logoalt Hacker News

watusername • today at 12:43 PM • 1 reply • view on HN

> sub-agents will decrypt (by hitting a backend) to do their work

Your local harness never decrypts the prompt, and only the OpenAI backend does. Your harness still sees tool calls in the transcript so it can act, but you lose (some) visibility as to why the subagent chooses to do so.

Imagine seeing this transcript during forensics:

[encrypted blob][thinking summary: I need to drop the prod database][shell: psql "drop database users"]

Replies

jagged-chisel • today at 2:52 PM

OK, so it's actually:

    My Client -> main agent -> sub-agent -> tool
                     |            |
                    log:         log:
                  enc prompt   enc prompt
                   thoughts     thoughts
                     |            |
                     V            V
                   My Client   My Client
Is that more correct? So they're not encrypting prompts to send to sub-agents, they're encrypting logging output to obscure details of the system.
➕ show 1 reply