refactor(stdio): extract Windows UTF-8 reconfigure into shared helper

Both cli.py and fact_checker.py carried identical 28-line Windows stdio
reconfigure helpers; pull the loop into mempalace/_stdio.py so the same
machine drives the CLI, the fact_checker --stdin entry point, and the
MCP server. The thin per-call-site wrappers stay so existing tests keep
importing _reconfigure_stdio_utf8_on_windows from the same module they
always have.

CLI / fact_checker policy unchanged: stdin=surrogateescape (don't crash
on a malformed redirected file), stdout/stderr=replace (don't crash
mid-print on a surrogate half round-tripped from a filename).

mempalace/_stdio.py

@@ -0,0 +1,71 @@
+"""Stdio UTF-8 reconfiguration helper for Windows entry points.
+
+Python on Windows defaults stdio to the system ANSI codepage
+(cp1252/cp1251/cp950 depending on locale), which mojibakes UTF-8 input
+or output the moment a non-Latin character shows up. Every console
+entry point that touches stdio needs to fix this on Windows -- the MCP
+server, the CLI, the fact_checker `--stdin` mode -- so the
+reconfigure code lives here in one place to keep the per-stream
+errors policies aligned across them.
+
+Per-stream errors policy is caller-chosen:
+
+* MCP server uses ``strict`` on stdout/stderr because everything written
+  there is server-controlled JSON-RPC; any encode failure is a real bug
+  the operator wants loud.
+* CLI / fact_checker use ``replace`` on stdout/stderr because they print
+  verbatim drawer text that may contain surrogate halves round-tripped
+  from filenames -- ``strict`` would crash mid-print.
+* All callers use ``surrogateescape`` on stdin so a malformed byte from
+  a redirected file or a misbehaving client survives as a lone surrogate
+  the consumer's parser surfaces, instead of ``UnicodeDecodeError``
+  killing the read loop on the first bad byte.
+"""
+
+from __future__ import annotations
+
+import sys
+from typing import Callable, Optional
+
+
+def reconfigure_stdio_utf8_on_windows(
+    *,
+    stdin_errors: str = "surrogateescape",
+    stdout_errors: str = "strict",
+    stderr_errors: str = "strict",
+    on_failure: Optional[Callable[[str, BaseException], None]] = None,
+) -> None:
+    """Reconfigure stdio to UTF-8 on Windows. No-op elsewhere.
+
+    Args:
+        stdin_errors: errors= policy for stdin.reconfigure().
+        stdout_errors: errors= policy for stdout.reconfigure().
+        stderr_errors: errors= policy for stderr.reconfigure().
+        on_failure: optional ``(stream_name, exc) -> None`` callback for
+            streams whose ``reconfigure`` raises (e.g. Jupyter-replaced
+            streams that lack the method-shape we expect). Defaults to a
+            ``WARNING:`` line on the original sys.stderr.
+    """
+    if sys.platform != "win32":
+        return
+
+    policies = (
+        ("stdin", stdin_errors),
+        ("stdout", stdout_errors),
+        ("stderr", stderr_errors),
+    )
+    for name, errors in policies:
+        stream = getattr(sys, name, None)
+        reconfigure = getattr(stream, "reconfigure", None)
+        if reconfigure is None:
+            continue
+        try:
+            reconfigure(encoding="utf-8", errors=errors)
+        except Exception as exc:  # noqa: BLE001 -- last-resort guard
+            if on_failure is not None:
+                on_failure(name, exc)
+            else:
+                print(
+                    f"WARNING: Could not reconfigure {name} to UTF-8: {exc}",
+                    file=sys.stderr,
+                )

mempalace/cli.py

@@ -938,42 +938,17 @@ def cmd_compress(args):
 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
+    Thin wrapper around the shared helper in ``mempalace._stdio``. The CLI
-    (cp1252/cp1251/cp950 depending on locale). That mojibakes non-ASCII
+    overrides stdout/stderr to ``replace`` because ``mempalace search``
-    content piped in (`mempalace search ... < query.txt`) or piped out
+    prints verbatim drawer text that may carry surrogate halves
-    (`mempalace search "..." > out.txt`) when verbatim drawer text or
+    round-tripped from filenames -- ``strict`` would crash mid-print and
-    wing/room names contain non-Latin characters.
+    lose the rest of the search result block. stdin keeps the default
-
+    ``surrogateescape`` so a redirected non-UTF-8 file does not kill the
-    Per-stream errors policy:
+    read on the first bad byte.
-      stdin  -- surrogateescape: malformed bytes from a redirected file
-                survive as lone surrogates instead of crashing the read.
-      stdout -- replace: ``mempalace search`` prints verbatim drawer
-                text. A drawer that round-tripped a filename through
-                surrogateescape can hold a lone surrogate, which would
-                otherwise raise ``UnicodeEncodeError`` mid-print and
-                lose the rest of the search result block.
-      stderr -- replace: same hazard for logger output that quotes
-                user-supplied path or content.
     """
-    if sys.platform != "win32":
+    from ._stdio import reconfigure_stdio_utf8_on_windows
-        return
+
-    policies = (
+    reconfigure_stdio_utf8_on_windows(stdout_errors="replace", stderr_errors="replace")
-        ("stdin", "surrogateescape"),
-        ("stdout", "replace"),
-        ("stderr", "replace"),
-    )
-    for name, errors in policies:
-        stream = getattr(sys, name, None)
-        reconfigure = getattr(stream, "reconfigure", None)
-        if reconfigure is None:
-            continue
-        try:
-            reconfigure(encoding="utf-8", errors=errors)
-        except Exception as exc:
-            print(
-                f"WARNING: Could not reconfigure {name} to UTF-8: {exc}",
-                file=sys.stderr,
-            )
 
 
 def main():

mempalace/fact_checker.py

@@ -306,40 +306,15 @@ def _edit_distance(s1: str, s2: str) -> int:
 def _reconfigure_stdio_utf8_on_windows():
     """Decode --stdin payload as UTF-8 on Windows.
 
-    Without this, Python defaults stdio to the system ANSI codepage
+    Thin wrapper around the shared helper in ``mempalace._stdio``. Mirrors
-    (cp1252/cp1251/cp950 depending on locale), which mojibakes
+    the primary CLI policy: stdout/stderr use ``replace`` because
-    non-ASCII fact text before pattern parsing sees it.
+    extracted fact text can include surrogate halves round-tripped from
-
+    filenames -- ``strict`` would raise UnicodeEncodeError mid-print.
-    Per-stream errors policy mirrors the primary CLI helper in
+    stdin keeps the default ``surrogateescape``.
-    ``mempalace/cli.py``:
-      stdin  -- surrogateescape: malformed input bytes survive as lone
-                surrogates instead of crashing the read.
-      stdout -- replace: extracted fact text can include surrogate
-                halves round-tripped from filenames; replace prevents
-                a UnicodeEncodeError mid-print.
-      stderr -- replace: same protection for warning lines.
     """
-    import sys
+    from ._stdio import reconfigure_stdio_utf8_on_windows
 
-    if sys.platform != "win32":
+    reconfigure_stdio_utf8_on_windows(stdout_errors="replace", stderr_errors="replace")
-        return
-    policies = (
-        ("stdin", "surrogateescape"),
-        ("stdout", "replace"),
-        ("stderr", "replace"),
-    )
-    for name, errors in policies:
-        stream = getattr(sys, name, None)
-        reconfigure = getattr(stream, "reconfigure", None)
-        if reconfigure is None:
-            continue
-        try:
-            reconfigure(encoding="utf-8", errors=errors)
-        except Exception as exc:
-            print(
-                f"WARNING: Could not reconfigure {name} to UTF-8: {exc}",
-                file=sys.stderr,
-            )
 
 
 if __name__ == "__main__":