Agent context should explain what it cannot represent.
That may matter as much as what it can represent.
A public page can expose routes, notes, concepts, dates, source trails, and related ideas.
It cannot hold the full texture of a life.
It cannot make private context public.
It cannot know which parts are emotionally live unless that has been made visible.
So the agent layer should say where the edge is.
This is public.
This is provisional.
This is askable.
This should not be inferred.
That is not a weakness in the context.
It is part of making the context usable.