From b2230cf4f2e41d6fbe694986ae3a6ffc708b1388 Mon Sep 17 00:00:00 2001
From: sandikodev <androxoss@hotmail.com>
Date: Sat, 4 Apr 2026 20:48:06 +0700
Subject: [PATCH] fix(chat): prevent panic on UTF-8 boundary when rendering
 response

When the AI response contains multi-byte characters (e.g. non-ASCII
text adjacent to triple backticks), the byte offset accumulated via
parsed.offset_from() can land in the middle of a UTF-8 character
boundary. The subsequent &buf[offset..] slice then panics at runtime.

The same pattern existed in two places:
- crates/chat-cli/src/cli/chat/mod.rs  (streaming response loop)
- crates/chat-cli/src/cli/chat/parse.rs (validate! test macro loop)

Replace the direct slice with .get(offset..) which returns None
instead of panicking, and break the loop gracefully.

Add a regression test with Indonesian, Chinese, and emoji inputs
adjacent to triple backticks to verify no panic occurs.

Fixes #3715
---
 crates/chat-cli/src/cli/chat/mod.rs   |  6 +++-
 crates/chat-cli/src/cli/chat/parse.rs | 41 ++++++++++++++++++++++++++-
 2 files changed, 45 insertions(+), 2 deletions(-)

diff --git a/crates/chat-cli/src/cli/chat/mod.rs b/crates/chat-cli/src/cli/chat/mod.rs
index 099c0c8761..2599ea9e61 100644
--- a/crates/chat-cli/src/cli/chat/mod.rs
+++ b/crates/chat-cli/src/cli/chat/mod.rs
@@ -3099,7 +3099,11 @@ impl ChatSession {
 
             // Print the response for normal cases
             loop {
-                let input = Partial::new(&buf[offset..]);
+                // Use `get` to avoid panicking if `offset` lands on a non-UTF-8 boundary,
+                // which can happen when the response contains multi-byte characters (e.g.
+                // non-ASCII text adjacent to triple backticks). See: #3715
+                let Some(slice) = buf.get(offset..) else { break };
+                let input = Partial::new(slice);
                 if self.stdout.should_send_structured_event {
                     match interpret_markdown(input, &mut temp_buf, &mut state) {
                         Ok(parsed) => {
diff --git a/crates/chat-cli/src/cli/chat/parse.rs b/crates/chat-cli/src/cli/chat/parse.rs
index cf457b56f3..5a5013107b 100644
--- a/crates/chat-cli/src/cli/chat/parse.rs
+++ b/crates/chat-cli/src/cli/chat/parse.rs
@@ -672,7 +672,8 @@ mod tests {
                 let mut offset = 0;
 
                 loop {
-                    let input = Partial::new(&input[offset..]);
+                    let Some(slice) = input.get(offset..) else { break };
+                    let input = Partial::new(slice);
                     match interpret_markdown(input, &mut presult, &mut state) {
                         Ok(parsed) => {
                             offset += parsed.offset_from(&input);
@@ -824,4 +825,42 @@ mod tests {
         [style::Print("+ % @ . ?")],
         true
     );
+
+    /// Regression test for #3715: multi-byte UTF-8 characters adjacent to triple backticks
+    /// must not cause a panic from byte-index slicing.
+    #[test]
+    fn multibyte_utf8_adjacent_to_triple_backticks_does_not_panic() {
+        // Indonesian / non-ASCII text followed by a code fence — the combination that
+        // triggered "byte index N is out of bounds" in the wild.
+        let inputs = [
+            "Benar. Ganti dengan deskripsi langsung. Gunakan ini:\n\n```\ncontoh kode\n```",
+            "移除 eagleeye-ec-databases 任務狀況確認\n```bash\necho ok\n```",
+            "emoji 🎉 before ``` fence ```",
+        ];
+
+        for raw in inputs {
+            let mut input = raw.to_owned();
+            input.push_str("  "); // simulate incomplete stream sentinel
+
+            let mut state = ParseState::new(Some(80), Some(false));
+            let mut out = vec![];
+            let mut offset = 0;
+
+            loop {
+                let Some(slice) = input.get(offset..) else { break };
+                let partial = Partial::new(slice);
+                match interpret_markdown(partial, &mut out, &mut state) {
+                    Ok(parsed) => {
+                        offset += parsed.offset_from(&partial);
+                        state.newline = state.set_newline;
+                        state.set_newline = false;
+                    },
+                    Err(err) => match err.into_inner() {
+                        Some(err) => panic!("parse error on input {:?}: {err}", raw),
+                        None => break,
+                    },
+                }
+            }
+        }
+    }
 }