Does it make sense to _also_ have a way for orchestrators/ops to pose

Dispatch

canonical · plan

Spec

markdown

hand-off · dispatch

Auto-dispatch

when it reaches planned

Design-loop

design pass before build

target project worktree · optional branch · optional agent tool · optional session id · optional

kind

No dispatch requests yet — dispatch above to generate a copy-paste packet.

provenance · append-only

live

note added 4d ago

Does it make sense to _also_ have a way for orchestrators/ops to pose questions to the human? ie: orchestrator is operating through things, comes into a situation where it needs some feedback/direction from the human but then also the loops keep going and it's now working on something else and the human never saw the messages about feedback/input... how does that ever get resolved? So should those messages for input/feedback go into some sort of queue like the orchestrator inbox so they can be addressed at some point by the human? (and maybe used as a nagging trailer on orchestrator messages until it's done? or some alerts/change of navbar color in flower/etc?)

operator · operator:mike
participant joined 4d ago
system · operator:mike

epic · dependencies

epic parent

depends on

No dependencies — dispatchable once planned.

agents · waves

trace · graph

No links yet — they accrue as agents work the brief.

scope

dogfood · read-only

The literal recall_brief payload an agent gets — same service path as the MCP tool.