feat: bill OpenAI cache_write_tokens at cache-creation price with zero clamp

Parse OpenAI's native cache_write_tokens (chat prompt_tokens_details /
responses input_tokens_details), bill it at the cache-creation ratio, and
clamp the uncached prompt remainder at zero since cached + cache-write can
exceed prompt_tokens. Propagate the field through chat/responses/claude
format conversions and tiered expression billing (cc variable).

dto/openai_request.go

@@ -849,6 +849,7 @@ type OpenAIResponsesRequest struct {
 	MaxOutputTokens    *uint           `json:"max_output_tokens,omitempty"`
 	TopLogProbs        *int            `json:"top_logprobs,omitempty"`
 	Metadata           json.RawMessage `json:"metadata,omitempty"`
+	Moderation         json.RawMessage `json:"moderation,omitempty"`
 	ParallelToolCalls  json.RawMessage `json:"parallel_tool_calls,omitempty"`
 	PreviousResponseID string          `json:"previous_response_id,omitempty"`
 	Reasoning          *Reasoning      `json:"reasoning,omitempty"`
@@ -859,6 +860,7 @@ type OpenAIResponsesRequest struct {
 	// This field is allowed by default and can be disabled via channel setting disable_store.
 	Store                json.RawMessage `json:"store,omitempty"`
 	PromptCacheKey       json.RawMessage `json:"prompt_cache_key,omitempty"`
+	PromptCacheOptions   json.RawMessage `json:"prompt_cache_options,omitempty"`
 	PromptCacheRetention json.RawMessage `json:"prompt_cache_retention,omitempty"`
 	// SafetyIdentifier carries client identity for policy abuse detection.
 	// This field is filtered by default and can be enabled via channel setting allow_safety_identifier.