copilot-sdk — Интеграция агентов GitHub Copilot для разработки

--- name: copilot-sdk description: Build agentic applications with GitHub Copilot SDK. Use when embedding AI agents in apps, creating custom tools, implementing streaming responses, managing sessions, connecting to MCP servers, or creating custom agents. Triggers on Copilot SDK, GitHub SDK, agentic app, embed Copilot, programmable agent, MCP server, custom agent. --- # GitHub Copilot SDK Embed Copilot's agentic workflows in any application using Python, TypeScript, Go, or .NET. ## Overview The GitHub Copilot SDK exposes the same engine behind Copilot CLI: a production-tested agent runtime you can invoke programmatically. No need to build your own orchestration - you define agent behavior, Copilot handles planning, tool invocation, file edits, and more. ## Prerequisites 1. **GitHub Copilot CLI** installed and authenticated ([Installation guide](https://docs.github.com/en/copilot/how-tos/set-up/install-copilot-cli)) 2. **Language runtime**: Node.js 18+, Python 3.8+, Go 1.21+, or .NET 8.0+ Verify CLI: `copilot --version` ## Installation ### Node.js/TypeScript ```bash mkdir copilot-demo && cd copilot-demo npm init -y --init-type module npm install @github/copilot-sdk tsx ``` ### Python ```bash pip install github-copilot-sdk ``` ### Go ```bash mkdir copilot-demo && cd copilot-demo go mod init copilot-demo go get github.com/github/copilot-sdk/go ``` ### .NET ```bash dotnet new console -n CopilotDemo && cd CopilotDemo dotnet add package GitHub.Copilot.SDK ``` ## Quick Start ### TypeScript ```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); ``` Run: `npx tsx index.ts` ### Python ```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 ```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#) ```csharp 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); ``` Run: `dotnet run` ## Streaming Responses Enable real-time output for better UX: ### TypeScript ```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 ```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 ```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 ```csharp 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" }); ``` ## Custom Tools Define tools that Copilot can invoke during reasoning. When you define a tool, you tell Copilot: 1. **What the tool does** (description) 2. **What parameters it needs** (schema) 3. **What code to run** (handler) ### TypeScript (JSON Schema) ```typescript 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) ```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: 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 ```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) ```csharp 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 = $"{temp}°F", condition }; }, "get_weather", "Get the current weather for a city" ); await using var session = await client.CreateSessionAsync(new SessionConfig { OnPermissionRequest = PermissionHandler.ApproveAll, Model = "gpt-4.1", Streaming = true, Tools = [getWeather], }); ``` ## How Tools Work When Copilot decides to call your tool: 1. Copilot sends a tool call request with the parameters 2. The SDK runs your handler function 3. The result is sent back to Copilot 4. Copilot incorporates the result into its response Copilot decides when to call your tool based on the user's question and your tool's description. ## Interactive CLI Assistant Build a complete interactive assistant: ### TypeScript ```typescript import { CopilotClient, approveAll, defineTool, SessionEvent } from "@github/copilot-sdk"; import * as readline from "readline"; const getWeather = defineTool("get_weather", { description: "Get the current weather for a city", parameters: { type: "object", properties: { city: { type: "string", description: "The city name" }, }, required: ["city"], }, handler: async ({ city }) => { const conditions = ["sunny", "cloudy", "rainy", "partly cloudy"]; const temp = Math.floor(Math.random() * 30) + 50; const condition = conditions[Math.floor(Math.random() * conditions.length)]; return { city, temperature: `${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 ```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 Server Integration Connect to MCP (Model Context Protocol) servers for pre-built tools. Connect to GitHub's MCP server for repository, issue, and PR access: ### TypeScript ```typescript const session = await client.createSession({ onPermissionRequest: approveAll, model: "gpt-4.1", mcpServers: { github: { type: "http", url: "https://api.githubcopilot.com/mcp/", }, }, }); ``` ### Python ```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 ```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 ```csharp 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/", }, }, }); ``` ## Custom Agents Define specialized AI personas for specific tasks: ### TypeScript ```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 ```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.", }], }) ``` ## System Message Customize the AI's behavior and personality: ### TypeScript ```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 ```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.", }, }) ``` ## External CLI Server Run the CLI in server mode separately and connect the SDK to it. Useful for debugging, resource sharing, or custom environments. ### Start CLI in Server Mode ```bash copilot --server --port 4321 ``` ### Connect SDK to External Server #### TypeScript ```typescript const client = new CopilotClient({ cliUrl: "localhost:4321" }); const session = await client.createSession({ onPermissionRequest: approveAll, model: "gpt-4.1", }); ``` #### Python ```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 ```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 ```csharp 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", }); ``` **Note:** When `cliUrl` is provided, the SDK will not spawn or manage a CLI process - it only connects to the existing server. ## Event Types | Event | Description | |-------|-------------| | `user.message` | User input added | | `assistant.message` | Complete model response | | `assistant.message_delta` | Streaming response chunk | | `assistant.reasoning` | Model reasoning (model-dependent) | | `assistant.reasoning_delta` | Streaming reasoning chunk | | `tool.execution_start` | Tool invocation started | | `tool.execution_complete` | Tool execution finished | | `session.idle` | No active processing | | `session.error` | Error occurred | ## Client Configuration | Option | Description | Default | |--------|-------------|---------| | `cliPath` | Path to Copilot CLI executable | System PATH | | `cliUrl` | Connect to existing server (e.g., "localhost:4321") | None | | `port` | Server communication port | Random | | `useStdio` | Use stdio transport instead of TCP | true | | `logLevel` | Logging verbosity | "info" | | `autoStart` | Launch server automatically | true | | `autoRestart` | Restart on crashes | true | | `cwd` | Working directory for CLI process | Inherited | ## Session Configuration | Option | Description | |--------|-------------| | `model` | LLM to use ("gpt-4.1", "claude-sonnet-4.5", etc.) | | `sessionId` | Custom session identifier | | `tools` | Custom tool definitions | | `mcpServers` | MCP server connections | | `customAgents` | Custom agent personas | | `systemMessage` | Override default system prompt | | `streaming` | Enable incremental response chunks | | `availableTools` | Whitelist of permitted tools | | `excludedTools` | Blacklist of disabled tools | ## Session Persistence Save and resume conversations across restarts: ### Create with Custom ID ```typescript const session = await client.createSession({ onPermissionRequest: approveAll, sessionId: "user-123-conversation", model: "gpt-4.1" }); ``` ### Resume Session ```typescript const session = await client.resumeSession("user-123-conversation", { onPermissionRequest: approveAll }); await session.send({ prompt: "What did we discuss earlier?" }); ``` ### List and Delete Sessions ```typescript const sessions = await client.listSessions(); await client.deleteSession("old-session-id"); ``` ## Error Handling ```typescript 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(); } ``` ## Graceful Shutdown ```typescript process.on("SIGINT", async () => { console.log("Shutting down..."); await client.stop(); process.exit(0); }); ``` ## Common Patterns ### Multi-turn Conversation ```typescript 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" ``` ### File Attachments ```typescript await session.send({ prompt: "Analyze this file", attachments: [{ type: "file", path: "./data.csv", displayName: "Sales Data" }] }); ``` ### Abort Long Operations ```typescript const timeoutId = setTimeout(() => { session.abort(); }, 60000); session.on((event) => { if (event.type === "session.idle") { clearTimeout(timeoutId); } }); ``` ## Available Models Query available models at runtime: ```typescript const models = await client.getModels(); // Returns: ["gpt-4.1", "gpt-4o", "claude-sonnet-4.5", ...] ``` ## Best Practices 1. **Always cleanup**: Use `try-finally` or `defer` to ensure `client.stop()` is called 2. **Set timeouts**: Use `sendAndWait` with timeout for long operations 3. **Handle events**: Subscribe to error events for robust error handling 4. **Use streaming**: Enable streaming for better UX on long responses 5. **Persist sessions**: Use custom session IDs for multi-turn conversations 6. **Define clear tools**: Write descriptive tool names and descriptions ## Architecture ``` Your Application | SDK Client | JSON-RPC Copilot CLI (server mode) | GitHub (models, auth) ``` The SDK manages the CLI process lifecycle automatically. All communication happens via JSON-RPC over stdio or TCP. ## Resources - **GitHub Repository**: https://github.com/github/copilot-sdk - **Getting Started Tutorial**: https://github.com/github/copilot-sdk/blob/main/docs/tutorials/first-app.md - **GitHub MCP Server**: https://github.com/github/github-mcp-server - **MCP Servers Directory**: https://github.com/modelcontextprotocol/servers - **Cookbook**: https://github.com/github/copilot-sdk/tree/main/cookbook - **Samples**: https://github.com/github/copilot-sdk/tree/main/samples ## Status This SDK is in **Technical Preview** and may have breaking changes. Not recommended for production use yet.