<Workflow>

import { Workflow } from "smthrs";

type WorkflowProps = {
  name: string;
  cache?: boolean; // skip already-completed nodes on resume
  children?: ReactNode;
};

import { CodexAgent, createSmithers } from "smthrs";
import { z } from "zod";

const { Workflow, Task, smithers, outputs } = createSmithers({
  research: z.object({ findings: z.string() }),
});

const researcher = new CodexAgent({
  model: "gpt-5.6-luna",
  config: { model_reasoning_effort: "medium" },
  instructions: "You are a research assistant.",
});

export default smithers((ctx) => (
  <Workflow name="research-pipeline" cache>
    <Task id="research" output={outputs.research} agent={researcher}>
      {`Research: ${ctx.input.topic}`}
    </Task>
  </Workflow>
));

​

Notes

• Direct children run sequentially; <Sequence> is only needed inside other control-flow components.
• Input schemas run before workflow rendering. Fresh runs and bunx smthrs graph apply Zod defaults and transforms before the workflow reads ctx.input. Explicit caller values take precedence over .default() values. Coalesce only fields declared optional or nullable.
• Two ways to get <Workflow>, both equivalent. Import it directly (import { Workflow } from "smthrs") or destructure it from createSmithers(...); both render the identical node, since the factory’s Workflow is a thin pass-through injecting no schema or context, unlike Task/Approval/Sandbox/Signal, which the factory wires to the run’s context and your output schemas. Convention: destructure Workflow from createSmithers alongside Task, smithers, and outputs, so a workflow’s components all come from one place, as the example above and ~95% of examples/ do. A direct top-level import (also fine for Sequence, Branch, Loop, Parallel, and other pure structural components) suits tiny single-file workflows.
• Custom Drizzle tables require runId, nodeId, and iteration columns with a composite primary key (run_id, node_id, iteration). Tasks outside a <Loop> write iteration = 0.