pastilhasandClaude Opus 5
c7b767aa04
Diagnosed across a full night of one session managing another. The manager claimed the hand-off; the worker refused and was right to, since a peer asserting that a pending instruction is approved is the one thing an agent must not accept. Two problems, and only one is about identity. Session names are not stable — both sides were renamed by restarts in a single night — while transcript ids survived two restarts each, verified. So durability is nearly free. Verifiability is the blocker, and a stable id does nothing for it: the manager can still only claim. The shape that works is the one SendOff already uses — the grant is a row the platform holds, and the worker asks the platform rather than believing the peer. Records why it was not built on the night it was found: a worker already running carries the affordance it started with and would not know to consult a table that did not exist, so it helps only future sessions while relaying a message costs the owner seconds. Shipping the table is the easy half. Co-Authored-By: Claude Opus 5 <noreply@anthropic.com>
505 B
505 B
theme, heading, kind
| theme | heading | kind |
|---|---|---|
| agent-coordination | Agents coordinating agents | theme |
One agent made responsible for another's work — writing its prompts, reviewing what it pushed, deciding what comes next — so the owner stops being the clipboard between two chats. The mechanism exists and was used for a whole night on 2026-08-23; what is missing is the part that lets the worker believe it.
See capabilities/affordances/officer/core/coordinating-another-agent.md for what an agent is told today.