Users report that a long-running multi-agent planning session “forgets” goals stated at the beginning of the conversation after many turns, even though no explicit memory wipe was coded. Engineers confirm the implementation uses a simple last-N message window with no summarization of older turns. Which context-window issue is this, and what is the appropriate diagnostic framing?
Select an answer to reveal the explanation.
Short Explanation
If you only keep the last N messages, early goals fall off the cliff—that is sliding-window amnesia. Diagnose by seeing which turns were dropped; fix with summaries, pinned instructions, or real memory—not by blaming DNS, client GPUs, or random SKUs. D names the issue and the remediation framing.
Full Explanation
Correct answer: D. Optimizing multi-agent context requires diagnosing issues such as sliding-window amnesia, summary drift, vector-only recall limits, and entity continuity problems. A pure last-N window without summarization or durable memory will drop early goals as conversations grow.
A is incorrect because regional SKU choice does not explain systematic loss of early turns in a last-N window.
B is incorrect because DNS issues cause connectivity problems, not selective loss of early conversational goals.
C is incorrect because client GPU thermal state does not implement server-side context windowing for Azure-hosted agents.
Exam focus: name context failure modes precisely—sliding-window amnesia is the last-N drop pattern.