Robust code generation combining grammars and LLMs

[librasteve]

TL;DR

  - Combining grammars and LLMs produces robust translators.
  - Three translators with different faithfulness and coverage are demonstrated and used.
  - Two of the simplest, yet effective, combinations are implemented and  - demonstrated.
  - Parallel race and grammar-to-LLM fallback.
  - Asynchronous implementations with LLM-graphs are a very good fit!
  - Just look at the LLM-graph plots (and be done reading.)