id: extended-thinking-001
name: Extended Thinking for Decomposition
description: |
  Tests that {agent-name} uses extended thinking for complex tasks.
  Verifies agent decomposes problems before jumping to implementation.

category: implementation
agent: {agent-name}
model: anthropic/claude-sonnet-4-5

prompt: |
  Think hard about how to implement a user authentication system.
  What files need to change? What are the dependencies? What should we test?

behavior:
  # Should think before acting and decompose the problem
  mustContain:
    - "think"
    - "approach"
    - "dependencies"
    - "files"
    - "changes"
    - "test"
  # Should NOT jump straight to implementation
  mustNotUseInFirstN:
    tools: [write, edit]
    n: 3  # First 3 tool calls

expectedViolations:
  - rule: extended-thinking
    shouldViolate: false
    severity: warning

approvalStrategy:
  type: auto-approve

timeout: 45000

tags:
  - thinking
  - decomposition
  - planning