fix(upstream): use UTF-8 for framework version checks (#587)

* fix(upstream): use UTF-8 for framework version checks

* test(upstream): isolate argument and console codecs

* docs(changelog): record fix for #587

* changelog: place the #587 entry under [Unreleased]

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

---------

Co-authored-by: Mads Lorentzen <madslorentzen_17@hotmail.com>
Co-authored-by: Claude Opus 5.5 <noreply@anthropic.com>

CHANGELOG.md

@@ -428,6 +428,8 @@ per-file diff commands.
 
 - **Upstream triage distinguishes subject-only matches from verified patch matches** (#569) - matching subjects with different patches now name the fork commit and request verification instead of claiming the change was already cherry-picked.
 
+- **Upstream version checks decode Git output as UTF-8** (#587) - future non-Latin framework lines and non-Latin branch names no longer depend on the host code page, guarding a latent case absent from the shipped framework files.
+
 ### Security
 
 - **CI no longer leaves the job token in `.git/config` or expands a PR-controlled name into a

tests/test_check_upstream_updates.py

@@ -1,3 +1,4 @@
+import os
 import shutil
 import subprocess
 import sys
@@ -185,6 +186,45 @@ class UpstreamRefMissingFileTests(UpstreamCheckerRepoFixture):
         self.assertIn("[WARNING]", result.stdout)
 
 
+class LegacyEncodingTests(UpstreamCheckerRepoFixture):
+    def setUp(self):
+        super().setUp()
+        # Use the actual shipped framework files, whose UTF-8 prose git show
+        # returns, rather than a constructed string passed to run_git().
+        for rel in FRAMEWORK_FILES:
+            shutil.copy(REPO_ROOT / rel, self.root / rel)
+        subprocess.run(["git", "add", "-A"], cwd=self.root, check=True, capture_output=True)
+        subprocess.run(["git", "commit", "-qm", "copy actual framework files"], cwd=self.root, check=True, capture_output=True)
+        self.add_remote("upstream", TEMPLATE_URL)
+        self.materialize_remote_ref("upstream")
+
+    def run_legacy_checker(self, *args, ascii_git_codec=True):
+        env = dict(os.environ, LC_ALL="C", LANG="C", PYTHONUTF8="0",
+                   PYTHONCOERCECLOCALE="0", PYTHONIOENCODING="cp1252")
+        if not ascii_git_codec:
+            # Keep valid Unicode argv while independently forcing legacy stdout.
+            # Linux's ASCII filesystem decoder would instead create surrogate
+            # escapes, testing argument decoding rather than console output.
+            env["PYTHONUTF8"] = "1"
+        return subprocess.run(
+            [sys.executable, str(self.root / "tools/check_upstream_updates.py"), "--no-fetch", *args],
+            cwd=self.root, env=env, capture_output=True,
+        )
+
+    def test_actual_framework_prose_is_decoded_as_utf8(self):
+        result = self.run_legacy_checker()
+        self.assertEqual(result.returncode, 0, result.stderr.decode("utf-8", "replace"))
+        self.assertIn("[OK]", result.stdout.decode("utf-8"))
+
+    def test_non_latin_branch_is_printed_as_utf8(self):
+        branch = "release-版本"
+        subprocess.run(["git", "update-ref", f"refs/remotes/upstream/{branch}", "HEAD"],
+                       cwd=self.root, check=True, capture_output=True)
+        result = self.run_legacy_checker("--branch", branch, ascii_git_codec=False)
+        self.assertEqual(result.returncode, 0, result.stderr.decode("utf-8", "replace"))
+        self.assertIn(f"upstream/{branch}", result.stdout.decode("utf-8"))
+
+
 class IncompleteComparisonTests(UpstreamCheckerRepoFixture):
     def setUp(self):
         super().setUp()

tools/check_upstream_updates.py

@@ -38,7 +38,10 @@ FRAMEWORK_FILES = [
 UPSTREAM_REPO_SLUG = "MadsLorentzen/ai-job-search"
 
 def run_git(args: list[str]) -> tuple[int, str, str]:
-    res = subprocess.run(["git"] + args, cwd=str(ROOT), capture_output=True, text=True)
+    res = subprocess.run(
+        ["git"] + args, cwd=str(ROOT), capture_output=True, text=True,
+        encoding="utf-8", errors="replace",
+    )
     return res.returncode, res.stdout, res.stderr
 
 def get_remote_url(remote_name: str) -> str:
@@ -65,7 +68,16 @@ def parse_semver(version_str: str) -> tuple[int, int, int]:
         return (0, 0, 0)
     return tuple(int(x) for x in match.groups())
 
+def _force_utf8_output() -> None:
+    """Use UTF-8 for piped output even on legacy-console hosts."""
+    for stream in (sys.stdout, sys.stderr):
+        reconfigure = getattr(stream, "reconfigure", None)
+        if reconfigure:
+            reconfigure(encoding="utf-8")
+
+
 def main() -> int:
+    _force_utf8_output()
     parser = argparse.ArgumentParser(description="Check for framework updates upstream.")
     parser.add_argument("--remote", default="upstream", help="Name of the git remote for upstream (default: upstream)")
     parser.add_argument("--branch", default="master", help="Branch name of the upstream repo (default: master)")