fix(cli): use UTF-8 for config files

src/openjarvis/cli/config_cmd.py

@@ -158,7 +158,7 @@ def _show_toml_config(console: Console, config_path: Path) -> None:
     console.print(f"[dim]Loading config from: {config_path}[/dim]")
 
     if config_path.exists():
-        config_content = config_path.read_text()
+        config_content = config_path.read_text(encoding="utf-8")
         syntax = Syntax(config_content, "toml", theme="monokai", line_numbers=True)
         console.print(Panel(syntax, title="Config File", border_style="cyan"))
     else:
@@ -170,7 +170,7 @@ def _show_json_config(console: Console, config_path: Path) -> None:
     console.print(f"[dim]Loading config from: {config_path}[/dim]")
 
     if config_path.exists():
-        config_content = config_path.read_text()
+        config_content = config_path.read_text(encoding="utf-8")
 
         try:
             import tomllib  # Python 3.11+
@@ -375,7 +375,7 @@ def set_config(key: str, value: str) -> None:
         os.environ.get("OPENJARVIS_CONFIG", DEFAULT_CONFIG_DIR / "config.toml")
     )
     if config_path.exists():
-        doc = tomlkit.parse(config_path.read_text())
+        doc = tomlkit.parse(config_path.read_text(encoding="utf-8"))
     else:
         doc = tomlkit.document()
         config_path.parent.mkdir(parents=True, exist_ok=True)
@@ -390,7 +390,7 @@ def set_config(key: str, value: str) -> None:
     current[parts[-1]] = typed_value
 
     # Write back
-    config_path.write_text(tomlkit.dumps(doc))
+    config_path.write_text(tomlkit.dumps(doc), encoding="utf-8")
 
     console.print(f"[green]Set[/green] {key} = {value!r}")
 

src/openjarvis/cli/init_cmd.py

@@ -344,7 +344,9 @@ def init(
             console.print(f"  Looked in: {examples_dir}")
             raise SystemExit(1)
         DEFAULT_CONFIG_DIR.mkdir(parents=True, exist_ok=True)
-        DEFAULT_CONFIG_PATH.write_text(preset_path.read_text())
+        DEFAULT_CONFIG_PATH.write_text(
+            preset_path.read_text(encoding="utf-8"), encoding="utf-8"
+        )
         console.print(
             f"[green]Preset '{preset}' installed to {DEFAULT_CONFIG_PATH}[/green]"
         )

tests/cli/test_cli.py

@@ -138,6 +138,38 @@ class TestCLI:
         content = config_path.read_text()
         assert "[engine]" in content
 
+    def test_init_preset_uses_utf8_for_config_copy(self, tmp_path: Path) -> None:
+        """Preset installation reads and writes shipped TOML as UTF-8."""
+        config_dir = tmp_path / ".openjarvis"
+        config_path = config_dir / "config.toml"
+        original_read_text = Path.read_text
+        original_write_text = Path.write_text
+
+        def read_text(path: Path, *args: object, **kwargs: object) -> str:
+            if path.name == "chat-simple.toml":
+                assert kwargs.get("encoding") == "utf-8"
+            return original_read_text(path, *args, **kwargs)
+
+        def write_text(path: Path, data: str, *args: object, **kwargs: object) -> int:
+            if path == config_path:
+                assert kwargs.get("encoding") == "utf-8"
+            return original_write_text(path, data, *args, **kwargs)
+
+        with (
+            mock.patch("openjarvis.cli.init_cmd.DEFAULT_CONFIG_DIR", config_dir),
+            mock.patch("openjarvis.cli.init_cmd.DEFAULT_CONFIG_PATH", config_path),
+            mock.patch.object(Path, "read_text", autospec=True, side_effect=read_text),
+            mock.patch.object(
+                Path, "write_text", autospec=True, side_effect=write_text
+            ),
+        ):
+            result = CliRunner().invoke(cli, ["init", "--preset", "chat-simple"])
+
+        assert result.exit_code == 0
+        assert "lightweight conversational AI" in config_path.read_text(
+            encoding="utf-8"
+        )
+
 
 class TestStartupResilience:
     """Importing the CLI must not force heavy/native deps (#404, #309).

tests/cli/test_config_cmd.py

@@ -4,6 +4,7 @@ from __future__ import annotations
 
 import json
 from pathlib import Path
+from unittest import mock
 
 import pytest
 from click.testing import CliRunner
@@ -109,18 +110,34 @@ temperature = 0.7
         except json.JSONDecodeError:
             pytest.fail(f"Output is not valid JSON: {result.output}")
 
-    def test_config_show_toml_displays_raw_content(self, tmp_path: Path) -> None:
-        """Test that config show toml displays the raw TOML content."""
+    @pytest.mark.parametrize("output_format", ["toml", "json"])
+    def test_config_show_uses_utf8_for_config_file(
+        self, tmp_path: Path, output_format: str
+    ) -> None:
+        """Test that config show reads UTF-8 config files explicitly."""
         # Create a temporary config file
         config_file = tmp_path / "test_config.toml"
-        config_file.write_text('[engine]\ndefault = "ollama"\n')
-
-        result = CliRunner().invoke(
-            cli, ["config", "show", "toml", "--path", str(config_file)]
+        config_file.write_text(
+            '# Preset comment — stored as UTF-8\n[engine]\ndefault = "ollama"\n',
+            encoding="utf-8",
         )
+        original_read_text = Path.read_text
+
+        def read_text(path: Path, *args: object, **kwargs: object) -> str:
+            if path == config_file:
+                assert kwargs.get("encoding") == "utf-8"
+            return original_read_text(path, *args, **kwargs)
+
+        with mock.patch.object(Path, "read_text", autospec=True, side_effect=read_text):
+            result = CliRunner().invoke(
+                cli, ["config", "show", output_format, "--path", str(config_file)]
+            )
 
         assert result.exit_code == 0
-        assert "[engine]" in result.output
+        if output_format == "toml":
+            assert "[engine]" in result.output
+        else:
+            assert '"engine"' in result.output
         assert "ollama" in result.output
 
     def test_config_show_json_displays_parsed_content(self, tmp_path: Path) -> None:

tests/cli/test_config_set.py

@@ -60,6 +60,42 @@ class TestConfigSet:
         assert "vllm" in content
         assert "qwen2.5:3b" in content
 
+    def test_set_uses_utf8_for_existing_config(self, tmp_path: Path) -> None:
+        """config set preserves a UTF-8 config regardless of the system locale."""
+        config_file = tmp_path / "config.toml"
+        config_file.write_text(
+            '# Preset comment — stored as UTF-8\n[engine]\ndefault = "ollama"\n',
+            encoding="utf-8",
+        )
+        original_read_text = Path.read_text
+        original_write_text = Path.write_text
+
+        def read_text(path: Path, *args: object, **kwargs: object) -> str:
+            if path == config_file:
+                assert kwargs.get("encoding") == "utf-8"
+            return original_read_text(path, *args, **kwargs)
+
+        def write_text(path: Path, data: str, *args: object, **kwargs: object) -> int:
+            if path == config_file:
+                assert kwargs.get("encoding") == "utf-8"
+            return original_write_text(path, data, *args, **kwargs)
+
+        with (
+            mock.patch.dict(os.environ, {"OPENJARVIS_CONFIG": str(config_file)}),
+            mock.patch.object(Path, "read_text", autospec=True, side_effect=read_text),
+            mock.patch.object(
+                Path, "write_text", autospec=True, side_effect=write_text
+            ),
+        ):
+            result = CliRunner().invoke(
+                cli, ["config", "set", "engine.default", "vllm"]
+            )
+
+        assert result.exit_code == 0
+        content = config_file.read_text(encoding="utf-8")
+        assert "Preset comment — stored as UTF-8" in content
+        assert "vllm" in content
+
     def test_set_invalid_key_rejected(self, tmp_path: Path) -> None:
         """config set rejects unknown keys."""
         config_file = tmp_path / "config.toml"