LLM 0.37.2 fixes potential OpenAI API key exposure to other providersMachine translation
LLM 发布 0.37.2，修复可能向第三方服务商泄露 OpenAI API 密钥的问题
LLM 0.37.2 fixes two cases that could accidentally send a configured OpenAI API key to another provider: when the key named by api_key_name had never been stored, or when a responses: true model was run with -o chat_completions 1. The issue affects its support for OpenAI-compatible API endpoints from other providers.
The complete source text is not yet available.
Read at the original source