The cheap-model-picks-the-lens, strong-model-extracts-under-it split is the part I hadn't seen articulated this cleanly before. One thing I'm not sure the two-stage design handles: your three example compressions (task, relationship, who-knows-what) each read like they're picking a single dominant constraint per scene, but a lot of real next-actions need more than one satisfied at once - Alice has to act on the tail without confronting Bob about knowing, while their trust is still broken. If the cheap model is choosing one lens per compression pass, does the axis that didn't get picked just silently fall back into the same rediscovery risk for that turn, or does the packet actually carry more than one constraint at a time?
The cheap-model-picks-the-lens, strong-model-extracts-under-it split is the part I hadn't seen articulated this cleanly before. One thing I'm not sure the two-stage design handles: your three example compressions (task, relationship, who-knows-what) each read like they're picking a single dominant constraint per scene, but a lot of real next-actions need more than one satisfied at once - Alice has to act on the tail without confronting Bob about knowing, while their trust is still broken. If the cheap model is choosing one lens per compression pass, does the axis that didn't get picked just silently fall back into the same rediscovery risk for that turn, or does the packet actually carry more than one constraint at a time?