fix: cleanup keeps the generated files of today

scripts/cleanup_disk.py

@@ -8,7 +8,8 @@ sessions create theirs. A worktree elsewhere on disk and the automation
 worktree (.cache/autorun/worktree) are never candidates. One is removed only
 when no process runs in or holds a file of it, it is older than --hours, and
 nothing tracked is modified in it except generated artifacts (database.json,
-install/*.json, exports/*.json, README.md, mkdocs.yml). Branches are always
+install/*.json, exports/*.json, README.md, CONTRIBUTING.md,
+website/src/data/*.json). Branches are always
 kept, so committed work stays reachable. A worktree with real uncommitted
 code is listed, never removed.
 
@@ -39,7 +40,8 @@ from dataclasses import dataclass
 from pathlib import Path
 
 GENERATED = re.compile(
-    r"^(database\.json|install/.*\.json|exports/.*\.json|README\.md|mkdocs\.yml)$"
+    r"^(database\.json|install/.*\.json|exports/.*\.json|README\.md|CONTRIBUTING\.md"
+    r"|website/src/data/[^/]+\.json)$"
 )
 KEPT_TMP = ("acquire",)
 AUTOMATION_WORKTREE = Path(".cache") / "autorun" / "worktree"

tests/test_autorun.py

@@ -687,6 +687,15 @@ class Cleanup(Origin):
     def _decisions(self, busy=()) -> dict[str, cd.Decision]:
         return {d.path.name: d for d in cd.plan(self.repo, busy, self.HOURS, time.time())}
 
+    def test_generated_files_are_the_ones_a_run_rewrites(self):
+        """mkdocs.yml stayed in the list after the site moved to Starlight,
+        while CONTRIBUTING.md and website/src/data/*.json were left out."""
+        for path in ("README.md", "CONTRIBUTING.md", "database.json", "install/retroarch.json",
+                     "exports/batocera.json", "website/src/data/source-paths.json"):
+            self.assertTrue(cd.GENERATED.match(path), path)
+        for path in ("mkdocs.yml", "website/src/data/x/y.json", "scripts/verify.py"):
+            self.assertFalse(cd.GENERATED.match(path), path)
+
     def test_worktree_and_tmp_rules(self):
         old_clean = self._worktree("old-clean", 100)
         old_code = self._worktree("old-code", 100)