Files
fleetd/docs
Dai Ha 9b8d55bc18 CB-500: design note — multi-tier coordination (Stage 6)
Scopes the lead's next direction on top of the peer-launcher arc, as a
proposal (ticket split deferred):
- A · sandboxed, role-specific workers — a sandbox is a *placement*, so it
  slots into the CB-401 SPI as a new kind: sandbox adapter exactly the way
  CB-402's opencode slotted in as a new provider (SPI proven placement-neutral,
  not just provider-neutral). Ownership line held: bridge launches INTO a
  peer-owned image, never provisions the IDE/dev-tools inside it.
- B · main-agent pairs (Opus + cloud) — both mains are MCP clients so neither
  can be called into; each needs a pull inbox → depends on CB-308's per-agent
  channels. PrimaryRegistry single-slot → multi-slot.
- C · orchestrator tier — SessionManager recursed one tier up
  (orchestrator:mains :: main:workers) + context scoping; re-roots the human
  from a live primary to the orchestrator.

10 mermaid diagrams (component + sequence per development, ownership guardrail,
staging graph), all mmdc-validated and theme-safe. §7 pins the bus-vs-env-manager
boundary as an acceptance criterion on A; §8 stages A → CB-308 substrate → B → C.
2026-07-28 15:20:16 +02:00
..
2026-07-14 12:30:20 +07:00
2026-07-14 19:14:25 +07:00