From 01332902bbabedf977a8406dacab930d859565d1 Mon Sep 17 00:00:00 2001
From: rootkiller6788 <c8688rickowens@outlook.com>
Date: Thu, 20 Aug 2026 01:23:11 +0800
Subject: [PATCH] Fix escaped-quote detection in JSON cleanup for strings
 ending with a backslash

cleanup_json detected an escaped quote by looking at only the single
preceding character, so a closing quote that follows an escaped backslash
(e.g. a string value ending in a literal backslash) was misread as an
escaped quote. This caused otherwise-valid JSON to fail with 'Malformated
JSON: missing 1 closing curly braces'. Count consecutive backslashes and
treat the quote as escaped only when the count is odd.
---
 langfun/core/structured/schema/json.py      | 18 +++++++++++++++++-
 langfun/core/structured/schema/json_test.py |  5 +++++
 2 files changed, 22 insertions(+), 1 deletion(-)

diff --git a/langfun/core/structured/schema/json.py b/langfun/core/structured/schema/json.py
index cf282a39..ed6c4877 100644
--- a/langfun/core/structured/schema/json.py
+++ b/langfun/core/structured/schema/json.py
@@ -123,6 +123,22 @@ def parse_value(
     return v['result']
 
 
+def _is_unescaped_quote(json_str: str, i: int) -> bool:
+  """Returns True if the quote at position i is not escaped by a backslash.
+
+  In JSON, a double quote is escaped only when it is preceded by an odd number
+  of consecutive backslashes. This distinguishes an escaped quote from a
+  closing quote that follows a literal backslash (e.g. a string value that ends
+  with a backslash).
+  """
+  num_backslashes = 0
+  j = i - 1
+  while j >= 0 and json_str[j] == '\\':
+    num_backslashes += 1
+    j -= 1
+  return num_backslashes % 2 == 0
+
+
 def cleanup_json(json_str: str) -> str:
   """Cleans up the LM responded JSON string."""
   # Treatments:
@@ -151,7 +167,7 @@ def cleanup_json(json_str: str) -> str:
       curly_brackets -= 1
       if curly_brackets == 0:
         break
-    elif c == '"' and json_str[i - 1] != '\\':
+    elif c == '"' and _is_unescaped_quote(json_str, i):
       under_str = not under_str
       if under_str:
         str_begin = i
diff --git a/langfun/core/structured/schema/json_test.py b/langfun/core/structured/schema/json_test.py
index 4a997768..ed6a20f6 100644
--- a/langfun/core/structured/schema/json_test.py
+++ b/langfun/core/structured/schema/json_test.py
@@ -104,6 +104,11 @@ def test_parse_with_new_lines(self):
         """,
         ['foo\nbar'])
 
+  def test_parse_with_escaped_backslash(self):
+    # A string value ending with a literal backslash must not be mistaken for
+    # an escaped closing quote. `{"result": "C:\\"}` parses to `C:\`.
+    self.assert_parse_value('{"result": "C:\\\\"}', 'C:\\')
+
   def test_parse_with_malformated_json(self):
     with self.assertRaisesRegex(
         json.JsonError, 'No JSON dict in the output'