Failures in multi-turn reasoning models are largely invisible to terminal-score evaluation. A model can lock onto an unsafe stance early in a long dialogue, yet its final-turn refusal rate may appear indistinguishable from a robustly aligned baseline. To expose these hidden temporal dynamics, we propose a trace-level diagnostic - the CoT-Output 2x2 safety matrix. This framework labels every turn along two independent axes (internal reasoning and visible output), yielding four operationally defined failure cells: robust alignment, alignment faking, overt jailbreak, and a distinct failure mode we term context-injection failure (where the CoT maintains safe reasoning, but the visible output produces harm, highlighting a multi-turn manifestation of reasoning unfaithfulness). We evaluate three distilled reasoning targets against a fixed attacker across five oversight conditions, collecting 6750 turn-level observations on the Information-Hazard scenario. Our analysis reveals two reproducible vulnerabilities: an oversight paradox where explicit monitoring cues paradoxically increase alignment-faking rates rather than suppress them, and a context-injection failure where models lock onto unsafe external outputs despite safe internal states. We release the full dataset of multi-turn dialogues and CoT traces to support follow-up trace-diagnostic research.

翻译：多轮推理模型的故障在很大程度上对最终轮次评分评估是不可见的。在长对话的早期，模型可能锁定在一种不安全立场上，但其最终轮次的拒绝率可能与稳健对齐的基线模型无法区分。为揭示这些隐藏的时间动态，我们提出一种轨迹级诊断方法——CoT-输出2x2安全矩阵。该框架沿两个独立轴（内部推理和可见输出）对每一轮次进行标注，生成四个操作定义的故障单元：稳健对齐、对齐伪装、显式越狱，以及一种我们称之为上下文注入故障的独特故障模式（其中思维链维持安全推理，但可见输出产生危害，突显了多轮情景下的推理不忠实现象）。我们在五个监督条件下，针对固定攻击者评估了三个经过知识蒸馏的推理目标，收集了信息-危险场景下的6750个轮次级观测值。我们的分析揭示了两个可复现的漏洞：一个监督悖论，即显式监督线索反而增加而非抑制对齐伪装率；以及一个上下文注入故障，即模型在内部状态安全的情况下锁定不安全的 外部输出。我们发布了多轮对话和思维链轨迹的完整数据集，以支持后续的轨迹诊断研究。