v1.0.166: aggressive JSON repair — close unterminated strings/braces

deploy/services/classify.py

@@ -98,31 +98,53 @@ def classify_batch(batch_id):
 
 
 def _safe_json_parse(raw):
-    """Parse LLM response, fixing common JSON errors (multiline, markdown, unescaped chars)."""
+    """Parse LLM response, fixing common JSON errors."""
     if not raw:
         raise ValueError("empty LLM response")
 
-    # Strip markdown wrappers
     text = raw.strip()
+    # Strip markdown
     if "```json" in text:
         text = text.split("```json")[1].split("```")[0].strip()
     elif "```" in text:
         text = text.split("```")[1].split("```")[0].strip()
 
-    # Try strict parse first
+    # Remove non-JSON prefix/suffix (LLM chatter)
+    brace_start = text.find("{")
+    brace_end = text.rfind("}")
+    if brace_start >= 0 and brace_end > brace_start:
+        text = text[brace_start:brace_end + 1]
+
+    # Try strict parse
     try:
         return json.loads(text)
     except json.JSONDecodeError:
         pass
 
-    # Fix common issues: unescaped newlines inside strings, unterminated strings
-    # Replace literal newlines inside JSON values
     import re as _re
-    # Collapse multiline to single line
+    # Collapse multiline
-    text = _re.sub(r'\n\s*', ' ', text)
+    text = _re.sub(r"\n\s*", " ", text)
-    # Remove trailing commas before closing braces
+    # Remove trailing commas
-    text = _re.sub(r',\s*}', '}', text)
+    text = _re.sub(r",\s*}", "}", text)
-    text = _re.sub(r',\s*]', ']', text)
+    text = _re.sub(r",\s*]", "]", text)
+
+    # Try again
+    try:
+        return json.loads(text)
+    except json.JSONDecodeError:
+        pass
+
+    # Aggressive: try adding missing closing quotes/braces
+    text = text.rstrip()
+    if not text.endswith("}"):
+        # Count unclosed quotes
+        in_string = False
+        for i, ch in enumerate(text):
+            if ch == '"' and (i == 0 or text[i-1] != "\\"):
+                in_string = not in_string
+        if in_string:
+            text += '"'
+        text += "}"
 
     return json.loads(text)