openai

api: expand Live Decision item and question types. Breaking change in a minor release. Live Decision item events now include messages and function/custom-tool calls and outputs. DecisionItemCreatedEvent.item and DecisionItemCreateEvent.item are unions, so callers that directly access item.content or item.role may no longer compile. For both event types, use if ('content' in event.item) before accessing message fields, and handle tool-item variants separately. Message items may omit type, so checking only item.type === 'message' can skip valid messages. This release also updates image-model documentation: gpt-image-1 was shut down on October 23, 2026; replace explicit selections with gpt-image-2.5-sunburst or gpt-image-2.5-flare. The documented default for Responses image-generation tools is now gpt-image-2; specify a supported model explicitly when you need a particular model.

api: Breaking change in a minor release. A Live response's Decisions question instructions can now be a string or an array of text, image, or JSON parts. Code such as question.instructions.trim() can fail when it receives an array; check typeof question.instructions === 'string' and handle the array case. Decisions request inputs also accept new message roles and tool-history items, so update code that assumes it knows every input type. DecisionInputMessage is now a union: code that extends or implements the old interface must use DecisionInputMessage.DecisionInputUserMessage instead. Existing string instructions and user-message inputs still work.