Accumulating evidence suggests that the brain continuously monitors the predictability of rapidly evolving sound sequences, even when they are not behaviorally relevant. An increasing body of empirical evidence links sustained tonic M/EEG activity to evidence accumulation and tracking the predictability, or inferred precision, of the auditory stimulus. However, it remains unclear whether, and how, this process depends on auditory contextual memory. We investigated how the history of sound sequences influences the neural representation of ongoing regularity under different structural contexts. We recorded EEG responses from naïve participants passively listening to sequences of 50-ms tone-pips across two experiments and compared these responses to predictions from ideal observer models with varying memory spans. In Experiment 1 (N = 26; both sexes), a regularly repeating sequence of 10 tones transitioned directly to a different regular sequence. In Experiment 2 (N = 28; both sexes), the same regular sequence was repeated after an intervening random segment. Results showed that in Experiment 1, neural responses were best explained by models with minimal memory. In contrast, in Experiment 2, inferred predictability of the resumed sequence was influenced by the intervening random tones, even several seconds after the interruption, indicating that the brain retains contextual memory over time. This dissociation implies that the brain can dynamically adjust its strategy based on inferred environmental structure—resetting context when interruptions signal change and preserving context when patterns are likely to resume.