agential-ai/agential

[Feature Request]: Robust Code Interpreter Tool

Opened this issue · 0 comments

Feature Description

HumanEval has a robust code interpreter set up that uses the Python exec() function internally. We currently just have safe_execute which doesn't have all the guardrails in-place like HumanEval has in their repository. Maybe we can create a more robust function/class that houses this exec() internally.

Reason

No response