++

backend/app/services/llm.py

@@ -51,6 +51,9 @@ class LLMClient:
                     response = await self.client.chat.completions.create(**kwargs)
                 await self._track(response.usage)
                 content = response.choices[0].message.content or ""
+                if not content:
+                    finish = getattr(response.choices[0], 'finish_reason', 'unknown')
+                    logger.warning("LLM returned empty content (finish_reason=%s)", finish)
                 return content.strip()
             except Exception as e:
                 if attempt == retries - 1:
@@ -83,16 +86,66 @@ class LLMClient:
 
 def parse_json(text: str) -> dict:
     text = text.strip()
+
+    # Strip modern LLM "thinking" blocks (Anthropic, DeepSeek, etc.) that may
+    # appear either before or around the JSON payload.
+    text = re.sub(r"<think>.*?</think>", "", text, flags=re.DOTALL)
+
+    # Markdown code fence: ```json ... ``` or ``` ... ```
     if text.startswith("```"):
         match = re.search(r"```(?:json)?\s*\n?(.*?)```", text, re.DOTALL)
         if match:
             text = match.group(1).strip()
 
+    # Try the whole text first.
     try:
         return json.loads(text)
     except json.JSONDecodeError:
         pass
 
+    # Otherwise find the first balanced { ... } or [ ... ] substring that parses.
+    def _balanced_at(start: int) -> int | None:
+        open_ch, other_ch = ("{", "}") if text[start] == "{" else (("[", "]") if text[start] == "[" else (None, None))
+        if open_ch is None:
+            return None
+        depth = 0
+        in_str = False
+        esc = False
+        for j in range(start, len(text)):
+            c = text[j]
+            if in_str:
+                if esc:
+                    esc = False
+                elif c == "\\":
+                    esc = True
+                elif c == '"':
+                    in_str = False
+                continue
+            if c == '"':
+                in_str = True
+            elif c == open_ch:
+                depth += 1
+            elif c == other_ch:
+                depth -= 1
+                if depth == 0:
+                    return j
+        return None
+
+    for opener in ("{", "["):
+        i = 0
+        while True:
+            idx = text.find(opener, i)
+            if idx == -1:
+                break
+            end = _balanced_at(idx)
+            if end is not None:
+                try:
+                    return json.loads(text[idx : end + 1])
+                except json.JSONDecodeError:
+                    pass
+            i = idx + 1
+
+    # Last-ditch: trim from the end while we can find a parseable prefix.
     for i in range(len(text) - 1, -1, -1):
         if text[i] in "]}":
             try: