The strategies are manually reviewed with clear prompt injection attempts rejected.

I think the program approach proved unworkable. It is simply too difficult to write a program that can analyze another program effectively when the program being analyzed has to be complex enough to do its own analysis of other programs.

I've actually never heard of diffusion for planning. Do you have a reference?

A diffusion model for text generation (like Diffusion-LM) still has the training objective to produce text from the training distribution, optimizing over only the current episode - in this case a short text.