Progressive title truncation, publisher tiebreak, thematic-year fix

Long transcribed box titles that defeat search now retry with shorter
heads (pre-separator, pre-"Game ..." descriptor, first-two-words from
the pre-subtitle part) matched exact-only against the head — fuzzy
thresholds stay untouched. Tie-breaks gain a publisher pick: when the
box showed a publisher and exactly one exact-named candidate is from
that publisher, it wins (SPI's Sorcerer 1975 now beats the more-owned
White Wizard Sorcerer 2019). The extract prompt excludes thematic/
subject years from year_hint; re-extracting Flat Top's photo drops the
bogus 1942, and a regression test pins that a wrong year can never
drive version selection. Re-extraction also drifted two transcriptions
(DUNGEON!, and Herbaceous misread as "Hebarceos") — fixtures added; the
misread demos review's re-search rescue in the end-to-end run.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>

tests/test_resolve.py

@@ -187,3 +187,110 @@ def test_score_version_no_overlap():
         languages=("English",),
     )
     assert _score_version(entry, version) == 0
+
+
+# -- progressive title truncation (long transcribed box titles) ---------
+
+from bggpipe.normalize import normalize_title  # noqa: E402
+from bggpipe.resolve import _truncation_heads  # noqa: E402
+
+CIV_TITLE = (
+    "CIVILIZATION Game of the Heroic Age - The Dawn of History 8000 BC to 250 BC"
+)
+AH_HINT = "The Avalon Hill Game Company, Baltimore, Maryland"
+
+
+def _entry(title, **kw):
+    return TitleEntry(title_raw=title, title_normalized=normalize_title(title), **kw)
+
+
+def test_truncation_heads_order_and_dedupe():
+    heads = _truncation_heads(CIV_TITLE)
+    assert heads[0] == "CIVILIZATION Game of the Heroic Age"  # before separator
+    assert heads[1] == "CIVILIZATION"  # before the "Game ..." descriptor
+    assert len(heads) <= 3
+
+
+def test_truncation_heads_game_word_without_separator():
+    assert _truncation_heads("SORCERER The Game of Magical Conflict")[0] == "SORCERER"
+
+
+def test_truncation_heads_two_word_fallback():
+    heads = _truncation_heads(
+        "STARFORCE ALPHA CENTAURI Interstellar Conflict in the 25th Century"
+    )
+    assert heads[-1] == "STARFORCE ALPHA"
+
+
+def test_short_titles_get_no_heads():
+    assert _truncation_heads("Catan") == []
+    assert _truncation_heads("Herbaceous") == []
+
+
+def test_civilization_resolves_via_truncation(client):
+    entry = _entry(
+        CIV_TITLE,
+        publisher_hint=AH_HINT,
+        edition_hint="Bookcase Game",
+        language_hint="English",
+    )
+    row = resolve_entry(client, entry)
+    assert (row.match_status, row.bgg_id) == ("auto", 71)
+    # publisher cue picks the Avalon Hill version, not Hartland/Gibsons
+    assert row.version_status == "version_auto"
+    assert row.version_id == 71001
+
+
+def test_advanced_civilization_resolves_as_expansion(client):
+    entry = _entry(
+        "ADVANCED CIVILIZATION Game Expansion of the Heroic Age - "
+        "Featuring New Civilization, Commodity, and Calamity Cards",
+        publisher_hint=AH_HINT,
+        edition_hint="Bookcase Game",
+        language_hint="English",
+    )
+    row = resolve_entry(client, entry)
+    assert (row.match_status, row.bgg_id, row.type) == (
+        "auto",
+        177,
+        "boardgameexpansion",
+    )
+    assert row.version_status == "version_auto"
+
+
+def test_sorcerer_publisher_tiebreak_beats_owned_dominance(client):
+    """Head search finds TWO games named 'Sorcerer' (SPI 1975 vs White
+    Wizard 2019, which has far more owners) — the SPI publisher cue must
+    pick the SPI game, and the edition cue the Designer's Edition."""
+    entry = _entry(
+        "SORCERER The Game of Magical Conflict",
+        publisher_hint="Simulations Publications Incorporated (SPI)",
+        edition_hint="Designer's Edition",
+        language_hint="English",
+    )
+    row = resolve_entry(client, entry)
+    assert (row.match_status, row.bgg_id) == ("auto", 3585)
+    assert row.version_status == "version_auto"
+    assert row.version_name == "SPI Designer's Edition"
+
+
+def test_starforce_two_word_head_matches_full_title(client):
+    entry = _entry(
+        "STARFORCE ALPHA CENTAURI Interstellar Conflict in the 25th Century",
+        publisher_hint="Simulations Publications Incorporated (SPI)",
+        edition_hint="Designer's Edition",
+        language_hint="English",
+    )
+    row = resolve_entry(client, entry)
+    assert (row.match_status, row.bgg_id) == ("auto", 2524)
+    assert row.version_status == "version_auto"
+
+
+def test_wrong_year_hint_never_drives_a_version(client):
+    """Flat Top's box says 1942 (the theme, not the print year): version
+    scoring must not pick any version off the back of it."""
+    entry = _entry("FLAT TOP", year_hint=1942, language_hint="English")
+    row = resolve_entry(client, entry)
+    assert (row.match_status, row.bgg_id) == ("auto", 2529)
+    assert row.version_status == "version_unknown"
+    assert row.version_id is None