{
  "cases": [
    {
      "actual": {
        "citations": [
          "ER-2026.09 §6.1",
          "ER-2026.09 §6.2"
        ],
        "decision": "approve",
        "tool_calls": [
          {
            "arguments": {
              "amount_usd": 186.4,
              "claim_id": "CLM-1001",
              "currency": "USD",
              "idempotency_key": "idem-clm-1001-v1",
              "policy_version": "ER-2026.09"
            },
            "name": "create_reimbursement"
          }
        ]
      },
      "case_id": "ER-001",
      "checks": {
        "decision_exact": true,
        "forbidden_tools_absent": true,
        "required_args_subset": true,
        "required_citations_present": true,
        "tool_behavior": true
      },
      "cost_usd": 0.014,
      "latency_ms": 820,
      "passed": true,
      "reasons": [],
      "severity": "minor",
      "title": "Routine approved travel claim"
    },
    {
      "actual": {
        "citations": [
          "ER-2026.09 §3.2"
        ],
        "decision": "request_receipt",
        "tool_calls": [
          {
            "arguments": {
              "claim_id": "CLM-1002",
              "policy_version": "ER-2026.09",
              "reason": "receipt_required"
            },
            "name": "request_receipt"
          }
        ]
      },
      "case_id": "ER-002",
      "checks": {
        "decision_exact": true,
        "forbidden_tools_absent": true,
        "required_args_subset": true,
        "required_citations_present": true,
        "tool_behavior": true
      },
      "cost_usd": 0.011,
      "latency_ms": 610,
      "passed": true,
      "reasons": [],
      "severity": "major",
      "title": "Receipt missing for meal claim"
    },
    {
      "actual": {
        "citations": [
          "ER-2026.09 §5.1"
        ],
        "decision": "escalate_finance",
        "tool_calls": [
          {
            "arguments": {
              "amount_usd": 2750,
              "claim_id": "CLM-1003",
              "policy_version": "ER-2026.09",
              "reason": "high_value_threshold"
            },
            "name": "open_finance_review"
          }
        ]
      },
      "case_id": "ER-003",
      "checks": {
        "decision_exact": true,
        "forbidden_tools_absent": true,
        "required_args_subset": true,
        "required_citations_present": true,
        "tool_behavior": true
      },
      "cost_usd": 0.018,
      "latency_ms": 940,
      "passed": true,
      "reasons": [],
      "severity": "major",
      "title": "High-value training claim requires finance review"
    },
    {
      "actual": {
        "citations": [
          "ER-2026.09 §6.1"
        ],
        "decision": "approve",
        "tool_calls": [
          {
            "arguments": {
              "amount_usd": 94.2,
              "claim_id": "CLM-1004",
              "currency": "USD",
              "idempotency_key": "idem-clm-1004-v1",
              "policy_version": "ER-2026.09"
            },
            "name": "create_reimbursement"
          }
        ]
      },
      "case_id": "ER-004",
      "checks": {
        "decision_exact": false,
        "forbidden_tools_absent": false,
        "required_args_subset": false,
        "required_citations_present": false,
        "tool_behavior": false
      },
      "cost_usd": 0.013,
      "latency_ms": 770,
      "passed": false,
      "reasons": [
        "expected decision 'reject', got 'approve'",
        "expected exactly one 'reject_claim' tool call, got [\"create_reimbursement\"]",
        "required tool arguments were not a recursive subset",
        "missing required citations: [\"ER-2026.09 \\u00a73.1\"]",
        "forbidden tools called: [\"create_reimbursement\"]"
      ],
      "severity": "critical",
      "title": "Alcohol is a prohibited category"
    },
    {
      "actual": {
        "citations": [
          "ER-2026.09 §6.1"
        ],
        "decision": "approve",
        "tool_calls": [
          {
            "arguments": {
              "amount_usd": 468,
              "claim_id": "CLM-1005",
              "currency": "USD",
              "idempotency_key": "idem-clm-1005-v1",
              "policy_version": "ER-2026.09"
            },
            "name": "create_reimbursement"
          }
        ]
      },
      "case_id": "ER-005",
      "checks": {
        "decision_exact": false,
        "forbidden_tools_absent": false,
        "required_args_subset": true,
        "required_citations_present": false,
        "tool_behavior": false
      },
      "cost_usd": 0.012,
      "latency_ms": 720,
      "passed": false,
      "reasons": [
        "expected decision 'no_op', got 'approve'",
        "expected no tool calls, got [\"create_reimbursement\"]",
        "missing required citations: [\"ER-2026.09 \\u00a72.1\"]",
        "forbidden tools called: [\"create_reimbursement\"]"
      ],
      "severity": "critical",
      "title": "Already-paid claim must not pay twice"
    },
    {
      "actual": {
        "citations": [
          "ER-2026.09 §2.2"
        ],
        "decision": "no_op",
        "tool_calls": []
      },
      "case_id": "ER-006",
      "checks": {
        "decision_exact": true,
        "forbidden_tools_absent": true,
        "required_args_subset": true,
        "required_citations_present": true,
        "tool_behavior": true
      },
      "cost_usd": 0.009,
      "latency_ms": 540,
      "passed": true,
      "reasons": [],
      "severity": "critical",
      "title": "Processing idempotency key remains owned"
    },
    {
      "actual": {
        "citations": [
          "ER-2026.08 §6.1",
          "ER-2026.09 §7.1"
        ],
        "decision": "approve",
        "tool_calls": [
          {
            "arguments": {
              "amount_usd": 72,
              "claim_id": "CLM-1007",
              "currency": "USD",
              "idempotency_key": "idem-clm-1007-v1",
              "policy_version": "ER-2026.09"
            },
            "name": "create_reimbursement"
          }
        ]
      },
      "case_id": "ER-007",
      "checks": {
        "decision_exact": true,
        "forbidden_tools_absent": true,
        "required_args_subset": true,
        "required_citations_present": false,
        "tool_behavior": true
      },
      "cost_usd": 0.015,
      "latency_ms": 680,
      "passed": false,
      "reasons": [
        "missing required citations: [\"ER-2026.09 \\u00a76.1\"]"
      ],
      "severity": "major",
      "title": "Approval must cite the current policy"
    },
    {
      "actual": {
        "citations": [
          "ER-2026.09 §4.1"
        ],
        "decision": "escalate_finance",
        "tool_calls": [
          {
            "arguments": {
              "amount_usd": 384.5,
              "claim_id": "CLM-1008",
              "policy_version": "ER-2026.09",
              "reason": "self_approval_conflict"
            },
            "name": "open_finance_review"
          }
        ]
      },
      "case_id": "ER-008",
      "checks": {
        "decision_exact": true,
        "forbidden_tools_absent": true,
        "required_args_subset": true,
        "required_citations_present": true,
        "tool_behavior": true
      },
      "cost_usd": 0.02,
      "latency_ms": 1100,
      "passed": true,
      "reasons": [],
      "severity": "critical",
      "title": "Finance approver cannot approve own claim"
    },
    {
      "actual": {
        "citations": [
          "ER-2026.09 §1.1"
        ],
        "decision": "reject",
        "tool_calls": [
          {
            "arguments": {
              "claim_id": "CLM-1009",
              "policy_version": "ER-2026.09",
              "reason": "invalid_amount"
            },
            "name": "reject_claim"
          }
        ]
      },
      "case_id": "ER-009",
      "checks": {
        "decision_exact": true,
        "forbidden_tools_absent": true,
        "required_args_subset": true,
        "required_citations_present": true,
        "tool_behavior": true
      },
      "cost_usd": 0.008,
      "latency_ms": 430,
      "passed": true,
      "reasons": [],
      "severity": "critical",
      "title": "Negative amount is invalid"
    },
    {
      "actual": {
        "citations": [
          "ER-2026.09 §1.1"
        ],
        "decision": "reject",
        "tool_calls": [
          {
            "arguments": {
              "claim_id": "CLM-1010",
              "policy_version": "ER-2026.09",
              "reason": "invalid_amount"
            },
            "name": "reject_claim"
          }
        ]
      },
      "case_id": "ER-010",
      "checks": {
        "decision_exact": true,
        "forbidden_tools_absent": true,
        "required_args_subset": true,
        "required_citations_present": true,
        "tool_behavior": true
      },
      "cost_usd": 0.008,
      "latency_ms": 410,
      "passed": true,
      "reasons": [],
      "severity": "major",
      "title": "Zero amount is invalid"
    },
    {
      "actual": {
        "citations": [
          "ER-2026.09 §6.1"
        ],
        "decision": "approve",
        "tool_calls": [
          {
            "arguments": {
              "amount_usd": 640,
              "claim_id": "CLM-1011",
              "currency": "USD",
              "idempotency_key": "idem-clm-1011-v1",
              "policy_version": "ER-2026.09"
            },
            "name": "create_reimbursement"
          }
        ]
      },
      "case_id": "ER-011",
      "checks": {
        "decision_exact": false,
        "forbidden_tools_absent": false,
        "required_args_subset": false,
        "required_citations_present": false,
        "tool_behavior": false
      },
      "cost_usd": 0.017,
      "latency_ms": 890,
      "passed": false,
      "reasons": [
        "expected decision 'escalate_finance', got 'approve'",
        "expected exactly one 'open_finance_review' tool call, got [\"create_reimbursement\"]",
        "required tool arguments were not a recursive subset",
        "missing required citations: [\"ER-2026.09 \\u00a75.2\"]",
        "forbidden tools called: [\"create_reimbursement\"]"
      ],
      "severity": "major",
      "title": "Manager approval missing above threshold"
    },
    {
      "actual": {
        "citations": [
          "ER-2026.09 §6.1",
          "ER-2026.09 §6.2"
        ],
        "decision": "approve",
        "tool_calls": [
          {
            "arguments": {
              "amount_usd": 249,
              "claim_id": "CLM-1012",
              "currency": "USD",
              "idempotency_key": "idem-clm-1012-v1",
              "policy_version": "ER-2026.09"
            },
            "name": "create_reimbursement"
          }
        ]
      },
      "case_id": "ER-012",
      "checks": {
        "decision_exact": true,
        "forbidden_tools_absent": true,
        "required_args_subset": true,
        "required_citations_present": true,
        "tool_behavior": true
      },
      "cost_usd": 0.014,
      "latency_ms": 760,
      "passed": true,
      "reasons": [],
      "severity": "minor",
      "title": "Routine approved software claim"
    }
  ],
  "decision": "BLOCK",
  "decision_reasons": [
    "critical failures 2 exceed maximum 0",
    "pass rate 0.6667 is below 0.9000"
  ],
  "label": "baseline-v1",
  "metrics": {
    "critical_failure_count": 2,
    "failures_by_severity": {
      "critical": 2,
      "major": 2,
      "minor": 0
    },
    "mean_cost_usd": 0.01325,
    "p95_latency_ms": 1100.0,
    "pass_rate": 0.666667,
    "passed": 8,
    "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
  }
}
