One of the following:
class PromptCacheDiagnosticsCacheMiss: …
cache_missed_tokens: int

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

reason: Literal["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: Literal["cache_miss"]
comparison_reusable_tokens: Optional[int]

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

class PromptCacheDiagnosticsCacheHit: …
type: Literal["cache_hit"]
class PromptCacheDiagnosticsComparisonResponseNotFound: …
type: Literal["comparison_response_not_found"]
class PromptCacheDiagnosticsUnavailable: …
type: Literal["unavailable"]