Configuring Copilot in GitHub Desktop

Choose which AI model GitHub Desktop 中的Copilot uses for each feature, or connect your own LLM provider.

Platform navigation

在本文中

You can choose which model Copilot uses for each GitHub Desktop feature, such as commit message generation and conflict resolution.

You can also configure GitHub Desktop 中的Copilot to use your own LLM provider (BYOK) instead of GitHub-hosted models. This lets you connect to OpenAI-compatible endpoints, Azure OpenAI, or Anthropic, including locally running models such as Ollama.

Prerequisites

  • You must be signed in to a GitHub account with access to GitHub Desktop 中的Copilot.
  • If your access is managed by an organization or enterprise, GitHub Desktop 中的Copilot must be enabled for your account.
  • You have an API key or bearer token from a supported LLM provider, or you have a local model running, such as Ollama.
  • You have the base URL and at least one model identifier for the provider you want to use.

注意

Custom LLM providers in GitHub Desktop require access to GitHub Desktop 中的Copilot. To use your own LLM models with Copilot 命令行界面（CLI）, see 在 GitHub Copilot CLI 中使用自己的 LLM 模型.

Supported provider types

GitHub Desktop supports three custom provider types:

Provider typeCompatible services
OpenAI / OpenAI-compatibleOpenAI, Ollama, vLLM, Foundry Local, and any other endpoint that is compatible with the selected API format.
AzureAzure OpenAI Service.
AnthropicAnthropic Claude models.

Configuring your provider

You configure your model provider by adding a custom provider in GitHub Desktop settings.

  1. 在菜单栏中，选择“GitHub Desktop”，然后单击“设置”********。

    Mac 上的菜单栏的屏幕截图。 在打开的“GitHub Desktop”下拉菜单下，光标悬停在“设置”上，该设置以蓝色突出显示。

  2. In the left sidebar, click Copilot.

  3. Click the Providers tab.

  4. Click Add Provider.

  5. Under Name, type a name for the LLM provider.

  6. Under Type, select the provider type.

  7. Under Base URL, type the base URL of your model provider's API endpoint.

    The base URL must be an HTTPS URL, or an HTTP URL that points to the local machine.

  8. If you selected OpenAI / OpenAI-compatible, under API Format, select the API format your provider expects.

    • Select Chat completions (default) for providers that use the OpenAI Chat Completions API.
    • Select Responses (GPT-5 series) for providers that use the OpenAI Responses API.

  9. If you selected Azure, under Azure API Version, type the API version for your deployment.

  10. Optionally, under Request Timeout (seconds), type the number of seconds GitHub Desktop waits for the provider to respond.

  11. Under Authentication, select the authentication method.

    • Select API key to authenticate with an API key.
    • Select Bearer token to authenticate with a bearer token.
    • Select None only for endpoints that do not require credentials.

  12. If you selected API key or Bearer token, type the required credential.

  13. Add at least one model to the provider. For more information, see Adding models to your provider.

  14. Click Add.

  1. 使用文件”菜单，然后单击“选项” 。

    Windows 上的“GitHub Desktop”菜单栏的屏幕截图。 在展开的“文件”下拉菜单中，以橙色框出了“选项”项。

  2. In the left sidebar, click Copilot.

  3. Click the Providers tab.

  4. Click Add Provider.

  5. Under Name, type a name for the LLM provider.

  6. Under Type, select the provider type.

  7. Under Base URL, type the base URL of your model provider's API endpoint.

    The base URL must be an HTTPS URL, or an HTTP URL that points to the local machine.

  8. If you selected OpenAI / OpenAI-compatible, under API Format, select the API format your provider expects.

    • Select Chat completions (default) for providers that use the OpenAI Chat Completions API.
    • Select Responses (GPT-5 series) for providers that use the OpenAI Responses API.

  9. If you selected Azure, under Azure API Version, type the API version for your deployment.

  10. Optionally, under Request Timeout (seconds), type the number of seconds GitHub Desktop waits for the provider to respond.

  11. Under Authentication, select the authentication method.

    • Select API key to authenticate with an API key.
    • Select Bearer token to authenticate with a bearer token.
    • Select None only for endpoints that do not require credentials.

  12. If you selected API key or Bearer token, type the required credential.

  13. Add at least one model to the provider. For more information, see Adding models to your provider.

  14. Click Add.

Adding models to your provider

Add the models you want to use from your provider. Each model you add appears in the model picker alongside GitHub-hosted models.

  1. In the Add Custom Provider or Edit Custom Provider dialog, under Models, click Add Model.

  2. Under Display Name, type the friendly name shown in the Copilot model picker.

  3. Under Model Identifier, type the exact model name your provider expects.

  4. Under Reasoning Effort, select the reasoning level for the model.

    For non-reasoning models, or to let the provider choose, leave Default (provider's choice) selected.

  5. Click Add.

Reviewing provider responsibilities

When you use your own LLM provider, GitHub Desktop sends prompts and repository context to that provider instead of GitHub. Check your provider's data handling and retention policies before adding credentials.

Always review generated commit messages and conflict-resolution suggestions before committing. For more information, see 负责任地使用GitHub Copilot功能.

Further reading