Agent teams: state machines that drive multi-agent work (v1.17.0 to v1.19.2)

Loomcycle released multi-agent team workflows as a state-machine primitive in versions 1.17.0 to 1.19.2, enabling deterministic and LLM-driven execution with human-in-the-loop interruptions. The update includes parallel fan-out, durable boards, and starter templates for SDLC and marketing teams.

RFC AP + RFC BD add a first-class multi-agent workflow primitive to loomcycle. A TeamDef is a state-machine graph over your agents: states, transitions success / pushback: / conditional:, bounded by a per-state max iterations , and per-state handlers agent | parallel + consolidator | consolidator | terminal . Content-addressed, tenant-scoped, versioned — peer of AgentDef / SkillDef / VolumeDef. Two drivers run the same graph: a deterministic op=run walk engine pure Go, testable end to end, right for scheduled/headless pipelines and the bundled LLM team/orchestrator agent reads the graph as its map, drives transitions, keeps a human in the loop through the Interruption tool . The Web UI teams board is a two-pane editor with graph JSON on the left, a live Mermaid state diagram on the right, dry-run render on unsaved edits no persist , a draggable splitter, a starter-template dropdown, and a tenant-scoped delete op. v1.19.0 filled the deferrals: parallel fan-out plus consolidator execution in the deterministic engine three wait modes: all, any, at least:N , durable Document-backed boards that survive restarts board chunk id , interrupt-on-cap that escalates an iteration-cap overflow to a human with continue / reroute / abort options, gRPC RPC + @loomcycle/client + Python adapter methods at 1.19.0 parity, and per-tenant credentials for raw Bash via LOOMCYCLE BASH ALLOWED CREDS. v1.19.1 made the Interruption tool self-enable on tool-list presence. v1.19.2 added startup warnings for empty capability gates and caught three shipped-bundle bugs. Two starter teams SDLC and marketing ship in the team-examples bundle.