Image sets by their numbered name, digits kept

Without a file counter a subject-named image release was bounded by the
image's name with all numbers removed:
- STIRILING SILVER's sets stp250x…stp465x became one 44k-image release
  (all "stp x"); picture threads of many sets (keira_s04, keira_s05,
  perla_s01, apneatic-7, -8 …) one release each.
- Free-text names without numbers ("JimAndJoey Kindly Husband-to-Be.JPG")
  made each image a set: one thread was 1,177 releases.
The bound is now the name up to its last number with its digits
("stp250x", "keira_s05_l keira_s05_", "apneatic-7-"), and nothing for a
name without numbers. models fixture: 172 -> 754 releases, by set. Both
implementations; tests; fixtures identical.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

lib/release/identity.ts

@@ -254,8 +254,12 @@ export function releaseIdentity(input: ReleaseInput): ReleaseIdentity | null {
     // Bounded by the counter's total, so the uploads a poster names alike are apart while the files
     // of one upload (par2 and nfo included) share it (LOG.md 2026-10-09 (9)).
     const total = counterTotal(input.subject)
+    // Without a counter an image's set bounds it: its name up to its last number, digits kept ("stp250x001.jpg"
+    // → "stp250x": STIRILING SILVER's 300 sets were one release of 44k images); a name without numbers names no
+    // set ("Kindly Husband-to-Be.JPG": a thread of 1,177 releases), so the subject alone (LOG.md 2026-10-12 (2)).
+    const set = image && /\d/.test(stem) ? stem.replace(/\d+\D*$/, '') : ''
     return {
-      key: hash('subject', poster, remainder, total ?? prefix),
+      key: hash('subject', poster, remainder, total ?? set),
       name: remainder,
       fileTotal,
       source: 'subject',