IssueRaiser

Support BYOK/Custom Models for Inline Code Completions

**Problem** VS Code's GitHub Copilot extension currently supports BYOK (Bring Your Own Key) models for chat via chatLanguageModels.json (VS Code insiders) or with other openAI compatible provider extensions like the Unify Chat Provider, **but not for inline code completions**. When setting "**github.copilot.selectedCompletionModel**" to a custom model ID (e.g., a local model served via OpenAI-compatible API), the setting is silently ignored because the model ID is not in the list returned by GitHub's API. The extension falls back to the default Copilot cloud model (gpt-41-copilot), and completions always go through proxy.business.githubcopilot.com. This means: Chat works with local models ✅ Inline code completions always require GitHub's cloud ❌ Disconnecting from the internet disables completions entirely ❌ **Current Behavior** https://github.com/microsoft/vscode/blob/40a9d5688c49bf00f3b401bad228fb64c8a8e0fe/extensions/copilot/src/extension/completions-core/vscode-node/lib/src/openai/model.ts#L139 ```ts if (!genericModels.includes(userSelectedCompletionModel)) {     // Silently falls back to default model     userSelectedCompletionModel = null;} ``` The fallback is silent — no warning or error is shown to the user. Completions continue to go to GitHub's cloud proxy. **Expected Behavior** Users should be able to configure a custom/OpenAI-compatible endpoint for inline code completions, similar to how chat completions work with chatLanguageModels.json or the Unify Chat

Posted by DamirLisak on May 27, 2026, 10:45 AM

Tags

Related issues

Raise real-world problems, find people facing the same issue, and discuss solutions.2,000 issues0 comments

support (Network)

Support BYOK/Custom Models for Inline Code Completions

DamirLisakMay 27, 2026, 10:45 AM

**Problem** VS Code's GitHub Copilot extension currently supports BYOK (Bring Your Own Key) models for chat via chatLanguageModels.json (VS Code insiders) or with other openAI compatible provider extensions like the Unify Chat Provider, **but not for inline code completions**. When setting "**github.copilot.selectedCompletionModel**" to a custom model ID (e.g., a local model served via OpenAI-compatible API), the setting is silently ignored because the model ID is not in the list returned by GitHub's API. The extension falls back to the default Copilot cloud model (gpt-41-copilot), and completions always go through proxy.business.githubcopilot.com. This means: Chat works with local models ✅ Inline code completions always require GitHub's cloud ❌ Disconnecting from the internet disables completions entirely ❌ **Current Behavior** https://github.com/microsoft/vscode/blob/40a9d5688c49bf00f3b401bad228fb64c8a8e0fe/extensions/copilot/src/extension/completions-core/vscode-node/lib/src/openai/model.ts#L139 ```ts if (!genericModels.includes(userSelectedCompletionModel)) {     // Silently falls back to default model     userSelectedCompletionModel = null;} ``` The fallback is silent — no warning or error is shown to the user. Completions continue to go to GitHub's cloud proxy. **Expected Behavior** Users should be able to configure a custom/OpenAI-compatible endpoint for inline code completions, similar to how chat completions work with chatLanguageModels.json or the Unify Chat

Comments (0)

No comments yet. Start the discussion.

Comment on this issue