re: the chatter phase merge is not additive; 224 authored variants never play

sub_82215A58 reads CrewCount + PresetMessage_Phase1/2/3 and reaches the loader
from ONE call site, so the three phase tables fold into one map keyed by the
event record name.  Every merge collides; sub_82213840 reconciles on the
message list plus +16/+17/+18/+20/+24/+28 (NOT the +32 Yes mask), and the
incumbent always wins.  Measured: 26432 collisions, 26208 identical, 224
different (189 differ only in the message list), 0 mask-only differences.

Refuted handle: intersecting functions by the object's offsets finds dozens of
unrelated layouts -- offset shape is not an identifier.

Co-Authored-By: Claude Opus 5 (1M context) <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01PMRJjbxLqZtsb5Vb7KunPE

tools/re-capture/preset_messages.py

@@ -190,6 +190,63 @@ def main():
     for m in miss:
         print('  %s' % m)
 
+    # phase-merge reconciliation: sub_82215A58 loads a unit's Phase1/2/3 tables
+    # into ONE map keyed by the event record name, and sub_82213840 compares a
+    # duplicate against the incumbent on (message list, +16, +17, +18, +20, +24,
+    # +28) -- not on the Yes mask at +32.
+    CMP = ('Probability', 'Priority', 'Pattern', 'Interval',
+           'IntervalFluctuation', 'EffectiveTime')
+    def _core(rec):
+        d = U.named(rec)
+        pos = [v for _, nm, v in rec['fields'] if nm is None]
+        return ((tuple(d.get(f) for f in CMP), tuple(pos[0::2])), tuple(pos[1::2]))
+    sets = dup = same = diff = mask_only = 0
+    why = collections.Counter()
+    for st in STAGES:
+        h = U.name_hash('message\\UnitMessageSet_%s.tbl' % st)
+        if h not in entries:
+            continue
+        for r in U.parse(entries[h]):
+            d = U.named(r)
+            phases = [d.get('PresetMessage_Phase%d' % i) for i in (1, 2, 3)]
+            phases = [n for n in phases if n]
+            if len(phases) < 2:
+                continue
+            sets += 1
+            seen = {}
+            for n in phases:
+                hh = U.name_hash('message\\' + n)
+                if hh not in entries:
+                    continue
+                for rec in U.parse(entries[hh]):
+                    if rec['squadron'] == 'Sperkers':
+                        continue
+                    core, mask = _core(rec)
+                    k = rec['squadron']
+                    if k not in seen:
+                        seen[k] = (core, mask)
+                        continue
+                    dup += 1
+                    if seen[k][0] == core:
+                        same += 1
+                        if seen[k][1] != mask:
+                            mask_only += 1
+                    else:
+                        diff += 1
+                        w = [f for f, a, b in zip(CMP, seen[k][0][0], core[0]) if a != b]
+                        if seen[k][0][1] != core[1]:
+                            w.append('MESSAGE_LIST')
+                        why[tuple(w)] += 1
+    print()
+    print('phase merge (the loader folds Phase1/2/3 into one map):')
+    print('  UnitMessageSet records naming >= 2 phase tables : %d' % sets)
+    print('  duplicate-key insertions to reconcile           : %d' % dup)
+    print('    identical on the compared fields              : %d' % same)
+    print('    DIFFERENT -> loader clears its ok flag        : %d' % diff)
+    print('    compared fields equal but Yes mask differs    : %d' % mask_only)
+    for w, c in why.most_common():
+        print('      x%-5d %s' % (c, ', '.join(w)))
+
     # naming, two independent routes
     harvest = set()
     for p in sorted(glob.glob(os.path.join(DAT, '**', '*.pak'), recursive=True)):