# Test Cases for review-adversarial-general.xml with also_consider input
#
# Purpose: Evaluate how the optional also_consider input influences review findings
# Content: All tests use sample-content.md (User Authentication API docs)
#
# To run: Manually invoke the task with each configuration and compare outputs

test_cases:
  # BASELINE - No also_consider
  - id: TC01
    name: "Baseline - no also_consider"
    description: "Control test with no also_consider input"
    also_consider: null
    expected_behavior: "Generic adversarial findings across all aspects"

  # DOCUMENTATION-FOCUSED
  - id: TC02
    name: "Documentation - reader confusion"
    description: "Nudge toward documentation UX issues"
    also_consider:
      - What would confuse a first-time reader?
      - What questions are left unanswered?
      - What could be interpreted multiple ways?
      - What jargon is unexplained?
    expected_behavior: "More findings about clarity, completeness, reader experience"

  - id: TC03
    name: "Documentation - examples and usage"
    description: "Nudge toward practical usage gaps"
    also_consider:
      - Missing code examples
      - Unclear usage patterns
      - Edge cases not documented
    expected_behavior: "More findings about practical application gaps"

  # SECURITY-FOCUSED
  - id: TC04
    name: "Security review"
    description: "Nudge toward security concerns"
    also_consider:
      - Authentication vulnerabilities
      - Token handling issues
      - Input validation gaps
      - Information disclosure risks
    expected_behavior: "More security-related findings"

  # API DESIGN-FOCUSED
  - id: TC05
    name: "API design"
    description: "Nudge toward API design best practices"
    also_consider:
      - REST conventions not followed
      - Inconsistent response formats
      - Missing pagination or filtering
      - Versioning concerns
    expected_behavior: "More API design pattern findings"

  # SINGLE ITEM
  - id: TC06
    name: "Single item - error handling"
    description: "Test with just one also_consider item"
    also_consider:
      - Error handling completeness
    expected_behavior: "Some emphasis on error handling while still covering other areas"

  # BROAD/VAGUE
  - id: TC07
    name: "Broad items"
    description: "Test with vague also_consider items"
    also_consider:
      - Quality issues
      - Things that seem off
    expected_behavior: "Minimal change from baseline - items too vague to steer"

  # VERY SPECIFIC
  - id: TC08
    name: "Very specific items"
    description: "Test with highly specific also_consider items"
    also_consider:
      - Is the JWT token expiration documented?
      - Are refresh token mechanics explained?
      - What happens on concurrent sessions?
    expected_behavior: "Specific findings addressing these exact questions if gaps exist"

  # MIXED DOMAINS
  - id: TC09
    name: "Mixed domain concerns"
    description: "Test with items from different domains"
    also_consider:
      - Security vulnerabilities
      - Reader confusion points
      - API design inconsistencies
      - Performance implications
    expected_behavior: "Balanced findings across multiple domains"

  # CONTRADICTORY/UNUSUAL
  - id: TC10
    name: "Contradictory items"
    description: "Test resilience with odd inputs"
    also_consider:
      - Things that are too detailed
      - Things that are not detailed enough
    expected_behavior: "Reviewer handles gracefully, finds issues in both directions"