A new capability family at packages/workflow/ in the bash seam shape,
modeled on Claude Code's dynamic workflows: the model writes a JavaScript
orchestration script (export const meta = {...} + plain-JS body), a runtime
executes it, and the script — not the conversation — holds the loop, the
branching, and the intermediate results.
- dsh-workflow (ctx.workflows): abstract WorkflowService + run vocabulary
(WorkflowRun whose result NEVER rejects) + observe-only workflow/* events
carrying data snapshots (id + meta, never the live run), per-listener
contained like subagent/*.
- dsh-workflow-vm: in-process node:vm engine. Meta extraction via a
string/comment-aware scanner (template interpolation rejected; literal
evaluated alone in an empty timed context; statement blanked line-
preservingly so stacks keep script line numbers). Hooks: agent(prompt,
{label, phase, schema, model}) over ctx.subagents, parallel(), pipeline()
(no cross-stage barrier), phase(), log(), args. Fatal-vs-null discipline:
hook misuse (unknown/deferred options, bad arguments, unsupported
schemas, tripped caps, seam start failures, cancellation) throws fatal
WorkflowErrors the combinators RE-THROW — never dissolved into the
per-item null reserved for child failures. Realm boundary: inbound values
materialized by descriptor walks that never invoke accessors (defineProperty
copies, __proto__-safe); outbound values rebuilt in-realm via the
context's own JSON.parse. Determinism bans (Date.now/Math.random/argless
new Date) kept so future resume support cannot break scripts. Caps and
timeouts are validated Config. Every hook promise carries a no-op
rejection consumer (app-boot exits on unhandled rejections).
- dsh-tool-workflow: the model-facing workflow tool, synchronous like
dsh-tool-subagent (start → await → try/finally dispose; abort bridged;
non-completed → isError). Generic render card titled by a textual
meta.name sniff. The tool description carries the authoring contract.
Wired into examples/{coding-agent,acp-agent} with explicit-ask-only
guidance. Coverage at every tier: unit (meta scanner, materializer incl.
counting-getter and __proto__ regressions, combinator semantics,
concurrency ceiling, caps, cancellation, no-unhandled-rejection abandon),
integration over the real spawn stack, with-key e2e (real two-phase run +
the tool through the registry pipeline), and a recorded ACP snapshot
scenario (workflow-run, 1 child session). RFC:
docs/rfc/implemented/feature/2026-07-05-dynamic-workflows.md (deferred
work explicitly listed). AGENTS.md budget 1575 → 1590 for the new group's
layout line.
1.5 KiB
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.