Summary
Guides insist one idea per row and no prose in fields, but the engine does not generally reject sentence-length field values. Quality depends on LAW text in warm plus skill memory.
Evidence
- Docs:
LLM-GUIDE.md atomisation checklist; application-notes/llm-novel-writer.md LAW-ATOM01 as prompt discipline ("Engine enforcement | Partly... | Prompt discipline only").
- Engine checks: exact field counts, id patterns, relation vocabulary, JSON rejection (
sanitiser.py) — not "is this a sentence?".
- Contrast: novel domain adds many LAW rows prepended on warm; generic MemNet sessions may lack them.
Impact
Graphs bloat; warm slices become paragraph dumps; token-efficiency claim fails when agents ignore discipline.
Suggested direction
Optional soft/hard caps (max chars per field, max tokens per warm row) with @WRN / @ERR; or a housekeep lint for fat fields.
Summary
Guides insist one idea per row and no prose in fields, but the engine does not generally reject sentence-length field values. Quality depends on LAW text in warm plus skill memory.
Evidence
LLM-GUIDE.mdatomisation checklist;application-notes/llm-novel-writer.mdLAW-ATOM01 as prompt discipline ("Engine enforcement | Partly... | Prompt discipline only").sanitiser.py) — not "is this a sentence?".Impact
Graphs bloat; warm slices become paragraph dumps; token-efficiency claim fails when agents ignore discipline.
Suggested direction
Optional soft/hard caps (max chars per field, max tokens per warm row) with
@WRN/@ERR; or ahousekeeplint for fat fields.