Reads cache tokens from openai response

Author: Workshop Participant

src/strands/types/models/openai.py

@@ -260,6 +260,10 @@ def format_chunk(self, event: dict[str, Any]) -> StreamEvent:
                             "inputTokens": event["data"].prompt_tokens,
                             "outputTokens": event["data"].completion_tokens,
                             "totalTokens": event["data"].total_tokens,
+                            "cacheReadInputTokens": event["data"].prompt_tokens_details.cached_tokens,
+                            "cacheWriteInputTokens": getattr(
+                                event["data"], "cache_creation_input_tokens", 0
+                            ),  # litellm
                         },
                         "metrics": {
                             "latencyMs": 0,  # TODO