Multi-Machine

A3S Code runs multi-agent orchestration as a grammar expressed in code, then places the resulting steps wherever you want them to run. The split is drawn along the framework / host boundary, introduced in [3.4.0]:

The framework owns the orchestration grammar and the serializable data contracts. It never decides where a step runs.
The host owns placement, transport, and scheduling — which node executes a step, how the spec gets there, and how concurrency maps to a cluster.

The single point of contact between the two is one trait, AgentExecutor.

The framework / host boundary

The framework's contract is two serializable types:

AgentStepSpec — what to run, independent of where: task_id, agent, description, prompt, and optional max_steps, parent_session_id, output_schema.
StepOutcome — the result of running one spec: task_id, session_id, agent, output, success, and optional structured.

Both serialize cleanly, so a host may ship a spec to another node and persist an outcome in a checkpoint. The combinators that compose specs are written purely against the AgentExecutor trait and never observe where a step ran, so the same orchestration scales from one process to a cluster without changing.

The AgentExecutor seam

AgentExecutor is the boundary between the grammar and the host:

combinators (parallel / pipeline / resumable)
  -> AgentExecutor::execute_step(spec) -> StepOutcome
       ├─ in-box TaskExecutor: runs the step as a local child agent
       └─ host executor: places the step on a remote node

The in-box TaskExecutor runs each step as a child agent locally — in-process, on Tokio — inheriting the session's agent registry, LLM client, workspace, MCP tools, and subagent tracker. A host such as a cluster runtime substitutes its own executor to place steps across a cluster; the combinators are unaffected.

concurrency_hint() is advisory, not a hard local bound. The local default returns the session's max_parallel_tasks; a scheduler-backed host may return its cluster-wide target. Because it is a hint rather than a ceiling, orchestration scales past a single process.

A session exposes the in-box seam directly:

AgentSession::agent_executor() returns a session-backed AgentExecutor.
AgentSession::session_store() returns the session's store (when one is configured), which the resumable combinator needs to journal progress.

The SDK grammar below calls agent_executor() for you; you only reach for these when implementing or substituting a custom executor.

Parallel: barrier fan-out

execute_steps_parallel fans specs out across the executor and awaits all of them (a barrier). Results preserve input order, a panicked branch becomes a failed StepOutcome instead of dropping the batch, and concurrency is bounded by the executor's concurrency hint.

const outcomes = await session.parallel([
  { taskId: 'a', agent: 'explore', description: 'survey', prompt: 'Map the auth module' },
  { taskId: 'b', agent: 'review', description: 'audit', prompt: 'Review error handling' },
]);

for (const o of outcomes) {
  console.log(o.taskId, o.success, o.output);
}

outcomes = session.parallel([
    {"task_id": "a", "agent": "explore", "description": "survey", "prompt": "Map the auth module"},
    {"task_id": "b", "agent": "review", "description": "audit", "prompt": "Review error handling"},
])

for o in outcomes:
    print(o["task_id"], o["success"], o["output"])

Pipeline: per-item chains, no inter-stage barrier

execute_pipeline runs each item through a chain of PipelineStages independently. There is no barrier between stages — item A can be in stage 3 while item B is still in stage 1 — so wall-clock is the slowest single chain, not the sum of the slowest step per stage.

A stage is a (ctx) => spec | null callback where ctx carries the previous outcome and the original item. Return a spec to run the next step, or null to stop that item's chain early; a chain also stops when a step fails (later stages would only build on a failed result). The bridges fail closed: a stage that hangs, returns null, or raises stops only its own chain.

A Node stage callback must not throw — wrap your logic in try/catch and return null on error (the same constraint as setBudgetGuard). A stage that hangs past the timeout fails closed for that chain. A Python stage that raises is caught and treated as null.

const outcomes = await session.pipeline(['src/auth', 'src/api'], [
  (ctx) => ({ taskId: 's1', agent: 'explore', description: 'survey', prompt: `Survey ${ctx.item}` }),
  (ctx) => ctx.previous?.success
    ? { taskId: 's2', agent: 'review', description: 'review', prompt: `Review: ${ctx.previous.output}` }
    : null,
]);

def survey(ctx):
    return {"task_id": "s1", "agent": "explore", "description": "survey",
            "prompt": f"Survey {ctx['item']}"}

def review(ctx):
    prev = ctx["previous"]
    if prev and prev["success"]:
        return {"task_id": "s2", "agent": "review", "description": "review",
                "prompt": f"Review: {prev['output']}"}
    return None

outcomes = session.pipeline(["src/auth", "src/api"], [survey, review])

Resumable: cross-node resume

execute_steps_parallel_resumable is parallel plus a journal. At each step boundary it writes a WorkflowCheckpoint to the SessionStore under a workflowId. On resume it skips already-completed steps and re-dispatches the rest. It records only successful steps, so a failed step retries on resume — its effect did not complete.

A SessionStore is required. The Node bridge rejects with "parallelResumable requires a sessionStore" when none is configured; Python raises the equivalent.

import { Agent, FileSessionStore } from '@a3s-lab/code';

const session = agent.session('/repo', {
  sessionStore: new FileSessionStore('./.a3s/sessions'),
});

const outcomes = await session.parallelResumable([
  { taskId: 'a', agent: 'explore', description: 'survey', prompt: 'Map the auth module' },
  { taskId: 'b', agent: 'review', description: 'audit', prompt: 'Review error handling' },
], 'release-audit');

from a3s_code import Agent, FileSessionStore

session = agent.session("/repo", session_store=FileSessionStore("./.a3s/sessions"))

outcomes = session.parallel_resumable([
    {"task_id": "a", "agent": "explore", "description": "survey", "prompt": "Map the auth module"},
    {"task_id": "b", "agent": "review", "description": "audit", "prompt": "Review error handling"},
], "release-audit")

Because the checkpoint is serializable and the executor is a parameter, a host can resume an interrupted workflow on a different node by passing that node's executor — the framework migrates the what, the host supplies the where.

Schema-forced step output

A spec carrying an output_schema (outputSchema in Node) must return a value conforming to that JSON Schema; the validated object lands in StepOutcome.structured. The executor reuses the structured-output coercion and repair machinery. A coercion failure demotes the step to unsuccessful, so a caller never treats unvalidated text as the promised object.

const [finding] = await session.parallel([{
  taskId: 'classify', agent: 'review', description: 'classify', prompt: 'Classify this defect',
  outputSchema: {
    type: 'object',
    properties: { severity: { type: 'string' }, summary: { type: 'string' } },
    required: ['severity', 'summary'],
  },
}]);

if (finding.success && finding.structured) {
  console.log(finding.structured.severity);
}

Placing orchestration steps across machines

Lane queues remain a valid transport — but they are now one option behind the AgentExecutor seam, not the sole integration point. To distribute work, a host implements AgentExecutor::execute_step over whatever transport fits its platform (HTTP, message queues, a job system, lane queues, internal RPC), wires concurrency_hint() to its cluster target, and hands that executor to the combinators. The grammar — parallel, pipeline, resumable — stays identical; only placement moves.

The result: a coordinator session owns the conversation, final synthesis, and release decision, while its orchestration steps execute wherever the host places them, with cross-node resume carried by the serializable checkpoint.

See Orchestration for the combinator grammar in depth and Persistence for the checkpoint store.

Multi-Machine

On this page