From 32f4dfa26d25b8ff243bfd2e636f5e96d8947a83 Mon Sep 17 00:00:00 2001
From: mvalentsev <michael@valentsev.ru>
Date: Thu, 30 Apr 2026 15:00:37 +0500
Subject: [PATCH] fix(cli): reconfigure stdio to UTF-8 on Windows

The primary `mempalace` console_script (`cli.py:main()`) reads non-ASCII
arguments via piped stdin and writes verbatim drawer text / wing names
through `print()`. On Windows, Python defaults stdio to the system ANSI
codepage (cp1252/cp1251/cp950), so:

- `mempalace search "..." > out.txt` mojibakes any drawer text containing
  non-Latin characters
- `mempalace ... < input.txt` mojibakes piped non-ASCII input

Reconfigure stdin/stdout/stderr to UTF-8 (`errors="strict"`) at the top
of `main()`, mirroring the helper added in this PR for fact_checker's
`__main__` block. Wrapped in try/except so a replaced stream (Jupyter,
test harness) logs a warning and continues rather than crashing the CLI.

The reconfigure cascades through every `mempalace` subcommand
(`init`/`mine`/`search`/`status`/`hook`/etc.) and through the interactive
flows that read non-ASCII names via `input()` (onboarding, entity
detector, room detector). With this commit the package's three
user-facing entry points (`mempalace`, `mempalace-mcp`, and
`python -m mempalace.fact_checker`) all reconfigure stdio identically on
Windows.
---
 mempalace/cli.py  | 27 ++++++++++++++++++++++++
 tests/test_cli.py | 52 +++++++++++++++++++++++++++++++++++++++++++++++
 2 files changed, 79 insertions(+)

diff --git a/mempalace/cli.py b/mempalace/cli.py
index f2606a4..7372cd7 100644
--- a/mempalace/cli.py
+++ b/mempalace/cli.py
@@ -935,7 +935,34 @@ def cmd_compress(args):
         print("  (dry run -- nothing stored)")
 
 
+def _reconfigure_stdio_utf8_on_windows():
+    """Decode stdio as UTF-8 on Windows for the primary `mempalace` CLI.
+
+    Without this, Python defaults stdio to the system ANSI codepage
+    (cp1252/cp1251/cp950 depending on locale). That mojibakes non-ASCII
+    content piped in (`mempalace search ... < query.txt`) or piped out
+    (`mempalace search "..." > out.txt`) when verbatim drawer text or
+    wing/room names contain non-Latin characters.
+    """
+    if sys.platform != "win32":
+        return
+    for name in ("stdin", "stdout", "stderr"):
+        stream = getattr(sys, name, None)
+        reconfigure = getattr(stream, "reconfigure", None)
+        if reconfigure is None:
+            continue
+        try:
+            reconfigure(encoding="utf-8", errors="strict")
+        except Exception as exc:
+            print(
+                f"WARNING: Could not reconfigure {name} to UTF-8: {exc}",
+                file=sys.stderr,
+            )
+
+
 def main():
+    _reconfigure_stdio_utf8_on_windows()
+
     version_label = f"MemPalace {__version__}"
     parser = argparse.ArgumentParser(
         description="MemPalace — Give your AI a memory. No API key required.",
diff --git a/tests/test_cli.py b/tests/test_cli.py
index 328b90c..4836d69 100644
--- a/tests/test_cli.py
+++ b/tests/test_cli.py
@@ -1042,3 +1042,55 @@ def test_cmd_repair_trailing_slash_does_not_recurse():
     palace_path = os.path.expanduser(args.palace).rstrip(os.sep)
     backup_path = palace_path + ".backup"
     assert not backup_path.startswith(palace_path + os.sep)
+
+
+# ── stdio reconfigure on Windows ─────────────────────────────────────
+
+
+class _ReconfigurableStringIO:
+    def __init__(self):
+        self.reconfigure_calls = []
+
+    def reconfigure(self, **kwargs):
+        self.reconfigure_calls.append(kwargs)
+
+
+def test_reconfigures_stdio_to_utf8_on_windows():
+    """Windows `mempalace` CLI must decode/encode stdio as UTF-8.
+
+    Without this, piped non-ASCII input (`mempalace search ... < q.txt`)
+    or piped non-ASCII output (`mempalace search "..." > out.txt`) is
+    mojibaked through the system ANSI codepage on non-Latin Windows
+    locales (cp1252/cp1251/cp950).
+    """
+    from mempalace.cli import _reconfigure_stdio_utf8_on_windows
+
+    stdin = _ReconfigurableStringIO()
+    stdout = _ReconfigurableStringIO()
+    stderr = _ReconfigurableStringIO()
+    with (
+        patch.object(sys, "platform", "win32"),
+        patch.object(sys, "stdin", stdin),
+        patch.object(sys, "stdout", stdout),
+        patch.object(sys, "stderr", stderr),
+    ):
+        _reconfigure_stdio_utf8_on_windows()
+
+    expected = {"encoding": "utf-8", "errors": "strict"}
+    assert stdin.reconfigure_calls == [expected]
+    assert stdout.reconfigure_calls == [expected]
+    assert stderr.reconfigure_calls == [expected]
+
+
+def test_reconfigure_stdio_is_noop_off_windows():
+    """Linux/macOS already default to UTF-8 stdio -- helper must not touch streams."""
+    from mempalace.cli import _reconfigure_stdio_utf8_on_windows
+
+    stdin = _ReconfigurableStringIO()
+    with (
+        patch.object(sys, "platform", "linux"),
+        patch.object(sys, "stdin", stdin),
+    ):
+        _reconfigure_stdio_utf8_on_windows()
+
+    assert stdin.reconfigure_calls == []