OpenAI adds automatic reviews to Agents API sessions
In brief
OpenAI introduced automatic review for Agents API sessions. Developers can allow a model to evaluate conversation intent and risk to automatically approve or deny tool and permission requests.
How it works
To enable the feature, set a session's review field to auto_review. A model then evaluates supported tool and permission requests based on context, intent, and risk levels. The model automatically approves or denies each request, which incurs additional token billing.
Developers building with the OpenAI Agents API who want automated control over tool and permission approvals.
Availability
Sources
1 merged into this cardMore from OpenAI
GPT-6.2 Sol and Astra added to Codex model catalogs
OpenAI added GPT-6.2 Sol and Astra to the model catalogs in Codex 0.171.0, with Sol set as the default selection.
Remote Sessions in codex exec
OpenAI's Codex CLI now allows users to start or resume noninteractive sessions on an existing app server via the new `codex exec --remote <ADDR>` flag.
OpenAI Codex TUI workspace enabled by default
OpenAI's Codex CLI now enables its TUI workspace by default, showing document previews, image previews, and subagent transcripts beside the main conversation.