Перевод не возобновляем: --all переводит все главы заново, механизм progress не работает

SKILL.md

@@ -180,8 +180,16 @@ is the bridge: it writes the repo's input format, shells out to
 
    `python scripts/translate.py book.html book.ru.html --repo <clone> --workdir <dir> --workers 12`
 
-   Resumable: the external repo tracks completed chapters and skips them on a
+   ⚠️ **Not resumable, despite what the external repo claims.** Its
-   re-run, so an interrupted run costs nothing to restart.
+   `progress/translation_progress.json` stays `{"chapters": {}}` and `--all`
+   re-translates every chapter, including ones already sitting in
+   `translations/`. Measured 2026-08-21 on Stroustrup: a re-run to repair 4
+   failed chapters re-did all 29. Budget a full book on every restart, and
+   prefer getting one clean run over patching a partial one.
+
+   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.
 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

scripts/test_translate.py

@@ -105,6 +105,33 @@ def test_code_listings_are_left_alone(tmp: Path):
     assert t.verify_output(src, "ru"), "код не должен заваливать приёмку"
 
 
+def test_junk_translation_falls_back_to_original(tmp: Path):
+    """Модель иногда возвращает на длинный абзац огрызок «, v», а число абзацев
+    при этом сходится — прежние ворота такое пропускали."""
+    src = tmp / "book.html"
+    long_en = ("A vector is simply a sequence of elements that you can access by "
+               "an index, and it is the workhorse of the standard library. ") * 2
+    src.write_text("\n".join([
+        "<h1>Chapter</h1>",
+        "<p>%s</p>" % long_en,
+        "<p>Second paragraph of the very same chapter, also reasonably long.</p>",
+    ]), encoding="utf-8")
+    chapters = t.split_chapters(t.parse_blocks(src))
+    trans = tmp / "translations"
+    trans.mkdir()
+    (trans / "chapter_000_translated.json").write_text(json.dumps(
+        {"number": 0, "paragraphs": ["Глава", ", v",
+                                     "Второй абзац той же самой главы, тоже достаточно длинный."]},
+        ensure_ascii=False), encoding="utf-8")
+
+    out = tmp / "out.html"
+    t.rebuild(src, chapters, tmp, out)
+    result = out.read_text(encoding="utf-8")
+    assert ", v" not in result, "огрызок не должен попадать в книгу"
+    assert "A vector is simply a sequence" in result, "вместо огрызка нужен оригинал"
+    assert "Второй абзац" in result, "нормальный перевод должен остаться"
+
+
 def test_workdir_belongs_to_one_book(tmp: Path):
     """Имена chapter_NNN.json у всех книг одинаковы: чужой workdir склеит
     перевод одной книги с текстом другой."""
@@ -155,6 +182,7 @@ if __name__ == "__main__":
     test_broken_marks_drop_tags()
     test_language_detection()
     for case in (test_split_and_rebuild, test_code_listings_are_left_alone,
+                 test_junk_translation_falls_back_to_original,
                  test_workdir_belongs_to_one_book, test_stale_chapters_removed,
                  test_verify_output_catches_untranslated):
         with tempfile.TemporaryDirectory() as d:

scripts/translate.py

@@ -148,9 +148,15 @@ def run_translator(repo, workdir, extracted, workers):
         sys.exit("book_translator завершился с кодом %d" % r.returncode)
 
 
+# Доля от длины оригинала, ниже которой перевод считается мусором. Совпадение
+# числа абзацев ничего не гарантирует: модель иногда возвращает на длинный абзац
+# огрызок вида «, v», и прежние ворота такое пропускали.
+MIN_LEN_SHARE = 0.25
+
+
 def rebuild(src, chapters, workdir, out):
     lines = src.read_text(encoding="utf-8").splitlines()
-    broken = missing = translated = 0
+    broken = missing = translated = junk = 0
     for n, ch in enumerate(chapters):
         f = workdir / "translations" / ("chapter_%03d_translated.json" % n)
         if not f.exists():
@@ -162,15 +168,20 @@ def rebuild(src, chapters, workdir, out):
                   % (n, len(paragraphs), len(ch)))
             missing += len(ch)
             continue
-        for (idx, tag, attrs, _), text in zip(ch, paragraphs):
+        for (idx, tag, attrs, original), text in zip(ch, paragraphs):
+            plain_src = re.sub("<[^>]+>", "", original)
+            if len(plain_src) > 120 and len(text) < max(20, len(plain_src) * MIN_LEN_SHARE):
+                junk += 1
+                lines[idx] = "<%s%s>%s</%s>" % (tag, attrs, original, tag)
+                continue  # оставляем оригинал: английский абзац лучше огрызка
             body, ok = from_marks(text)
             broken += not ok
             translated += 1
             lines[idx] = "<%s%s>%s</%s>" % (tag, attrs, body, tag)
     out.write_text("\n".join(lines) + "\n", encoding="utf-8")
-    print("переведено блоков: %d, без перевода: %d, разметка потеряна в %d"
+    print("переведено блоков: %d, без перевода: %d, разметка потеряна в %d, "
-          % (translated, missing, broken))
+          "огрызков заменено оригиналом: %d" % (translated, missing, broken, junk))
-    return missing == 0
+    return missing == 0 and junk * 200 <= translated
 
 
 def verify_output(out, target):