langchain + xinference llm.with_structured_output Probabilistic error reporting occurs under high concurrency

[berserker3912]

vllm 0.11.0 xinference 1.17.0 langchain 1.2.6 qwen3-install-30b

class DicInfo(BaseModel):
"""xxxx"""
category: StateType = Field(description="xxxx")
confidence: Optional[float] = Field(
default=0.0,
ge=0.0,
le=1.0,
description="xxxx"
)
detail_categories: Optional[List[str]] = Field(
default_factory=list,
description="xxxx"
)

structured_llm = llm.with_structured_output(DicInfo)
messages = [SystemMessage(content=system_prompt), HumanMessage(content=f"{user_input}")]
final_answer = structured_llm.invoke(messages)

Traceback (most recent call last):
File "/xxxx/xxxx.py", line 130, in classification_execution
final_answer = structured_llm.invoke(messages)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/xxxx/site-packages/langchain_core/runnables/base.py", line 3149, in invoke
input_ = context.run(step.invoke, input_, config, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/xxxx/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 402, in invoke
self.generate_prompt(
File "/xxxx/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 1121, in generate_prompt
return self.generate(prompt_messages, stop=stop, callbacks=callbacks, **kwargs)
^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/xxxx/site-packages/langchain_core/language_models/chat_models.py", line 931, in generate
self._generate_with_cache(
File "/xxxx/lib/python3.12/site-packages/langchain_core/language_models/chat_models.py", line 1225, in _generate_with_cache
result = self._generate(
^^^^^^^^^^^^^^^
File "/xxxx/lib/python3.12/site-packages/langchain_xinference/chat_models.py", line 226, in _generate
final_chunk = self._chat_with_aggregation(
^^^^^^^^^^^^^^^^^^^^^^^^^^^^
File "/xxxx/lib/python3.12/site-packages/langchain_xinference/chat_models.py", line 310, in _chat_with_aggregation
for stream_resp in response:
^^^^^^^^
File "/xxxx/lib/python3.12/site-packages/xinference/client/common.py", line 62, in streaming_response_iterator
raise Exception(str(error))
Exception: [address=127.0.0.1:39175, pid=167075] Expecting ',' delimiter: line 3 column 1 (char 120)