Unexpected event format when using ibm-watsonx-ai with LangChain extension

[barvhaim]

Describe the feature or potential improvement

I'm able to partly use Langfuse with ibm-watsonx-ai with LangChain extension, I do see the traces in Langfuse but it's missing some values, and I get this error message.

Langfuse was not able to parse the LLM model. The LLM call will be recorded without model name. Please create an issue so we can fix your integration: https://github.com/langfuse/langfuse/issues/new/choose
Unexpected event format: No trace id found in event
Usage object must have either {input, output, total, unit} or {promptTokens, completionTokens, totalTokens}
Traceback (most recent call last):
  File ".venv/lib/python3.11/site-packages/langfuse/client.py", line 2473, in update
    "usage": _convert_usage_input(usage) if usage is not None else None,
             ^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File ".venv/lib/python3.11/site-packages/langfuse/utils/__init__.py", line 101, in _convert_usage_input
    raise ValueError(
ValueError: Usage object must have either {input, output, total, unit} or {promptTokens, completionTokens, totalTokens}

Additional information

I am trying to debug to get further information.