fix(ml): preserve digit-only tag names in normalize (year tags)

Rule 8 'no letters -> drop' was over-eager: bare digit tags like '2005'
returned None even though they're legitimate (booru year-tag shape).
Widen the keep-condition to any alphanumeric. Emoticons (':/', '^_^',
'+_+') still drop since they contain neither letters nor digits.

backend/app/services/ml/tag_name.py

@@ -18,7 +18,8 @@ Rules (operator-approved 2026-06-03):
   6. Preserve hyphens (booru hyphens often carry meaning)
   7. Title-case each space-separated word (first character only —
      apostrophes, digits, hyphens stay)
-  8. If no letters remain, return None (drop emoticons like `:/`)
+  8. If no letters AND no digits remain, return None (drops emoticons
+     like `:/` or `^_^`; preserves bare digit tags like `2005`)
   9. No surname/givenname swap — no reliable signal in the vocab
 """
 
@@ -28,7 +29,7 @@ _LEADING_JUNK = re.compile(r"^[#.+;~_\s]+")
 _TRAILING_DISAMBIG = re.compile(r"_\([^)]*\)\s*$")
 _MULTISPACE = re.compile(r"\s+")
 _COLON_NOSPACE = re.compile(r":(?=\S)")
-_HAS_LETTER = re.compile(r"[A-Za-z]")
+_HAS_ALPHANUMERIC = re.compile(r"[A-Za-z0-9]")
 
 
 def _strip_wrapping_quotes(s: str) -> str:
@@ -56,6 +57,6 @@ def normalize(raw: str) -> str | None:
     s = s.replace("_", " ")
     s = _COLON_NOSPACE.sub(": ", s)
     s = _MULTISPACE.sub(" ", s).strip()
-    if not s or not _HAS_LETTER.search(s):
+    if not s or not _HAS_ALPHANUMERIC.search(s):
         return None
     return " ".join(_title_word(w) for w in s.split(" "))