I'd love to help you see exactly what's being sent to the OpenAI Chat Completion API! You can do this by overriding the

llm_node

method in your custom Agent class. This way, you can take a closer look at the

chat_ctx

,

tools

, and

model_settings

before the API call happens. Here's a simple example to guide you:

from livekit.agents import Agent, llm, ModelSettings

class MyCustomAgent(Agent):
    async def llm_node(
        self,
        chat_ctx: llm.ChatContext,
        tools: list[llm.FunctionTool],
        model_settings: ModelSettings,
    ):
        # Log the full data being passed to the LLM
        print("Chat Context:", chat_ctx)
        print("Tools:", [tool.name for tool in tools])
        print("Model Settings:", model_settings)

        # Delegate to default implementation
        async for chunk in Agent.default.llm_node(self, chat_ctx, tools, model_settings):
            yield chunk

Also, if you'd like a more detailed look, you can enable debug logging by setting the environment variable

LK_OPENAI_DEBUG=1

. This will give you insights into key parts of the request, like the converted

chat_ctx

,

tool_choice

, and the function calling context. If you're interested in taking full control and customizing the LLM interaction, you can skip the default method and call

self.llm.chat()

directly inside

llm_node

. Please feel free to reach out if you'd like me to walk you through that or if you have any other questions—I'm here to help! Sources: Docs::Agents | livekit-plugins/livekit-plugins-openai/livekit/plugins/openai/llm.py | pipeline-llm/replacing_llm_output.py | Modifying LLM output before TTS | LiveKit Docs | Agents 0.x migration guide | LiveKit Docs