One of the following:
CacheMiss { cache_missed_tokens, reason, type, comparison_reusable_tokens }
cache_missed_tokens: number

The estimated number of input tokens affected after the first detected divergence.

reason: "model_changed" | "prompt_cache_key_changed" | "tools_changed" | 6 more

The reason prompt cache reuse did not occur.

One of the following:
"model_changed"
"prompt_cache_key_changed"
"tools_changed"
"text_format_changed"
"reasoning_effort_changed"
"verbosity_changed"
"context_compacted"
"input_changed"
"service_tier_changed"
type: "cache_miss"
comparison_reusable_tokens?: number

The raw token count of the reusable prefix in the compared response.

CacheHit { type }
type: "cache_hit"
ComparisonResponseNotFound { type }
type: "comparison_response_not_found"
Unavailable { type }
type: "unavailable"