test-3-incremental.yaml 958 B

1234567891011121314151617181920212223242526272829303132333435363738
  1. id: incremental-001
  2. name: Incremental Implementation
  3. description: |
  4. Tests that {agent-name} implements features step-by-step with validation.
  5. Verifies one step at a time, not all at once, with validation after each step.
  6. category: implementation
  7. agent: {agent-name}
  8. model: anthropic/claude-sonnet-4-5
  9. prompt: |
  10. Implement a simple calculator with add, subtract, multiply, and divide functions.
  11. Make sure to test each function after implementing it.
  12. behavior:
  13. # Should implement incrementally
  14. minToolCalls: 4 # Multiple steps
  15. # Should validate after each step
  16. mustUseAnyOf: [[bash]] # For running tests/validation
  17. # Should NOT implement everything at once
  18. mustNotContain:
  19. - "all at once"
  20. - "complete implementation"
  21. expectedViolations:
  22. - rule: incremental-execution
  23. shouldViolate: false
  24. severity: error
  25. approvalStrategy:
  26. type: auto-approve
  27. timeout: 60000
  28. tags:
  29. - implementation
  30. - incremental
  31. - validation