fix: fall back on Windows skill file encodings (#6058)

Co-authored-by: stablegenius49 <185121704+stablegenius49@users.noreply.github.com>

astrbot/core/computer/booters/local.py

@@ -53,31 +53,45 @@ def _ensure_safe_path(path: str) -> str:
     return abs_path
 
 
-def _decode_shell_output(output: bytes | None) -> str:
+def _decode_bytes_with_fallback(
+    output: bytes | None,
+    *,
+    preferred_encoding: str | None = None,
+) -> str:
     if output is None:
         return ""
 
     preferred = locale.getpreferredencoding(False) or "utf-8"
-    try:
-        return output.decode("utf-8")
-    except (LookupError, UnicodeDecodeError):
-        pass
+    attempted_encodings: list[str] = []
+
+    def _try_decode(encoding: str) -> str | None:
+        normalized = encoding.lower()
+        if normalized in attempted_encodings:
+            return None
+        attempted_encodings.append(normalized)
+        try:
+            return output.decode(encoding)
+        except (LookupError, UnicodeDecodeError):
+            return None
+
+    for encoding in filter(None, [preferred_encoding, "utf-8", "utf-8-sig"]):
+        if decoded := _try_decode(encoding):
+            return decoded
 
     if os.name == "nt":
-        for encoding in ("mbcs", "cp936", "gbk", "gb18030"):
-            try:
-                return output.decode(encoding)
-            except (LookupError, UnicodeDecodeError):
-                continue
-
-    try:
-        return output.decode(preferred)
-    except (LookupError, UnicodeDecodeError):
-        pass
+        for encoding in ("mbcs", "cp936", "gbk", "gb18030", preferred):
+            if decoded := _try_decode(encoding):
+                return decoded
+    elif decoded := _try_decode(preferred):
+        return decoded
 
     return output.decode("utf-8", errors="replace")
 
 
+def _decode_shell_output(output: bytes | None) -> str:
+    return _decode_bytes_with_fallback(output, preferred_encoding="utf-8")
+
+
 @dataclass
 class LocalShellComponent(ShellComponent):
     async def exec(
@@ -184,8 +198,12 @@ class LocalFileSystemComponent(FileSystemComponent):
     async def read_file(self, path: str, encoding: str = "utf-8") -> dict[str, Any]:
         def _run() -> dict[str, Any]:
             abs_path = _ensure_safe_path(path)
-            with open(abs_path, encoding=encoding) as f:
-                content = f.read()
+            with open(abs_path, "rb") as f:
+                raw_content = f.read()
+            content = _decode_bytes_with_fallback(
+                raw_content,
+                preferred_encoding=encoding,
+            )
             return {"success": True, "content": content}
 
         return await asyncio.to_thread(_run)

tests/test_local_filesystem_component.py

@@ -0,0 +1,57 @@
+from __future__ import annotations
+
+import asyncio
+from pathlib import Path
+
+from astrbot.core.computer.booters import local as local_booter
+from astrbot.core.computer.booters.local import LocalFileSystemComponent
+
+
+def _allow_tmp_root(monkeypatch, tmp_path: Path) -> None:
+    monkeypatch.setattr(local_booter, "get_astrbot_root", lambda: str(tmp_path))
+    monkeypatch.setattr(local_booter, "get_astrbot_data_path", lambda: str(tmp_path))
+    monkeypatch.setattr(local_booter, "get_astrbot_temp_path", lambda: str(tmp_path))
+
+
+def test_local_file_system_component_prefers_utf8_before_windows_locale(
+    monkeypatch,
+    tmp_path: Path,
+):
+    _allow_tmp_root(monkeypatch, tmp_path)
+    monkeypatch.setattr(local_booter.os, "name", "nt", raising=False)
+    monkeypatch.setattr(
+        local_booter.locale,
+        "getpreferredencoding",
+        lambda _do_setlocale=False: "cp936",
+    )
+
+    skill_path = tmp_path / "skills" / "demo.txt"
+    skill_path.parent.mkdir(parents=True, exist_ok=True)
+    skill_path.write_bytes("技能内容".encode("utf-8"))
+
+    result = asyncio.run(LocalFileSystemComponent().read_file(str(skill_path)))
+
+    assert result["success"] is True
+    assert result["content"] == "技能内容"
+
+
+def test_local_file_system_component_falls_back_to_gbk_on_windows(
+    monkeypatch,
+    tmp_path: Path,
+):
+    _allow_tmp_root(monkeypatch, tmp_path)
+    monkeypatch.setattr(local_booter.os, "name", "nt", raising=False)
+    monkeypatch.setattr(
+        local_booter.locale,
+        "getpreferredencoding",
+        lambda _do_setlocale=False: "cp1252",
+    )
+
+    skill_path = tmp_path / "skills" / "weibo-hot.txt"
+    skill_path.parent.mkdir(parents=True, exist_ok=True)
+    skill_path.write_bytes("微博热搜".encode("gbk"))
+
+    result = asyncio.run(LocalFileSystemComponent().read_file(str(skill_path)))
+
+    assert result["success"] is True
+    assert result["content"] == "微博热搜"