The two tests that wait for two children IN FLIGHT (the pipeline no-barrier test and the dropped-promise cancellation test) inherited the engine's auto-resolved maxConcurrentAgents, which is min(16, max(1, cores - 2)) — exactly 1 on the 2-core CI runner, so the second child never started and vi.waitFor timed out. Reproduced locally under taskset -c 0,1; the full spec passes there with the helper pinning a fixed ceiling. Tests about the ceiling itself keep their explicit overrides, and the auto-resolve arm stays covered by the default-config provider tests.
workflow/ — dynamic-workflow capability family
The workflow seam: a model-written JavaScript orchestration script that fans out subagents at scale (phases, structured per-agent results, concurrency caps), modeled on Claude Code's dynamic workflows. A capability seam (see capability seams) in the bash shape: ONE engine implementation per context registers as ctx.workflows; the model-facing tool consumes it.
| Package | Role | ctx key |
|---|---|---|
workflow/ |
Abstract workflow seam: service base class + run vocabulary + workflow/* events |
ctx.workflows |
workflow-vm/ |
In-process node:vm engine: parses the script, injects the hooks, drives ctx.subagents |
(provides ctx.workflows) |
tool-workflow/ |
Model-facing workflow tool over ctx.workflows |
(registers on ctx.tools) |
The interface lives at workflow/workflow/. The engine's agent() hook rides the subagent seam (any registered provider; the shipped examples use spawn), and agent({ schema }) rides the structured-output support the in-process backends implement. The seam split exists for engine hardening: node:vm is in-process and cannot kill a pathological synchronous spin — a worker-thread or isolated-vm engine swaps in behind the same interface if that ever matters.
The proposal, decisions, and deferred work: docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md.