Most agent demos keep one chat list in memory and hope for the best. Production agents need more than that: short-term history that does not blow the context window, task-local working memory that dies with the task, and a way to pause a run when a tool is too risky or a user hits stop.
Solon AI models those needs with three related pieces:
AgentSession + sessionWindowSize for multi-turn history
A layered memory model (messages vs working memory)
session.pending(...) for pause / resume style control
