fix: issue 1138 windows encoding (#1139)

* fix(windows): use utf-8 for text file operations

* fix(windows): normalize sandbox path masking

* fix(windows): preserve utf-8 handling after backend split

backend/tests/test_artifacts_router.py

@@ -0,0 +1,27 @@
+import asyncio
+from pathlib import Path
+
+from starlette.requests import Request
+
+import app.gateway.routers.artifacts as artifacts_router
+
+
+def test_get_artifact_reads_utf8_text_file_on_windows_locale(tmp_path, monkeypatch) -> None:
+    artifact_path = tmp_path / "note.txt"
+    text = "Curly quotes: \u201cutf8\u201d"
+    artifact_path.write_text(text, encoding="utf-8")
+
+    original_read_text = Path.read_text
+
+    def read_text_with_gbk_default(self, *args, **kwargs):
+        kwargs.setdefault("encoding", "gbk")
+        return original_read_text(self, *args, **kwargs)
+
+    monkeypatch.setattr(Path, "read_text", read_text_with_gbk_default)
+    monkeypatch.setattr(artifacts_router, "resolve_thread_virtual_path", lambda _thread_id, _path: artifact_path)
+
+    request = Request({"type": "http", "method": "GET", "path": "/", "headers": [], "query_string": b""})
+    response = asyncio.run(artifacts_router.get_artifact("thread-1", "mnt/user-data/outputs/note.txt", request))
+
+    assert bytes(response.body).decode("utf-8") == text
+    assert response.media_type == "text/plain"

backend/tests/test_local_sandbox_encoding.py

@@ -0,0 +1,33 @@
+import builtins
+
+import deerflow.sandbox.local.local_sandbox as local_sandbox
+from deerflow.sandbox.local.local_sandbox import LocalSandbox
+
+
+def _open(base, file, mode="r", *args, **kwargs):
+    if "b" in mode:
+        return base(file, mode, *args, **kwargs)
+    return base(file, mode, *args, encoding=kwargs.pop("encoding", "gbk"), **kwargs)
+
+
+def test_read_file_uses_utf8_on_windows_locale(tmp_path, monkeypatch):
+    path = tmp_path / "utf8.txt"
+    text = "\u201cutf8\u201d"
+    path.write_text(text, encoding="utf-8")
+    base = builtins.open
+
+    monkeypatch.setattr(local_sandbox, "open", lambda file, mode="r", *args, **kwargs: _open(base, file, mode, *args, **kwargs), raising=False)
+
+    assert LocalSandbox("t").read_file(str(path)) == text
+
+
+def test_write_file_uses_utf8_on_windows_locale(tmp_path, monkeypatch):
+    path = tmp_path / "utf8.txt"
+    text = "emoji \U0001F600"
+    base = builtins.open
+
+    monkeypatch.setattr(local_sandbox, "open", lambda file, mode="r", *args, **kwargs: _open(base, file, mode, *args, **kwargs), raising=False)
+
+    LocalSandbox("t").write_file(str(path), text)
+
+    assert path.read_text(encoding="utf-8") == text

backend/tests/test_sandbox_tools_security.py

@@ -18,8 +18,8 @@ def test_replace_virtual_path_maps_virtual_root_and_subpaths() -> None:
         "outputs_path": "/tmp/deer-flow/threads/t1/user-data/outputs",
     }
 
-    assert replace_virtual_path("/mnt/user-data/workspace/a.txt", thread_data) == "/tmp/deer-flow/threads/t1/user-data/workspace/a.txt"
-    assert replace_virtual_path("/mnt/user-data", thread_data) == "/tmp/deer-flow/threads/t1/user-data"
+    assert Path(replace_virtual_path("/mnt/user-data/workspace/a.txt", thread_data)).as_posix() == "/tmp/deer-flow/threads/t1/user-data/workspace/a.txt"
+    assert Path(replace_virtual_path("/mnt/user-data", thread_data)).as_posix() == "/tmp/deer-flow/threads/t1/user-data"
 
 
 def test_mask_local_paths_in_output_hides_host_paths() -> None:

backend/tests/test_skills_router.py

@@ -58,3 +58,31 @@ unsupported: true
     assert valid is False
     assert "unsupported" in message
     assert skill_name is None
+
+
+def test_validate_skill_frontmatter_reads_utf8_on_windows_locale(tmp_path, monkeypatch) -> None:
+    skill_dir = tmp_path / "demo-skill"
+    _write_skill(
+        skill_dir,
+        """---
+name: demo-skill
+description: "Curly quotes: \u201cutf8\u201d"
+---
+
+# Demo Skill
+""",
+    )
+
+    original_read_text = Path.read_text
+
+    def read_text_with_gbk_default(self, *args, **kwargs):
+        kwargs.setdefault("encoding", "gbk")
+        return original_read_text(self, *args, **kwargs)
+
+    monkeypatch.setattr(Path, "read_text", read_text_with_gbk_default)
+
+    valid, message, skill_name = VALIDATE_SKILL_FRONTMATTER(skill_dir)
+
+    assert valid is True
+    assert message == "Skill is valid!"
+    assert skill_name == "demo-skill"