issues with chat returning 2 of the same message

llama_index/chat_engine/simple.py
@trace_method("chat")
    def chat(
        self, message: str, chat_history: Optional[List[ChatMessage]] = None
    ) -> AgentChatResponse:
        if chat_history is not None:
            self._memory.set(chat_history)
        self._memory.put(ChatMessage(content=message, role="user"))
        initial_token_count = len(
            self._memory.tokenizer_fn(
                " ".join([(m.content or "") for m in self._prefix_messages])
            )
        )
        all_messages = self._prefix_messages + self._memory.get(
            initial_token_count=initial_token_count
        )
        print("==================")
        print(all_messages)
        print("==================")
        chat_response = self._llm.chat(all_messages)
        ai_message = chat_response.message
        self._memory.put(ai_message)

        return AgentChatResponse(response=str(chat_response.message.content))

...
  chat_engine = get_simple_chat_engine(history, model)
          response = run_with_fallback(chat_engine.stream_chat, chat_engine.chat, message)
...
def get_simple_chat_engine(history: List[ChatMessage], model: ChatLLM):
    service_context = get_service_context(model=model)
    chat_engine = SimpleChatEngine.from_defaults(
        service_context=service_context, chat_history=history
    )
    return chat_engine

        print(chat_history, message)
        if chat_history is not None:
            self._memory.set(chat_history)
        self._memory.put(ChatMessage(content=message, role="user"))
        initial_token_count = len(
            self._memory.tokenizer_fn(
                " ".join([(m.content or "") for m in self._prefix_messages])
            )
        )
        all_messages = self._prefix_messages + self._memory.get(
            initial_token_count=initial_token_count
        )

User: Hello
User: Hello
Assistant:

>>> from llama_index.chat_engine import SimpleChatEngine
>>> engine = SimpleChatEngine.from_defaults()
>>> engine.chat("Hello!", chat_history=[])
> /Users/loganmarkewich/llama_index_next/llama_index/chat_engine/simple.py(79)chat()
-> if chat_history is not None:
(Pdb) chat_history
[]

engine = SimpleChatEngine.from_defaults(history=[])

   
 chat_engine = SimpleChatEngine.from_defaults(
        service_context=service_context, chat_history=history
    )

>>> from llama_index.chat_engine import SimpleChatEngine
>>> engine = SimpleChatEngine.from_defaults(chat_history=[])
>>> engine.chat("Hello!")
> /Users/loganmarkewich/llama_index_next/llama_index/chat_engine/simple.py(90)chat()
-> chat_response = self._llm.chat(all_messages)
(Pdb) len(all_messages)
1

chat_engine = get_simple_chat_engine(history, model)
print("history", history) # []
response = run_with_fallback(
  chat_engine.stream_chat, chat_engine.chat, message, chat_history=history

@trace_method("chat")
def chat(
    self, message: str, chat_history: Optional[List[ChatMessage]] = None
) -> AgentChatResponse:
    print("======== start of simple chat =======")
    print(chat_history, message) # [ChatMessage(role=<MessageRole.USER: 'user'>, content='hello\n', additional_kwargs={})] hello
    if chat_history is not None:
        self._memory.set(chat_history)
    self._memory.put(ChatMessage(content=message, role="user"))
    initial_token_count = len(
        self._memory.tokenizer_fn(
            " ".join([(m.content or "") for m in self._prefix_messages])
        )
    )
    all_messages = self._prefix_messages + self._memory.get(
        initial_token_count=initial_token_count
    )
    print("==================")
    print(all_messages)
    print("==================")
    chat_response = self._llm.chat(all_messages)
    ai_message = chat_response.message
    self._memory.put(ai_message)
    print("======== end of simple chat =======")
    return AgentChatResponse(response=str(chat_response.message.content))

==================
[ChatMessage(role=<MessageRole.USER: 'user'>, content='hello\n', additional_kwargs={}), ChatMessage(role=<MessageRole.USER: 'user'>, content='hello\n', additional_kwargs={})]
==================

response = run_with_fallback(
            primary_fn=chat_engine.stream_chat,
            fallback_fn=chat_engine.chat,
            message=message,
        )