OpenAgentsControl/evals/results/latest.json

{
  "meta": {
    "timestamp": "2026-01-11T21:13:52.792Z",
    "agent": "task-manager",
    "model": "opencode/minimax-m2.1-free",
    "framework_version": "0.1.0",
    "git_commit": "c8733ee"
  },
  "summary": {
    "total": 1,
    "passed": 0,
    "failed": 1,
    "duration_ms": 62017,
    "pass_rate": 0
  },
  "by_category": {
    "developer": {
      "passed": 0,
      "total": 1
    }
  },
  "tests": [
    {
      "id": "core-task-manager-smoke-test",
      "category": "developer",
      "passed": false,
      "duration_ms": 62017,
      "events": 32,
      "approvals": 0,
      "violations": {
        "total": 4,
        "errors": 3,
        "warnings": 1,
        "details": [
          {
            "type": "missing-approval",
            "severity": "error",
            "message": "Execution tool 'write' called without requesting approval",
            "expected": true
          },
          {
            "type": "missing-approval",
            "severity": "error",
            "message": "Execution tool 'task' called without requesting approval",
            "expected": true
          },
          {
            "type": "insufficient-read",
            "severity": "warning",
            "message": "Read/execution ratio < 1 (0.50)"
          },
          {
            "type": "missing-required-tool",
            "severity": "error",
            "message": "Required tool 'bash' was not used"
          }
        ]
      }
    }
  ]
}