إعطاء Jev رؤية: OCR محلي أولاً ثم التسليم

Keno's breakdown of giving Jev eyes is a small example of a much bigger pattern in agent design. Jev can't see images. So the fix isn't to bolt vision onto a decision model, it's to run local OCR first, pull structured text and objects out of the picture, and only then hand Jev