Bug Report: LangChain Metrics issues

1. I see that we are adding custom attributes to metrics, However, TRACELOOP_ENTITY_NAME (traceloop.entity.name) is a very high cardinality attribute - https://github.com/traceloop/openllmetry/pull/2154/files#diff-caff857eafc9121a585e40cdac1c0815d97f474cd3d0bf1a23755572e3b38105R473

• Most destinations would have limits on such fields with very high cardinality for metrics.
• I feel this kind of information is best understood with traces/spans instead or at-least some control should be given to enable/disable this metric as required or limit attributes.

2. Seeing this error generated for gen_ai.response.model when invoked as a agent.

Failed to encode key gen_ai.response.model: Invalid type <class 'NoneType'> of value None
Traceback (most recent call last):
  File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/opentelemetry/exporter/otlp/proto/common/_internal/__init__.py", line 113, in _encode_attributes
    pb2_attributes.append(_encode_key_value(key, value))
                          ^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/opentelemetry/exporter/otlp/proto/common/_internal/__init__.py", line 94, in _encode_key_value
    return PB2KeyValue(key=key, value=_encode_value(value))
                                      ^^^^^^^^^^^^^^^^^^^^
  File "/Library/Frameworks/Python.framework/Versions/3.12/lib/python3.12/site-packages/opentelemetry/exporter/otlp/proto/common/_internal/__init__.py", line 90, in _encode_value
    raise Exception(f"Invalid type {type(value)} of value {value}")
Exception: Invalid type <class 'NoneType'> of value None

3. I do not see gen_ai.client.token.usage being generated when used like below, I do see it generated with simple LLMChain but not when invoked via agent.

    llm = AzureChatOpenAI(
        openai_api_version=os.environ.get("AZURE_OPENAI_VERSION"),
        azure_deployment=os.environ.get("AZURE_OPENAI_DEPLOYMENT"),
        azure_endpoint=os.environ.get("AZURE_OPENAI_ENDPOINT"),
        api_key=os.environ.get("AZURE_OPENAI_KEY"),
        model="gpt-4"
        )
    event_message = "this is a test"
    tools = [Tool().useless_tool]
    
    agent_template = categorise_event_prompt
    input_template = "{input}"
    
    prompt = ChatPromptTemplate.from_messages([
        ("system", agent_template),
        ("human", input_template),
        MessagesPlaceholder("agent_scratchpad")
    ])
    agent = create_openai_tools_agent(llm=llm, tools=tools, prompt=prompt)
    agent_executor = AgentExecutor(agent=agent, tools=tools, verbose=True)
    result = agent_executor.invoke({"input": event_message})

Originally posted by @nitin302 in https://github.com/traceloop/openllmetry/issues/2154#issuecomment-2418772694

Start by reproducing the AzureChatOpenAI agent example using create_openai_tools_agent and AgentExecutor, then inspect the instrumentation path that emits metrics and gen_ai attributes. Compare the agent behavior with the simple LLMChain case and the OTLP encoding error. Done means the reported high-cardinality, None-valued, and missing-token-usage cases are addressed or clearly scoped with regression coverage.