Researchers disclosed in August 2026 that encrypted reasoning objects across OpenAI, Anthropic, and Google APIs could be replayed outside their original context. Not just replayed by the same user in a later session. Replayed across users.
Source: [Dev.to](https://dev.to/coridev/when-hidden-reasoning-isnt-hidden-the-openaianthropicgoogle-encrypted-trace-replay-bug-2a5j)