I'm not sure the idea is really from a single set place or lineage like that.
If it was, it was at least from before smolagents and those papers - ChatGPT had already been using automatic Python scripting+evaluation calls and people calling it in agentic loops in 2023. The ReAct paper for agentic loops and PAL paper for dynamically calling Python for tasks which can be better done computationally were both from 2022 (but that doesn't mean the idea necessarily sprung from those either, they're just earlier papers published on the topics).
It is based on this paper https://huggingface.co/papers/2402.01030 and calls this idea CodeAct. The paper is actually from Apple: https://machinelearning.apple.com/research/codeact
So Astra and Fable seem to take this idea to the extreme causing some unwanted side-effects.