Recorder

OpenAI API

Wrap each call. usage_from reads both Chat Completions and Responses usage, including reasoning and cached tokens.

Copy harness_recorder.py into your project.
Wrap the shared function that calls the model.

Wrap a call

with run.agent("classify", prompt_ref="prompts/classifier@3", model="openai/gpt-6-luna") as step:
    resp = client.responses.create(model="gpt-6-luna", input=ticket_text)
    step.model_call(**usage_from(resp))

Where the log lands

Wherever your service logs go, or a folder.

How it reaches the harness

You download the logs with your own access.

When streaming, ask for usage in the final chunk (OpenAI only sends it when requested) and record it then.

Read the full guide on GitHub

OpenAI API

Add the recorder