How to capture CodeAgent's full thinking including the code, not just the final response into a variable

[KannamSridharKumar]

When we run a CodeAgent in a notebook, it print the question/task, the LLM model used, code (Executing this code, Execution logs) and the Final answer.

The return value from agent.run contrains only the final response.

I'm working on some demos for which I wanted to run a number of tasks, capture all the output (not just the final answer) and write them to an md or html file, so that I can show everything including the code generated by the agent without running the agents live in the demo.

I tried logging, stdout, from contextlib import redirect_stdout, etc but couldn't capture the full output to a variable.

Thanks,

[Deng-Xian-Sheng]

I think you may need to intercept the http request and then output both the content sent to the model and the content returned by the model to a file.

[Deng-Xian-Sheng]

I found https://huggingface.co/docs/smolagents/tutorials/inspect_runs

[matthewcarbone]

#284 Related!
(Though I think some of this information is already stored in the logs).

[Deng-Xian-Sheng]

What do you think of this display?

[Deng-Xian-Sheng]

Give me $1 and I'll tell you how to do it :-)