mirror of
https://github.com/openai/codex.git
synced 2026-11-11 21:10:39 +00:00
## What changed Mark `untrusted_as_tool_output` as stable and enable it by default. Untrusted additional context, such as browser information and goal objectives, now reaches the model as `function_call_output` items in the `agent` namespace instead of user messages. Setting `features.untrusted_as_tool_output = false` preserves the message format. ## Testing Update core, app-server, TUI, and Python SDK test expectations for the default output format. Cover context persistence, deduplication, goal continuation, and explicit opt-out behavior. GitOrigin-RevId: 30828351e2ed584928f6055b6dcf276d8288c0fb