ó
    àhjü  ã                   ó   • S r SSKJr  S/rg)u¬  Prompts held outside the code that uses them, as TOML.

One file per processor, named `<processor_name>.toml`. Each prompt sits at
`[prompts.<key>]` with its body in a `text` field, and `load_prompt(processor,
key)` returns that body stripped. Adding a prompt means adding a key to the
TOML, not editing Python.

This covers the table-inference processor behind `quber analyze` and `quber
batch`, and nothing else. The agents under `quber.agents` â€” the grid locator,
the structure vetter, the status inspector, and the rest of the Set-of-Mark and
figure paths â€” define their system prompts inline at the call site instead.
Look there first when changing how one of those behaves.
é    )Úload_promptr   N)Ú__doc__Úquber.prompts.loaderr   Ú__all__© ó    Ú4/home/mande/repo/quber/src/quber/prompts/__init__.pyÚ<module>r
      s   ðñõ -àˆ/�r   