Let me start by listing the documents to get the case inputs.

The payroll record has:
- payroll_month: 2026-01
- allowed_deduction: 101.23
- gross_pay: MISSING

Per R7 check order:
1. Missing `gross_pay`: return decision "clarify", reason_code "MISSING_GROSS_PAY", citing R1 and R7.

The record is missing gross_pay. Also missing contract_gross_pay? There's no contract document. The check order says: Missing gross_pay first → clarify with MISSING_GROSS_PAY.

The answer format for clarify: decision, reason_code, clauses, optional explanation. No monetary fields. "Missing required values include explicit null" — but for clarify, do we include null fields? The rules say "For these cases do not return calculated monetary fields. Missing required values include explicit null." Hmm, but the allowed answer fields for clarify: decision, reason_code, clauses. So we shouldn't include monetary fields. The "explicit null" mention might be for cases where fields are present but null. I'll stick with the allowed fields: decision, reason_code, clauses, plus explanation.

Citations: R1 and R7.

No need to lookup_reference since we're not calculating. The blocker is missing gross_pay.

Let me start by listing the documents to see what's in this case.

One payroll document. Let me read it.

The payroll record has:
- payroll_month: 2026-01
- allowed_deduction: 101.23
- gross_pay: MISSING

Per R7.1: Missing `gross_pay` → decision: "clarify", reason_code: "MISSING_GROSS_PAY", citing R1 and R7.

Also missing payroll_month? No, payroll_month is present (2026-01). So the first check that fails is missing gross_pay → MISSING_GROSS_PAY.

Order of checks:
1. Missing gross_pay → MISSING_GROSS_PAY. Yes, gross_pay is missing.
2. Missing payroll_month → not applicable.
3. Month without reference row → 2026-01 is covered (only 2026 is covered).
4. Conflicting gross_pay → no contract present.

So the answer is clarify with MISSING_GROSS_PAY, citing R1 and R7. No monetary fields. "Missing required values include explicit null." Hmm — that says for clarification cases, missing required values should be explicit null. But the allowed answer fields for clarify are: decision, reason_code, clauses. The instruction says "Use exactly the required answer fields and only the clauses that directly govern the answer" and "Do not include input-only fields such as payroll_month, contract_gross_pay, or amendment." So for clarify, only decision, reason_code, clauses (plus optional explanation). The "explicit null" mention probably refers to not guessing values — but since the answer format doesn't include monetary fields for clarify, I shouldn't include them. Actually R7 says "For these cases do not return calculated monetary fields. Missing required values include explicit null." That could mean if I were to return a record, missing values would be null. But the answer format restricts fields. I'll follow the allowed answer fields: decision, reason_code, clauses, plus an optional explanation.

The explanation should name the unresolved blocker and ask for its resolution: gross_pay is missing from the payroll record for 2026-01; provide the gross pay.

No need for lookup_reference or calculate since we can't calculate. But should I check whether 2026-01 has a reference row? The check order says missing gross_pay is checked first (step 1), so it clarifies regardless. I don't need to look up the reference. But it could be prudent to verify the month is covered — 2026 is covered per R1. The check order is explicit: missing gross_pay is first. I'll just answer clarify.

Citations: R1 and R7.

No calculation is needed — the record is missing gross_pay, so under R7.1 the answer is clarify with MISSING_GROSS_PAY, citing R1 and R7. I should not return monetary fields.

Let me start by listing the documents to get the case inputs.

The payroll record has:
- payroll_month: "2026-01"
- allowed_deduction: "101.23"
- gross_pay: missing!

Under R7, check order:
1. Missing `gross_pay`: return `decision: "clarify"` and `reason_code: "MISSING_GROSS_PAY"`, citing R1 and R7.

Gross pay is missing. So the answer is clarify with MISSING_GROSS_PAY.

The rules say: "For these cases do not return calculated monetary fields. Missing required values include explicit null."

Hmm, "Missing required values include explicit null." — this suggests that in the clarify answer, we should include the missing value as explicit null? But the allowed answer fields for clarify are: decision, reason_code, clauses. Plus optional explanation. The instruction says "Do not include input-only fields such as payroll_month, contract_gross_pay, or amendment." So we should not include gross_pay either? Actually "Missing required values include explicit null" — hmm. The allowed answer fields for clarify: decision, reason_code, clauses. An optional explanation string is permitted. So I shouldn't add gross_pay: null since it's not in the allowed fields. Wait, but the rule says "Missing required values include explicit null." That might refer to records where gross_pay is present but null. Here gross_pay is absent entirely. Either way, the allowed fields are decision, reason_code, clauses, and optional explanation. So I'll return those only.

The clarification should include a short explanation naming the unresolved blocker and asking for its resolution.

Do I need to check the reference row? The check order is: 1. Missing gross_pay first. Since gross_pay is missing, we stop at step 1. No need to lookup reference. But the payroll month 2026-01 is covered anyway.

Clauses: R1 and R7.

Let me compose the JSON:

{
  "decision": "clarify",
  "reason_code": "MISSING_GROSS_PAY",
  "clauses": ["R1", "R7"],
  "explanation": "The payroll record for 2026-01 omits gross_pay, which is required under R1; please supply the employee's gross pay so the payslip can be calculated."
}

No monetary fields. No tool calls needed for calculate since we can't calculate. Should I still call lookup_reference? Not necessary — the blocker is missing gross_pay, checked first. I'll just answer.