Update openai.py

[MrEchoFi]

• PR title: fix(community): mask openai_api_key in ChatOpenAI.__repr__to_prevent_leakage

• PR message:

  • Description: This PR prevents accidental leakage of OpenAI API keys when printing or logging
    ChatOpenAI instances by overriding __repr__ to mask the openai_api_key
    field.

This affects common usage patterns such as:

• print(llm)

• logging model objects

• debugging in notebooks or error traces

• Lint and test:

• current version of code-

from langchain_community.chat_models import ChatOpenAI

llm = ChatOpenAI(api_key="FAKEKEY123", model="gpt-4o")
print(llm)

• Current version output:

lm = ChatOpenAI(api_key="FAKEKEY123", model="gpt-4o")
client=<openai.resources.chat.completions.completions.Completions object at 0x7593c05cee40> async_client=<openai.resources.chat.completions.completions.AsyncCompletions object at 0x7593c05cf8c0> model_name='gpt-4o' model_kwargs={} openai_api_key='FAKEKEY123' openai_proxy=''

• After Fix via this:

  def __repr__(self) -> str:
        """Safe string representation that avoids leaking API keys."""
        masked_key = "***" if self.openai_api_key else None
        return (
            f"ChatOpenAI("
            f"model_name={self.model_name!r}, "
            f"openai_api_key={masked_key}, "
            f"openai_proxy={self.openai_proxy!r})"
        )
  

### OUTPUT->    ChatOpenAI(model_name='gpt-4o', openai_api_key='***', openai_proxy='')