Camera-first agents must act on the visual world as it unfolds. We argue that the main obstacle for future camera-first agents is not recognition ability—multimodal models (including vision‑language and streaming variants) generalize well through language and remain the right tool for semantic reasoning—but time. Many visual targets are fleeting: they appear, become query‑relevant, and disappear within a short window. Binding memory to the same end‑to‑end path as reasoning means that by the time a monolithic pipeline finishes, the evidence is gone. We formalize this as Ephemeral‑Target Interaction (ETI) and a Perceptual Deadline Contract, separating a hard memory deadline from a soft reasoning deadline, grounded in the bounded, passive nature of sensory and working memory. We propose a two‑deadline architecture: an always‑on, bounded, non‑semantic fast path; an active remembering mechanism that commits a moment to durable memory before it is overwritten (event‑driven in v1); and a deferred deliberation layer (multimodal model + tools). We instantiate the contract on real MOT17 track windows, perform a consistency check, and calibrate the single‑path baseline from measured frontier‑model latency: even a short answer takes 1.2‑9.3 s, and an agentic identify‑and‑search takes longer. Answers can be late; evidence cannot be missed.
Review