The digest read `PULLING THREAD` and `LITERAL QUESTION` with a case-sensitive
`str.find`. /wrap-up names these fields in prose — "The pulling thread",
"**Pulling thread:**" — and has never mandated a case. The reader was demanding
a shape its own producer had no instruction to write, so the wrap wrote
correctly and the digest reported DEGRADED.
Censused by running the real function over all 195 wrap files rather than by
grep: 102 threads and 103 questions unreadable, of which 86 and 84 were present
in the body in the wrong case. The remaining 16 and 19 are wraps that never
wrote the field. After the fix: 16 and 19. Predicted and achieved agree.
Second defect, distinct and found only because the first was traced to its
class: the label terminator was "first colon within 40 characters", a proxy for
"same line". When an aside pushed the colon past the window the function
returned THE LABEL, and with the paragraph cut assuming label and content share
a paragraph, a question written below its heading was invisible. The 2026-08-22
wrap hit both defects at once. The terminator is now the first colon on the
anchor's own line, and a label that ends its line takes the paragraph below.
Case-insensitivity alone would have let a narrative "…as the pulling thread
showed…" outrank the field it describes, so a match in label position now wins
over an earlier mention. Four checks added (71 -> 75), including that negative
control and a positive control proving it cannot pass vacuously.
Not changed: file selection (ledgers were already excluded correctly, line 124),
frontmatter stripping, and the verbatim-never-summarised contract. The ladder's
"61 checks" is stale — it was 71 before this commit — and stays stale: the
ladder is frozen under REVIEWED-123 and this is not an exemption.
Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01JQKeKY9T9d95KpvHwwok8T
