Attention engine
The subsystem that allocates cognitive resources across competing signals based on a six-dimensional salience score: importance, relevance, urgency, novelty, risk, and goal relevance. Manages a working-memory budget of five primary and ten background items.
The attention engine is the gating mechanism that decides which signals from the environment and which retrieved memories enter working memory and receive cognitive processing. Without attention gating, every incoming event would compete equally for processing resources, producing incoherent responses to a flood of equally-weighted signals. The six salience dimensions - importance, relevance, urgency, novelty, risk, and goal relevance - are not static weights: affect state modulates them in real time, so a system in a high-urgency emotional context weights urgency more heavily than one in a stable, exploratory context. The working memory budget of five primary slots and ten background slots is a hard limit that forces prioritization: the five highest-salience items get primary processing, the next ten get background monitoring, and the rest are discarded for this cycle. Items promoted to primary slots produce richer trace data and receive stronger reinforcement signal from subsequent outcomes.