medium92%
OpenAI-compatible responses discard nested token usage details in UsageMetadata
langchain-openai's `_create_usage_metadata` only extracts known keys (`audio`, `cached_tokens`, `reasoning_tokens`) from `prompt_tokens_details` and `completion_tokens_details`, causing provider-specific fields like `text_tokens`, `accepted_prediction_tokens`, and `rejected_prediction_tokens` to be silently lost.