Probes the reasoning-effort levels a third-party OpenAI-compatible pi-ai provider actually accepts (a low and a max request per undeclared chat model) and declares the detected levels in the llm-pi-ai settings namespace, so the composer model picker offers a reasoning-strength switch. A sidebar panel switches reasoning declaration and sniffing per provider, and routes that declare levels but lack compat.supportsReasoningEffort are given that flag automatically. The concrete level is chosen in the native composer picker.
This plugin has not published an npm package, so the store does not offer an install command yet. Use the repository link below to view the source.