Skip to main content

Plugin settings

Model context size​

Model context size setting

For models connected via OpenAI-compatible mode, a field is available for manually specifying the context size.

Previously, the plugin couldn't always correctly determine the context limit for such models, which resulted in incorrect values being displayed in the interface. You can now set the exact context size manually, and the plugin will correctly manage the size of the requests it sends.

When it's useful​

  • You're using OpenAI-compatible models (for example, Qwen or DeepSeek) with a non-standard context size.
  • You need the plugin to calculate limits correctly when sending requests and compressing the chat.