fix serving issues when requesting real data

qwen3_6_scripts/chat_utils.py

@@ -113,6 +113,11 @@ class ConversationMessage(TypedDict, total=False):
     tool_calls: Optional[Iterable[ChatCompletionMessageToolCallParam]]
     """The tool calls generated by the model, such as function calls."""
 
+    reasoning_content: Optional[str]
+    """Reasoning / thinking content for assistant messages.
+    Passed directly to the chat template (Qwen3 reads message.reasoning_content
+    natively) instead of being manually wrapped in <think>...</think>."""
+
 
 ModalityStr = Literal["image", "audio", "video"]
 _T = TypeVar("_T")
@@ -480,15 +485,13 @@ def _parse_chat_message_content(
             if "tool_calls" in parsed_msg:
                 result_msg["tool_calls"] = list(parsed_msg["tool_calls"])
 
-            # Prepend reasoning_content as <think>...</think> so the model
-            # sees its own chain-of-thought in multi-turn conversations.
-            reasoning = message.get("reasoning_content")  # type: ignore[arg-type]
+            # Pass reasoning content as a dedicated field so the chat template
+            # can render it natively (Qwen3: message.reasoning_content branch).
+            # Accept both "reasoning" (new vllm) and "reasoning_content" (ours).
+            reasoning = (message.get("reasoning")  # type: ignore[arg-type]
+                         or message.get("reasoning_content"))  # type: ignore[arg-type]
             if reasoning and isinstance(reasoning, str):
-                existing = result_msg.get("content") or ""
-                result_msg["content"] = (
-                    f"<think>{reasoning}</think>\n\n{existing}"
-                    if existing else f"<think>{reasoning}</think>"
-                )
+                result_msg["reasoning_content"] = reasoning
 
         elif role == "tool":
             parsed_msg = _ToolParser(message)