Force UTF-8 and full manifest validation

Force UTF-8 decoding for registry and manifest reads in the Bash and
PowerShell embedded-Python parsers so resolution no longer depends on the
process locale, and validate every manifest template entry's required
fields, type, and strategy consistent with the canonical PresetManifest.

Assisted-by: GitHub Copilot (model: claude-opus-4.8, autonomous)
Co-authored-by: Copilot App <223556219+Copilot@users.noreply.github.com>
Copilot-Session: 3158e06f-95df-4e3a-843f-f159a35aa30c

Author: mnriem

scripts/bash/common.sh

@@ -428,7 +428,7 @@ registered = {}
 registry = root / '.registry'
 if registry.is_file():
     try:
-        data = json.loads(registry.read_text())
+        data = json.loads(registry.read_text(encoding='utf-8'))
         value = data.get('extensions', {}) if isinstance(data, dict) else {}
         registered = value if isinstance(value, dict) else {}
     except Exception:
@@ -503,7 +503,7 @@ resolve_template() {
             if sorted_presets=$(SPECKIT_REGISTRY="$registry_file" "${python_cmd[@]}" -c "
 import json, re, sys, os
 try:
-    with open(os.environ['SPECKIT_REGISTRY']) as f:
+    with open(os.environ['SPECKIT_REGISTRY'], encoding='utf-8') as f:
         data = json.load(f)
     presets = data.get('presets', {})
     def priority(meta):
@@ -622,7 +622,7 @@ resolve_template_content() {
             if sorted_presets=$(SPECKIT_REGISTRY="$registry_file" "${python_cmd[@]}" -c "
 import json, re, sys, os
 try:
-    with open(os.environ['SPECKIT_REGISTRY']) as f:
+    with open(os.environ['SPECKIT_REGISTRY'], encoding='utf-8') as f:
         data = json.load(f)
     presets = data.get('presets', {})
     def priority(meta):
@@ -675,7 +675,7 @@ except ImportError:
     print('yaml_missing', file=sys.stderr)
     sys.exit(2)
 try:
-    with open(os.environ['SPECKIT_MANIFEST']) as f:
+    with open(os.environ['SPECKIT_MANIFEST'], encoding='utf-8') as f:
         data = yaml.safe_load(f)
     if not isinstance(data, dict):
         raise ValueError('manifest root must be a mapping')
@@ -685,15 +685,26 @@ try:
     templates = provides.get('templates', [])
     if not isinstance(templates, list):
         raise ValueError('manifest templates must be a list')
+    valid_types = ('template', 'command', 'script')
+    valid_strategies = ('replace', 'prepend', 'append', 'wrap')
     for t in templates:
         if not isinstance(t, dict):
             raise ValueError('manifest template entries must be mappings')
-        file_value = t.get('file', '')
+        if 'type' not in t or 'name' not in t or 'file' not in t:
+            raise ValueError('manifest template entry missing type, name, or file')
+        for field in ('type', 'name', 'file'):
+            if not isinstance(t[field], str):
+                raise ValueError('manifest template ' + field + ' must be a string')
+        if t['type'] not in valid_types:
+            raise ValueError('invalid manifest template type')
         strategy = t.get('strategy', 'replace')
-        if not isinstance(file_value, str):
-            raise ValueError('manifest template file must be a string')
         if not isinstance(strategy, str):
             raise ValueError('manifest template strategy must be a string')
+        strategy = strategy.lower()
+        if strategy not in valid_strategies:
+            raise ValueError('invalid manifest template strategy')
+        if t['type'] == 'script' and strategy not in ('replace', 'wrap'):
+            raise ValueError('invalid manifest script strategy')
     for t in templates:
         if t.get('name') == os.environ['SPECKIT_TMPL'] and t.get('type', 'template') == 'template':
             file_value = t.get('file', '')

scripts/powershell/common.ps1

@@ -598,7 +598,7 @@ except ImportError:
     print('yaml_missing', file=sys.stderr)
     sys.exit(2)
 try:
-    with open(sys.argv[1]) as f:
+    with open(sys.argv[1], encoding='utf-8') as f:
         data = yaml.safe_load(f)
     if not isinstance(data, dict):
         raise ValueError('manifest root must be a mapping')
@@ -608,15 +608,26 @@ try:
     templates = provides.get('templates', [])
     if not isinstance(templates, list):
         raise ValueError('manifest templates must be a list')
+    valid_types = ('template', 'command', 'script')
+    valid_strategies = ('replace', 'prepend', 'append', 'wrap')
     for t in templates:
         if not isinstance(t, dict):
             raise ValueError('manifest template entries must be mappings')
-        file_value = t.get('file', '')
+        if 'type' not in t or 'name' not in t or 'file' not in t:
+            raise ValueError('manifest template entry missing type, name, or file')
+        for field in ('type', 'name', 'file'):
+            if not isinstance(t[field], str):
+                raise ValueError('manifest template ' + field + ' must be a string')
+        if t['type'] not in valid_types:
+            raise ValueError('invalid manifest template type')
         strategy = t.get('strategy', 'replace')
-        if not isinstance(file_value, str):
-            raise ValueError('manifest template file must be a string')
         if not isinstance(strategy, str):
             raise ValueError('manifest template strategy must be a string')
+        strategy = strategy.lower()
+        if strategy not in valid_strategies:
+            raise ValueError('invalid manifest template strategy')
+        if t['type'] == 'script' and strategy not in ('replace', 'wrap'):
+            raise ValueError('invalid manifest script strategy')
     for t in templates:
         if t.get('name') == sys.argv[2] and t.get('type', 'template') == 'template':
             file_value = t.get('file', '')

scripts/python/common.py

@@ -335,6 +335,36 @@ class TemplateResolutionError(RuntimeError):
     """Raised when template layers exist but cannot be composed safely."""
 
 
+# Mirror the canonical PresetManifest contract (see src/specify_cli/presets)
+# so runtime resolution rejects the same structurally malformed manifests.
+_VALID_TEMPLATE_TYPES = ("template", "command", "script")
+_VALID_TEMPLATE_STRATEGIES = ("replace", "prepend", "append", "wrap")
+_VALID_SCRIPT_STRATEGIES = ("replace", "wrap")
+
+
+def _validate_manifest_template_entry(entry: object) -> None:
+    """Validate a single manifest template entry against the canonical rules."""
+    if not isinstance(entry, dict):
+        raise ValueError("manifest template entries must be mappings")
+    if "type" not in entry or "name" not in entry or "file" not in entry:
+        raise ValueError("manifest template entry missing type, name, or file")
+    for field in ("type", "name", "file"):
+        if not isinstance(entry[field], str):
+            raise ValueError(f"manifest template {field} must be a string")
+    if entry["type"] not in _VALID_TEMPLATE_TYPES:
+        raise ValueError(f"invalid manifest template type '{entry['type']}'")
+    strategy = entry.get("strategy", "replace")
+    if not isinstance(strategy, str):
+        raise ValueError("manifest template strategy must be a string")
+    strategy = strategy.lower()
+    if strategy not in _VALID_TEMPLATE_STRATEGIES:
+        raise ValueError(f"invalid manifest template strategy '{strategy}'")
+    if entry["type"] == "script" and strategy not in _VALID_SCRIPT_STRATEGIES:
+        raise ValueError(
+            f"invalid manifest script strategy '{strategy}'"
+        )
+
+
 def _preset_template_layer(
     preset_dir: Path, template_name: str
 ) -> tuple[Path, str] | None:
@@ -363,14 +393,7 @@ def _preset_template_layer(
             if not isinstance(templates, list):
                 raise ValueError("manifest templates must be a list")
             for entry in templates:
-                if not isinstance(entry, dict):
-                    raise ValueError("manifest template entries must be mappings")
-                file_value = entry.get("file", "")
-                strategy = entry.get("strategy", "replace")
-                if not isinstance(file_value, str):
-                    raise ValueError("manifest template file must be a string")
-                if not isinstance(strategy, str):
-                    raise ValueError("manifest template strategy must be a string")
+                _validate_manifest_template_entry(entry)
             for entry in templates:
                 if (
                     entry.get("name") != template_name

tests/test_resolve_template_python_parity.py

@@ -91,6 +91,59 @@ def test_all_variants_preserve_composition_parity(
     )
 
 
+@requires_bash
+def test_all_variants_read_utf8_registry_under_ascii_locale(
+    tmp_path: Path,
+) -> None:
+    """Registry/manifest reads must force UTF-8, not the process locale.
+
+    With UTF-8 mode disabled and a C locale, the interpreter's default text
+    encoding is ASCII. Non-ASCII *metadata* in the registry or a manifest must
+    still resolve, because the resolvers open those files as UTF-8 explicitly.
+    Template content stays ASCII so the pure-Python variant can emit it on the
+    ASCII stdout this configuration forces.
+    """
+    repo = make_repo(tmp_path)
+    install_scripts(repo, SCRIPT)
+    expected = install_composition_stack(repo, TEMPLATE, "# Core\n")
+
+    # Inject non-ASCII metadata into the preset registry and a manifest so a
+    # locale-dependent decode would raise instead of resolving cleanly.
+    registry = repo / ".specify" / "presets" / ".registry"
+    registry_data = json.loads(registry.read_text(encoding="utf-8"))
+    registry_data["presets"]["wrap-pack"]["description"] = "Café ✓ wrapper"
+    registry.write_text(
+        json.dumps(registry_data, separators=(",", ":")) + "\n",
+        encoding="utf-8",
+    )
+    manifest = repo / ".specify" / "presets" / "wrap-pack" / "preset.yml"
+    manifest.write_text(
+        manifest.read_text(encoding="utf-8") + '      description: "Café ✓"\n',
+        encoding="utf-8",
+    )
+
+    env = clean_env()
+    # Force the interpreter's default text encoding to ASCII so an unqualified
+    # open() would fail on the non-ASCII metadata above.
+    env["PYTHONUTF8"] = "0"
+    env["PYTHONCOERCECLOCALE"] = "0"
+    env["LC_ALL"] = "C"
+    env["LANG"] = "C"
+
+    results = [
+        run(bash_cmd(repo, SCRIPT, TEMPLATE, "--json"), repo, env),
+        run(py_cmd(repo, SCRIPT, TEMPLATE, "--json"), repo, env),
+    ]
+    if HAS_POWERSHELL:
+        results.append(run(ps_cmd(repo, SCRIPT, TEMPLATE, "-Json"), repo, env))
+
+    assert all(result.returncode == 0 for result in results)
+    assert all(
+        json_stdout(result)["TEMPLATE_CONTENT"] == expected
+        for result in results
+    )
+
+
 @requires_bash
 @pytest.mark.parametrize(
     "template_name",
@@ -531,6 +584,45 @@ def test_bash_fails_when_override_read_fails(tmp_path: Path) -> None:
       name: unrelated-template
       file: null
       strategy: append
+""",
+        f"""provides:
+  templates:
+    - name: {TEMPLATE}
+      file: templates/{TEMPLATE}.md
+      strategy: wrap
+    - type: template
+      name: unrelated-template
+      file: templates/other.md
+""",
+        f"""provides:
+  templates:
+    - type: template
+      name: {TEMPLATE}
+      file: templates/{TEMPLATE}.md
+      strategy: wrap
+    - type: template
+      name: unrelated-template
+""",
+        f"""provides:
+  templates:
+    - type: template
+      name: {TEMPLATE}
+      file: templates/{TEMPLATE}.md
+      strategy: wrap
+    - type: bogus
+      name: unrelated-template
+      file: templates/other.md
+""",
+        f"""provides:
+  templates:
+    - type: template
+      name: {TEMPLATE}
+      file: templates/{TEMPLATE}.md
+      strategy: wrap
+    - type: template
+      name: unrelated-template
+      file: templates/other.md
+      strategy: merge
 """,
     ],
     ids=[
@@ -541,6 +633,10 @@ def test_bash_fails_when_override_read_fails(tmp_path: Path) -> None:
         "non_string_file",
         "non_string_strategy",
         "malformed_entry_after_match",
+        "entry_missing_type",
+        "entry_missing_file",
+        "unsupported_type",
+        "unsupported_strategy",
     ],
 )
 def test_all_variants_fail_for_malformed_preset_manifest(