Счётчик абзацев, вернувшихся на языке оригинала: упражнения вида [2] модель не переводит

2026-08-21 17:47:48 +03:00
parent 7ed6e500ca
commit 14c7fad763
3 changed files with 43 additions and 2 deletions
@@ -190,6 +190,13 @@ is the bridge: it writes the repo's input format, shells out to
   The one thing that *does* skip work: deleting a chapter from `extracted/`
   before the run. It is then never sent, and `rebuild` keeps the original
   English for it — the right treatment for an index.
+**Numbered exercise items come back untranslated.** Measured on Stroustrup
+2026-08-21: 182 paragraphs of 10151 (1.8%) shaped `[2] Expanding on what you
+have learned…` were echoed back in English. The document-wide Cyrillic check
+cannot see this — 1.8% drowns in it — so `rebuild` counts them separately as
+"осталось на языке оригинала". If the count is high, add an explicit line to the
+prompt that numbered items are prose and must be translated too.
+
 4. **Read the reported counts.** "без перевода" above zero means a chapter came
   back with a different paragraph count and kept its original text; "разметка
   потеряна" counts paragraphs where the model mangled the inline-tag markers