refactor: deduplicate and improve OpenAI Responses API conversion

- Extract shared map_responses_stop_reason and build_anthropic_usage_from_responses into transform_responses.rs as pub(crate)
- Align cache token extraction priority: OpenAI nested details as fallback, direct Anthropic fields as override
- Extract resolve_content_index helper to eliminate 3x copy-paste in streaming_responses.rs
- Add streaming reasoning/thinking event handlers (response.reasoning.delta/done)
- Add explanatory comment to transform_response heuristic detection
- Add openai_responses to api_format doc comment and needs_transform test
- Add explicit no-op match arms for lifecycle events
- Add promptCacheKey to TS ProviderMeta type
- Update toast i18n key to be generic for both OpenAI formats (zh/en/ja)

src/types.ts

@@ -147,6 +147,8 @@ export interface ProviderMeta {
   // - "openai_chat": OpenAI Chat Completions 格式，需要格式转换
   // - "openai_responses": OpenAI Responses API 格式，需要格式转换
   apiFormat?: "anthropic" | "openai_chat" | "openai_responses";
+  // Prompt cache key for OpenAI-compatible endpoints (improves cache hit rate)
+  promptCacheKey?: string;
 }
 
 // Skill 同步方式