Three review findings on the engine's child seam, one mechanism each: - Cancellation now bridges to run.cancel() on every in-flight child, not just the shared request signal — the subagent seam leaves a provider free to honor either channel, so the consumer drives both (listener removed in the child finally). - A child result REJECTION (an infrastructure fault the seam allows) now emits the paired workflow/agent-end before propagating, and propagates as a fatal WorkflowError with the new AGENT_RESULT code — previously it skipped agent-end (permanently open child for seq-matching observers) and dissolved to a per-item null inside parallel()/pipeline(), letting a broken provider read as an ordinary failed child. A rejection landing after cancel stays a cancellation (cancelled outcome + CANCELLED). - Every hook now guards its entry with a shared throwIfCancelled(): phase()/log() no longer emit observer events after a script caught an earlier cancelled rejection, and parallel()/pipeline() refuse entry — cancellation is the next HOOK boundary, not just the next agent().
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.