From aa467e9b3c7d61cdce9938b4da79368ae58fe173 Mon Sep 17 00:00:00 2001
From: Levi Neely <141506390+lneely@users.noreply.github.com>
Date: Sat, 18 Jul 2026 16:15:10 +0200
Subject: [PATCH] tools: explicit UTF-8 encoding for file_read, file_write,
 file_edit

---
 tools/file_edit  | 11 ++++++++---
 tools/file_read  | 22 ++++++++++++++++------
 tools/file_write | 10 +++++++---
 3 files changed, 31 insertions(+), 12 deletions(-)

diff --git a/tools/file_edit b/tools/file_edit
index d7d871c..f0e70fe 100644
--- a/tools/file_edit
+++ b/tools/file_edit
@@ -101,8 +101,13 @@ if not os.path.exists(file_path):
     print(f"error: file not found: {file_path}")
     sys.exit(1)
 
-with open(file_path, 'r', errors='replace') as f:
-    original = f.read()
+try:
+    with open(file_path, 'r', encoding='utf-8') as f:
+        original = f.read()
+except UnicodeDecodeError:
+    print(f"STATUS=error STATE_CHANGED=false RETRYABLE=false")
+    print(f"error: file is not valid UTF-8: {file_path}")
+    sys.exit(1)
 
 new_content, err, retryable = robust_replace(original, old_string, new_string, replace_all)
 if err:
@@ -111,7 +116,7 @@ if err:
     sys.exit(1)
 
 try:
-    with open(file_path, 'w') as f:
+    with open(file_path, 'w', encoding='utf-8') as f:
         f.write(new_content)
 except OSError as e:
     print(f"STATUS=error STATE_CHANGED=false RETRYABLE=false")
diff --git a/tools/file_read b/tools/file_read
index 1cc84cf..bcada32 100644
--- a/tools/file_read
+++ b/tools/file_read
@@ -62,8 +62,12 @@ with open(file_path, 'rb') as f:
         sys.exit(0)
 
 # Count total lines
-with open(file_path, 'r', errors='replace') as f:
-    total_lines = sum(1 for _ in f)
+try:
+    with open(file_path, 'r', encoding='utf-8') as f:
+        total_lines = sum(1 for _ in f)
+except UnicodeDecodeError:
+    with open(file_path, 'r', encoding='utf-8', errors='replace') as f:
+        total_lines = sum(1 for _ in f)
 
 start = max(1, start)
 if head:
@@ -73,10 +77,16 @@ elif end is None:
 else:
     end = min(end, start + MAX_SEGMENT - 1)
 
-with open(file_path, 'r', errors='replace') as f:
-    for _ in islice(f, start - 1):
-        pass
-    segment_lines = list(islice(f, end - start + 1))
+try:
+    with open(file_path, 'r', encoding='utf-8') as f:
+        for _ in islice(f, start - 1):
+            pass
+        segment_lines = list(islice(f, end - start + 1))
+except UnicodeDecodeError:
+    with open(file_path, 'r', encoding='utf-8', errors='replace') as f:
+        for _ in islice(f, start - 1):
+            pass
+        segment_lines = list(islice(f, end - start + 1))
 
 if not segment_lines:
     if start == 1:
diff --git a/tools/file_write b/tools/file_write
index 6797d6b..76c54e2 100644
--- a/tools/file_write
+++ b/tools/file_write
@@ -34,11 +34,15 @@ if parent and not os.path.isdir(parent):
 
 old_content = ""
 if os.path.exists(file_path):
-    with open(file_path, 'r', errors='replace') as f:
-        old_content = f.read()
+    try:
+        with open(file_path, 'r', encoding='utf-8') as f:
+            old_content = f.read()
+    except UnicodeDecodeError:
+        with open(file_path, 'r', encoding='utf-8', errors='replace') as f:
+            old_content = f.read()
 
 try:
-    with open(file_path, 'w') as f:
+    with open(file_path, 'w', encoding='utf-8') as f:
         f.write(content)
 except OSError as e:
     print(f"STATUS=error STATE_CHANGED=false RETRYABLE=false")