Writing Agent Relay Workflows

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

Quick Reference

```typescript

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);

⚡ 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);
});

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

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
• 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

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'], ... })

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.

Concurrency

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

Common Mistakes

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.