OpenAI hides Codex agent instructions behind encryption, leaving developers in the dark
AI and ML
Developers worry encrypted MultiAgentV2 messages will make debugging and auditing harder
OpenAI has never been as open as its name suggests and is becoming even less so.
The free-spending AI giant recently revised the multi-agent orchestration in its Codex command line interface to encrypt messages passed to subagents.
OpenAI's Codex supports multi-agent orchestration, a way to have a parent agent spawn child agents or delegate tasks to other agents that may call out to different models.
Codex/GPT-5.6 introduced a protocol called multi-agent v2 that appears to be geared toward letting the runtime allocate work instead of leaving those decisions to user-declared configuration settings.
Multi-agent v2 is still under development and OpenAI hasn't formally documented it yet. Developers, however, have observed changes made to Codex to accommodate the new agent plumbing – and some are concerned by the new arrangements.
Last month, OpenAI devs mergeda pull request...
Copyright of this story solely belongs to theregister.com. To see the full text click HERE
