From 313ee3003b5bd527f10df66e849073c9b843a9f9 Mon Sep 17 00:00:00 2001
From: David Gilbertson <gilbertson.david@gmail.com>
Date: Tue, 27 Jan 2026 10:11:27 +1100
Subject: [PATCH] fix: handle utf-8 in windows sandbox logs (#8647)

Currently `apply_patch` will fail on Windows if the file contents happen
to have a multi-byte character at the point where the `preview` function
truncates.

I've used the existing `take_bytes_at_char_boundary` helper and added a
regression test (that fails without the fix).

This is related to #4013 but doesn't fix it.
---
 codex-rs/Cargo.lock                        |  1 +
 codex-rs/windows-sandbox-rs/Cargo.toml     |  1 +
 codex-rs/windows-sandbox-rs/src/logging.rs | 20 +++++++++++++++++++-
 3 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/codex-rs/Cargo.lock b/codex-rs/Cargo.lock
index d0b3a0ec3..836854b0e 100644
--- a/codex-rs/Cargo.lock
+++ b/codex-rs/Cargo.lock
@@ -2006,6 +2006,7 @@ dependencies = [
  "chrono",
  "codex-protocol",
  "codex-utils-absolute-path",
+ "codex-utils-string",
  "dirs-next",
  "dunce",
  "pretty_assertions",
diff --git a/codex-rs/windows-sandbox-rs/Cargo.toml b/codex-rs/windows-sandbox-rs/Cargo.toml
index aa872035b..f92c389e4 100644
--- a/codex-rs/windows-sandbox-rs/Cargo.toml
+++ b/codex-rs/windows-sandbox-rs/Cargo.toml
@@ -25,6 +25,7 @@ chrono = { version = "0.4.42", default-features = false, features = [
     "std",
 ] }
 codex-utils-absolute-path = { workspace = true }
+codex-utils-string = { workspace = true }
 dunce = "1.0"
 serde = { version = "1.0", features = ["derive"] }
 serde_json = "1.0"
diff --git a/codex-rs/windows-sandbox-rs/src/logging.rs b/codex-rs/windows-sandbox-rs/src/logging.rs
index 2e4de1d29..f575ce3b8 100644
--- a/codex-rs/windows-sandbox-rs/src/logging.rs
+++ b/codex-rs/windows-sandbox-rs/src/logging.rs
@@ -4,6 +4,8 @@ use std::path::Path;
 use std::path::PathBuf;
 use std::sync::OnceLock;
 
+use codex_utils_string::take_bytes_at_char_boundary;
+
 const LOG_COMMAND_PREVIEW_LIMIT: usize = 200;
 pub const LOG_FILE_NAME: &str = "sandbox.log";
 
@@ -22,7 +24,7 @@ fn preview(command: &[String]) -> String {
     if joined.len() <= LOG_COMMAND_PREVIEW_LIMIT {
         joined
     } else {
-        joined[..LOG_COMMAND_PREVIEW_LIMIT].to_string()
+        take_bytes_at_char_boundary(&joined, LOG_COMMAND_PREVIEW_LIMIT).to_string()
     }
 }
 
@@ -72,3 +74,19 @@ pub fn log_note(msg: &str, base_dir: Option<&Path>) {
     let ts = chrono::Local::now().format("%Y-%m-%d %H:%M:%S%.3f");
     append_line(&format!("[{ts} {}] {}", exe_label(), msg), base_dir);
 }
+
+#[cfg(test)]
+mod tests {
+    use super::*;
+
+    #[test]
+    fn preview_does_not_panic_on_utf8_boundary() {
+        // Place a 4-byte emoji such that naive (byte-based) truncation would split it.
+        let prefix = "x".repeat(LOG_COMMAND_PREVIEW_LIMIT - 1);
+        let command = vec![format!("{prefix}😀")];
+        let result = std::panic::catch_unwind(|| preview(&command));
+        assert!(result.is_ok());
+        let previewed = result.unwrap();
+        assert!(previewed.len() <= LOG_COMMAND_PREVIEW_LIMIT);
+    }
+}