Files
NODEDC_1C/llm_normalizer/backend/src/services/assistantClaimBoundEvidence.ts
T

1146 lines
45 KiB
TypeScript

import { nanoid } from "nanoid";
import type { UnifiedRetrievalResult } from "../types/assistant";
import type { EvidenceItem, EvidenceSourceNamespace } from "../types/stage1Contracts";
import type { CompanyAnchorSet } from "./companyAnchorResolver";
export type ClaimType =
| "prove_settlement_closure_state"
| "prove_advance_offset_state"
| "prove_vat_chain_completeness"
| "prove_month_close_state"
| "prove_rbp_tail_state"
| "prove_fixed_asset_amortization_coverage";
export type ContextExpansionReason =
| "prehistory"
| "carryover"
| "post_period_closure"
| "long_running_contract_context";
export interface TemporalWindow {
from: string;
to: string;
granularity: "day" | "month";
}
export interface ClaimBoundAnchorAudit {
claim_type: ClaimType;
settlement_role?: "supplier" | "customer" | "mixed" | "unknown";
settlement_role_resolution_reason?: string[];
polarity_resolution_status?: "resolved_supplier" | "resolved_customer" | "mixed" | "unknown" | "not_applicable";
required_anchors: string[];
resolved_anchors: Record<string, string[]>;
missing_anchors: string[];
claim_anchor_resolution_rate: number;
primary_period: TemporalWindow | null;
allowed_context_window: TemporalWindow | null;
context_expansion_reasons_allowed: ContextExpansionReason[];
reason_codes: string[];
}
export interface TargetedEvidenceAcquisitionAudit {
claim_type: ClaimType;
required_checks: string[];
check_status: Record<string, "found" | "not_found">;
targeted_item_hits: number;
targeted_evidence_hits: number;
targeted_evidence_hit_rate: number;
targeted_evidence_source_refs: string[];
fa_expected_set?: string[];
fa_actual_set_from_amortization?: string[];
fa_missing_candidates?: string[];
fa_uncertain_candidates?: string[];
fa_relation_map?: Array<{
fa_object: string;
document_amortization: string[];
movement: boolean;
posting: boolean;
period: string[];
coverage_status: "covered" | "missing" | "uncertain";
}>;
reason_codes: string[];
}
interface ContextExpansionDecision {
allowed: boolean;
reason: ContextExpansionReason | null;
inside_primary_period: boolean;
}
function uniqueStrings(values: string[]): string[] {
return Array.from(new Set(values.map((item) => String(item ?? "").trim()).filter(Boolean)));
}
function toObject(value: unknown): Record<string, unknown> | null {
if (!value || typeof value !== "object" || Array.isArray(value)) {
return null;
}
return value as Record<string, unknown>;
}
function normalizeTwoDigits(value: string): string {
return String(value).padStart(2, "0");
}
function normalizeDateIso(value: string): string | null {
const raw = String(value ?? "").trim();
if (!raw) {
return null;
}
const isoDay = raw.match(/\b(20\d{2})[-/.](0?[1-9]|1[0-2])[-/.](0?[1-9]|[12]\d|3[01])\b/);
if (isoDay) {
return `${isoDay[1]}-${normalizeTwoDigits(isoDay[2])}-${normalizeTwoDigits(isoDay[3])}`;
}
const isoMonth = raw.match(/\b(20\d{2})[-/.](0?[1-9]|1[0-2])\b/);
if (isoMonth) {
return `${isoMonth[1]}-${normalizeTwoDigits(isoMonth[2])}-01`;
}
const localDay = raw.match(/\b(0?[1-9]|[12]\d|3[01])[./-](0?[1-9]|1[0-2])[./-](\d{2}|\d{4})\b/);
if (localDay) {
const year = localDay[3].length === 2 ? `20${localDay[3]}` : localDay[3];
return `${year}-${normalizeTwoDigits(localDay[2])}-${normalizeTwoDigits(localDay[1])}`;
}
return null;
}
function isoToDate(value: string): Date | null {
const normalized = normalizeDateIso(value);
if (!normalized) {
return null;
}
const date = new Date(`${normalized}T00:00:00Z`);
return Number.isNaN(date.getTime()) ? null : date;
}
function formatDate(date: Date): string {
const year = date.getUTCFullYear();
const month = normalizeTwoDigits(String(date.getUTCMonth() + 1));
const day = normalizeTwoDigits(String(date.getUTCDate()));
return `${year}-${month}-${day}`;
}
function shiftDays(iso: string, deltaDays: number): string | null {
const date = isoToDate(iso);
if (!date) {
return null;
}
date.setUTCDate(date.getUTCDate() + deltaDays);
return formatDate(date);
}
function accountPrefix(value: string): string | null {
const token = String(value ?? "").trim();
const match = token.match(/^(\d{2})/);
return match ? match[1] : null;
}
function accountPrefixesFromAnchors(anchors?: CompanyAnchorSet | null): Set<string> {
const prefixes = new Set<string>();
const accounts = Array.isArray(anchors?.accounts) ? anchors.accounts : [];
for (const item of accounts) {
const prefix = accountPrefix(String(item ?? ""));
if (prefix) {
prefixes.add(prefix);
}
}
return prefixes;
}
function inferClaimType(input: { userMessage: string; focusDomainHint?: string | null; companyAnchors?: CompanyAnchorSet | null }): ClaimType {
const lower = String(input.userMessage ?? "").toLowerCase();
const accountPrefixes = accountPrefixesFromAnchors(input.companyAnchors);
const hasSettlementAccount = ["51", "60", "62", "76"].some((item) => accountPrefixes.has(item));
const hasVatAccount = ["19", "68"].some((item) => accountPrefixes.has(item));
const hasFixedAssetAccount = ["01", "02", "08"].some((item) => accountPrefixes.has(item));
const hasRbpAccount = accountPrefixes.has("97");
const hasMonthCloseAccount = ["20", "21", "23", "25", "26", "28", "29", "44"].some((item) =>
accountPrefixes.has(item)
);
const hasAdvanceSignal = /(?:advance|аванс|offset|зач[её]т|62\.02|60\.02)/i.test(lower);
const hasSettlementLexical = /(?:долг|аванс|зач[её]т|взаимозач|расч[её]т|оплат|плате[жж]|платёж|постав|покупател|settlement|payment|supplier|customer)/i.test(
lower
);
const hasVatLexical = /(?:\bvat\b|ндс|invoice|сч[её]т[- ]?фактур|register|книга\s+покупок|книга\s+продаж|книг[аи]\s+(?:покуп|продаж))/i.test(
lower
);
const hasFixedAssetLexical = /(?:depreciat|amortization|fixed\s*asset|амортиз|основн(?:ые|ых)?\s+сред|объект\s+ос|сч[её]т\s*0[128]|account\s*0[128])/i.test(
lower
);
const hasRbpLexical = /(?:\brbp\b|рбп|deferred\s*expense|writeoff|расходы\s+будущих\s+периодов|списани[ея]\s+рбп|account\s*97|сч[её]т\s*97)/i.test(
lower
);
const hasMonthCloseLexical = /(?:month[- ]?close|закрыт|закрытие\s+месяца|косвен|account\s*20|account\s*44|сч[её]т\s*20|сч[её]т\s*44|распределен|period\s*close)/i.test(
lower
);
if (input.focusDomainHint === "settlements_60_62") {
return hasAdvanceSignal ? "prove_advance_offset_state" : "prove_settlement_closure_state";
}
if (input.focusDomainHint === "vat_document_register_book") {
return "prove_vat_chain_completeness";
}
if (input.focusDomainHint === "fixed_asset_amortization") {
return "prove_fixed_asset_amortization_coverage";
}
if (input.focusDomainHint === "month_close_costs_20_44") {
if (hasRbpLexical || hasRbpAccount) {
return "prove_rbp_tail_state";
}
return "prove_month_close_state";
}
const settlementPriority =
(hasSettlementLexical || hasSettlementAccount || hasAdvanceSignal) && !hasVatLexical && !hasFixedAssetLexical;
const broadMonthClosePriority =
(hasMonthCloseLexical || hasMonthCloseAccount) &&
!hasVatLexical &&
!hasVatAccount &&
!hasFixedAssetLexical &&
!hasFixedAssetAccount;
if (hasAdvanceSignal && settlementPriority) {
return "prove_advance_offset_state";
}
if (settlementPriority) {
return "prove_settlement_closure_state";
}
if (hasVatLexical || (hasVatAccount && !settlementPriority)) {
return "prove_vat_chain_completeness";
}
if (broadMonthClosePriority) {
return hasRbpLexical || hasRbpAccount ? "prove_rbp_tail_state" : "prove_month_close_state";
}
if (hasFixedAssetLexical || (hasFixedAssetAccount && !settlementPriority && !hasVatLexical)) {
return "prove_fixed_asset_amortization_coverage";
}
if (hasRbpLexical || hasRbpAccount) {
return "prove_rbp_tail_state";
}
if (hasMonthCloseLexical || hasMonthCloseAccount) {
return "prove_month_close_state";
}
if (hasSettlementLexical || hasSettlementAccount) {
return "prove_settlement_closure_state";
}
return "prove_settlement_closure_state";
}
function inferCounterpartyScope(message: string): string[] {
const lower = message.toLowerCase();
const out: string[] = [];
if (/(?:supplier|vendor|поставщик|кредитор)/i.test(lower)) out.push("supplier");
if (/(?:customer|buyer|покупатель|дебитор)/i.test(lower)) out.push("customer");
return uniqueStrings(out);
}
function detectSignals(message: string): Record<string, boolean> {
const lower = message.toLowerCase();
return {
hasAdvance: /(?:advance|аванс|offset|зач[её]т|62\.02|60\.02)/i.test(lower),
hasClosure: /(?:close|closure|закрыт|хвост|tail|reconcile|зач[её]т)/i.test(lower),
hasVat: /(?:\bvat\b|ндс|сч[её]т[- ]?фактур|invoice|книга\s+покупок|книга\s+продаж|register)/i.test(lower),
hasMonthClose: /(?:month[- ]?close|закрытие\s+месяца|косвен|20\/44|account 20|account 44|сч[её]т 20|сч[её]т 44)/i.test(lower),
hasRbp: /(?:\brbp\b|рбп|account 97|сч[её]т 97|writeoff|списани)/i.test(lower),
hasFixedAsset: /(?:depreciat|amortization|fixed\s*asset|амортиз|основн(?:ые|ых)?\s+сред|объект\s+ос|сч[её]т\s*0[128]|account\s*0[128])/i.test(
lower
)
};
}
function resolveSettlementRole(input: {
claimType: ClaimType;
counterpartyScope: string[];
accountPrefixes: Set<string>;
userMessage: string;
}): "supplier" | "customer" | "mixed" | "unknown" | undefined {
if (input.claimType !== "prove_settlement_closure_state" && input.claimType !== "prove_advance_offset_state") {
return undefined;
}
const scopes = new Set(input.counterpartyScope.map((item) => String(item ?? "").trim().toLowerCase()));
const lower = String(input.userMessage ?? "").toLowerCase();
const hasSupplierLexical = /(?:supplier|vendor|поставщ|кредитор|обязательств|payable)/i.test(lower);
const hasCustomerLexical = /(?:customer|buyer|покупат|дебитор|receivable)/i.test(lower);
const hasSupplierAccount = input.accountPrefixes.has("60");
const hasCustomerAccount = input.accountPrefixes.has("62");
const supplierSignal = scopes.has("supplier") || hasSupplierLexical || (hasSupplierAccount && !hasCustomerAccount);
const customerSignal = scopes.has("customer") || hasCustomerLexical || (hasCustomerAccount && !hasSupplierAccount);
if (supplierSignal && !customerSignal) {
return "supplier";
}
if (customerSignal && !supplierSignal) {
return "customer";
}
if (supplierSignal && customerSignal) {
return "mixed";
}
return "unknown";
}
function mergeAnchors(anchors: CompanyAnchorSet | null | undefined, key: keyof CompanyAnchorSet): string[] {
return uniqueStrings(Array.isArray(anchors?.[key]) ? (anchors?.[key] as string[]) : []);
}
function buildAllowedContextWindow(primaryPeriod: TemporalWindow | null): TemporalWindow | null {
if (!primaryPeriod) {
return null;
}
const from = shiftDays(primaryPeriod.from, -365);
const to = shiftDays(primaryPeriod.to, 365);
if (!from || !to) {
return null;
}
return {
from,
to,
granularity: "month"
};
}
function missingFromRequired(required: string[], resolved: Record<string, string[]>): string[] {
const missing: string[] = [];
for (const anchor of required) {
if (anchor === "counterparty_scope_or_contract") {
if ((resolved.counterparty_scope?.length ?? 0) <= 0 && (resolved.contract?.length ?? 0) <= 0) {
missing.push(anchor);
}
continue;
}
if (anchor === "settlement_object") {
if ((resolved.contract?.length ?? 0) <= 0 && (resolved.document_numbers?.length ?? 0) <= 0) {
missing.push(anchor);
}
continue;
}
if (anchor === "amount_or_document") {
const hasAmount = (resolved.amounts?.length ?? 0) > 0;
const hasDoc = (resolved.document_numbers?.length ?? 0) > 0 || (resolved.document_types?.length ?? 0) > 0;
if (!hasAmount && !hasDoc) {
missing.push(anchor);
}
continue;
}
if (anchor === "account_scope_or_document_type") {
const hasAccount = (resolved.account_scope?.length ?? 0) > 0;
const hasDocType = (resolved.document_types?.length ?? 0) > 0;
if (!hasAccount && !hasDocType) {
missing.push(anchor);
}
continue;
}
if ((resolved[anchor]?.length ?? 0) <= 0) {
missing.push(anchor);
}
}
return uniqueStrings(missing);
}
export function resolveClaimBoundAnchors(input: {
userMessage: string;
companyAnchors?: CompanyAnchorSet | null;
focusDomainHint?: string | null;
primaryPeriod?: TemporalWindow | null;
}): ClaimBoundAnchorAudit {
const claimType = inferClaimType({
userMessage: input.userMessage,
focusDomainHint: input.focusDomainHint,
companyAnchors: input.companyAnchors
});
const signals = detectSignals(input.userMessage);
const accountPrefixes = accountPrefixesFromAnchors(input.companyAnchors);
const includeVatAnchors = claimType === "prove_vat_chain_completeness";
const includeMonthCloseAnchors = claimType === "prove_month_close_state";
const includeRbpAnchors = claimType === "prove_rbp_tail_state";
const includeFixedAssetAnchors = claimType === "prove_fixed_asset_amortization_coverage";
const hasVatSignal = signals.hasVat || accountPrefixes.has("19") || accountPrefixes.has("68");
const hasRbpSignal = signals.hasRbp || accountPrefixes.has("97");
const hasFixedAssetSignal = signals.hasFixedAsset || accountPrefixes.has("01") || accountPrefixes.has("02") || accountPrefixes.has("08");
const hasMonthCloseSignal =
signals.hasMonthClose ||
accountPrefixes.has("20") ||
accountPrefixes.has("21") ||
accountPrefixes.has("23") ||
accountPrefixes.has("25") ||
accountPrefixes.has("26") ||
accountPrefixes.has("28") ||
accountPrefixes.has("29") ||
accountPrefixes.has("44");
const resolvedAnchors: Record<string, string[]> = {
period: uniqueStrings([...mergeAnchors(input.companyAnchors, "periods"), ...mergeAnchors(input.companyAnchors, "dates")]),
account_scope: mergeAnchors(input.companyAnchors, "accounts"),
amounts: mergeAnchors(input.companyAnchors, "amounts"),
contract: mergeAnchors(input.companyAnchors, "contract_numbers"),
document_numbers: mergeAnchors(input.companyAnchors, "document_numbers"),
document_types: mergeAnchors(input.companyAnchors, "document_types"),
counterparty_scope: inferCounterpartyScope(input.userMessage),
advance_signal: signals.hasAdvance ? ["advance"] : [],
closure_signal: signals.hasClosure ? ["closure"] : [],
vat_signal: includeVatAnchors && hasVatSignal ? ["vat"] : [],
chain_signal: includeVatAnchors && hasVatSignal ? ["chain"] : [],
close_signal: includeMonthCloseAnchors && hasMonthCloseSignal ? ["month_close"] : [],
cost_scope: [],
rbp_signal: includeRbpAnchors && hasRbpSignal ? ["rbp"] : [],
writeoff_signal: includeRbpAnchors && hasRbpSignal ? ["writeoff"] : [],
fixed_asset_signal: includeFixedAssetAnchors && hasFixedAssetSignal ? ["fixed_asset"] : [],
amortization_signal: includeFixedAssetAnchors && hasFixedAssetSignal ? ["amortization"] : [],
expected_fa_set: [],
actual_fa_set: []
};
if (
includeMonthCloseAnchors &&
(/(?:^|[^\d])(20|44)(?:[^\d]|$)/.test((resolvedAnchors.account_scope ?? []).join(" ")) || hasMonthCloseSignal)
) {
resolvedAnchors.cost_scope = ["20_44"];
}
// For FA amortization claims, document type is implicit in user intent
// even when the phrase does not carry explicit document keywords.
if (includeFixedAssetAnchors && hasFixedAssetSignal && (resolvedAnchors.document_types?.length ?? 0) <= 0) {
resolvedAnchors.document_types = ["amortization_document"];
}
if (input.primaryPeriod) {
resolvedAnchors.period = uniqueStrings([...(resolvedAnchors.period ?? []), input.primaryPeriod.from, input.primaryPeriod.to]);
}
const requiredByClaim: Record<ClaimType, string[]> = {
prove_settlement_closure_state: ["period", "account_scope", "counterparty_scope_or_contract", "closure_signal"],
prove_advance_offset_state: ["period", "account_scope", "advance_signal", "settlement_object"],
prove_vat_chain_completeness: ["period", "document_types", "vat_signal", "chain_signal"],
prove_month_close_state: ["period", "close_signal", "cost_scope"],
prove_rbp_tail_state: ["period", "rbp_signal", "writeoff_signal"],
prove_fixed_asset_amortization_coverage: [
"period",
"fixed_asset_signal",
"amortization_signal",
"amount_or_document",
"account_scope_or_document_type"
]
};
const requiredAnchors = requiredByClaim[claimType];
const missingAnchors = missingFromRequired(requiredAnchors, resolvedAnchors);
const resolutionRate =
requiredAnchors.length > 0
? Number(((requiredAnchors.length - missingAnchors.length) / requiredAnchors.length).toFixed(4))
: 1;
const allowedContextWindow = buildAllowedContextWindow(input.primaryPeriod ?? null);
const reasonCodes: string[] = [];
if (missingAnchors.length > 0) {
reasonCodes.push("claim_missing_required_anchors");
}
if (resolutionRate < 0.8) {
reasonCodes.push("claim_anchor_resolution_low");
}
if (!allowedContextWindow && input.primaryPeriod) {
reasonCodes.push("controlled_temporal_expansion_window_unavailable");
}
const settlementRoleRaw = resolveSettlementRole({
claimType,
counterpartyScope: resolvedAnchors.counterparty_scope ?? [],
accountPrefixes,
userMessage: input.userMessage
});
const settlementRole = typeof settlementRoleRaw === "string" ? settlementRoleRaw : undefined;
const settlementRoleReason: string[] =
claimType === "prove_settlement_closure_state" || claimType === "prove_advance_offset_state"
? settlementRole
? [`settlement_role_resolved_${settlementRole}`]
: ["no_supplier_customer_anchor"]
: [];
const polarityResolutionStatus =
claimType === "prove_settlement_closure_state" || claimType === "prove_advance_offset_state"
? settlementRole === "supplier"
? "resolved_supplier"
: settlementRole === "customer"
? "resolved_customer"
: settlementRole === "mixed"
? "mixed"
: "unknown"
: "not_applicable";
if (
(claimType === "prove_settlement_closure_state" || claimType === "prove_advance_offset_state") &&
(settlementRole === "mixed" || settlementRole === "unknown")
) {
reasonCodes.push("unresolved_supplier_customer_polarity");
}
return {
claim_type: claimType,
settlement_role: settlementRole,
settlement_role_resolution_reason: settlementRoleReason,
polarity_resolution_status: polarityResolutionStatus,
required_anchors: requiredAnchors,
resolved_anchors: resolvedAnchors,
missing_anchors: missingAnchors,
claim_anchor_resolution_rate: resolutionRate,
primary_period: input.primaryPeriod ?? null,
allowed_context_window: allowedContextWindow,
context_expansion_reasons_allowed: [
"prehistory",
"carryover",
"post_period_closure",
"long_running_contract_context"
],
reason_codes: uniqueStrings(reasonCodes)
};
}
function buildCorpusFromItem(item: Record<string, unknown>): string {
return JSON.stringify({
source_entity: item.source_entity,
source_id: item.source_id,
period: item.period ?? item.Period,
account_context: item.account_context,
account_debit: item.account_debit,
account_credit: item.account_credit,
document_context: item.document_context,
relation_pattern_hits: item.relation_pattern_hits,
graph_domain_scope: item.graph_domain_scope,
lifecycle_markers: item.lifecycle_markers,
live_call_id: item.live_call_id,
live_call_purpose: item.live_call_purpose,
fa_object_hint: item.fa_object_hint,
fa_expected_set_candidate: item.fa_expected_set_candidate,
fa_actual_set_candidate: item.fa_actual_set_candidate,
fa_coverage_status: item.fa_coverage_status
}).toLowerCase();
}
function buildCorpusFromEvidence(evidence: EvidenceItem): string {
return JSON.stringify({
source_ref: evidence.source_ref,
pointer: evidence.pointer,
payload: evidence.payload,
mechanism_note: evidence.mechanism_note,
limitation: evidence.limitation
}).toLowerCase();
}
function requiredChecksByClaim(claimType: ClaimType): string[] {
if (claimType === "prove_settlement_closure_state") {
return [
"payment_document_found",
"contract_matched",
"settlement_object_matched",
"closing_document_found",
"register_closure_entry_found",
"posting_link_found"
];
}
if (claimType === "prove_advance_offset_state") {
return [
"payment_document_found",
"advance_marker_found",
"settlement_object_matched",
"closing_document_found",
"register_closure_entry_found",
"posting_link_found"
];
}
if (claimType === "prove_vat_chain_completeness") {
return ["source_document_found", "invoice_found", "tax_register_entry_found", "book_entry_found", "chain_linkage_status"];
}
if (claimType === "prove_month_close_state") {
return ["close_operation_found", "distribution_step_found", "residual_tail_found"];
}
if (claimType === "prove_fixed_asset_amortization_coverage") {
return [
"amortization_document_found",
"fixed_asset_object_identified",
"expected_fa_set_reconstructed",
"actual_fa_set_reconstructed",
"movement_or_posting_link_found",
"missing_fa_candidates_assessed"
];
}
return [
"rbp_writeoff_document_found",
"rbp_object_identified",
"rbp_movement_found",
"rbp_period_end_residual_found",
"rbp_writeoff_lifecycle_confirmed",
"residual_tail_found",
"close_contradiction_or_normal_residual"
];
}
function detectChecksForCorpus(corpus: string, claimType: ClaimType, anchors: Record<string, string[]>): string[] {
const checks = new Set<string>();
const hasContractAnchor =
(anchors.contract ?? []).some((token) => token.length >= 3 && corpus.includes(String(token).toLowerCase())) ||
/(?:contract|договор)/i.test(corpus);
const hasSettlementAccount = /(?:\b60(?:\.\d{2})?\b|\b62(?:\.\d{2})?\b|payable|receivable|settlement)/i.test(corpus);
const hasPosting = /(?:document_to_posting|posting|проводк)/i.test(corpus);
const hasRegister = /(?:register|accumulationregister|accountingregister|регистр)/i.test(corpus);
const hasClose = /(?:close|closure|закрыт|reconcile|зач[её]т|tail|хвост)/i.test(corpus);
const hasPayment = /(?:payment|оплат|списаниесрасчетногосчета|payment_order|bank_statement)/i.test(corpus);
const hasAdvance = /(?:advance|аванс|offset|зач[её]т|62\.02|60\.02)/i.test(corpus);
const hasVat = /(?:\bvat\b|ндс|invoice_to_vat|сч[её]т[- ]?фактур|invoice)/i.test(corpus);
const hasBook = /(?:книг[аи](?:\s+)?(?:покупок|продаж)|book)/i.test(corpus);
const hasChain = /(?:chain|link|document_to_posting|invoice_to_vat|связ)/i.test(corpus);
const hasMonthClose = /(?:month[- ]?close|period_close|закрытие\s+месяца|косвен|20|44)/i.test(corpus);
const hasDistribution = /(?:distribution|распредел|writeoff|deferred_expense_to_writeoff)/i.test(corpus);
const hasRbp = /(?:\brbp\b|рбп|account\s*97|сч[её]т\s*97|deferred)/i.test(corpus);
const hasResidual = /(?:tail|остат|незакры|overdue|period_boundary|terminal_state_gap)/i.test(corpus);
const hasContradiction = /(?:contradiction|invalid_transition|normal residual|нормальн)/i.test(corpus);
const hasRbpWriteoffDoc = /(?:списани[ея]\s+рбп|rbp_writeoff|deferred_expense_document|writeoff document)/i.test(corpus);
const hasRbpObject = /(?:rbp[_\s-]?object|объект\s+рбп|analytics|subkonto|расходыбудущихпериодов)/i.test(corpus);
const hasMovement = /(?:movement|движен|хозрасчетный|document_to_posting|posting|проводк)/i.test(corpus);
const hasPeriodEndResidual = /(?:period_boundary|end_period|2020-07-31|остат)/i.test(corpus);
const hasFixedAsset = /(?:fixed_asset|asset_card|объект\s+ос|основн(?:ые|ых)?\s+сред|depreciat|амортиз|account[:\s]*0[12]|\b0[12](?:\.\d{2})?\b)/i.test(
corpus
);
const hasAmortizationDoc = /(?:depreciat|amortization|начислен[а-я]*\s+амортиз|документ\s+амортиз)/i.test(corpus);
const hasExpectedFaSet = /(?:expected_fa_set|expected[_\s-]?set|find_fixed_asset_cards_expected_for_period|expected_set_seed|fa_expected_set_candidate)/i.test(
corpus
);
const hasActualFaSet = /(?:actual_fa_set|find_fixed_asset_movements_accounts_01_02|fa_actual_set_candidate|seed_amortization_documents|collect_fa_object_movements)/i.test(
corpus
);
const hasFaCoverageCompare = /(?:expected_vs_actual|compare_expected_vs_actual|missing_fa|coverage_compare|missing_fa_candidates)/i.test(
corpus
);
if (claimType === "prove_settlement_closure_state") {
if (hasPayment) checks.add("payment_document_found");
if (hasContractAnchor) checks.add("contract_matched");
if (hasSettlementAccount) checks.add("settlement_object_matched");
if (hasClose) checks.add("closing_document_found");
if (hasRegister) checks.add("register_closure_entry_found");
if (hasPosting) checks.add("posting_link_found");
} else if (claimType === "prove_advance_offset_state") {
if (hasPayment) checks.add("payment_document_found");
if (hasAdvance) checks.add("advance_marker_found");
if (hasSettlementAccount) checks.add("settlement_object_matched");
if (hasClose) checks.add("closing_document_found");
if (hasRegister) checks.add("register_closure_entry_found");
if (hasPosting) checks.add("posting_link_found");
} else if (claimType === "prove_vat_chain_completeness") {
if (/(?:document|receipt|realization|поступлен|реализац)/i.test(corpus)) checks.add("source_document_found");
if (/(?:invoice|сч[её]т[- ]?фактур)/i.test(corpus)) checks.add("invoice_found");
if (hasRegister || hasVat) checks.add("tax_register_entry_found");
if (hasBook) checks.add("book_entry_found");
if (hasChain) checks.add("chain_linkage_status");
} else if (claimType === "prove_month_close_state") {
if (hasMonthClose || hasClose) checks.add("close_operation_found");
if (hasDistribution) checks.add("distribution_step_found");
if (hasResidual) checks.add("residual_tail_found");
} else if (claimType === "prove_fixed_asset_amortization_coverage") {
if (hasAmortizationDoc) checks.add("amortization_document_found");
if (hasFixedAsset) checks.add("fixed_asset_object_identified");
if (hasExpectedFaSet) checks.add("expected_fa_set_reconstructed");
if (hasActualFaSet || hasAmortizationDoc) checks.add("actual_fa_set_reconstructed");
if (hasMovement || hasPosting) checks.add("movement_or_posting_link_found");
if (hasFaCoverageCompare || (hasExpectedFaSet && hasActualFaSet)) checks.add("missing_fa_candidates_assessed");
} else {
if (hasRbpWriteoffDoc || (hasRbp && hasDistribution)) checks.add("rbp_writeoff_document_found");
if (hasRbpObject || hasRbp) checks.add("rbp_object_identified");
if (hasMovement) checks.add("rbp_movement_found");
if (hasPeriodEndResidual || hasResidual) checks.add("rbp_period_end_residual_found");
if (hasRbp && hasDistribution) checks.add("rbp_writeoff_lifecycle_confirmed");
if (hasResidual) checks.add("residual_tail_found");
if (hasContradiction || hasClose) checks.add("close_contradiction_or_normal_residual");
}
return Array.from(checks);
}
function hasAnchorLink(corpus: string, claimAudit: ClaimBoundAnchorAudit): boolean {
const values = Object.values(claimAudit.resolved_anchors).flat();
return values.some((token) => {
const value = String(token ?? "").toLowerCase().trim();
if (value.length < 2) return false;
return corpus.includes(value);
});
}
function resolveContextExpansionDecision(input: {
period: string | null;
claimAudit: ClaimBoundAnchorAudit;
corpus: string;
matchedChecks: string[];
}): ContextExpansionDecision {
if (!input.period || !input.claimAudit.primary_period) {
return { allowed: true, reason: null, inside_primary_period: true };
}
const normalized = normalizeDateIso(input.period);
if (!normalized) {
return { allowed: false, reason: null, inside_primary_period: false };
}
const primaryFrom = normalizeDateIso(input.claimAudit.primary_period.from);
const primaryTo = normalizeDateIso(input.claimAudit.primary_period.to);
if (!primaryFrom || !primaryTo) {
return { allowed: true, reason: null, inside_primary_period: true };
}
if (normalized >= primaryFrom && normalized <= primaryTo) {
return { allowed: true, reason: null, inside_primary_period: true };
}
const allowedFrom = normalizeDateIso(input.claimAudit.allowed_context_window?.from ?? "");
const allowedTo = normalizeDateIso(input.claimAudit.allowed_context_window?.to ?? "");
if (allowedFrom && normalized < allowedFrom) {
return { allowed: false, reason: null, inside_primary_period: false };
}
if (allowedTo && normalized > allowedTo) {
return { allowed: false, reason: null, inside_primary_period: false };
}
const linked = hasAnchorLink(input.corpus, input.claimAudit) || input.matchedChecks.length > 0;
const fromDate = isoToDate(primaryFrom);
const toDate = isoToDate(primaryTo);
const curDate = isoToDate(normalized);
const hasContractAnchor = (input.claimAudit.resolved_anchors.contract?.length ?? 0) > 0;
if (!fromDate || !toDate || !curDate) {
return { allowed: linked, reason: linked ? "carryover" : null, inside_primary_period: false };
}
const diffBefore = Math.floor((fromDate.getTime() - curDate.getTime()) / (24 * 3600 * 1000));
const diffAfter = Math.floor((curDate.getTime() - toDate.getTime()) / (24 * 3600 * 1000));
if (curDate < fromDate) {
if (linked && hasContractAnchor && diffBefore > 31) {
return { allowed: true, reason: "long_running_contract_context", inside_primary_period: false };
}
if (linked) {
return { allowed: true, reason: "prehistory", inside_primary_period: false };
}
if (diffBefore <= 31) {
return { allowed: true, reason: "carryover", inside_primary_period: false };
}
return { allowed: false, reason: null, inside_primary_period: false };
}
if (curDate > toDate) {
if (diffAfter <= 31) {
return { allowed: true, reason: "carryover", inside_primary_period: false };
}
if (linked && hasContractAnchor) {
return { allowed: true, reason: "long_running_contract_context", inside_primary_period: false };
}
if (linked) {
return { allowed: true, reason: "post_period_closure", inside_primary_period: false };
}
return { allowed: false, reason: null, inside_primary_period: false };
}
return { allowed: true, reason: null, inside_primary_period: true };
}
function evidenceSourceNamespaceFromItem(item: Record<string, unknown>): EvidenceSourceNamespace {
const sourceLayer = String(item.source_layer ?? "").toLowerCase();
if (sourceLayer.includes("snapshot")) {
return "snapshot_2020";
}
return "assistant_derived";
}
function buildDerivedEvidenceFromItem(input: {
result: UnifiedRetrievalResult;
item: Record<string, unknown>;
claimType: ClaimType;
matchedChecks: string[];
expansion: ContextExpansionDecision;
}): EvidenceItem {
const sourceEntity = String(input.item.source_entity ?? "unknown");
const sourceId = String(input.item.source_id ?? `derived-${nanoid(8)}`);
const period = String(input.item.period ?? input.item.Period ?? "").trim() || null;
const namespace = evidenceSourceNamespaceFromItem(input.item);
const canonical = `evidence_source_ref_v1|${namespace}|${sourceEntity.toLowerCase()}|${sourceId.toLowerCase()}|${String(period ?? "").toLowerCase()}`;
const confidence = input.matchedChecks.length >= 2 ? "high" : "medium";
return {
evidence_id: `claim-ev-${nanoid(10)}`,
claim_ref: `claim:${input.claimType}`,
source_type: "derived",
source_ref: {
schema_version: "evidence_source_ref_v1",
namespace,
entity: sourceEntity,
id: sourceId,
period,
canonical_ref: canonical
},
pointer: {
fragment_id: input.result.fragment_id,
route: input.result.route,
source: {
namespace,
entity: sourceEntity,
id: sourceId,
period
},
locator: {
field_path: null,
item_index: null
}
},
evidence_kind: "mechanism_link",
mechanism_note: input.matchedChecks[0] ?? null,
confidence,
limitation: null,
payload: {
from_targeted_item: true,
claim_type: input.claimType,
claim_target_checks: input.matchedChecks,
context_expansion_allowed: input.expansion.allowed,
context_expansion_reason: input.expansion.reason,
period,
source_entity: sourceEntity,
source_id: sourceId,
account_context: Array.isArray(input.item.account_context) ? input.item.account_context : [],
account_debit: input.item.account_debit ?? null,
account_credit: input.item.account_credit ?? null,
relation_pattern_hits: Array.isArray(input.item.relation_pattern_hits) ? input.item.relation_pattern_hits : [],
fa_object_hint: String(input.item.fa_object_hint ?? "").trim() || null,
fa_expected_set_candidate: Boolean(input.item.fa_expected_set_candidate),
fa_actual_set_candidate: Boolean(input.item.fa_actual_set_candidate),
fa_coverage_status: String(input.item.fa_coverage_status ?? "").trim() || null
}
};
}
function buildClaimStatusTemplate(requiredChecks: string[]): Record<string, "found" | "not_found"> {
const out: Record<string, "found" | "not_found"> = {};
for (const check of requiredChecks) {
out[check] = "not_found";
}
return out;
}
function normalizeFaObjectToken(value: string): string | null {
const normalized = String(value ?? "")
.replace(/\s+/g, " ")
.trim();
if (!normalized) {
return null;
}
if (/^live movement row #\d+$/i.test(normalized)) {
return null;
}
return normalized.slice(0, 140);
}
function periodFromEvidence(evidence: EvidenceItem): string | null {
const payload = toObject(evidence.payload);
return (
String(evidence.source_ref?.period ?? "").trim() ||
String(evidence.pointer?.source?.period ?? "").trim() ||
String(payload?.period ?? "").trim() ||
null
);
}
function collectFaCoverage(input: {
retrievalResults: UnifiedRetrievalResult[];
}): {
expectedSet: string[];
actualSet: string[];
missingCandidates: string[];
uncertainCandidates: string[];
relationMap: Array<{
fa_object: string;
document_amortization: string[];
movement: boolean;
posting: boolean;
period: string[];
coverage_status: "covered" | "missing" | "uncertain";
}>;
} {
const state = new Map<
string,
{
expected: boolean;
actual: boolean;
movement: boolean;
posting: boolean;
docs: Set<string>;
periods: Set<string>;
}
>();
const touch = (objectName: string) => {
const key = objectName.toLowerCase();
const existing = state.get(key);
if (existing) {
return existing;
}
const created = {
expected: false,
actual: false,
movement: false,
posting: false,
docs: new Set<string>(),
periods: new Set<string>()
};
state.set(key, created);
return created;
};
for (const result of input.retrievalResults) {
const items = Array.isArray(result.items) ? result.items : [];
for (const item of items) {
const objectToken = normalizeFaObjectToken(
String(item.fa_object_hint ?? item.display_name ?? item.source_id ?? "").trim()
);
if (!objectToken) {
continue;
}
const slot = touch(objectToken);
if (Boolean(item.fa_expected_set_candidate)) {
slot.expected = true;
}
if (Boolean(item.fa_actual_set_candidate)) {
slot.actual = true;
}
const corpus = JSON.stringify(item).toLowerCase();
if (/(?:movement|движен|хозрасчет|document_to_posting)/i.test(corpus)) {
slot.movement = true;
}
if (/(?:posting|проводк|account_)/i.test(corpus)) {
slot.posting = true;
}
const documentContext = Array.isArray(item.document_context) ? item.document_context : [];
for (const doc of documentContext) {
const token = String(doc ?? "").trim();
if (token) {
slot.docs.add(token);
}
}
const period = String(item.period ?? item.Period ?? "").trim();
if (period) {
slot.periods.add(period);
}
}
const evidence = Array.isArray(result.evidence) ? result.evidence : [];
for (const evidenceItem of evidence) {
const payload = toObject(evidenceItem.payload) ?? {};
const objectToken = normalizeFaObjectToken(
String(payload.fa_object_hint ?? evidenceItem.source_ref?.id ?? evidenceItem.pointer?.source?.id ?? "").trim()
);
if (!objectToken) {
continue;
}
const slot = touch(objectToken);
if (Boolean(payload.fa_expected_set_candidate)) {
slot.expected = true;
}
if (Boolean(payload.fa_actual_set_candidate)) {
slot.actual = true;
}
const corpus = JSON.stringify({
payload,
mechanism_note: evidenceItem.mechanism_note,
source_ref: evidenceItem.source_ref
}).toLowerCase();
if (/(?:movement|движен|хозрасчет|document_to_posting)/i.test(corpus)) {
slot.movement = true;
}
if (/(?:posting|проводк|account_)/i.test(corpus)) {
slot.posting = true;
}
const documentContext = Array.isArray(payload.document_context) ? payload.document_context : [];
for (const doc of documentContext) {
const token = String(doc ?? "").trim();
if (token) {
slot.docs.add(token);
}
}
const period = periodFromEvidence(evidenceItem);
if (period) {
slot.periods.add(period);
}
}
}
const entries = Array.from(state.entries());
const expectedSet = entries
.filter(([, slot]) => slot.expected)
.map(([objectName]) => objectName)
.slice(0, 32);
const actualSet = entries
.filter(([, slot]) => slot.actual)
.map(([objectName]) => objectName)
.slice(0, 32);
const expectedResolved = expectedSet.length > 0 ? expectedSet : actualSet;
const missingCandidates = expectedResolved.filter((item) => !actualSet.includes(item)).slice(0, 32);
const uncertainCandidates = entries
.filter(([, slot]) => !slot.expected && !slot.actual)
.map(([objectName]) => objectName)
.slice(0, 32);
const relationMap = entries.slice(0, 48).map(([objectName, slot]) => {
const coverageStatus: "covered" | "missing" | "uncertain" =
slot.expected && slot.actual ? "covered" : slot.expected && !slot.actual ? "missing" : "uncertain";
return {
fa_object: objectName,
document_amortization: Array.from(slot.docs).slice(0, 4),
movement: slot.movement,
posting: slot.posting,
period: Array.from(slot.periods).slice(0, 4),
coverage_status: coverageStatus
};
});
return {
expectedSet: expectedResolved,
actualSet,
missingCandidates,
uncertainCandidates,
relationMap
};
}
export function applyTargetedEvidenceAcquisition(input: {
retrievalResults: UnifiedRetrievalResult[];
claimAudit: ClaimBoundAnchorAudit;
}): {
retrievalResults: UnifiedRetrievalResult[];
audit: TargetedEvidenceAcquisitionAudit;
} {
const requiredChecks = requiredChecksByClaim(input.claimAudit.claim_type);
const checkStatus = buildClaimStatusTemplate(requiredChecks);
let targetedItemHits = 0;
let targetedEvidenceHits = 0;
const sourceRefs = new Set<string>();
const adjustedResults = input.retrievalResults.map((result) => {
const items = Array.isArray(result.items) ? result.items : [];
const targetedItems: Array<Record<string, unknown>> = [];
const derivedEvidence: EvidenceItem[] = [];
for (const item of items) {
const corpus = buildCorpusFromItem(item);
const matchedChecks = detectChecksForCorpus(corpus, input.claimAudit.claim_type, input.claimAudit.resolved_anchors);
for (const check of matchedChecks) {
if (check in checkStatus) checkStatus[check] = "found";
}
if (matchedChecks.length <= 0) {
continue;
}
targetedItemHits += 1;
const expansion = resolveContextExpansionDecision({
period: String(item.period ?? item.Period ?? "").trim() || null,
claimAudit: input.claimAudit,
corpus,
matchedChecks
});
const enrichedItem = {
...item,
claim_target_checks: matchedChecks,
context_expansion_allowed: expansion.allowed,
context_expansion_reason: expansion.reason
};
targetedItems.push(enrichedItem);
if (derivedEvidence.length < 8) {
const evidence = buildDerivedEvidenceFromItem({
result,
item: enrichedItem,
claimType: input.claimAudit.claim_type,
matchedChecks,
expansion
});
derivedEvidence.push(evidence);
sourceRefs.add(evidence.source_ref.canonical_ref);
}
}
const evidence = Array.isArray(result.evidence) ? result.evidence : [];
const targetedEvidence: EvidenceItem[] = [];
for (const evidenceItem of evidence) {
const corpus = buildCorpusFromEvidence(evidenceItem);
const matchedChecks = detectChecksForCorpus(corpus, input.claimAudit.claim_type, input.claimAudit.resolved_anchors);
for (const check of matchedChecks) {
if (check in checkStatus) checkStatus[check] = "found";
}
if (matchedChecks.length <= 0) {
continue;
}
const payload = toObject(evidenceItem.payload) ?? {};
const expansion = resolveContextExpansionDecision({
period:
String(evidenceItem.source_ref?.period ?? "").trim() ||
String(evidenceItem.pointer?.source?.period ?? "").trim() ||
String(payload.period ?? "").trim() ||
null,
claimAudit: input.claimAudit,
corpus,
matchedChecks
});
targetedEvidence.push({
...evidenceItem,
payload: {
...payload,
claim_type: input.claimAudit.claim_type,
claim_target_checks: matchedChecks,
context_expansion_allowed: expansion.allowed,
context_expansion_reason: expansion.reason
}
});
}
const mergedEvidence = [...targetedEvidence, ...derivedEvidence];
targetedEvidenceHits += mergedEvidence.length;
for (const item of mergedEvidence) {
sourceRefs.add(item.source_ref.canonical_ref);
}
const summary = {
...(toObject(result.summary) ?? {}),
claim_bound_targeting: {
claim_type: input.claimAudit.claim_type,
required_checks: requiredChecks,
targeted_items: targetedItems.length,
targeted_evidence: mergedEvidence.length,
derived_evidence_added: derivedEvidence.length
}
};
return {
...result,
items: targetedItems.length > 0 ? targetedItems : items,
evidence: mergedEvidence.length > 0 ? mergedEvidence : evidence,
summary
};
});
const foundChecks = Object.values(checkStatus).filter((status) => status === "found").length;
const targetedEvidenceHitRate =
requiredChecks.length > 0 ? Number((foundChecks / requiredChecks.length).toFixed(4)) : 0;
const reasonCodes: string[] = [];
if (targetedEvidenceHits <= 0) {
reasonCodes.push("targeted_evidence_not_found");
}
if (targetedEvidenceHitRate < 0.8) {
reasonCodes.push("targeted_evidence_hit_rate_low");
}
const faCoverage =
input.claimAudit.claim_type === "prove_fixed_asset_amortization_coverage"
? collectFaCoverage({
retrievalResults: adjustedResults
})
: null;
if (faCoverage) {
if (faCoverage.expectedSet.length <= 0) {
reasonCodes.push("fa_expected_set_not_reconstructed");
}
if (faCoverage.actualSet.length <= 0) {
reasonCodes.push("fa_actual_set_not_reconstructed");
}
}
return {
retrievalResults: adjustedResults,
audit: {
claim_type: input.claimAudit.claim_type,
required_checks: requiredChecks,
check_status: checkStatus,
targeted_item_hits: targetedItemHits,
targeted_evidence_hits: targetedEvidenceHits,
targeted_evidence_hit_rate: targetedEvidenceHitRate,
targeted_evidence_source_refs: Array.from(sourceRefs).slice(0, 24),
...(faCoverage
? {
fa_expected_set: faCoverage.expectedSet,
fa_actual_set_from_amortization: faCoverage.actualSet,
fa_missing_candidates: faCoverage.missingCandidates,
fa_uncertain_candidates: faCoverage.uncertainCandidates,
fa_relation_map: faCoverage.relationMap
}
: {}),
reason_codes: uniqueStrings(reasonCodes)
}
};
}