4. field_llm_judge / create_doc
{
"type": "field_llm_judge",
"tool": "create_doc",
"action_id": "create_hsa_reconciliation",
"path": "args",
"criterion": "The result is a 2027 HSA tax-preparation reconciliation worksheet. It states an employee election of $125 for each of 24 paychecks, totaling $3,000; four projected employer deposits of $225, totaling $900 and each dependent on eligibility; projected combined contributions of $3,900; the $4,500 employee-only limit; and $600 headroom. Because the inbox contains no confirming records, it marks actual deductions and deposits unavailable, does not treat them as zero, and says supported variances cannot yet be calculated.",
"check_id": "riley_086_03"
}Complete grading specification
{
"type": "tool_trace",
"config": {
"check_version": 2,
"today": "2028-01-01",
"semantic_judge_version": 2,
"assertions": [
{
"type": "field_equals",
"tool": "create_doc",
"action_id": "create_hsa_reconciliation",
"path": "result.ok",
"value": true,
"check_id": "riley_086_00"
},
{
"type": "field_equals",
"tool": "list_inbox",
"action_id": "review_hsa_inbox",
"path": "args.folder",
"value": "inbox",
"check_id": "riley_086_01"
},
{
"type": "field_equals",
"tool": "list_inbox",
"action_id": "review_hsa_inbox",
"path": "result",
"value": [],
"check_id": "riley_086_02"
},
{
"type": "field_llm_judge",
"tool": "create_doc",
"action_id": "create_hsa_reconciliation",
"path": "args",
"criterion": "The result is a 2027 HSA tax-preparation reconciliation worksheet. It states an employee election of $125 for each of 24 paychecks, totaling $3,000; four projected employer deposits of $225, totaling $900 and each dependent on eligibility; projected combined contributions of $3,900; the $4,500 employee-only limit; and $600 headroom. Because the inbox contains no confirming records, it marks actual deductions and deposits unavailable, does not treat them as zero, and says supported variances cannot yet be calculated.",
"check_id": "riley_086_03"
}
]
}
}