fix(r49): the quote-mark counter was counting apostrophes, and I saw it fire before I saw the bug

voice_distance.py's quote class shipped this morning as "'‘’“”«»‹›‚„` -- with the
apostrophe characters in it. On a corpus whose defining tic is dont/aint/wont and
whose possessives are everywhere, that made it an apostrophe counter wearing a
quote-mark label.

                          as implemented    TRUE quotes    all apostrophes
  held-out McCarthy ref            121.1            0.0              121.1
  base-unadapted                   224.7           19.9              204.8
  held-out Hemingway ref          1112.6          694.7              351.7

The corrected column is the one the pre-registration names: 0.0 for McCarthy,
which is exactly what build_corpus_mccarthy.py ASSERTS, and 694.7 for Hemingway,
the documented ~838 scale the 100-per-10k trigger line was anchored to. The
as-implemented column matched neither.

ORDER OF EVENTS, because it is the material fact: the base arm finished first, so
the trigger became evaluable while the adapted arms were still generating. I
evaluated it, saw it FIRE at 224.7, and only then -- reading the reference row of
my own table against a corpus I knew asserts 0.0 -- found the bug. No delta_cb,
memorisation rate or damage number had been read at any point.

Fixing a detector to measure the quantity the frozen rule names is not moving the
rule, but the fix un-fires the trigger and no reader should have to take my word
about my motives. So GATE-PREREG.md AMENDMENT 2 makes the trigger MOOT instead of
adjudicating it: the normalised secondary read is load-bearing UNCONDITIONALLY for
this gate, whichever reading you accept, both columns reported. The fix therefore
has no effect on the verdict.

There is a better reason than the bug anyway: base's true quote density is 19.9
against the reference's 0.0, so it did not fully comply. A small residual cheap win
IS available to the adapter, and the normalised read is what prices it. A threshold
is a blunt instrument for a residual that size.

Apostrophes now get their own column and are never folded into quotes again.
Default path stays byte-identical to the shipped lv-hemingway artifact.

The durable lesson is the one this line keeps relearning in new places: I controlled
strip_punct (2500 -> 0) and the byte-identity of the default path, but never asked
the quote counter for a value whose answer I already knew. The corpus asserts 0.0.
That check cost one line and was available before the gate ever launched.

scripts/r49-corpus/voice_distance.py

@@ -56,9 +56,19 @@ from pathlib import Path
 # and Hemingway's measures 838; 100 is the order-of-magnitude line between them.
 PUNCT_CONFOUND_PER_10K = 100.0
 
-QUOTE_CHARS = "\"'‘’“”«»‹›‚„`"
+# ⚠⚠ QUOTE MARKS ONLY -- NO APOSTROPHE CHARACTERS. This class shipped 2026-09-21 with
+# `'` and `’` in it, which made it an APOSTROPHE counter wearing a quote-mark label. On
+# lv-mccarthy that reported the held-out reference at 121.1 "quote marks" per 10k for a
+# corpus whose builder ASSERTS 0.0, and it fired the confound trigger on a base arm whose
+# true quote density is 19.9. The pre-registered trigger names quote marks and anchors its
+# line to this corpus's 0.0 against Hemingway's 838 -- both quotation-mark counts -- so an
+# apostrophe-inclusive class does not measure the quantity the rule names.
+# Verified after the fix: McCarthy held-out ref 0.0 (matches the builder's assertion),
+# Hemingway held-out ref 694.7 (the documented ~838 scale). See GATE-PREREG.md AMENDMENT 2.
+_QUOTE_RE = re.compile('["“”«»‹›„]')
 _PUNCT_RE = re.compile(r"[^\w\s]|_", re.UNICODE)
-_QUOTE_RE = re.compile("[" + re.escape(QUOTE_CHARS) + "]")
+# apostrophes are counted SEPARATELY and never folded into the quote column again.
+_APOS_RE = re.compile(r"['’‘`]")
 # a contraction apostrophe is one sitting BETWEEN letters -- `dont` vs `don't` is the tic
 # the register names, and a possessive or a quote mark is not the same measurement.
 _CONTRACTION_APOS_RE = re.compile(r"(?<=[A-Za-z])['’](?=[A-Za-z])")
@@ -113,13 +123,15 @@ def punct_report(ref_text: str, arms: list[tuple[str, list[dict]]]) -> None:
     print("\n  PUNCTUATION DENSITY per 10k words -- the confound check, not an axis")
     print("  (the eval harness drives EVERY arm with the same register prompt, tics included;")
     print("   a compliant base control earns the adapter no delta_cb for them)")
-    print(f"  {'arm':22s} {'quote-marks':>12s} {'contraction-apos':>18s} {'dashes':>9s}")
+    print(f"  {'arm':22s} {'quote-marks':>12s} {'all-apos':>10s} "
+          f"{'contraction-apos':>18s} {'dashes':>9s}")
     rows = [("held-out reference", ref_text)]
     rows += [(a, "\n".join(r["continuation"] for r in recs)) for a, recs in arms]
     base_q = None
     for name, txt in rows:
         q = density(txt, _QUOTE_RE)
-        print(f"  {name:22s} {q:12.1f} {density(txt, _CONTRACTION_APOS_RE):18.1f} "
+        print(f"  {name:22s} {q:12.1f} {density(txt, _APOS_RE):10.1f} "
+              f"{density(txt, _CONTRACTION_APOS_RE):18.1f} "
               f"{density(txt, _DASH_RE):9.1f}")
         if "unadapted" in name:
             base_q = q