Since early June, users have reported that OpenAI changed OpenAI Codex’s experimental `multi_agent_v2` workflow so the prompts and messages passed from a main agent to its sub-agents are now encrypted. In practical terms, the plain-text handoff details that used to appear in session logs no longer show up there. You can still see the outcomes, but not the exact internal instructions behind a task split, a mistake, or a failed run.
Those same reports say the change is required for the larger GPT-5.6 Sol and Terra variants. The lighter Luna model, at least for now, doesn’t appear to be affected.
If you use OpenAI Codex for more complex coding work, this matters. Once those readable inter-agent logs disappear, debugging gets harder. It can also create problems around audit trails, security, compliance, change management, and simple trust, especially for regulated teams, sensitive codebases, and customer-facing systems.
OpenAI hasn’t given a direct reason for the change beyond broad documentation about encryption at rest and in transit. So the guesses have filled the gap: model distillation, unauthorized API pooling, data harvesting, or an effort to protect proprietary orchestration methods.
You can access OpenAI Codex, including the experimental `multi_agent_v2` mode, through the Codex CLI in OpenAI’s developer tooling.
Author: Sharilyn Deseo
{
"social": {
"email": "",
"facebook": "",
"twitter": "",
"linkedin": ""
},
"ja-JP": "",
"de-DE": "Sharilyn Deseo ist Content-Writerin und Rezensentin, die sich auf Software und digitale Tools spezialisiert hat. Sie bewertet Anwendungen kritisch und gibt Nutzern klare Einblicke, bevor sie eine Entscheidung treffen.",
"en-US": "Sharilyn Deseo is a content writer and reviewer specializing in software and digital tools. She critically evaluates applications and provides users with clear insights before they commit to a download or purchase.",
"es-ES": "Sharilyn Deseo es redactora y reseñadora especializada en software y herramientas digitales. Evalúa aplicaciones de forma crítica y ofrece a los usuarios información clara antes de tomar una decisión de descarga o compra.",
"fr-FR": "Sharilyn Deseo est rédactrice et critique spécialisée dans les logiciels et les outils numériques. Elle évalue de manière critique les applications et fournit aux utilisateurs des informations claires avant tout téléchargement ou achat.",
"it-IT": "Sharilyn Deseo è una content writer e recensore specializzata in software e strumenti digitali. Valuta criticamente le applicazioni e fornisce agli utenti informazioni chiare prima di procedere con download o acquisti.",
"nl-NL": "Sharilyn Deseo is een content writer en recensent gespecialiseerd in software en digitale tools. Ze beoordeelt applicaties kritisch en geeft gebruikers duidelijke inzichten voor ze een download- of aankoopbeslissing nemen.",
"pl-PL": "Sharilyn Deseo jest content writerką i recenzentką specjalizującą się w oprogramowaniu i narzędziach cyfrowych. Krytycznie ocenia aplikacje i dostarcza użytkownikom jasnych informacji przed podjęciem decyzji o pobraniu lub zakupie.",
"pt-BR": "Sharilyn Deseo é redatora e revisora especializada em software e ferramentas digitais. Ela avalia aplicativos de forma criteriosa e oferece aos usuários informações claras antes de baixar ou comprar."
}
View all posts by Sharilyn Deseo
