dispatching-parallel-agents

Jesse Vincent ｜ Agent 與工作流 ｜ 原文 ｜ MIT

遇到互不相關的獨立問題時，一個問題一個 agent 平行處理

---
name: dispatching-parallel-agents
description: 當你面對 2 個以上、可以在沒有共享狀態或先後依賴的情況下各自處理的獨立任務時使用
---

# Dispatching Parallel Agents

## 概述

你把任務委派給 context 隔離的專門 agent。精準地寫好它們的指示和 context，確保它們專注、把任務做好。它們絕對不該繼承你這個 session 的 context 或歷史，你要自己組出它們剛好需要的東西。這樣也能替你自己保留 context，專心做協調的工作。

當你有多個互不相關的失敗（不同的測試檔、不同的子系統、不同的 bug），一個一個依序調查是在浪費時間。每個調查都是獨立的，可以平行進行。

**核心原則：** 每個獨立的問題領域派一個 agent，讓它們同時工作。

## 何時使用

```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"];
}
```

**適合使用：**
- 3 個以上的測試檔失敗，而且 root cause 各不相同
- 多個子系統各自獨立壞掉
- 每個問題不需要其他問題的 context 就能理解
- 各調查之間沒有共享狀態

**不適合使用：**
- 失敗之間有關聯（修好一個可能就修好其他的）
- 需要了解整個系統的狀態
- Agent 之間會互相干擾

## 模式

### 1. 找出獨立的領域

依壞掉的東西把失敗分組：
- 檔案 A 的測試：Tool 核准流程
- 檔案 B 的測試：批次完成的行為
- 檔案 C 的測試：中止功能

每個領域都是獨立的，修好 tool 核准不會影響中止的測試。

### 2. 建立聚焦的 Agent 任務

每個 agent 拿到：
- **明確的範圍：** 一個測試檔或一個子系統
- **清楚的目標：** 讓這些測試通過
- **限制：** 不要改其他程式碼
- **預期輸出：** 你發現什麼、修了什麼的摘要

### 3. 平行派出

在同一個回應裡一次發出這三個 subagent 的派工，它們就會平行執行：

```text
Subagent (general-purpose): "Fix agent-tool-abort.test.ts failures"
Subagent (general-purpose): "Fix batch-completion-behavior.test.ts failures"
Subagent (general-purpose): "Fix tool-approval-race-conditions.test.ts failures"
# All three run concurrently.
```

一個回應裡有多個派工呼叫 = 平行執行。一個回應只放一個 = 依序執行。

### 4. 審查並整合

Agent 回來之後：
- 讀每一份摘要
- 確認修正之間沒有衝突
- 跑完整的測試套件
- 整合所有變更

## Agent Prompt 結構

好的 agent prompt 是：
1. **聚焦的**：一個清楚的問題領域
2. **自給自足的**：包含理解問題所需的所有 context
3. **對輸出很明確的**：agent 該回傳什麼？

```markdown
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.
```

## 常見錯誤

**❌ 太籠統：** 「Fix all the tests」，agent 會迷路
**✅ 明確：** 「Fix agent-tool-abort.test.ts」，範圍聚焦

**❌ 沒有 context：** 「Fix the race condition」，agent 不知道在哪裡
**✅ 有 context：** 貼上錯誤訊息和測試名稱

**❌ 沒有限制：** agent 可能把所有東西都重構一遍
**✅ 有限制：** 「Do NOT change production code」或「Fix tests only」

**❌ 輸出含糊：** 「Fix it」，你不知道改了什麼
**✅ 明確：** 「Return summary of root cause and changes」

## 何時不要使用

**失敗之間有關聯：** 修好一個可能就修好其他的，先一起調查
**需要完整的 context：** 要理解問題必須看到整個系統
**探索式除錯：** 你還不知道是什麼壞了
**共享狀態：** Agent 會互相干擾（編輯同樣的檔案、使用同樣的資源）

## Session 中的真實範例

**情境：** 大規模重構之後，3 個檔案共 6 個測試失敗

**失敗：**
- agent-tool-abort.test.ts：3 個失敗（時序問題）
- batch-completion-behavior.test.ts：2 個失敗（tool 沒有執行）
- tool-approval-race-conditions.test.ts：1 個失敗（執行次數 = 0）

**決定：** 獨立的領域：中止邏輯、批次完成和 race condition 彼此是分開的

**派工：**
```
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
```

**結果：**
- Agent 1：把 timeout 換成基於事件的等待
- Agent 2：修好事件結構的 bug（threadId 放錯位置）
- Agent 3：加上等待非同步 tool 執行完成

**整合：** 所有修正都是獨立的，沒有衝突，整套測試全綠

## 驗證

Agent 回來之後：
1. **審查每一份摘要**：了解改了什麼
2. **檢查衝突**：agent 有沒有編輯同一段程式碼？
3. **跑完整套件**：確認所有修正合在一起也能運作
4. **抽樣檢查**：agent 可能會犯系統性的錯誤

---
name: dispatching-parallel-agents
description: Use when facing 2+ independent tasks that can be worked on without shared state or sequential dependencies
---

# Dispatching Parallel Agents

## Overview

You delegate tasks to specialized agents with isolated context. By precisely crafting their instructions and context, you ensure they stay focused and succeed at their task. They should never inherit your session's context or history — you construct exactly what they need. This also preserves your own context for coordination work.

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

```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

Issue all three subagent dispatches in the same response — they run in parallel:

```text
Subagent (general-purpose): "Fix agent-tool-abort.test.ts failures"
Subagent (general-purpose): "Fix batch-completion-behavior.test.ts failures"
Subagent (general-purpose): "Fix tool-approval-race-conditions.test.ts failures"
# All three run concurrently.
```

Multiple dispatch calls in one response = parallel execution. One per response = sequential.

### 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?

```markdown
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

## Verification

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