deepseek-harness/docs/core-data-structures/workflow.md

Workflow

The workflow seam — an agent running a model-written orchestration SCRIPT that fans out subagents. Like subagent it is one optional capability, not part of the agent-loop spine, so its vocabulary lives here rather than in core.md. Unlike the subagent registry it takes the bash shape: ONE engine implementation per context provides ctx.workflows; there is no named-provider registry (a second engine is a plugin swap, not a co-resident).

Interface: dsh-workflow (ctx.workflows + the vocabulary below). The implementation is dsh-workflow-vm (an in-process node:vm engine); the model-facing consumer is dsh-tool-workflow. The proposal and rationale: the dynamic-workflows RFC.

Source: packages/workflow/workflow/src/types.ts

The start request

What a caller asks for when starting a run. The tool layer builds this from the model's { script, args } plus the calling agent; the engine validates the script's meta block BEFORE the body runs. parent is REQUIRED — every child the script spawns is attributed to it (cwd, lineage, and depth flow through the subagent seam). args must be plain host-realm JSON data; the engine exposes it to the script as the args global.

interface WorkflowStartRequest {
  script: string
  args?: unknown
  parent: Agent
  signal?: AbortSignal
}

The script's identity: WorkflowMeta

The validated export const meta block (Claude Code dynamic-workflows format — a PURE object literal heading the script). phases is progress vocabulary only: phase() calls match titles for observers; no execution structure is implied.

interface WorkflowMeta {
  name: string
  description: string
  whenToUse?: string
  phases?: WorkflowPhase[]
}

The terminal result: WorkflowResult

The outcome of one run, resolved by WorkflowRun.result. value is the script's materialized return value — plain host-realm JSON data (null when the script returned nothing) — meaningful only for completed. stopReason is a CLOSED union (engine-owned; consumers may exhaust it): completed | cancelled | error. A non-completed reason carries the failure in error, and the consumer maps it to an isError tool result rather than reporting partial output as success.

interface WorkflowResult {
  value: unknown
  stopReason: WorkflowStopReason
  error?: string
  agentsStarted: number
}

A live run: WorkflowRun

The handle the consumer holds while a script executes. The consumer awaits result, may cancel mid-flight, and MUST dispose on every path. result does NOT reject — a script failure resolves with stopReason: 'error' — so the consumer maps a non-completed reason to an isError result. dispose() cancels, waits a bounded grace for the script to settle, then abandons it (the engine documents the abandonment semantics); it never hangs on a stuck script.

interface WorkflowRun {
  readonly id: WorkflowRunId
  readonly meta: WorkflowMeta
  readonly result: Promise<WorkflowResult>
  cancel(reason?: string): void
  dispose(): Promise<void>
}

Failure discipline: WorkflowError.fatal

Hook misuse inside a script — bad arguments, unknown/deferred agent() options, a schema outside the structured-output subset, a tripped cap, a seam start failure, cancellation — throws a WorkflowError with fatal: true. The parallel()/pipeline() combinators RE-THROW fatal errors instead of mapping the item to null: a typo'd option must kill the script loudly, never dissolve into something that reads as an ordinary child failure. The per-item null is reserved for child-run failures (a non-completed stop reason) and ordinary in-stage script errors.

Events

The workflow/* events (workflow/start, workflow/phase, workflow/log, workflow/agent-start, workflow/agent-end, workflow/end — see the events catalog) are observe-only emits carrying DATA SNAPSHOTS: every payload starts with WorkflowRunInfo (id + meta), never the live WorkflowRun, so a subscriber cannot gain cancel/dispose, and workflow/end deliberately omits the result value (a listener observing outcomes must not receive a mutable alias of the caller's result). Every emit is per-listener contained — a throwing subscriber is logged, never propagated, and cannot starve the listeners registered after it — mirroring subagent/start/subagent/end.