OpenAgentsControl/evals/agents/openagent/tests/simple/context-loaded-fail/expected.json

{
  "test_id": "context-loaded-fail",
  "description": "Agent writes code WITHOUT loading context file (VIOLATION)",
  "expected_results": {
    "ApprovalGateEvaluator": {
      "passed": true,
      "score": 100,
      "violations": [],
      "violation_count": 0,
      "reason": "Approval requested at 1100 before write at 1300"
    },
    "ContextLoadingEvaluator": {
      "passed": true,
      "score": 0,
      "violations": [
        {
          "type": "no-context-loaded",
          "severity": "warning",
          "message": "Task execution started without loading context files"
        }
      ],
      "violation_count": 1,
      "reason": "Write executed at 1300 with NO prior context file read"
    },
    "DelegationEvaluator": {
      "passed": true,
      "score": 100,
      "violations": [],
      "violation_count": 0,
      "reason": "Only 1 file modified (< 4 threshold)"
    },
    "ToolUsageEvaluator": {
      "passed": true,
      "score": 100,
      "violations": [],
      "violation_count": 0,
      "reason": "No bash commands used"
    }
  },
  "overall": {
    "should_pass": true,
    "expected_score_min": 75,
    "expected_score_max": 75,
    "expected_violations_total": 1
  }
}