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.
Nesting and scale: Subagents can spawn their own subagents up to 5 levels deep, so a dispatched agent owning a large domain can fan out helpers for its sub-steps rather than doing everything serially. When the work-list is large, repetitive, or unknown in size (every route, every package in a monorepo, every finding to verify), stop hand-dispatching and escalate to a dynamic Workflow — describe the task and include the word "workflow" so an orchestration script pipelines the items across background subagents with a verification stage built in. Rule of thumb: a few independent tasks → dispatch agents here; dozens of items or fan-out-then-verify → a Workflow.
When to Use
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
// 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 the agent needs, INCLUDING relevant code snippets
- Specific about output - What should the agent return?
- Permission to explore - Agent can read files it needs, not just files you anticipated
The #1 reason subagents fail is context starvation. The controller thinks it provided enough context but didn't. When in doubt, include more:
- Paste the actual error messages, not paraphrases
- Paste relevant code snippets inline (don't make the agent find them)
- Name the exact files and line numbers involved
- Describe the patterns/conventions the codebase uses
- Tell the agent what adjacent files exist and what they do
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. The abort implementation is in
src/agents/agent-tool-handler.ts (the abortTool method around line 150).
Tests use a helper createMockToolStream() from test-utils.ts.
Your task:
1. Read the test file and the implementation file
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
4. You may read other files if needed to understand the system
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, test names, AND relevant source code inline
❌ 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"
❌ "Don't explore": Agent can't read files → guesses → fails → you redo the work ✅ Permission: "Read any files you need to understand the system"
❌ Tight tool budget (15 calls): Agent rushes → BLOCKED → you redo the work ✅ Reasonable budget: Let agents work until done, cap at 25-30 for safety
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
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 c