ai-agents-cost-tracking-when-using-langchain-s-openaicallbackhandler-with--6b507197

THEN In the token cost calculation logic (typically in openai_info.py), retrieve `reasoning_tokens` from `usage_metadata.output_token_details` and add them to `completion_tokens` before computing `completion_cost`. Ensure the model name is standardized and the total cost reflects both regular completion tokens and reasoning tokens.

# Inside the cost calculation block:
if 'reasoning' in usage_metadata.get('output_token_details', {}):
    reasoning_tokens = usage_metadata['output_token_details']['reasoning']
    completion_tokens += reasoning_tokens
# Then compute completion_cost as usual
completion_cost = get_openai_token_cost_for_model(model_name, completion_tokens, token_type=TokenType.COMPLETION)