#Teams

Teams are a harness pattern built from named agent definitions plus the task and parallel_task delegation core. A3S Code does not expose a separate team runner API; the parent session stays responsible for synthesis, policy, and final verification.

#Recommended Shape

1. Put durable roles in .a3s/agents or configure additional agentDirs.
2. Keep each role focused: description, prompt, allowed tools, denied tools.
3. Enable autoDelegation when the runtime should select high-confidence subagents.
4. Use session.task(...) or session.tasks(...) when the host already knows the lanes.
5. Merge child summaries, evidence references, and risks in the parent.

const session = agent.session('/repo', {
  agentDirs: ['./.a3s/agents'],
  planningMode: 'auto',
  autoDelegation: { enabled: true, maxTasks: 4 },
  maxParallelTasks: 8,
  autoParallel: false,
});

await session.send(`
Build a release-readiness team:
- explorer: find risky changed areas
- tester: identify missing verification
- security: review side-effect paths

Use independent subagents where useful and return a single prioritized report.
`);

#Custom Agent Files

Markdown agent files use Claude-compatible frontmatter, with A3S-native placement under .a3s/agents:

---
name: release-reviewer
description: Use proactively after release or CI changes
tools: Read, Grep, Glob, Bash(cargo test*)
disallowedTools:
  - Write
  - Bash(git push*)
---

Review release blockers first, then risks, then follow-up work.

A3S also reads .claude/agents as a migration source. Prefer .a3s/agents for new projects.

#Built-in Team Roles

Use these without creating files:

• explore: read-only repository exploration
• plan: read-only implementation planning
• general / general-purpose: multi-step implementation
• verification: checks, repros, and regression validation
• review: findings-first code review

#Manual Lanes

SDK callers can call direct helpers when the host already knows the lanes:

const result = await session.tasks([
  {
    agent: 'explore',
    description: 'Changed files',
    prompt: 'Find risky changed files.',
  },
  {
    agent: 'verification',
    description: 'Test gaps',
    prompt: 'Find missing verification.',
  },
  {
    agent: 'review',
    description: 'Regression review',
    prompt: 'Review correctness risks.',
  },
]);

if (result.exitCode !== 0) throw new Error(result.output);
console.log(result.output);

session.tasks(...) is the host-driven wrapper around parallel_task; it returns a ToolResult, not a StepOutcome[]. Use session.parallel(...) when you need one structured outcome per lane.

When the team's lane structure is fixed and should be reproducible and resumable rather than model-chosen, use the programmable combinators in Orchestration (session.parallel / session.pipeline / session.parallelResumable).

#Worker Agents

Register disposable worker agents with workerAgents or registerWorkerAgent() when the role is constructed by the host instead of stored on disk:

const session = agent.session('/repo', {
  workerAgents: [
    {
      name: 'frontend-worker',
      description: 'Small verified frontend fixes',
      kind: 'implementer',
      model: 'provider/model-id',
      maxSteps: 24,
      confirmationInheritance: 'auto_approve',
    },
  ],
});

Control how child runs resolve Ask decisions with confirmationInheritance:

• 'auto_approve' (default): child runs auto-approve all Ask decisions
• 'deny_on_ask': child runs fail immediately when encountering an Ask
• 'inherit_parent': child runs inherit the parent's confirmation policy

#Runtime State

Applications should observe streaming events and run replay snapshots, then cancel active Node work with cancelRun(runId) when needed.