Local VS Code language model provider for AutoCode Codex reverse-proxy models.
Usage
Run npm install.
Run npm run compile.
Press F5 from this folder to start an Extension Development Host, or package and install the VSIX.
In the Extension Development Host, run AutoCode: Set API Key.
Open Copilot Chat and pick an AutoCode model.
The provider registers vendor: "autocode" and exposes a Codex-compatible Thinking Effort model setting for reasoning-capable models: none, low, medium, high, and xhigh.
Distribution
Run npm install.
Run npm run compile.
Run npm run package to generate a VSIX file for side loading.
Install the VSIX with code --install-extension autocode-copilot-provider-0.0.4.vsix or the VS Code Extensions UI.
Publish To Marketplace
Create or sign in to your Visual Studio Marketplace publisher account.
Confirm publisher in package.json matches your Marketplace publisher ID.
Create a Personal Access Token with the Marketplace Manage scope.
Run npx vsce login <publisher-id> and paste the PAT when prompted.
Run npx vsce publish 0.0.4.
If you want to verify the package before publishing, run npx vsce package --no-dependencies and inspect the generated VSIX.
Notes
The default base URL is https://vip.auto-code.net.
API keys entered via AutoCode: Set API Key are stored in VS Code SecretStorage.
Model IDs are prefixed with autocode- so they do not collide with built-in Copilot/Codex models.
gpt-image-2 is not exposed here because this is a chat provider; image generation should use the /v1/images/* APIs.
