feat(tags): scan roles/+playbooks/ and fail on unknown tags

Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>

scripts/check-tags.py

@@ -29,7 +29,6 @@ def _ignore(loader, tag_suffix, node):
 
 
 _IgnoreUnknownTags.add_multi_constructor("", _ignore)
-_IgnoreUnknownTags.add_multi_constructor("!", _ignore)
 
 
 def _static_str(value):
@@ -68,5 +67,52 @@ def collect_tags(node):
     return tags
 
 
-if __name__ == "__main__":  # pragma: no cover
-    sys.exit(0)
+def scan_text(text):
+    """Collect static tags from a (possibly multi-document) YAML string."""
+    found = set()
+    for doc in yaml.load_all(text, Loader=_IgnoreUnknownTags):
+        found |= collect_tags(doc)
+    return found
+
+
+def iter_yaml_files(repo=REPO, scan_dirs=SCAN_DIRS):
+    for name in scan_dirs:
+        base = repo / name
+        if not base.is_dir():
+            continue
+        for ext in ("*.yml", "*.yaml"):
+            yield from sorted(base.rglob(ext))
+
+
+def find_violations(used, allowed):
+    return sorted(used - allowed)
+
+
+def main():
+    allowed = load_vocab() | role_names()
+    violations = []
+    for path in iter_yaml_files():
+        try:
+            used = scan_text(path.read_text())
+        except yaml.YAMLError as exc:
+            print(f"warning: could not parse {path}: {exc}", file=sys.stderr)
+            continue
+        for tag in find_violations(used, allowed):
+            violations.append((path.relative_to(REPO), tag))
+
+    if violations:
+        print(
+            "error: Ansible tag(s) not in tests/tags.yml or role names "
+            "(see docs/decisions/019-tagging.md):",
+            file=sys.stderr,
+        )
+        for relpath, tag in violations:
+            print(f"  {relpath}: '{tag}'", file=sys.stderr)
+        print(f"\nallowed: {', '.join(sorted(allowed))}", file=sys.stderr)
+        sys.exit(1)
+
+    print(f"check-tags: OK ({len(allowed)} tags allowed across {len(SCAN_DIRS)} dirs)")
+
+
+if __name__ == "__main__":
+    main()

tests/test_check_tags.py

@@ -35,10 +35,38 @@ def test_load_vocab_unions_all_categories():
     assert "firewall" in vocab      # concern
     assert "always" in vocab        # special
     assert "bootstrap" in vocab     # playbook identity
-    assert len([c for c in vocab]) >= 12
+    assert len(vocab) >= 10
 
 
 def test_role_names_reads_role_dirs():
     names = ct.role_names()
     assert "base" in names
     assert "docker_host" in names
+
+
+def test_scan_text_collects_from_yaml_string():
+    text = """
+- hosts: all
+  roles:
+    - role: base
+      tags: [base]
+  tasks:
+    - name: open port
+      tags: [firewall]
+"""
+    assert ct.scan_text(text) == {"base", "firewall"}
+
+
+def test_scan_text_tolerates_custom_yaml_tags():
+    text = "- name: t\n  secret: !vault xxx\n  tags: [users]\n"
+    assert ct.scan_text(text) == {"users"}
+
+
+def test_find_violations_flags_unknown_tag():
+    allowed = {"base", "firewall"}
+    used = {"base", "frewall"}  # typo
+    assert ct.find_violations(used, allowed) == ["frewall"]
+
+
+def test_find_violations_empty_when_all_allowed():
+    assert ct.find_violations({"base", "firewall"}, {"base", "firewall"}) == []