From 352cbc34454e7d13b1aa018c253c437a0962a270 Mon Sep 17 00:00:00 2001
From: =?UTF-8?q?=E9=BB=84=E4=BA=91=E9=BE=99?=
 <76432572+nankingjing@users.noreply.github.com>
Date: Mon, 13 Jul 2026 00:19:59 +0800
Subject: [PATCH] fix(config): read YAML config files as UTF-8 (#124)

_load_yaml opened config files with the platform default (locale)
encoding instead of UTF-8. The shipped configs (e.g.
configs/_base_/default.yaml) contain UTF-8 non-ASCII characters
(em-dash, arrows, box-drawing), so load_config() raises
UnicodeDecodeError on any non-UTF-8 locale (e.g. Windows cp936/cp1252),
breaking scripts/train.py and scripts/eval_only.py before startup.

YAML is UTF-8 by spec, and the rest of the codebase already opens text
files with encoding="utf-8". Pass encoding="utf-8" here for parity.
---
 skillopt/config.py | 2 +-
 1 file changed, 1 insertion(+), 1 deletion(-)

diff --git a/skillopt/config.py b/skillopt/config.py
index e7dbb83..8b13367 100644
--- a/skillopt/config.py
+++ b/skillopt/config.py
@@ -158,7 +158,7 @@ def _load_yaml(path: str, _visited: set[str] | None = None) -> dict:
         raise ValueError(f"Circular _base_ inheritance: {abs_path}")
     _visited.add(abs_path)
 
-    with open(abs_path) as f:
+    with open(abs_path, encoding="utf-8") as f:
         cfg = yaml.safe_load(f) or {}
 
     base_ref = cfg.pop("_base_", None)