {"city": params.city, "temperature": "72°F", "condition": "sunny"}

session = await client.create_session({"model": "gpt-4.1", "tools": [get_weather]})

Go

type WeatherParams struct {
    City string `json:"city" jsonschema:"The city name"`
}

getWeather := copilot.DefineTool("get_weather", "Get weather for a city",
    func(params WeatherParams, inv copilot.ToolInvocation) (WeatherResult, error) {
        return WeatherResult{City: params.City, Temperature: "72°F"}, nil
    },
)

session, _ := client.CreateSession(ctx, &copilot.SessionConfig{
    Model: "gpt-4.1",
    Tools: []copilot.Tool{getWeather},
})

.NET

var getWeather = AIFunctionFactory.Create(
    ([Description("The city name")] string city) => new { city, temperature = "72°F" },
    "get_weather", "Get the current weather for a city");

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

Hooks

Intercept and customize session behavior at key lifecycle points.

Example: Tool Permission Control

const session = await client.createSession({
    hooks: {
        onPreToolUse: async (input) => {
            if (["shell", "bash"].includes(input.toolName)) {
                return { permissionDecision: "deny", permissionDecisionReason: "Shell access not permitted" };
            }
            return { permissionDecision: "allow" };
        },
    },
});

Pre-Tool Use Output

MCP Server Integration

Connect to MCP servers for pre-built tool capabilities.

Remote HTTP Server

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

Local Stdio Server

const session = await client.createSession({
    mcpServers: {
        filesystem: {
            type: "local",
            command: "npx",
            args: ["-y", "@modelcontextprotocol/server-filesystem", "/allowed/path"],
            tools: ["*"],
        },
    },
});

MCP Config Fields

Authentication

Methods (Priority Order)

1. Explicit token — githubToken in constructor
2. Environment variables — COPILOT_GITHUB_TOKEN → GH_TOKEN → GITHUB_TOKEN
3. Stored OAuth — From copilot auth login
4. GitHub CLI — gh auth credentials

Programmatic Token

const client = new CopilotClient({ githubToken: process.env.GITHUB_TOKEN });

BYOK (Bring Your Own Key)

Use your own API keys — no Copilot subscription required.

const session = await client.createSession({
    model: "gpt-5.2-codex",
    provider: {
        type: "openai",
        baseUrl: "https://your-resource.openai.azure.com/openai/v1/",
        wireApi: "responses",
        apiKey: process.env.FOUNDRY_API_KEY,
    },
});

Wire API: Use "responses" for GPT-5 series, "completions" (default) for others.

Session Persistence

Resume sessions across restarts by providing your own session ID.

// Create with explicit ID
const session = await client.createSession({
    sessionId: "user-123-task-456",
    model: "gpt-4.1",
});

// Resume later
const resumed = await client.resumeSession("user-123-task-456");
await resumed.sendAndWait({ prompt: "What did we discuss?" });

Session management:

const sessions = await client.listSessions();          // List all
await client.deleteSession("user-123-task-456");       // Delete
await session.destroy();                                // Destroy active

BYOK sessions: Must re-provide provider config on resume (keys are not persisted).

Infinite Sessions

For long-running workflows that may exceed context limits:

const session = await client.createSession({
    infiniteSessions: {
        enabled: true,
        backgroundCompactionThreshold: 0.80,
        bufferExhaustionThreshold: 0.95,
    },
});

Custom Agents

Define specialized AI personas:

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 security, performance, and maintainability.",
    }],
});

System Message

Control AI behavior and personality:

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

Skills Integration

Load skill directories to extend Copilot's capabilities:

const session = await client.createSession({
    skillDirectories: ["./skills/code-review", "./skills/documentation"],
    disabledSkills: ["experimental-feature"],
});

Permission & Input Handlers

Handle tool permissions and user input requests programmatically:

const session = await client.createSession({
    onPermissionRequest: async (request) => {
        // Auto-approve git commands only
        if (request.kind === "shell") {
            return { approved: request.command.startsWith("git") };
        }
        return { approved: true };
    },
    onUserInputRequest: async (request) => {
        // Handle ask_user tool calls
        return { response: "yes" };
    },
});

External CLI Server

Connect to a separately running CLI instead of auto-managing the process:

copilot --headless --port 4321

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

Client Configuration

Session Configuration

Debugging

Enable debug logging to troubleshoot issues:

const client = new CopilotClient({ logLevel: "debug" });

Common issues:

• CLI not found → Install CLI or set cliPath
• Not authenticated → Run copilot auth login or provide githubToken
• Session not found → Don't use session after destroy()
• Connection refused → Check CLI process, enable autoRestart

Key API Summary

References

• GitHub Copilot SDK
• Copilot CLI Installation
• MCP Protocol Specification

🧠 AGI Framework Integration

Adapted for @techwavedev/agi-agent-kit Original source: antigravity-awesome-skills

Hybrid Memory Integration (Qdrant + BM25)

Before executing complex tasks with this skill:

python3 execution/memory_manager.py auto --query "<task summary>"

Decision Tree:

• Cache hit? Use cached response directly — no need to re-process.
• Memory match? Inject context_chunks into your reasoning.
• No match? Proceed normally, then store results:

python3 execution/memory_manager.py store \
  --content "Description of what was decided/solved" \
  --type decision \
  --tags copilot-sdk <relevant-tags>

Note: Storing automatically updates both Vector (Qdrant) and Keyword (BM25) indices.

Agent Team Collaboration

• Strategy: This skill communicates via the shared memory system.
• Orchestration: Invoked by orchestrator via intelligent routing.
• Context Sharing: Always read previous agent outputs from memory before starting.

Local LLM Support

When available, use local Ollama models for embedding and lightweight inference:

• Embeddings: nomic-embed-text via Qdrant memory system
• Lightweight analysis: Local models reduce API costs for repetitive patterns