Dispatching Parallel Agents

Dispatching Parallel Agents

Overview

When you have multiple unrelated failures (different test files, different subsystems, different bugs), investigating them sequentially wastes time. Each investigation is independent and can happen in parallel.

Core principle: Dispatch one agent per independent problem domain. Let them work concurrently.

When to Use

Multiple tasks/failures?
    ↓ yes
Are they independent?
    ↓ yes (not related)
Can they work in parallel?
    ↓ yes (no shared state)
→ Use dispatching-parallel-agents

Use when:

• 3+ test files failing with different root causes
• Multiple subsystems broken independently
• Each problem can be understood without context from others
• No shared state between investigations
• Multiple independent implementation tasks

Don't use when:

• Failures are related (fix one might fix others)
• Need to understand full system state first
• Agents would interfere with each other (editing same files)
• Tasks have sequential dependencies

The Pattern

1. Identify Independent Domains

Group failures/tasks by what's broken or what they do:

• File A tests: Tool approval flow
• File B tests: Batch completion behavior
• File C tests: Abort functionality

Each domain is independent - fixing tool approval doesn't affect abort tests.

2. Create Focused Agent Tasks

Each agent gets:

• Specific scope: One test file or subsystem
• Clear goal: Make these tests pass / Complete this task
• Constraints: Don't change other code
• Expected output: Summary of what you found and fixed

3. Dispatch in Parallel

// In Claude Code - dispatch all at once
Task("Fix agent-tool-abort.test.ts failures")
Task("Fix batch-completion-behavior.test.ts failures")
Task("Fix tool-approval-race-conditions.test.ts failures")
// All three run concurrently

4. Review and Integrate

When agents return:

• Read each summary
• Verify fixes don't conflict
• Run full test suite
• Integrate all changes

Agent Prompt Structure

Good agent prompts are:

1. Focused - One clear problem domain
2. Self-contained - All context needed to understand the problem
3. Specific about output - What should the agent return?

Example prompt:

Fix the 3 failing tests in src/agents/agent-tool-abort.test.ts:

1. "should abort tool with partial output capture" - expects 'interrupted at' in message
2. "should handle mixed completed and aborted tools" - fast tool aborted instead of completed
3. "should properly track pendingToolCount" - expects 3 results but gets 0

These are timing/race condition issues. Your task:

1. Read the test file and understand what each test verifies
2. Identify root cause - timing issues or actual bugs?
3. Fix by:
   - Replacing arbitrary timeouts with event-based waiting
   - Fixing bugs in abort implementation if found
   - Adjusting test expectations if testing changed behavior

Do NOT just increase timeouts - find the real issue.

Return: Summary of what you found and what you fixed.

Common Mistakes

When NOT to Use

• Related failures: Fixing one might fix others - investigate together first
• Need full context: Understanding requires seeing entire system
• Exploratory debugging: You don't know what's broken yet
• Shared state: Agents would interfere (editing same files, using same resources)
• Sequential dependencies: Task B needs Task A's output

SuperSpec Integration

Parallel Task Implementation

When plan has independent tasks:

Phase 1 has:
- Task 1.1: Implement auth service
- Task 1.2: Implement user service
- Task 1.3: Implement logging service

These are independent → can dispatch in parallel

But remember: Each agent must still follow TDD individually.

Parallel Test Fixing

When multiple Scenarios have failing tests:

Failing:
- Scenario: Valid login → auth.test.ts
- Scenario: User creation → user.test.ts
- Scenario: Audit logging → logging.test.ts

Independent failures → dispatch parallel agents

Example Flow

You: I see 6 test failures across 3 files after refactoring.

[Analyze failures]
- agent-tool-abort.test.ts: 3 failures (timing issues)
- batch-completion-behavior.test.ts: 2 failures (tools not executing)
- tool-approval-race-conditions.test.ts: 1 failure (execution count = 0)

[Verify independence]
- Abort logic separate from batch completion
- Batch completion separate from race conditions
- No shared state between investigations

[Dispatch in parallel]
Agent 1 → Fix agent-tool-abort.test.ts
Agent 2 → Fix batch-completion-behavior.test.ts
Agent 3 → Fix tool-approval-race-conditions.test.ts

[Wait for all agents]

Agent 1: Replaced timeouts with event-based waiting
Agent 2: Fixed event structure bug (threadId in wrong place)
Agent 3: Added wait for async tool execution to complete

[Verify integration]
$ npm test
All tests pass

[Integration successful - no conflicts]

Verification After Parallel Execution

After agents return:

1. Review each summary - Understand what changed
2. Check for conflicts - Did agents edit same code?
3. Run full suite - Verify all fixes work together
4. Spot check - Agents can make systematic errors

# After all agents complete
git status                    # See all changes
git diff                      # Review changes
npm test                      # Verify everything works

Key Benefits

1. Parallelization - Multiple investigations happen simultaneously
2. Focus - Each agent has narrow scope, less context to track
3. Independence - Agents don't interfere with each other
4. Speed - 3 problems solved in time of 1

Red Flags

Never:

• Dispatch parallel agents for related issues
• Let agents work on same files
• Skip verification after parallel completion
• Assume agents won't conflict

Always:

• Verify independence before dispatching
• Give clear, focused scope
• Review all results before integrating
• Run full test suite after integration

Integration

Called by:

• When encountering multiple independent failures
• When plan has independent tasks

Pairs with:

• systematic-debugging - For analyzing failures first
• superspec:execute - For parallel task implementation