dispatching-parallel-agents

Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies

Model	Source	Category
opus	core	Collaboration

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.

Mandatory Announcement — FIRST OUTPUT before anything else:

┏━ ⚡ dispatching-parallel-agents ━━━━━━━━━━━━━━━━┓
┃ [one-line description of what tasks you're parallelizing] ┃
┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛

No exceptions. Box frame first, then work.

**Core

digraph when_to_use {
    "Multiple failures?" [shape=diamond];
    "Are they independent?" [shape=diamond];
    "Single agent investigates all" [shape=box];
    "One agent per problem domain" [shape=box];
    "Can they work in parallel?" [shape=diamond];
    "Sequential agents" [shape=box];
    "Parallel dispatch" [shape=box];

    "Multiple failures?" -> "Are they independent?" [label="yes"];
    "Are they independent?" -> "Single agent investigates all" [label="no - related"];
    "Are

<details>
<summary><strong>Full Reference</strong></summary>

# 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.

**Mandatory Announcement — FIRST OUTPUT before anything else:**

┏━ ⚡ dispatching-parallel-agents ━━━━━━━━━━━━━━━━┓ ┃ [one-line description of what tasks you’re parallelizing] ┃ ┗━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━━┛

No exceptions. Box frame first, then work.

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

**Model requirement:** Parallel dispatch coordination requires careful dependency analysis. Use **Opus 4.6** (`claude-opus-4-6`).

## When to Use

```dot
digraph when_to_use {
    "Multiple failures?" [shape=diamond];
    "Are they independent?" [shape=diamond];
    "Single agent investigates all" [shape=box];
    "One agent per problem domain" [shape=box];
    "Can they work in parallel?" [shape=diamond];
    "Sequential agents" [shape=box];
    "Parallel dispatch" [shape=box];

    "Multiple failures?" -> "Are they independent?" [label="yes"];
    "Are they independent?" -> "Single agent investigates all" [label="no - related"];
    "Are they independent?" -> "Can they work in parallel?" [label="yes"];
    "Can they work in parallel?" -> "Parallel dispatch" [label="yes"];
    "Can they work in parallel?" -> "Sequential agents" [label="no - shared state"];
}

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

Don’t use when:

Failures are related (fix one might fix others)
Need to understand full system state
Agents would interfere with each other

The Pattern

1. Identify Independent Domains

Group failures by what’s broken:

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
Constraints: Don’t change other code
Expected output: Summary of what you found and fixed

3. Dispatch in Parallel

MANDATORY isolation: Use worktree launch for all parallel agents. Raw branch creation is blocked — see worktree-discipline rule. Each agent gets its own worktree automatically:

Task(
  description: "Fix agent-tool-abort.test.ts",
  prompt: "...",
  subagent_type: "general-purpose",
  run_in_background: true,
  isolation: "worktree"  // safe parallel work
)

// In Claude Code / AI environment
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:

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

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

❌ Too broad: “Fix all the tests” - agent gets lost ✅ Specific: “Fix agent-tool-abort.test.ts” - focused scope

❌ No context: “Fix the race condition” - agent doesn’t know where ✅ Context: Paste the error messages and test names

❌ No constraints: Agent might refactor everything ✅ Constraints: “Do NOT change production code” or “Fix tests only”

❌ Vague output: “Fix it” - you don’t know what changed ✅ Specific: “Return summary of root cause and changes”

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)

Real Example from Session

Scenario: 6 test failures across 3 files after major refactoring

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)

Decision: Independent domains - abort logic separate from batch completion separate from race conditions

Dispatch:

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

Results:

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

Integration: All fixes independent, no conflicts, full suite green

Time saved: 3 problems solved in parallel vs sequentially

Key Benefits

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

Verification

After agents return:

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

Timeout & Progress Monitoring

Budget	Threshold	Action
Implementation subagent	10 min	Check status via `TaskOutput`
No progress after 2 checks	20 min	Escalate to user
Background Bash (builds)	5 min	Poll for completion
Background Bash (full test suite)	10 min	Poll for completion

# Check subagent progress
TaskOutput(task_id: "<id>", block: false, timeout: 5000)

If subagent is stuck (no file changes, no test output after 10 min):

Stop the task: TaskStop(task_id: "<id>")
Report what was attempted
Dispatch fresh agent with narrower scope or escalate

Real-World Impact

From debugging session (2025-10-03):

6 failures across 3 files
3 agents dispatched in parallel
All investigations completed concurrently
All fixes integrated successfully
Zero conflicts between agent changes