The runtime should therefore be built around a memory hierarchy that balances retrieval latency, relevance, privacy, and context-window cost. The decisive point is failure isolation: Option C keeps the agent’s decision path observable instead of burying behavior inside one prompt or one service. Short-term and long-term memory have different latency and retention requirements. A hierarchy avoids mixing conversational scratchpad with durable preferences. The stack-level anchor is clear: memory is an orchestration concern as much as a model concern, because the agent must decide what to keep, retrieve, and forget. The selected option specifically C states “Hierarchical memory with separate short-term and long-term layers”, which matches the operational requirement rather than a superficial wording match. The rejected options are weaker because sending full history every turn inflates latency and cost, while stateless prompts lose unresolved tasks, user preferences, and multi-step plan continuity. The answer is therefore about engineered control planes, not simply model capability. The memory policy should define what is persisted, what is summarized, and what is discarded to avoid both context loss and prompt bloat.