This week's release includes operating system-specific settings, improved Edit Prediction latency, subtle and eager modes for Copilot and Supermaven, thinking support for Mistral, the ability to clone Git repositories, file comparison through the project panel, and support for adjusting the reasoning effort for OpenAI models.
"language_models": {
"openai": {
"available_models": [
{
"name": "gpt-5-mini",
"display_name": "GPT 5 Mini (custom reasoning)",
"max_output_tokens": 128000,
"max_tokens": 272000,
"reasoning_effort": "high" // Can be minimal, low, medium (default), and high
}
],
"version": "1"
}
}