test: whole-table tag counts become non-system counts

The four remaining run-1895 failures were stale expectations, not
predicate bugs — prune/reset returned the right counts, but these tests
verified no-deletion by counting the ENTIRE tag table (or asserting the
full kind set), which now includes the three seeded hygiene tags that
survive prunes and resets by design. Filter is_system=false with a
pointer to #128 so future system tags cannot re-break them.

Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
Claude-Session: https://claude.ai/code/session_01CDgx8bQS5YrGRK76v8HUnM

tests/test_api_admin.py

@@ -660,8 +660,10 @@ async def test_reset_content_tagging_apply_requires_confirm_token(client, db):
     for bad in ({"dry_run": False}, {"dry_run": False, "confirm": "deadbeef"}):
         resp = await client.post("/api/admin/tags/reset-content", json=bad)
         assert resp.status_code == 400
+    # Non-system only: the seeded hygiene tags (#128) survive a reset by
+    # design, so they'd inflate a whole-table count.
     remaining = (await db.execute(
-        select(func.count()).select_from(Tag)
+        select(func.count()).select_from(Tag).where(Tag.is_system.is_(False))
     )).scalar_one()
     assert remaining == 1
 

tests/test_cleanup_service.py

@@ -377,8 +377,11 @@ def test_prune_unused_tags_dry_run_returns_count_and_names(db_sync, tmp_path):
     assert result["count"] == 2
     assert "prune-me-1" in result["sample_names"]
     assert "prune-me-2" in result["sample_names"]
-    # Nothing actually deleted.
+    # Nothing actually deleted. Non-system only — the seeded hygiene tags
-    surviving = db_sync.execute(select(func.count(Tag.id))).scalar_one()
+    # (#128) are exempt from pruning and would inflate a whole-table count.
+    surviving = db_sync.execute(
+        select(func.count(Tag.id)).where(Tag.is_system.is_(False))
+    ).scalar_one()
     assert surviving == 3
 
 
@@ -499,8 +502,11 @@ def test_reset_content_tagging_dry_run_counts_without_deleting(db_sync, tmp_path
     assert result["count"] == 2
     assert result["by_kind"] == {"general": 1, "character": 1}
     assert result["applications"] == 2
-    # Nothing deleted — all 4 tags still present.
+    # Nothing deleted — all 4 fixture tags still present (non-system count;
-    assert db_sync.execute(select(func.count(Tag.id))).scalar_one() == 4
+    # the seeded hygiene tags #128 also survive, by design).
+    assert db_sync.execute(
+        select(func.count(Tag.id)).where(Tag.is_system.is_(False))
+    ).scalar_one() == 4
 
 
 def test_reset_content_tagging_deletes_content_keeps_fandom_series(db_sync, tmp_path):
@@ -525,8 +531,11 @@ def test_reset_content_tagging_deletes_content_keeps_fandom_series(db_sync, tmp_
     result = cleanup_service.reset_content_tagging(db_sync, dry_run=False)
     assert result["deleted"] == 2
 
-    # general + character gone; fandom + series kept.
+    # general + character gone; fandom + series kept. Non-system only — the
-    kinds = db_sync.execute(select(Tag.kind)).scalars().all()
+    # seeded hygiene tags (#128, kind=general) survive a reset by design.
+    kinds = db_sync.execute(
+        select(Tag.kind).where(Tag.is_system.is_(False))
+    ).scalars().all()
     kind_vals = {k.value if hasattr(k, "value") else str(k) for k in kinds}
     assert kind_vals == {"fandom", "series"}
     # series_page ordering survived.