Audit: 5-reviewer sweep — 19 fixes across every stage, +24 tests

Correctness: review vetoes persist via a dedupe_veto column (resolve
re-runs no longer overturn humans); diff emits second copies whose
confident version matches no owned copy (spec: pairs own only on both
ids) and fetches the live collection with refresh; resolve pairs
titles.json entries to rows by title so a reshoot photo updates
provenance instead of duplicating rows; version lookups survive empty
/thing results; publisher tie-break now honors the mixed
base/expansion veto and refuses multi-candidate picks; empty-normalized
(non-Latin) titles never count as exact.

Upload: LoginError aborts a run instead of logging N bogus failures
(and 3 identical consecutive failures abort as systemic); Cloudflare
interstitials are detected; added-without-version gets its own logged
status that verify understands; same-game updates run one per pass so
the name-targeted row edit can't overwrite a fresh version; absent
diff outputs fail loudly; pagination clicks are paced.

Web review: a lock serializes freshen/decide (threadpool race dropped
decisions); failed saves roll memory back and always alert the browser
(non-JSON 500s included); session warnings reach the page instead of a
StringIO; state-load failures and dead servers show banners instead of
a blank page; duplicate (title, photos) rows are addressable by
ordinal.

Consistency: shared CONFIDENT_VERSION_STATUSES, client_for(),
Config paths for every artifact, one review-port constant, named
matching thresholds, strict collection-id parsing, error-doc responses
never cached, unknown config keys warn, extract reports dropped vision
entries, fixture generators share escaping + marker text.

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

scripts/fixture_common.py

@@ -0,0 +1,36 @@
+"""Shared plumbing for the two stub-fixture generators.
+
+Both write into the same cache dirs, so they must agree on XML escaping
+(a title containing & or " must not produce malformed XML) and on the
+provenance-marker text the upload guard depends on.
+"""
+
+from __future__ import annotations
+
+from pathlib import Path
+
+CACHE_MARKER_TEXT = (
+    "This cache contains hand-written stub XML, not real BGG "
+    "responses. Data resolved from it must not be uploaded.\n"
+)
+DATA_MARKER_TEXT = (
+    "The CSVs in this directory were resolved from hand-written stub "
+    "fixtures, not real BGG data — version_ids are SYNTHETIC. The "
+    "upload stage refuses to run while this file exists. Delete it "
+    "only after re-resolving against real recorded fixtures "
+    "(BGG_API_TOKEN + scripts/record_fixtures.py + resolve --force).\n"
+)
+
+
+def esc(text: str) -> str:
+    """Minimal XML attribute/text escaping for hand-built fixture strings."""
+    return str(text).replace("&", "&amp;").replace("<", "&lt;").replace('"', "&quot;")
+
+
+def write_cache_marker(target: Path) -> None:
+    (target / "STUB_FIXTURES.marker").write_text(CACHE_MARKER_TEXT)
+
+
+def write_data_marker(data_dir: Path = Path("data")) -> None:
+    data_dir.mkdir(parents=True, exist_ok=True)
+    (data_dir / "STUB_DATA.marker").write_text(DATA_MARKER_TEXT)

scripts/write_photo_fixtures.py

@@ -17,6 +17,8 @@ from __future__ import annotations
 
 from pathlib import Path
 
+from fixture_common import esc, write_cache_marker, write_data_marker
+
 from bggpipe.bgg_client import cache_key
 
 TARGETS = (Path("tests/fixtures/bgg_cache"), Path("data/bgg_cache"))
@@ -295,7 +297,7 @@ VERSIONS: dict[int, list[tuple]] = {
 def search_xml(results: list[tuple]) -> str:
     items = "".join(
         f'<item type="{type_}" id="{bgg_id}">'
-        f'<name type="{name_type}" value="{_esc(name)}"/>'
+        f'<name type="{name_type}" value="{esc(name)}"/>'
         f'<yearpublished value="{year}"/></item>'
         for bgg_id, name, year, type_, name_type in results
     )
@@ -306,12 +308,12 @@ def stats_xml(things: list[tuple]) -> str:
     items = ""
     for bgg_id, name, year, type_, owned, rank, publishers in things:
         links = "".join(
-            f'<link type="boardgamepublisher" id="1" value="{_esc(p)}"/>'
+            f'<link type="boardgamepublisher" id="1" value="{esc(p)}"/>'
             for p in publishers
         )
         items += (
             f'<item type="{type_}" id="{bgg_id}">'
-            f'<name type="primary" value="{_esc(name)}"/>'
+            f'<name type="primary" value="{esc(name)}"/>'
             f'<yearpublished value="{year}"/>{links}'
             f"<statistics><ratings>"
             f'<owned value="{owned}"/>'
@@ -326,14 +328,14 @@ def versions_xml(bgg_id: int, versions: list[tuple]) -> str:
     version_items = ""
     for vid, name, year, publishers, languages in versions:
         links = "".join(
-            f'<link type="boardgamepublisher" id="1" value="{_esc(p)}"/>'
+            f'<link type="boardgamepublisher" id="1" value="{esc(p)}"/>'
             for p in publishers
         ) + "".join(
-            f'<link type="language" id="1" value="{_esc(lang)}"/>' for lang in languages
+            f'<link type="language" id="1" value="{esc(lang)}"/>' for lang in languages
         )
         version_items += (
             f'<item type="boardgameversion" id="{vid}">'
-            f'<name type="primary" value="{_esc(name)}"/>'
+            f'<name type="primary" value="{esc(name)}"/>'
             f'<yearpublished value="{year}"/>{links}</item>'
         )
     return (
@@ -343,9 +345,6 @@ def versions_xml(bgg_id: int, versions: list[tuple]) -> str:
     )
 
 
-def _esc(text: str) -> str:
-    return text.replace("&", "&amp;").replace("<", "&lt;").replace('"', "&quot;")
-
 
 def main() -> None:
     files: dict[str, str] = {}
@@ -364,18 +363,8 @@ def main() -> None:
             (target / name).write_text(xml)
         # provenance marker: anything resolved from this cache is stub-derived
         # and NOT upload-ready; re-recording real fixtures removes the marker
-        (target / "STUB_FIXTURES.marker").write_text(
-            "This cache contains hand-written stub XML, not real BGG "
-            "responses. Data resolved from it must not be uploaded.\n"
-        )
-    DATA_MARKER.parent.mkdir(parents=True, exist_ok=True)
-    DATA_MARKER.write_text(
-        "The CSVs in this directory were resolved from hand-written stub "
-        "fixtures, not real BGG data — version_ids are SYNTHETIC. The "
-        "upload stage refuses to run while this file exists. Delete it "
-        "only after re-resolving against real recorded fixtures "
-        "(BGG_API_TOKEN + scripts/record_fixtures.py + resolve --force).\n"
-    )
+        write_cache_marker(target)
+    write_data_marker(DATA_MARKER.parent)
     print(f"Wrote {len(files)} fixture file(s) to {' and '.join(map(str, TARGETS))}")
     print(f"Wrote {DATA_MARKER} (committed; upload refuses while it exists)")
 

scripts/write_stub_fixtures.py

@@ -14,6 +14,8 @@ from __future__ import annotations
 
 from pathlib import Path
 
+from fixture_common import esc, write_cache_marker
+
 from bggpipe.bgg_client import cache_key
 
 FIXTURE_CACHE = Path("tests/fixtures/bgg_cache")
@@ -24,7 +26,7 @@ def search_item(bgg_id: int, name: str, year: int | None, type_: str) -> str:
     year_xml = f'<yearpublished value="{year}"/>' if year else ""
     return (
         f'<item type="{type_}" id="{bgg_id}">'
-        f'<name type="primary" value="{name}"/>{year_xml}</item>'
+        f'<name type="primary" value="{esc(name)}"/>{year_xml}</item>'
     )
 
 
@@ -104,10 +106,7 @@ THINGS = {
 
 def main() -> None:
     FIXTURE_CACHE.mkdir(parents=True, exist_ok=True)
-    (FIXTURE_CACHE / "STUB_FIXTURES.marker").write_text(
-        "This cache contains hand-written stub XML, not real BGG "
-        "responses. Data resolved from it must not be uploaded.\n"
-    )
+    write_cache_marker(FIXTURE_CACHE)
     for query, items in SEARCHES.items():
         key = cache_key("search", {"query": query, "type": SEARCH_TYPES})
         total = items.count("<item ")