writing-agent-relay-workflows

name

writing-agent-relay-workflows

description

Use when building multi-agent workflows with the relay broker-sdk - covers conversation-shape vs pipeline-shape coordination, the WorkflowBuilder API, DAG step dependencies, agent definitions, step output chaining via {{steps.X.output}}, verification gates, evidence-based completion, owner decisions, dedicated channels, dynamic channel management (subscribe/unsubscribe/mute/unmute), swarm patterns, chat-native coordination recipes (Q/A, broadcast-ack, peer review, standup, hand-off), error handling, event listeners, step sizing rules, authoring best practices, and the lead+workers team pattern for complex steps

Overview

The relay broker-sdk workflow system orchestrates multiple AI agents (Claude, Codex, Gemini, Aider, Goose) through typed DAG-based workflows. Workflows can be written in TypeScript (preferred), Python, or YAML.

Language preference: TypeScript > Python > YAML. Use TypeScript unless the project is Python-only or a simple config-driven workflow suits YAML.

Pattern selection: Do not default to dag blindly. If the job needs a different swarm/workflow type, consult the choosing-swarm-patterns skill when available and select the pattern that best matches the coordination problem.

When to Use

• Building multi-agent workflows with step dependencies
• Orchestrating different AI CLIs (claude, codex, gemini, aider, goose)
• Creating DAG, pipeline, fan-out, or other swarm patterns
• Needing verification gates, retries, or step output chaining
• Dynamic channel management: agents joining/leaving/muting channels mid-workflow

Choose Your Coordination Style — Conversation vs Pipeline

Before writing the workflow, decide how the agents will coordinate. The relay primitive supports two very different shapes, and picking the wrong one wastes the most valuable thing the SDK gives you.

Shape	What it is	Use when
Conversation (chat-native)	Interactive agents share a channel; messages, @-mentions, and ambient awareness drive coordination. Lead and workers spawn in parallel and self-organize. The relay is the coordination layer, not just transport.	Multi-file work, peer review loops, cross-agent feedback, dynamic re-planning, multi-PR coordination, anything with a human-in-the-loop escape, swarms where workers pick up each other's output.
Pipeline (one-shot DAG)	Each step runs as a one-shot subprocess (claude -p, codex exec); steps hand off via {{steps.X.output}} text injection. No agents are alive at the same time; no chat happens.	Linear, well-specified transformations; deterministic data passing; no review loop expected; the work could be expressed as a `bash

Default to Conversation for any non-trivial work. Pipeline DAGs are simpler to reason about but they do not exercise the relay primitive — they are a Unix pipe with extra steps. If you would happily write the same task as a single shell pipeline, pipeline-shape is fine. Otherwise, you almost certainly want a Conversation shape.

The two shapes can mix within one workflow: pipeline-style deterministic preflight → conversation in the middle → pipeline-style commit-and-PR at the end. See Quick Reference (Conversation) below and Common Patterns → Interactive Team for the canonical recipe.

A blunt rule of thumb: if your workflow only uses agent steps with preset: 'worker' chained by {{steps.X.output}}, you are not using the relay — you are using claude -p | codex exec. That may still be the right answer; just make it a deliberate choice.

Quick Reference (Pipeline shape)

> Use this when steps are linear, well-specified, and need no agent-to-agent feedback. For anything with iteration, review, or coordination, jump to Quick Reference (Conversation shape) below.

import { workflow } from '@agent-relay/sdk/workflows';

const result = await workflow('my-workflow')
  .description('What this workflow does')
  .pattern('dag') // or 'pipeline', 'fan-out', etc.
  .channel('wf-my-workflow') // dedicated channel (auto-generated if omitted)
  .maxConcurrency(3)
  .timeout(3_600_000) // global timeout (ms)

  .agent('lead', { cli: 'claude', role: 'Architect', retries: 2 })
  .agent('worker', { cli: 'codex', role: 'Implementer', retries: 2 })

  .step('plan', {
    agent: 'lead',
    task: `Analyze the codebase and produce a plan.`,
    retries: 2,
    verification: { type: 'output_contains', value: 'PLAN_COMPLETE' },
  })
  .step('implement', {
    agent: 'worker',
    task: `Implement based on this plan:\n{{steps.plan.output}}`,
    dependsOn: ['plan'],
    verification: { type: 'exit_code' },
  })

  .onError('retry', { maxRetries: 2, retryDelayMs: 10_000 })
  .run({ cwd: process.cwd() });

  console.log('Result:', result.status);

Quick Reference (Conversation shape)

> Use this for any non-trivial work — peer review, multi-file edits, cross-agent feedback, dynamic re-planning. Lead and workers spawn in parallel on a shared channel and self-organize via messages. The relay primitive does the coordinating; verification gates downstream of the lead close the workflow.

import { workflow } from '@agent-relay/sdk/workflows';
import { ClaudeModels, CodexModels } from '@agent-relay/config';

const result = await workflow('my-workflow')
  .description('Multi-file change with peer review')
  .pattern('dag')
  .channel('wf-my-feature')          // dedicated channel — agents share it
  .maxConcurrency(4)
  .timeout(3_600_000)

  // Interactive agents — no preset, they live on the channel
  .agent('lead', {
    cli: 'claude',
    model: ClaudeModels.OPUS,
    role: 'Architect + reviewer. Plans, assigns, reviews, posts feedback.',
    retries: 1,
  })
  .agent('impl-a', {
    cli: 'codex',
    model: CodexModels.GPT_5_4,
    role: 'Implementer. Listens on channel for assignments and feedback.',
    retries: 2,
  })
  .agent('impl-b', {
    cli: 'codex',
    model: CodexModels.GPT_5_4,
    role: 'Implementer. Listens on channel for assignments and feedback.',
    retries: 2,
  })

  // Deterministic context — pre-reads files once, posts to the channel for everyone
  .step('context', {
    type: 'deterministic',
    command: 'git ls-files src/',
    captureOutput: true,
  })

  // Lead and workers all depend on `context` — they start CONCURRENTLY.
  // They coordinate over #wf-my-feature, not via {{steps.X.output}}.
  .step('lead-coordinate', {
    agent: 'lead',
    dependsOn: ['context'],
    task: `You are the lead on #wf-my-feature. Workers: impl-a, impl-b.
Post the plan. Assign files. Review their PRs/diffs. Post feedback in-channel.
Workers iterate based on your feedback. Exit when both files pass review.`,
  })
  .step('impl-a-work', {
    agent: 'impl-a',
    dependsOn: ['context'],   // SAME dep as lead → starts in parallel, no deadlock
    task: `You are impl-a on #wf-my-feature. Wait for the lead's plan.
Implement your assigned file. Post a completion message. Address feedback.`,
  })
  .step('impl-b-work', {
    agent: 'impl-b',
    dependsOn: ['context'],   // SAME dep as lead
    task: `You are impl-b on #wf-my-feature. Wait for the lead's plan.
Implement your assigned file. Post a completion message. Address feedback.`,
  })

  // Downstream gates on the lead — lead exits when satisfied.
  .step('verify', {
    type: 'deterministic',
    dependsOn: ['lead-coordinate'],
    command: 'npm run typecheck && npm test',
    failOnError: true,
  })

  .onError('retry', { maxRetries: 2, retryDelayMs: 10_000 })
  .run({ cwd: process.cwd() });

⚡ Parallelism — Design for Speed

Cross-Workflow Parallelism: Wave Planning

# BAD — sequential (14 hours for 27 workflows at ~30 min each)
agent-relay run workflows/34-sst-wiring.ts
agent-relay run workflows/35-env-config.ts
agent-relay run workflows/36-loading-states.ts
# ... one at a time

# GOOD — parallel waves (3-4 hours for 27 workflows)
# Wave 1: independent infra (parallel)
agent-relay run workflows/34-sst-wiring.ts &
agent-relay run workflows/35-env-config.ts &
agent-relay run workflows/36-loading-states.ts &
agent-relay run workflows/37-responsive.ts &
wait
git add -A && git commit -m "Wave 1"

# Wave 2: testing (parallel — independent test suites)
agent-relay run workflows/40-unit-tests.ts &
agent-relay run workflows/41-integration-tests.ts &
agent-relay run workflows/42-e2e-tests.ts &
wait
git add -A && git commit -m "Wave 2"

Declare File Scope for Planning

workflow('48-comparison-mode')
  .packages(['web', 'core'])                // monorepo packages touched
  .isolatedFrom(['49-feedback-system'])      // explicitly safe to parallelize
  .requiresBefore(['46-admin-dashboard'])    // explicit ordering constraint

Within-Workflow Parallelism

// BAD — unnecessary sequential chain
.step('fix-component-a', { agent: 'worker', dependsOn: ['review'] })
.step('fix-component-b', { agent: 'worker', dependsOn: ['fix-component-a'] })  // why wait?

// GOOD — parallel fan-out, merge at the end
.step('fix-component-a', { agent: 'impl-1', dependsOn: ['review'] })
.step('fix-component-b', { agent: 'impl-2', dependsOn: ['review'] })  // same dep = parallel
.step('verify-all', { agent: 'reviewer', dependsOn: ['fix-component-a', 'fix-component-b'] })

Failure Prevention

1. Do not use raw top-level await

async function runWorkflow() {
  const result = await workflow('my-workflow')
    // ...
    .run({ cwd: process.cwd() });

  console.log('Workflow status:', result.status);
}

runWorkflow().catch((error) => {
  console.error(error);
  process.exit(1);
});

2b. Standard preflight template for resumable workflows

.step('preflight', {
  type: 'deterministic',
  command: [
    'set -e',
    'BRANCH=$(git rev-parse --abbrev-ref HEAD)',
    'echo "branch: $BRANCH"',
    'if [ "$BRANCH" != "fix/your-branch-name" ]; then echo "ERROR: wrong branch"; exit 1; fi',
    // Files the workflow is allowed to find dirty on entry:
    //   - package-lock.json: npm install is idempotent and often touches it
    //   - every file the workflow's edit steps will rewrite: a prior partial
    //     run may have left them dirty, and the edit step will rewrite
    //     them cleanly before commit
    // Everything else is unexpected drift and must fail preflight.
    'ALLOWED_DIRTY="package-lock.json|path/to/file1\\\\.ts|path/to/file2\\\\.ts"',
    'DIRTY=$(git diff --name-only | grep -vE "^(${ALLOWED_DIRTY})$" || true)',
    'if [ -n "$DIRTY" ]; then echo "ERROR: unexpected tracked drift:"; echo "$DIRTY"; exit 1; fi',
    'if ! git diff --cached --quiet; then echo "ERROR: staging area is dirty"; git diff --cached --stat; exit 1; fi',
    'gh auth status >/dev/null 2>&1 || (echo "ERROR: gh CLI not authenticated"; exit 1)',
    'echo PREFLIGHT_OK',
  ].join(' && '),
  captureOutput: true,
  failOnError: true,
}),

2c. Picking the right .join() for multi-line shell commands

command: [
  'set -e',
  'HITS=$(grep -c diag src/cli/commands/setup.ts || true)',
  'if [ "$HITS" -lt 6 ]; then echo "FAIL"; exit 1; fi',
  'echo OK',
].join(' && '),

3. Keep final verification boring and deterministic

grep -Eq "foo|bar|baz" file.ts

6. Be explicit about shell requirements

/opt/homebrew/bin/bash workflows/your-workflow/execute.sh --wave 2

9. Factor repo-specific setup into a shared helper

// workflows/lib/cloud-repo-setup.ts
export interface CloudRepoSetupOptions {
  branch: string;
  committerName?: string;
  extraSetupCommands?: string[];
  skipWorkspaceBuild?: boolean;
}

export function applyCloudRepoSetup<T>(wf: T, opts: CloudRepoSetupOptions): T {
  // adds two steps: setup-branch, install-deps
  // install-deps runs: npm install + workspace prebuilds (build:platform, build:core, etc.)
  // ...
}

End-to-End Bug Fix Workflows

• Capture the original failure
• Reproduce the bug first in a deterministic or evidence-capturing step
• Save exact commands, logs, status codes, or screenshots/artifacts
• State the acceptance contract
• Define the exact end-to-end success criteria before implementation
• Include the real entrypoint a user would run
• Implement the fix
• Rebuild / reinstall from scratch
• Do not trust dirty local state
• Prefer a clean environment when install/bootstrap behavior is involved
• Run targeted regression checks
• Unit/integration tests are helpful but not sufficient by themselves
• Run a full end-to-end validation
• Use the real CLI / API / install path
• Prefer a clean environment (Docker, sandbox, cloud workspace, Daytona, etc.) for install/runtime issues
• Compare before vs after evidence
• Show that the original failure no longer occurs
• Record residual risks
• Call out what was not covered
• Ship the result as a PR
• Open the pull request from the workflow itself with createGitHubStep
• See Shipping the Result — Open a PR via createGitHubStep below
• A workflow that fixes a bug and stops short of the PR has only done half the loop
• disposable sandbox / cloud workspace
• Docker / containerized environment
• fresh local shell with isolated paths
• compares candidate validation environments
• defines the acceptance contract
• chooses the best swarm pattern
• then authors the final fix/validation workflow

Shipping the Result — Open a PR via createGitHubStep

The minimal "open a PR" recipe

import { workflow } from '@agent-relay/sdk/workflows';
import { createGitHubStep } from '@agent-relay/sdk/github';

const REPO = 'AgentWorkforce/cloud';
const BRANCH = `agent-relay/run-${Date.now()}`;

await workflow('feature-x')
  // ... your real steps that produce code changes ...
  .step('write-marker', {
    type: 'deterministic',
    command: `echo "fix landed at $(date -u)" >> CHANGELOG.md`,
  })

  // Branch off main on the remote.
  .step('create-branch', createGitHubStep({
    dependsOn: ['write-marker'],
    action: 'createBranch',
    repo: REPO,
    params: { branch: BRANCH, source: 'main' },
  }))

  // Commit the change to the branch via Contents API.
  .step('commit-change', createGitHubStep({
    dependsOn: ['create-branch'],
    action: 'createFile',
    repo: REPO,
    params: {
      path: 'CHANGELOG.md',
      branch: BRANCH,
      content: '<file body here>',
      message: 'chore: changelog entry',
    },
  }))

  // Open the PR. This is the load-bearing step.
  .step('open-pr', createGitHubStep({
    dependsOn: ['commit-change'],
    action: 'createPR',
    repo: REPO,
    params: {
      title: 'feat: ship feature X',
      head: BRANCH,
      base: 'main',
      body: '## Summary\n\n- ...\n\n## Test plan\n\n- [x] ...',
      draft: false,
    },
    output: { mode: 'data', format: 'json', path: 'html_url' },
  }))

  .run({ cwd: process.cwd() });

Key Concepts

Verification Gates

verification: { type: 'exit_code' }                        // preferred for code-editing steps
verification: { type: 'output_contains', value: 'DONE' }   // optional accelerator
verification: { type: 'file_exists', value: 'src/out.ts' } // deterministic file check

DAG Dependencies

.step('fix-types',  { agent: 'worker', dependsOn: ['review'], ... })
.step('fix-tests',  { agent: 'worker', dependsOn: ['review'], ... })
.step('final',      { agent: 'lead',   dependsOn: ['fix-types', 'fix-tests'], ... })

SDK API

// Subscribe an agent to additional channels post-spawn
relay.subscribe({ agent: 'security-auditor', channels: ['review-pr-456'] });

// Unsubscribe — agent leaves the channel entirely
relay.unsubscribe({ agent: 'security-auditor', channels: ['general'] });

// Mute — agent stays subscribed (history access) but messages are NOT injected into PTY
relay.mute({ agent: 'security-auditor', channel: 'review-pr-123' });

// Unmute — resume PTY injection
relay.unmute({ agent: 'security-auditor', channel: 'review-pr-123' });

Events

relay.onChannelSubscribed = (agent, channels) => { /* ... */ };
relay.onChannelUnsubscribed = (agent, channels) => { /* ... */ };
relay.onChannelMuted = (agent, channel) => { /* ... */ };
relay.onChannelUnmuted = (agent, channel) => { /* ... */ };

Agent Definition

```typescript

.agent('name', {
  cli: 'claude' | 'codex' | 'gemini' | 'aider' | 'goose' | 'opencode' | 'droid',
  role?: string,
  preset?: 'lead' | 'worker' | 'reviewer' | 'analyst',
  retries?: number,
  model?: string,
  interactive?: boolean, // default: true
})

Model Constants

import { ClaudeModels, CodexModels, GeminiModels } from '@agent-relay/config';

.agent('planner', { cli: 'claude', model: ClaudeModels.OPUS })    // not 'opus'
.agent('worker',  { cli: 'claude', model: ClaudeModels.SONNET })  // not 'sonnet'
.agent('coder',   { cli: 'codex',  model: CodexModels.GPT_5_4 })  // not 'gpt-5.4'

Step Definition

Agent Steps

.step('name', {
  agent: string,
  task: string,                   // supports {{var}} and {{steps.NAME.output}}
  dependsOn?: string[],
  verification?: VerificationCheck,
  retries?: number,
})

Deterministic Steps (Shell Commands)

.step('verify-files', {
  type: 'deterministic',
  command: 'test -f src/auth.ts && echo "FILE_EXISTS"',
  dependsOn: ['implement'],
  captureOutput: true,
  failOnError: true,
})

Common Patterns

Interactive Team (lead + workers on shared channel)

.agent('lead', {
  cli: 'claude',
  model: ClaudeModels.OPUS,
  role: 'Architect and reviewer — assigns work, reviews, posts feedback',
  retries: 1,
  // No preset — interactive by default
})

.agent('impl-new', {
  cli: 'codex',
  model: CodexModels.O3,
  role: 'Creates new files. Listens on channel for assignments and feedback.',
  retries: 2,
  // No preset — interactive, receives channel messages
})

.agent('impl-modify', {
  cli: 'codex',
  model: CodexModels.O3,
  role: 'Edits existing files. Listens on channel for assignments and feedback.',
  retries: 2,
})

// All three share the same dependsOn — they start concurrently (no deadlock)
.step('lead-coordinate', {
  agent: 'lead',
  dependsOn: ['context'],
  task: `You are the lead on #channel. Workers: impl-new, impl-modify.
Post the plan. Assign files. Review their work. Post feedback if needed.
Workers iterate based on your feedback. Exit when all files are correct.`,
})
.step('impl-new-work', {
  agent: 'impl-new',
  dependsOn: ['context'],   // same dep as lead = parallel start
  task: `You are impl-new on #channel. Wait for the lead's plan.
Create files as assigned. Report completion. Fix issues from feedback.`,
})
.step('impl-modify-work', {
  agent: 'impl-modify',
  dependsOn: ['context'],   // same dep as lead = parallel start
  task: `You are impl-modify on #channel. Wait for the lead's plan.
Edit files as assigned. Report completion. Fix issues from feedback.`,
})
// Downstream gates on lead (lead exits when satisfied)
.step('verify', { type: 'deterministic', dependsOn: ['lead-coordinate'], ... })

1. Question / Answer (blocking ask)

.step('integrate', {
  agent: 'integrator',
  dependsOn: ['context'],
  task: `You are the integrator on #wf-feature.
Before writing code, post a direct question to @schema-owner asking which
table owns the new field. Do NOT proceed until @schema-owner replies in
channel. If no reply arrives in 5 minutes, @-mention the lead.`,
})

2. Broadcast / Ack

.step('lead-coordinate', {
  agent: 'lead',
  dependsOn: ['context'],
  task: `Post the plan to #wf-feature, then @impl-a @impl-b @impl-c.
Wait for each to reply with "ACK <agent-name>" before issuing assignments.
If any worker hasn't acked in 3 minutes, re-post and ping again.
Only after all three have acked, post per-worker assignments.`,
})

3. Peer Review Handoff

.step('impl-a-work', {
  agent: 'impl-a',
  dependsOn: ['context'],
  task: `Implement src/foo.ts per the lead's assignment.
When done, post to #wf-feature: "@reviewer ready: src/foo.ts" — include the
commit SHA. Then wait for @reviewer's verdict in channel.
- If "APPROVED", you're done.
- If "CHANGES_REQUESTED <notes>", apply the notes and re-post.
- If no verdict in 5 min, @-mention the lead.`,
})

4. Standup / Status Probe

.step('lead-coordinate', {
  agent: 'lead',
  task: `... coordinate the team ...

Every 10 minutes, post a status probe: "@impl-a @impl-b status?"
Each worker should reply with one of:
  - "RUNNING <step>" (still working)
  - "BLOCKED <reason>" (@-mention the lead with the blocker)
  - "DONE <artifact>" (ready for review)

If a worker is silent for two probes in a row, mark them stalled and
reassign their work to a peer.`,
})

5. Hand-Off with Context

.step('impl-a-work', {
  agent: 'impl-a',
  task: `... finish your part ...

When done, post a handoff to #wf-feature targeting the next worker:
"@impl-b HANDOFF: src/foo.ts ready. Touched: <files>. Open question: <if any>.
Tests: <pass/fail summary>. Commit: <sha>."`,
})

Pipeline (sequential handoff)

.pattern('pipeline')
.step('analyze', { agent: 'analyst', task: '...' })
.step('implement', { agent: 'dev', task: '{{steps.analyze.output}}', dependsOn: ['analyze'] })
.step('test', { agent: 'tester', task: '{{steps.implement.output}}', dependsOn: ['implement'] })

Error Handling

.onError('fail-fast')   // stop on first failure (default)
.onError('continue')    // skip failed branches, continue others
.onError('retry', { maxRetries: 3, retryDelayMs: 5000 })

Multi-File Edit Pattern

When a workflow needs to modify multiple existing files, use one agent step per file with a deterministic verify gate after each. Agents reliably edit 1-2 files per step but fail on 4+.

steps:
  - name: read-types
    type: deterministic
    command: cat src/types.ts
    captureOutput: true

  - name: edit-types
    agent: dev
    dependsOn: [read-types]
    task: |
      Edit src/types.ts. Current contents:
      {{steps.read-types.output}}
      Add 'pending' to the Status union type.
      Only edit this one file.
    verification:
      type: exit_code

  - name: verify-types
    type: deterministic
    dependsOn: [edit-types]
    command: 'if git diff --quiet src/types.ts; then echo "NOT MODIFIED"; exit 1; fi; echo "OK"'
    failOnError: true

  - name: read-service
    type: deterministic
    dependsOn: [verify-types]
    command: cat src/service.ts
    captureOutput: true

  - name: edit-service
    agent: dev
    dependsOn: [read-service]
    task: |
      Edit src/service.ts. Current contents:
      {{steps.read-service.output}}
      Add a handlePending() method.
      Only edit this one file.
    verification:
      type: exit_code

  - name: verify-service
    type: deterministic
    dependsOn: [edit-service]
    command: 'if git diff --quiet src/service.ts; then echo "NOT MODIFIED"; exit 1; fi; echo "OK"'
    failOnError: true

  # Deterministic commit — never rely on agents to commit
  - name: commit
    type: deterministic
    dependsOn: [verify-service]
    command: git add src/types.ts src/service.ts && git commit -m "feat: add pending status"
    failOnError: true

File Materialization: Verify Before Proceeding

After any step that creates files, add a deterministic file_exists check before proceeding. Non-interactive agents may exit 0 without writing anything (wrong cwd, stdout instead of disk).

- name: verify-files
  type: deterministic
  dependsOn: [impl-auth, impl-storage]
  command: |
    missing=0
    for f in src/auth/credentials.ts src/storage/client.ts; do
      if [ ! -f "$f" ]; then echo "MISSING: $f"; missing=$((missing+1)); fi
    done
    if [ $missing -gt 0 ]; then echo "$missing files missing"; exit 1; fi
    echo "All files present"
  failOnError: true

DAG Deadlock Anti-Pattern

```yaml

# WRONG — deadlock: coordinate depends on context, work-a depends on coordinate
steps:
  - name: coordinate
    dependsOn: [context]    # lead waits for WORKER_DONE...
  - name: work-a
    dependsOn: [coordinate] # ...but work-a can't start until coordinate finishes

# RIGHT — workers and lead start in parallel
steps:
  - name: context
    type: deterministic
  - name: work-a
    dependsOn: [context]    # starts with lead
  - name: coordinate
    dependsOn: [context]    # starts with workers
  - name: merge
    dependsOn: [work-a, coordinate]

Step Sizing

One agent, one deliverable. A step's task prompt should be 10-20 lines max.

# Team pattern: lead + workers on a shared channel
steps:
  - name: track-lead-coord
    agent: track-lead
    dependsOn: [prior-step]
    task: |
      Lead the track on #my-track. Workers: track-worker-1, track-worker-2.
      Post assignments to the channel. Review worker output.

  - name: track-worker-1-impl
    agent: track-worker-1
    dependsOn: [prior-step]  # same dep as lead — starts concurrently
    task: |
      Join #my-track. track-lead will post your assignment.
      Implement the file as directed.
    verification:
      type: exit_code

  - name: next-step
    dependsOn: [track-lead-coord]  # downstream depends on lead, not workers

Supervisor Pattern

When you set .pattern('supervisor') (or hub-spoke, fan-out), the runner auto-assigns a supervisor agent as owner for worker steps. The supervisor monitors progress, nudges idle workers, and issues OWNER_DECISION.

Auto-hardening only activates for hub patterns — not pipeline or dag.

Use case	Pattern	Why
Sequential, no monitoring	pipeline	Simple, no overhead
Workers need oversight	supervisor	Auto-owner monitors
Local/small models	supervisor	Supervisor catches stuck workers
All non-interactive	pipeline or dag	No PTY = no supervision needed

Concurrency

Cap maxConcurrency at 4-6. Spawning 10+ agents simultaneously causes broker timeouts.

Parallel agents	maxConcurrency
2-4	4 (default safe)
5-10	5
10+	6-8 max

Common Mistakes

Mistake	Fix
Treating relay as transport, not as a coordination layer (every step is preset: 'worker', every handoff is {{steps.X.output}})	Default to Conversation shape for non-trivial work — interactive agents on a shared channel. Pipeline-shape is only correct when the work could be expressed as a `bash
Interactive agents on a channel whose task strings don't tell them to talk to each other	Pick a Chat-Native Coordination Recipe (Q/A, Broadcast/Ack, Peer Review, Standup, Hand-Off) and bake it into the task prompt — otherwise you're paying for a chat substrate you're not using
All workflows run sequentially	Group independent workflows into parallel waves (4-7x speedup)
Every step depends on the previous one	Only add dependsOn when there's a real data dependency
Self-review step with no timeout	Set timeout: 300_000 (5 min) — Codex hangs in non-interactive review
One giant workflow per feature	Split into smaller workflows that can run in parallel waves
Adding exit instructions to tasks	Runner handles self-termination automatically
Setting timeoutMs on agents/steps	Use global .timeout() only
Using general channel	Set .channel('wf-name') for isolation
{{steps.X.output}} without dependsOn: ['X']	Output won't be available yet
Requiring exact sentinel as only completion gate	Use exit_code or file_exists verification
Writing 100-line task prompts	Split into lead + workers on a channel
maxConcurrency: 16 with many parallel steps	Cap at 5-6
Non-interactive agent reading large files via tools	Pre-read in deterministic step, inject via {{steps.X.output}}
Workers depending on lead step (deadlock)	Both depend on shared context step
fan-out/hub-spoke for simple parallel workers	Use dag instead
pipeline but expecting auto-supervisor	Only hub patterns auto-harden. Use .pattern('supervisor')
Workers without preset: 'worker' in one-shot DAG lead+worker flows	Add preset for clean stdout when chaining {{steps.X.output}} (not needed for interactive team patterns)
Using _ in YAML numbers (timeoutMs: 1_200_000)	YAML doesn't support _ separators
Workflow timeout under 30 min for complex workflows	Use 3600000 (1 hour) as default
Using require() in ESM projects	Check package.json for "type": "module" — use import if ESM
Wrapping in async function main() in ESM	ESM supports top-level await — no wrapper needed
Using createWorkflowRenderer	Does not exist. Use .run({ cwd: process.cwd() })
export default workflow(...)...build()	No .build(). Chain ends with .run() — the file must call .run(), not just export config
Relative import '../workflows/builder.js'	Use import { workflow } from '@agent-relay/sdk/workflows'
Hardcoded model strings (model: 'opus')	Use constants: import { ClaudeModels } from '@agent-relay/config' → model: ClaudeModels.OPUS
Thinking agent-relay run inspects exports	It executes the file as a subprocess. Only .run() invocations trigger steps
pattern('single') on cloud runner	Not supported — use dag
pattern('supervisor') with one agent	Same agent is owner + specialist. Use dag
Invalid verification type (type: 'deterministic')	Only exit_code, output_contains, file_exists, custom are valid
Chaining {{steps.X.output}} from interactive agents	PTY output is garbled. Use deterministic steps or preset: 'worker'
Single step editing 4+ files	Agents modify 1-2 then exit. Split to one file per step with verify gates
Relying on agents to git commit	Agents emit markers without running git. Use deterministic commit step
File-writing steps without file_exists verification	exit_code auto-passes even if no file written
Manual peer fanout in handleChannelMessage()	Use broker-managed channel subscriptions — broker fans out to all subscribers automatically
Client-side personaNames.has(from) filtering	Use relay.subscribe()/relay.unsubscribe() — only subscribed agents receive messages
Agents receiving noisy cross-channel messages during focused work	Use relay.mute({ agent, channel }) to silence non-primary channels without leaving them
Hardcoding all channels at spawn time	Use agent.subscribe() / agent.unsubscribe() for dynamic channel membership post-spawn
Using preset: 'worker' for Codex in interactive team patterns when coordination is needed	Codex interactive mode works fine with PTY channel injection. Drop the preset for interactive team patterns (keep it for one-shot DAG workers where clean stdout matters)
Separate reviewer agent from lead in interactive team	Merge lead + reviewer into one interactive Claude agent — reviews between rounds, fewer agents
Not printing PR URL after createGitHubStep({ action: 'createPR' })	Capture html_url with output: { mode: 'data', format: 'json', path: 'html_url' } and echo or write it in a final deterministic step
Workflow ending without worktree + PR for cross-repo changes	Add setup-worktree at start and push-and-pr + cleanup-worktree at end

YAML Alternative

```yaml

version: '1.0'
name: my-workflow
swarm:
  pattern: dag
  channel: wf-my-workflow
agents:
  - name: lead
    cli: claude
    role: Architect
  - name: worker
    cli: codex
    role: Implementer
workflows:
  - name: default
    steps:
      - name: plan
        agent: lead
        task: 'Produce a detailed implementation plan.'
      - name: implement
        agent: worker
        task: 'Implement: {{steps.plan.output}}'
        dependsOn: [plan]
        verification:
          type: exit_code

Available Swarm Patterns

dag (default), fan-out, pipeline, hub-spoke, consensus, mesh, handoff, cascade, debate, hierarchical, map-reduce, scatter-gather, supervisor, reflection, red-team, verifier, auction, escalation, saga, circuit-breaker, blackboard, swarm

See skill choosing-swarm-patterns for pattern selection guidance.