{
  "evaluations": [
    {
      "critical_failure_count": 2,
      "decision": "BLOCK",
      "decision_reasons": [
        "critical failures 2 exceed maximum 0",
        "pass rate 0.6667 is below 0.9000"
      ],
      "failures_by_severity": {
        "critical": 2,
        "major": 2,
        "minor": 0
      },
      "label": "baseline-v1",
      "mean_cost_usd": 0.01325,
      "p95_latency_ms": 1100.0,
      "pass_rate": 0.666667,
      "passed": 8,
      "total": 12
    },
    {
      "critical_failure_count": 0,
      "decision": "REVIEW",
      "decision_reasons": [
        "p95 latency 5200 ms exceeds 2500 ms"
      ],
      "failures_by_severity": {
        "critical": 0,
        "major": 1,
        "minor": 0
      },
      "label": "candidate-v2",
      "mean_cost_usd": 0.0125,
      "p95_latency_ms": 5200.0,
      "pass_rate": 0.916667,
      "passed": 11,
      "total": 12
    },
    {
      "critical_failure_count": 0,
      "decision": "PASS",
      "decision_reasons": [
        "all quality and performance thresholds passed"
      ],
      "failures_by_severity": {
        "critical": 0,
        "major": 0,
        "minor": 0
      },
      "label": "candidate-v3",
      "mean_cost_usd": 0.011,
      "p95_latency_ms": 2050.0,
      "pass_rate": 1.0,
      "passed": 12,
      "total": 12
    }
  ],
  "schema_version": 1,
  "thresholds": {
    "maximum_critical_failures": 0,
    "maximum_mean_cost_usd": 0.025,
    "maximum_p95_latency_ms": 2500.0,
    "minimum_pass_rate": 0.9
  }
}
