GitHub Copilot

Use GitHub Copilot's hosted models with Docker Agent through your existing GitHub subscription.

Overview

GitHub Copilot exposes an OpenAI-compatible Chat Completions API at https://api.githubcopilot.com. Docker Agent ships with built-in support for it as the github-copilot provider, so any user with a paid GitHub Copilot subscription can reuse their entitlement from Docker Agent.

Prerequisites

• An active GitHub Copilot subscription (Individual, Business, or Enterprise).
• A personal access token with the copilot scope, exported as GITHUB_TOKEN.

export GITHUB_TOKEN="ghp_..."

Running Evals

Eval cases (docker agent eval) run in isolated containers. Unlike dedicated provider API keys, GITHUB_TOKEN and GH_TOKEN are not forwarded into eval containers automatically, because a GitHub token grants far broader access than a model API key. Pass the token explicitly:

docker agent eval agent.yaml ./evals -e GITHUB_TOKEN

See Evaluation for details, including behavior with --env-from-file.

Configuration

Inline

agents:
  root:
    model: github-copilot/gpt-4o
    instruction: You are a helpful assistant.

Named model

models:
  copilot:
    provider: github-copilot
    model: gpt-4o
    temperature: 0.7
    max_tokens: 4000

agents:
  root:
    model: copilot

Available Models

The exact set of models you can call depends on your Copilot plan. The most commonly available ones today are:

Check the GitHub Copilot documentation for the current model list.

Copilot-Integration-Id Header

GitHub's Copilot API rejects requests that don't carry a Copilot-Integration-Id header with a Bad Request error. Docker Agent automatically sends copilot-developer-cli for the github-copilot provider, so PAT-based usage works out of the box.

We specifically chose copilot-developer-cli (instead of, say, vscode-chat) because it is the integration id accepted by the Copilot API for both OAuth tokens and Personal Access Tokens. Most Docker Agent users authenticate with a PAT exported as GITHUB_TOKEN, and vscode-chat is rejected for those tokens.

If you need to send a different integration id — for example if your organization allows-lists a specific value — you can override it via provider_opts.http_headers:

models:
  copilot:
    provider: github-copilot
    model: gpt-4o
    provider_opts:
      http_headers:
        Copilot-Integration-Id: my-custom-integration

Header names are matched case-insensitively, so copilot-integration-id works too.

Chat Completions vs. Responses API

GitHub Copilot proxies OpenAI models behind two endpoints: the legacy /chat/completions and the newer /responses. Newer models (the gpt-5 family, Codex variants, etc.) are only served via /responses and reject /chat/completions with a 400 Bad Request. Docker Agent auto-selects the right endpoint per model, so no configuration is needed in the common case.

If you ever need to force one or the other, set api_type explicitly:

models:
  copilot:
    provider: github-copilot
    model: gpt-5
    provider_opts:
      api_type: openai_responses # or openai_chatcompletions

Custom HTTP Headers

provider_opts.http_headers is a generic escape hatch that works for any OpenAI-compatible provider, not just GitHub Copilot. Every key/value pair is added to every outgoing request:

models:
  my_model:
    provider: openai
    model: gpt-4o
    provider_opts:
      http_headers:
        X-Request-Source: docker-agent
        X-Tenant-Id: my-team

How It Works

GitHub Copilot is implemented as a built-in alias in Docker Agent:

• API type: OpenAI-compatible (Chat Completions)
• Base URL: https://api.githubcopilot.com
• Token variable: GITHUB_TOKEN
• Default headers: Copilot-Integration-Id: copilot-developer-cli

This means the same client as OpenAI is used, so every OpenAI feature supported by Docker Agent (tool calling, structured output, multimodal inputs, etc.) is available when the underlying model supports it.