OpenAI structured output and background mode for long reasoning
A direct model call can require a reply that matches a JSON Schema. Everruns
sends it as text.format on the OpenAI Responses API and response_format on
Chat Completions. A driver that cannot enforce the schema refuses the call
instead of dropping it.
Calls at xhigh and max reasoning effort on OpenAI and Azure run as
background responses. If the stream drops or the worker restarts, Everruns
picks the response back up instead of paying for it twice. A cancelled turn
cancels the response, and the openai/background driver option overrides the
policy.