# OpenAI structured output and background mode for long reasoning

> OpenAI drivers enforce JSON Schema structured output, and xhigh or max reasoning calls run as background responses that resume after a drop or worker restart.

Source: <https://everruns.com/docs/changelog/2026-10-01-openai-structured-output-background/>

Date: 2026-10-01
Products: Platform, Cloud, Framework
Category: Feature
Available: In 0.34.0
Pull request: everruns/everruns#3932
Pull request: everruns/everruns#3969

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.

See [OpenAI](https://everruns.com/docs/providers/openai/). PRs [#3932](https://github.com/everruns/everruns/pull/3932), [#3969](https://github.com/everruns/everruns/pull/3969).