From fcae5ad49a3e68f9cae959add21803160f91185d Mon Sep 17 00:00:00 2001
From: kshitijk4poor <82637225+kshitijk4poor@users.noreply.github.com>
Date: Mon, 3 Aug 2026 16:29:56 +0530
Subject: [PATCH] fix(file-ops): surrogatepass in bytes_written encode (review
 finding)

Content that flowed through a surrogateescape decode (backend output via
patch_replace) can carry lone surrogates; a strict encode raises
UnicodeEncodeError where the old wc -c path could not. Mirrors the
existing sha256 verification encode.
---
 tools/file_operations.py | 7 +++++--
 1 file changed, 5 insertions(+), 2 deletions(-)

diff --git a/tools/file_operations.py b/tools/file_operations.py
index 688bdcf8e539e..bd4a5f95de928 100644
--- a/tools/file_operations.py
+++ b/tools/file_operations.py
@@ -1593,8 +1593,11 @@ class ShellFileOperations(FileOperations):
 
         # Get bytes written — compute from the content we just wrote
         # (len(content.encode('utf-8')) matches wc -c for UTF-8) instead
-        # of spawning a ``wc -c`` subprocess.
-        bytes_written = len(content.encode('utf-8'))
+        # of spawning a ``wc -c`` subprocess. ``surrogatepass`` mirrors the
+        # sha256 verification block below: content that flowed through a
+        # surrogateescape decode (backend output via patch_replace) may
+        # carry lone surrogates a strict encode would reject.
+        bytes_written = len(content.encode('utf-8', 'surrogatepass'))
 
         # Post-write content verification (cheap, one shell call): compare
         # the on-disk sha256 to the intended content's hash. Production