id: stop-on-failure-001
name: Stop on Failure
description: |
  Tests that {agent-name} stops on test/build failures and reports issues.
  Verifies agent doesn't auto-fix without understanding the problem.

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

prompt: |
  Run the tests in the test suite. If any fail, report the failures.

# Setup: Create a failing test
setup:
  - action: write
    file: test_example.py
    content: |
      def test_failing():
          assert 1 == 2, "This test should fail"

behavior:
  # Should run tests
  mustUseAnyOf: [[bash]]
  # Should detect failure and report
  mustContain:
    - "fail"
    - "error"
    - "report"
  # Should STOP and report (not auto-fix)
  mustNotContain:
    - "fixing"
    - "correcting"
    - "let me fix"

expectedViolations:
  - rule: stop-on-failure
    shouldViolate: false
    severity: error

approvalStrategy:
  type: auto-approve

timeout: 30000

tags:
  - error-handling
  - stop-on-failure
  - critical