LLMCallEvent fails to log "tools" to be chosen from by the LLM in BaseOpenAIChatCompletionClient

[afzalmushtaque]

What happened?

Describe the bug
LLMCallEvent fails to log "tools" passed to BaseOpenAIChatCompletionClient in autogen_ext.models.openai._openai_client.BaseOpenAIChatCompletionClient

class BaseOpenAIChatCompletionClient(ChatCompletionClient):
    ............
        async def create(
            self,
            messages: Sequence[LLMMessage],
            *,
            tools: Sequence[Tool | ToolSchema] = [], # tools are not being logged in the LLMCallEvent below
            json_output: Optional[bool | type[BaseModel]] = None,
            extra_create_args: Mapping[str, Any] = {},
            cancellation_token: Optional[CancellationToken] = None,
        ) -> CreateResult:
            
    ...........
            logger.info(
                LLMCallEvent(
                    messages=cast(List[Dict[str, Any]], create_params.messages),
                    response=result.model_dump(),
                    prompt_tokens=usage.prompt_tokens,
                    completion_tokens=usage.completion_tokens,
                    # where are the tools to be chosen from being logged?
                )
            )

Expected behavior
Logs should include tools available to the LLM to choose from along with messages and response

Which packages was the bug in?

Python Extensions (autogen-ext)

AutoGen library version.

Python dev (main branch)

Other library version.

No response

Model used

No response

Model provider

OpenAI

Other model provider

No response

Python version

None

.NET version

None

Operating system

None

[afzalmushtaque]

easy to fix.

class BaseOpenAIChatCompletionClient(ChatCompletionClient):
    ............
        async def create(
            self,
            messages: Sequence[LLMMessage],
            *,
            tools: Sequence[Tool | ToolSchema] = [],
            json_output: Optional[bool | type[BaseModel]] = None,
            extra_create_args: Mapping[str, Any] = {},
            cancellation_token: Optional[CancellationToken] = None,
        ) -> CreateResult:
            
    ...........
            logger.info(
                LLMCallEvent(
                    messages=cast(List[Dict[str, Any]], create_params.messages),
                    response=result.model_dump(),
                    prompt_tokens=usage.prompt_tokens,
                    completion_tokens=usage.completion_tokens,
                    tools=tools # fix for missing tools in logs
                )
            )