LLM 0.37.2 fixes two bugs that could leak OpenAI API keys to other providers
AISimon Willison releases LLM 0.37.2 to fix two security issues reported by Daniel de Araujo. The bugs could accidentally send a configured OpenAI API key to an OpenAI-compatible endpoint from another provider, either when the key named by api_key_name was never stored or when a responses: true model runs with -o chat_completions 1.