@claritylabs/cl-sdk 3.2.8 → 3.2.10
This diff represents the content of publicly available package versions that have been released to one of the supported registries. The information contained in this diff is provided for informational purposes only and reflects changes between package versions as they appear in their respective public registries.
- package/README.md +6 -8
- package/dist/index.js +55 -311
- package/dist/index.js.map +1 -1
- package/dist/index.mjs +55 -311
- package/dist/index.mjs.map +1 -1
- package/package.json +1 -1
package/dist/index.mjs
CHANGED
|
@@ -3576,16 +3576,6 @@ var OPERATIONAL_COVERAGE_TERM_KINDS2 = [
|
|
|
3576
3576
|
"other"
|
|
3577
3577
|
];
|
|
3578
3578
|
var OperationalCoverageTermKindSchema = z21.enum(OPERATIONAL_COVERAGE_TERM_KINDS2);
|
|
3579
|
-
var CleanupTermSchema = z21.object({
|
|
3580
|
-
kind: OperationalCoverageTermKindSchema,
|
|
3581
|
-
label: z21.string(),
|
|
3582
|
-
value: z21.string(),
|
|
3583
|
-
amount: z21.number().nullable().optional(),
|
|
3584
|
-
appliesTo: z21.string().nullable().optional(),
|
|
3585
|
-
sourceNodeIds: z21.array(z21.string()).optional(),
|
|
3586
|
-
sourceSpanIds: z21.array(z21.string()).optional(),
|
|
3587
|
-
reason: z21.string().optional()
|
|
3588
|
-
});
|
|
3589
3579
|
var OperationalProfileCleanupSchema = z21.object({
|
|
3590
3580
|
coverageDecisions: z21.array(z21.object({
|
|
3591
3581
|
coverageIndex: z21.number().int().nonnegative(),
|
|
@@ -3609,8 +3599,7 @@ var OperationalProfileCleanupSchema = z21.object({
|
|
|
3609
3599
|
appliesTo: z21.string().nullable().optional(),
|
|
3610
3600
|
sourceNodeIds: z21.array(z21.string()).optional(),
|
|
3611
3601
|
sourceSpanIds: z21.array(z21.string()).optional()
|
|
3612
|
-
})).optional()
|
|
3613
|
-
termAdditions: z21.array(CleanupTermSchema).optional()
|
|
3602
|
+
})).optional()
|
|
3614
3603
|
})).default([]),
|
|
3615
3604
|
warnings: z21.array(z21.string()).default([])
|
|
3616
3605
|
});
|
|
@@ -3618,7 +3607,6 @@ var CLEANUP_CANDIDATE_ID_LIMIT = 12;
|
|
|
3618
3607
|
var CLEANUP_SOURCE_NODE_LIMIT = 90;
|
|
3619
3608
|
var CLEANUP_SIBLING_WINDOW = 4;
|
|
3620
3609
|
var CLEANUP_KEYWORD = /\b(coverage|limit|liability|deductible|retention|retroactive|premium|aggregate|sublimit|sub-limit|claim|occurrence|loss|proceeding|endorsement|declarations?)\b|\$[0-9]/i;
|
|
3621
|
-
var CLEANUP_CONTINUATION_KEYWORD = /\b(coverage part|limit of liability|deductible|retention|retroactive date|aggregate|sublimit|sub-limit|each claim|each occurrence|each loss|each proceeding|coinsurance)\b|\$[0-9]/i;
|
|
3622
3610
|
function compactNode(node, maxText = 700) {
|
|
3623
3611
|
return {
|
|
3624
3612
|
id: node.id,
|
|
@@ -3747,15 +3735,11 @@ function selectCoverageCleanupNodes(sourceTree, coverages) {
|
|
|
3747
3735
|
const children = childrenByParent.get(selectedNode.id) ?? [];
|
|
3748
3736
|
for (const child of children.slice(0, 24)) addNode(child, 760);
|
|
3749
3737
|
}
|
|
3750
|
-
const continuationPages = new Set([...coveragePages].map((page) => page + 1));
|
|
3751
3738
|
for (const node of sourceTree) {
|
|
3752
3739
|
if (node.kind === "document") continue;
|
|
3753
|
-
if (
|
|
3754
|
-
const samePage = coveragePages.has(node.pageStart);
|
|
3755
|
-
const nearbyContinuationPage = continuationPages.has(node.pageStart);
|
|
3756
|
-
if (!samePage && !nearbyContinuationPage) continue;
|
|
3740
|
+
if (!node.pageStart || !coveragePages.has(node.pageStart)) continue;
|
|
3757
3741
|
const text = nodeTextForSelection(node);
|
|
3758
|
-
if (CLEANUP_KEYWORD.test(text) || nodeTextMatchesCoverage(node, coverageTerms)
|
|
3742
|
+
if (CLEANUP_KEYWORD.test(text) || nodeTextMatchesCoverage(node, coverageTerms)) {
|
|
3759
3743
|
addNode(node, 600);
|
|
3760
3744
|
}
|
|
3761
3745
|
}
|
|
@@ -3769,7 +3753,7 @@ function buildOperationalProfileCleanupPrompt(sourceTree, profile, options = {})
|
|
|
3769
3753
|
const coverageEntries = coverageCleanupEntries(profile, options.coverageIndexes);
|
|
3770
3754
|
const nodes = selectCoverageCleanupNodes(sourceTree, coverageEntries.map((entry) => entry.coverage)).map((node) => compactNode(
|
|
3771
3755
|
node,
|
|
3772
|
-
node.kind === "page" || node.kind === "page_group" ?
|
|
3756
|
+
node.kind === "page" || node.kind === "page_group" ? 260 : node.kind === "table_row" || node.kind === "table_cell" ? 520 : 360
|
|
3773
3757
|
));
|
|
3774
3758
|
const candidate = {
|
|
3775
3759
|
documentType: profile.documentType,
|
|
@@ -3793,23 +3777,20 @@ Projection defects to look for:
|
|
|
3793
3777
|
- Item references such as "shown in Item 7" or bare item numbers treated as money amounts.
|
|
3794
3778
|
- Policy wording, exclusions, or unsupported prose copied into operational limit/deductible fields.
|
|
3795
3779
|
- Header/value splits where "Limit of Liability", "Deductible", "Retroactive Date", "Aggregate", "Each Claim", or similar terms are attached to the wrong coverage row.
|
|
3796
|
-
- Collapsed combined bases where one candidate term says "Each Claim / Aggregate", "Each Loss / Aggregate", "Each Proceeding / Aggregate", or a continuation line supplies a separate policy aggregate, sub-limit, deductible, retention, retroactive date, or coinsurance term.
|
|
3797
3780
|
- Repeated schedule headings projected as separate coverages when they only introduce the next coverage group.
|
|
3798
3781
|
|
|
3799
3782
|
Rules:
|
|
3800
3783
|
- Use internal reasoning, but return JSON decisions only.
|
|
3801
|
-
- Do not invent policy facts. Keep, drop, or update only existing coverageIndex and termIndex entries
|
|
3784
|
+
- Do not invent policy facts. Keep, drop, or update only existing coverageIndex and termIndex entries.
|
|
3802
3785
|
- Use sourceNodeIds and sourceSpanIds only from the provided source nodes or from the existing candidate entry.
|
|
3803
3786
|
- Prefer dropping a malformed fact over speculative rewriting.
|
|
3804
3787
|
- Keep a coverage when it is a real operational coverage/benefit even if only one term needs cleanup.
|
|
3805
3788
|
- Never drop a declaration or schedule coverage row that names a coverage and states policy-specific amounts, dates, deductibles, retentions, premiums, or coverage terms. Repair its terms instead.
|
|
3806
3789
|
- When changing a term's semantic meaning, set kind to the corrected normalized term kind.
|
|
3807
|
-
- Do not add new coverage rows.
|
|
3808
|
-
-
|
|
3809
|
-
- When replacing one combined term with split terms, drop the combined term and add one term per basis. For example, "$1,000,000 Each Claim / Aggregate" should become one each_claim_limit term and one aggregate_limit term, both with value "$1,000,000".
|
|
3810
|
-
- When a schedule continues onto the next page before the next item marker, attach continuation terms such as "Aggregate", "Policy Aggregate", coinsurance, deductible, or retroactive date to the previous coverage row.
|
|
3790
|
+
- Do not add new coverage rows or new terms; this pass cleans the existing projection.
|
|
3791
|
+
- If one existing term combines multiple real limit bases, such as "Each Claim / Aggregate", keep the combined term unless another existing term already represents the other basis. Do not relabel it to only one basis and lose information.
|
|
3811
3792
|
- Include every JSON key in each decision. Use null for scalar fields you are not changing and [] for source ID lists you are not changing.
|
|
3812
|
-
- For each coverage decision, always include termDecisions
|
|
3793
|
+
- For each coverage decision, always include termDecisions. Use [] when no terms need cleanup.
|
|
3813
3794
|
- Keep reasons concise and factual.
|
|
3814
3795
|
|
|
3815
3796
|
Candidate projection:
|
|
@@ -3950,50 +3931,9 @@ function applyTermCleanupDecision(term, decision, validNodeIds, validSpanIds) {
|
|
|
3950
3931
|
}
|
|
3951
3932
|
return next;
|
|
3952
3933
|
}
|
|
3953
|
-
function termAdditionTouches(addition, predicate) {
|
|
3954
|
-
return predicate({
|
|
3955
|
-
kind: addition.kind,
|
|
3956
|
-
label: cleanProfileValue(addition.label) ?? "",
|
|
3957
|
-
value: cleanProfileValue(addition.value) ?? ""
|
|
3958
|
-
});
|
|
3959
|
-
}
|
|
3960
3934
|
function termDecisionsTouch(coverage, decisions, predicate) {
|
|
3961
3935
|
return decisions.filter((decision) => decision.action !== "keep").some((decision) => termDecisionTouches(coverage, decision, predicate));
|
|
3962
3936
|
}
|
|
3963
|
-
function termAdditionsTouch(additions, predicate) {
|
|
3964
|
-
return additions.some((addition) => termAdditionTouches(addition, predicate));
|
|
3965
|
-
}
|
|
3966
|
-
function termKey(term) {
|
|
3967
|
-
return [
|
|
3968
|
-
term.kind,
|
|
3969
|
-
cleanProfileValue(term.label)?.toLowerCase(),
|
|
3970
|
-
cleanProfileValue(term.value)?.toLowerCase()
|
|
3971
|
-
].join("|");
|
|
3972
|
-
}
|
|
3973
|
-
function applyTermAddition(addition, validNodeIds, validSpanIds) {
|
|
3974
|
-
const label = cleanProfileValue(addition.label);
|
|
3975
|
-
const value = cleanProfileValue(addition.value);
|
|
3976
|
-
if (!label || !value) return void 0;
|
|
3977
|
-
const sourceNodeIds = validIds(addition.sourceNodeIds, validNodeIds);
|
|
3978
|
-
const sourceSpanIds = validIds(addition.sourceSpanIds, validSpanIds);
|
|
3979
|
-
if (sourceNodeIds.length === 0 && sourceSpanIds.length === 0) return void 0;
|
|
3980
|
-
const term = {
|
|
3981
|
-
kind: addition.kind,
|
|
3982
|
-
label,
|
|
3983
|
-
value,
|
|
3984
|
-
sourceNodeIds,
|
|
3985
|
-
sourceSpanIds
|
|
3986
|
-
};
|
|
3987
|
-
if (typeof addition.amount === "number" && Number.isFinite(addition.amount)) {
|
|
3988
|
-
term.amount = addition.amount;
|
|
3989
|
-
} else if (term.kind !== "retroactive_date") {
|
|
3990
|
-
const amount = amountFromOperationalValue(value);
|
|
3991
|
-
if (amount !== void 0) term.amount = amount;
|
|
3992
|
-
}
|
|
3993
|
-
const appliesTo = cleanProfileValue(addition.appliesTo);
|
|
3994
|
-
if (appliesTo) term.appliesTo = appliesTo;
|
|
3995
|
-
return term;
|
|
3996
|
-
}
|
|
3997
3937
|
function applyCoverageCleanupDecision(coverage, decision, validNodeIds, validSpanIds) {
|
|
3998
3938
|
if (!decision || decision.action === "keep") return coverage;
|
|
3999
3939
|
if (decision.action === "drop") return void 0;
|
|
@@ -4024,31 +3964,23 @@ function applyCoverageCleanupDecision(coverage, decision, validNodeIds, validSpa
|
|
|
4024
3964
|
const termDecisions = (decision.termDecisions ?? []).filter((termDecision) => termDecision.termIndex < coverage.limits.length);
|
|
4025
3965
|
const termDecisionByIndex = new Map(termDecisions.map((termDecision) => [termDecision.termIndex, termDecision]));
|
|
4026
3966
|
next.limits = coverage.limits.map((term, index) => applyTermCleanupDecision(term, termDecisionByIndex.get(index), validNodeIds, validSpanIds)).filter((term) => Boolean(term));
|
|
4027
|
-
|
|
4028
|
-
|
|
4029
|
-
for (const term of termAdditions) {
|
|
4030
|
-
const key = termKey(term);
|
|
4031
|
-
if (existingTermKeys.has(key)) continue;
|
|
4032
|
-
next.limits.push(term);
|
|
4033
|
-
existingTermKeys.add(key);
|
|
4034
|
-
}
|
|
4035
|
-
if (termDecisions.length > 0 || termAdditions.length > 0) {
|
|
4036
|
-
if (decision.limit == null && (termDecisionsTouch(coverage, termDecisions, isLimitTerm) || termAdditionsTouch(termAdditions, isLimitTerm))) {
|
|
3967
|
+
if (termDecisions.length > 0) {
|
|
3968
|
+
if (decision.limit == null && termDecisionsTouch(coverage, termDecisions, isLimitTerm)) {
|
|
4037
3969
|
const value = primaryLimitFromTerms(next.limits);
|
|
4038
3970
|
if (value) next.limit = value;
|
|
4039
3971
|
else delete next.limit;
|
|
4040
3972
|
}
|
|
4041
|
-
if (decision.deductible == null &&
|
|
3973
|
+
if (decision.deductible == null && termDecisionsTouch(coverage, termDecisions, isDeductibleTerm)) {
|
|
4042
3974
|
const value = deductibleFromTerms(next.limits);
|
|
4043
3975
|
if (value) next.deductible = value;
|
|
4044
3976
|
else delete next.deductible;
|
|
4045
3977
|
}
|
|
4046
|
-
if (decision.premium == null &&
|
|
3978
|
+
if (decision.premium == null && termDecisionsTouch(coverage, termDecisions, isPremiumTerm)) {
|
|
4047
3979
|
const value = premiumFromTerms(next.limits);
|
|
4048
3980
|
if (value) next.premium = value;
|
|
4049
3981
|
else delete next.premium;
|
|
4050
3982
|
}
|
|
4051
|
-
if (decision.retroactiveDate == null &&
|
|
3983
|
+
if (decision.retroactiveDate == null && termDecisionsTouch(coverage, termDecisions, isRetroactiveDateTerm)) {
|
|
4052
3984
|
const value = retroactiveDateFromTerms(next.limits);
|
|
4053
3985
|
if (value) next.retroactiveDate = value;
|
|
4054
3986
|
else delete next.retroactiveDate;
|
|
@@ -4275,36 +4207,6 @@ function spanPageEnd(span) {
|
|
|
4275
4207
|
function spanSourceUnit(span) {
|
|
4276
4208
|
return span.sourceUnit ?? span.metadata?.sourceUnit ?? span.metadata?.elementType;
|
|
4277
4209
|
}
|
|
4278
|
-
function formNumberFromText(value) {
|
|
4279
|
-
return cleanText(value, "").match(/\b[A-Z]{2,}(?:-[A-Z0-9]+)+\s+\d{2}\s+\d{2}\b/)?.[0]?.replace(/\s+/g, " ");
|
|
4280
|
-
}
|
|
4281
|
-
function editionDateFromFormNumber(formNumber) {
|
|
4282
|
-
const match = formNumber?.match(/\b(\d{2})\s+(\d{2})$/);
|
|
4283
|
-
return match ? `${match[1]}/${match[2]}` : void 0;
|
|
4284
|
-
}
|
|
4285
|
-
function pageTitleFromText(text, fallback) {
|
|
4286
|
-
const normalized = cleanText(text, fallback);
|
|
4287
|
-
const patterns = [
|
|
4288
|
-
/\bIMPORTANT NOTICE\s+[—-]\s+HOW TO REPORT A CLAIM\b/i,
|
|
4289
|
-
/\bPRIVACY NOTICE TO POLICYHOLDERS\b/i,
|
|
4290
|
-
/\bOFAC ADVISORY NOTICE\b/i,
|
|
4291
|
-
/\bTERRORISM RISK INSURANCE ACT\s*\(TRIA\)\s*DISCLOSURE AND REJECTION\b/i,
|
|
4292
|
-
/\bDECLARATIONS PAGE\b/i,
|
|
4293
|
-
/\bTECHNOLOGY ERRORS?\s*&\s*OMISSIONS AND CYBER LIABILITY INSURANCE POLICY\b/i,
|
|
4294
|
-
/\bTRADE OR ECONOMIC SANCTIONS LIMITATION\b/i,
|
|
4295
|
-
/\bFORMS? AND ENDORSEMENTS\b/i
|
|
4296
|
-
];
|
|
4297
|
-
for (const pattern of patterns) {
|
|
4298
|
-
const match = normalized.match(pattern)?.[0];
|
|
4299
|
-
if (match) return cleanText(match, fallback);
|
|
4300
|
-
}
|
|
4301
|
-
const endorsement = normalized.match(/\bENDORSEMENT\s+(?:NO\.?|NUMBER|#)\s*[A-Z0-9][A-Z0-9.-]*\b/i)?.[0];
|
|
4302
|
-
if (endorsement) return cleanText(endorsement, fallback);
|
|
4303
|
-
const firstSentence = normalized.split(/(?<=\.)\s+/)[0];
|
|
4304
|
-
if (/^page\s+\d+\b/i.test(firstSentence)) return fallback;
|
|
4305
|
-
if (firstSentence && firstSentence.length <= 120) return firstSentence.replace(/[.]$/, "");
|
|
4306
|
-
return fallback;
|
|
4307
|
-
}
|
|
4308
4210
|
function pageHeadingTitleFromText(text, fallback) {
|
|
4309
4211
|
const normalized = cleanText(text, "");
|
|
4310
4212
|
const headingText = normalized.replace(/^page\s+\d+\s*(?:\|\s*page\s*\|\s*page\s+\d+\s*\|?)?/i, "").slice(0, 700);
|
|
@@ -4324,194 +4226,9 @@ function pageHeadingTitleFromText(text, fallback) {
|
|
|
4324
4226
|
}
|
|
4325
4227
|
return fallback;
|
|
4326
4228
|
}
|
|
4327
|
-
function pageFormTypeFromText(text) {
|
|
4328
|
-
if (hasSubstantiveDeclarationsScheduleText(text)) return "declarations";
|
|
4329
|
-
if (/\b(declarations?\s+page|declarations?\s+schedule)\b/i.test(text)) return "declarations";
|
|
4330
|
-
if (/\b(endorsement\s+(?:no\.?|number|#)|this endorsement changes the policy|[A-Z]{2,}-END\s+\d{2,})\b/i.test(text)) return "endorsement";
|
|
4331
|
-
if (/\b(technology errors?\s*&?\s*omissions.*liability insurance policy|policy form|coverage form|insuring agreement|definitions?|exclusions?|conditions?)\b/i.test(text)) return "coverage";
|
|
4332
|
-
if (/\b(important notice|privacy notice|ofac advisory|terrorism risk insurance act|tria|trade or economic sanctions)\b/i.test(text)) return "notice";
|
|
4333
|
-
return "other";
|
|
4334
|
-
}
|
|
4335
4229
|
function hasSubstantiveDeclarationsScheduleText(text) {
|
|
4336
4230
|
return /\bitem\s+\d+\.?\s*(?:named insured|policy number|policy period|renewal|form of business|coverage parts?|limits?|premium|extended reporting|producer|forms? and endorsements?)\b/i.test(text) || /\bforms? and endorsements attached at inception\b/i.test(text) || /\bcoverage parts?,?\s+limits? of liability,?\s+deductibles?,?\s+and retroactive dates\b/i.test(text) || /\bannual premium\s*\(all coverage parts?\)\b/i.test(text) || /\berp option\b/i.test(text) || /\bproducer\b[\s\S]{0,240}\blicense\b/i.test(text);
|
|
4337
4231
|
}
|
|
4338
|
-
function administrativeFormTypeFromText(text) {
|
|
4339
|
-
if (hasSubstantiveDeclarationsScheduleText(text)) return void 0;
|
|
4340
|
-
if (/\b(important notice|privacy notice|ofac advisory|terrorism risk insurance act|tria|trade or economic sanctions|economic sanctions limitation|how to report a claim)\b/i.test(text)) {
|
|
4341
|
-
return "notice";
|
|
4342
|
-
}
|
|
4343
|
-
if (/\b(specimen policy|policy jacket|countersigned|countersignature|licensed resident agent|corporate secretary|president and ceo|application of insurance executed)\b/i.test(text)) {
|
|
4344
|
-
return "other";
|
|
4345
|
-
}
|
|
4346
|
-
return void 0;
|
|
4347
|
-
}
|
|
4348
|
-
function pageTextByNumber(sourceSpans) {
|
|
4349
|
-
const pageTexts = /* @__PURE__ */ new Map();
|
|
4350
|
-
const pageSpanTexts = /* @__PURE__ */ new Map();
|
|
4351
|
-
for (const span of sourceSpans) {
|
|
4352
|
-
const start = spanPageStart(span);
|
|
4353
|
-
if (typeof start !== "number") continue;
|
|
4354
|
-
const end = spanPageEnd(span) ?? start;
|
|
4355
|
-
for (let page = start; page <= end; page += 1) {
|
|
4356
|
-
if (spanSourceUnit(span) === "page") {
|
|
4357
|
-
pageSpanTexts.set(page, cleanText(span.text, ""));
|
|
4358
|
-
continue;
|
|
4359
|
-
}
|
|
4360
|
-
const existing = pageTexts.get(page) ?? "";
|
|
4361
|
-
if (existing.length < 4e3) pageTexts.set(page, cleanText([existing, span.text].filter(Boolean).join(" "), ""));
|
|
4362
|
-
}
|
|
4363
|
-
}
|
|
4364
|
-
return new Map([.../* @__PURE__ */ new Set([...pageTexts.keys(), ...pageSpanTexts.keys()])].map((page) => [
|
|
4365
|
-
page,
|
|
4366
|
-
pageSpanTexts.get(page) ?? pageTexts.get(page) ?? ""
|
|
4367
|
-
]));
|
|
4368
|
-
}
|
|
4369
|
-
function reconcileFormTypeWithSourceText(form, pageTexts) {
|
|
4370
|
-
const pages = [];
|
|
4371
|
-
const start = form.pageStart;
|
|
4372
|
-
const end = form.pageEnd ?? start;
|
|
4373
|
-
if (typeof start === "number" && typeof end === "number") {
|
|
4374
|
-
for (let page = start; page <= end; page += 1) pages.push(pageTexts.get(page) ?? "");
|
|
4375
|
-
}
|
|
4376
|
-
const text = cleanText([form.title, form.formNumber, ...pages].filter(Boolean).join(" "), "");
|
|
4377
|
-
const administrativeType = administrativeFormTypeFromText(text);
|
|
4378
|
-
if (administrativeType && form.formType !== administrativeType) return administrativeType;
|
|
4379
|
-
return form.formType;
|
|
4380
|
-
}
|
|
4381
|
-
function inferFormHintsFromSourceSpans(sourceSpans) {
|
|
4382
|
-
const pageTexts = pageTextByNumber(sourceSpans);
|
|
4383
|
-
if (pageTexts.size === 0) return [];
|
|
4384
|
-
const pageHints = [...pageTexts.keys()].sort((left, right) => left - right).map((page) => {
|
|
4385
|
-
const text = pageTexts.get(page) ?? "";
|
|
4386
|
-
const formNumber = formNumberFromText(text);
|
|
4387
|
-
return {
|
|
4388
|
-
formNumber,
|
|
4389
|
-
editionDate: editionDateFromFormNumber(formNumber),
|
|
4390
|
-
title: pageTitleFromText(text, `Page ${page}`),
|
|
4391
|
-
formType: pageFormTypeFromText(text),
|
|
4392
|
-
pageStart: page,
|
|
4393
|
-
pageEnd: page
|
|
4394
|
-
};
|
|
4395
|
-
});
|
|
4396
|
-
const merged = [];
|
|
4397
|
-
for (const hint of pageHints) {
|
|
4398
|
-
const previous = merged[merged.length - 1];
|
|
4399
|
-
const startsNewEndorsement = hint.formType === "endorsement" && /\bendorsement\s+(?:no\.?|number|#)\s*[A-Z0-9]|this endorsement changes the policy/i.test(hint.title ?? "");
|
|
4400
|
-
const canMerge = previous && previous.formType === hint.formType && previous.pageEnd !== void 0 && hint.pageStart === previous.pageEnd + 1 && (hint.formType === "declarations" || hint.formType === "coverage" || hint.formType === "endorsement" && !startsNewEndorsement);
|
|
4401
|
-
if (!canMerge) {
|
|
4402
|
-
merged.push(hint);
|
|
4403
|
-
continue;
|
|
4404
|
-
}
|
|
4405
|
-
previous.pageEnd = hint.pageEnd;
|
|
4406
|
-
previous.title = previous.title ?? hint.title;
|
|
4407
|
-
previous.formNumber = previous.formNumber ?? hint.formNumber;
|
|
4408
|
-
previous.editionDate = previous.editionDate ?? hint.editionDate;
|
|
4409
|
-
}
|
|
4410
|
-
return merged;
|
|
4411
|
-
}
|
|
4412
|
-
function normalizeFormHints(forms, sourceSpans) {
|
|
4413
|
-
const pageTexts = pageTextByNumber(sourceSpans);
|
|
4414
|
-
const provided = (forms ?? []).filter(
|
|
4415
|
-
(form) => typeof form.pageStart === "number" && typeof form.pageEnd === "number" && form.pageStart > 0 && form.pageEnd >= form.pageStart
|
|
4416
|
-
).map((form) => ({
|
|
4417
|
-
...form,
|
|
4418
|
-
formType: reconcileFormTypeWithSourceText(form, pageTexts),
|
|
4419
|
-
title: form.title ? cleanText(form.title, "") : void 0
|
|
4420
|
-
})).sort(
|
|
4421
|
-
(left, right) => (left.pageStart ?? Number.MAX_SAFE_INTEGER) - (right.pageStart ?? Number.MAX_SAFE_INTEGER) || (left.pageEnd ?? Number.MAX_SAFE_INTEGER) - (right.pageEnd ?? Number.MAX_SAFE_INTEGER)
|
|
4422
|
-
);
|
|
4423
|
-
return provided.length ? provided : inferFormHintsFromSourceSpans(sourceSpans);
|
|
4424
|
-
}
|
|
4425
|
-
function formHintForPage(forms, page) {
|
|
4426
|
-
return forms.find(
|
|
4427
|
-
(form) => typeof form.pageStart === "number" && typeof form.pageEnd === "number" && page >= form.pageStart && page <= form.pageEnd
|
|
4428
|
-
);
|
|
4429
|
-
}
|
|
4430
|
-
function titleFromFormHint(form, fallback) {
|
|
4431
|
-
if (form.formType === "declarations") return "Declarations";
|
|
4432
|
-
if (form.formType === "coverage") return "Policy Form";
|
|
4433
|
-
if (form.formType === "endorsement") return endorsementTitle([form.title, form.formNumber].filter(Boolean).join(" ")) ?? cleanText(form.title, fallback);
|
|
4434
|
-
return cleanText(form.title, fallback);
|
|
4435
|
-
}
|
|
4436
|
-
function formGroupConfig(form) {
|
|
4437
|
-
if (form.formType === "declarations") {
|
|
4438
|
-
return {
|
|
4439
|
-
kind: "page_group",
|
|
4440
|
-
title: "Declarations",
|
|
4441
|
-
description: "Declarations pages and schedules grouped from form inventory",
|
|
4442
|
-
organizer: "form_inventory_declarations_grouping"
|
|
4443
|
-
};
|
|
4444
|
-
}
|
|
4445
|
-
if (form.formType === "coverage") {
|
|
4446
|
-
return {
|
|
4447
|
-
kind: "form",
|
|
4448
|
-
title: "Policy Form",
|
|
4449
|
-
description: "Policy form pages grouped from form inventory",
|
|
4450
|
-
organizer: "form_inventory_policy_form_grouping"
|
|
4451
|
-
};
|
|
4452
|
-
}
|
|
4453
|
-
if (form.formType === "endorsement") {
|
|
4454
|
-
const title = titleFromFormHint(form, "Endorsement");
|
|
4455
|
-
return {
|
|
4456
|
-
kind: "endorsement",
|
|
4457
|
-
title,
|
|
4458
|
-
description: `${title} grouped from form inventory`,
|
|
4459
|
-
organizer: "form_inventory_endorsement_grouping"
|
|
4460
|
-
};
|
|
4461
|
-
}
|
|
4462
|
-
return void 0;
|
|
4463
|
-
}
|
|
4464
|
-
function applyFormInventoryHints(sourceTree, forms) {
|
|
4465
|
-
if (forms.length === 0) return sourceTree;
|
|
4466
|
-
const rootId = sourceTreeRootId(sourceTree);
|
|
4467
|
-
if (!rootId) return sourceTree;
|
|
4468
|
-
const byParent = nodesByParent(sourceTree);
|
|
4469
|
-
const children = (byParent.get(rootId) ?? []).filter((node) => node.kind !== "document").sort((left, right) => left.order - right.order);
|
|
4470
|
-
const rootPages = children.filter((node) => node.kind === "page" && typeof node.pageStart === "number");
|
|
4471
|
-
let nextTree = sourceTree.map((node) => {
|
|
4472
|
-
if (node.kind !== "page" || typeof node.pageStart !== "number") return node;
|
|
4473
|
-
const form = formHintForPage(forms, node.pageStart);
|
|
4474
|
-
if (!form) return node;
|
|
4475
|
-
const isStartPage = form.pageStart === node.pageStart;
|
|
4476
|
-
const shouldRetitle = isStartPage && form.formType !== "other";
|
|
4477
|
-
return {
|
|
4478
|
-
...node,
|
|
4479
|
-
title: shouldRetitle ? titleFromFormHint(form, node.title) : node.title,
|
|
4480
|
-
metadata: {
|
|
4481
|
-
...node.metadata,
|
|
4482
|
-
formInventoryHint: {
|
|
4483
|
-
formType: form.formType,
|
|
4484
|
-
formNumber: form.formNumber,
|
|
4485
|
-
title: form.title,
|
|
4486
|
-
pageStart: form.pageStart,
|
|
4487
|
-
pageEnd: form.pageEnd
|
|
4488
|
-
}
|
|
4489
|
-
}
|
|
4490
|
-
};
|
|
4491
|
-
});
|
|
4492
|
-
const claimed = /* @__PURE__ */ new Set();
|
|
4493
|
-
for (const form of forms) {
|
|
4494
|
-
const config = formGroupConfig(form);
|
|
4495
|
-
const pageStart2 = form.pageStart;
|
|
4496
|
-
const pageEnd2 = form.pageEnd;
|
|
4497
|
-
if (!config || typeof pageStart2 !== "number" || typeof pageEnd2 !== "number") continue;
|
|
4498
|
-
const childIds = rootPages.filter(
|
|
4499
|
-
(page) => !claimed.has(page.id) && typeof page.pageStart === "number" && page.pageStart >= pageStart2 && page.pageStart <= pageEnd2
|
|
4500
|
-
).map((page) => page.id);
|
|
4501
|
-
if (childIds.length === 0) continue;
|
|
4502
|
-
nextTree = groupAdjacentChildren({
|
|
4503
|
-
sourceTree: nextTree,
|
|
4504
|
-
children,
|
|
4505
|
-
childIds,
|
|
4506
|
-
kind: config.kind,
|
|
4507
|
-
title: config.title,
|
|
4508
|
-
description: config.description,
|
|
4509
|
-
organizer: config.organizer
|
|
4510
|
-
});
|
|
4511
|
-
childIds.forEach((id) => claimed.add(id));
|
|
4512
|
-
}
|
|
4513
|
-
return normalizeDocumentSourceTreePaths(nextTree);
|
|
4514
|
-
}
|
|
4515
4232
|
function looksLikeDeclarationsStart(node) {
|
|
4516
4233
|
const title = cleanText(node.title, "");
|
|
4517
4234
|
const text = sourceNodeText(node);
|
|
@@ -4522,13 +4239,13 @@ function looksLikeDeclarationsStart(node) {
|
|
|
4522
4239
|
}
|
|
4523
4240
|
function looksLikeDeclarationsContinuation(node) {
|
|
4524
4241
|
const text = sourceNodeText(node);
|
|
4525
|
-
return looksLikeDeclarationsStart(node) || /\b(item\s+\d+\.|coverage part|each claim limit|aggregate limit|retroactive date|self-insured retention|premium|payment plan|producer|broker|forms? and endorsements?|extended reporting period|discovery period)\b/i.test(text);
|
|
4242
|
+
return looksLikeDeclarationsStart(node) || /\b(item\s+\d+\.|coverage part|limits?,?\s+sub-limits?|each claim limit|aggregate limit|retroactive date|self-insured retention|premium|payment plan|producer|broker|forms? and endorsements?|attached at inception|extended reporting period|discovery period)\b/i.test(text) || /\b(these declarations|policy form|[A-Z]{2,}-END\s+\d{3}|endorsement\s+(?:no\.?|number|#)?\s*\d+)\b/i.test(text);
|
|
4526
4243
|
}
|
|
4527
4244
|
function looksLikePolicyFormStart(node) {
|
|
4528
4245
|
const text = sourceNodeText(node);
|
|
4529
4246
|
const excerpt = cleanText(node.textExcerpt, "");
|
|
4530
4247
|
if (isAdministrativeNoticeNode(node) || looksLikeDeclarationsStart(node)) return false;
|
|
4531
|
-
return /\bpolicy form\b/i.test(node.title) || /^policy\s+form\b/i.test(excerpt) || /\btechnology errors?\s*&?\s*omissions\b/i.test(text) && /\bplease read this entire policy carefully\b/i.test(text) || /\bform\s+[A-Z]{2,}-[A-Z0-9-]+\s+\d{2}\s+\d{2}\b/i.test(text);
|
|
4248
|
+
return /\bpolicy form\b/i.test(node.title) || /^policy\s+form\b/i.test(excerpt) || /\btechnology errors?\s*&?\s*omissions\b/i.test(text) && /\bplease read this entire policy carefully\b/i.test(text) || /\bsection\s+[IVX0-9]+\s*[—-]\s*(insuring agreements?|definitions?|exclusions?|conditions?)\b/i.test(text) || /\bform\s+[A-Z]{2,}-[A-Z0-9-]+\s+\d{2}\s+\d{2}\b/i.test(text);
|
|
4532
4249
|
}
|
|
4533
4250
|
function looksLikePolicyFormContinuation(node) {
|
|
4534
4251
|
const text = sourceNodeText(node);
|
|
@@ -5290,25 +5007,51 @@ function isOperationalEvidenceAnchor(span) {
|
|
|
5290
5007
|
if (/\$[\d,.]+|[0-9]{1,2}\/[0-9]{1,2}\/[0-9]{2,4}|[0-9]{1,2}\s+[A-Za-z]{3,9}\s+[0-9]{4}/.test(text)) return true;
|
|
5291
5008
|
return false;
|
|
5292
5009
|
}
|
|
5010
|
+
function operationalEvidencePages(sourceSpans) {
|
|
5011
|
+
const scores = /* @__PURE__ */ new Map();
|
|
5012
|
+
for (const span of sourceSpans) {
|
|
5013
|
+
const page = spanPageStart(span);
|
|
5014
|
+
if (typeof page !== "number") continue;
|
|
5015
|
+
const text = cleanText([span.text, span.formNumber, spanSourceUnit(span)].filter(Boolean).join(" "), "");
|
|
5016
|
+
if (!text) continue;
|
|
5017
|
+
let score = Math.max(0, operationalEvidenceScore(span));
|
|
5018
|
+
if (/\bdeclarations?\s+(page|schedule)?\b/i.test(text)) score += 24;
|
|
5019
|
+
if (/\bitem\s+\d+\.?\s*(?:named insured|policy number|policy period|coverage parts?|limits?|premium|producer|forms? and endorsements?)\b/i.test(text)) score += 20;
|
|
5020
|
+
if (/\bcoverage parts?,?\s+limits? of liability,?\s+deductibles?,?\s+and retroactive dates\b/i.test(text)) score += 24;
|
|
5021
|
+
if (/\b(policy\s*(number|period|term)|effective date|expiration date|expiry date|named insured|insurer|carrier|security)\b/i.test(text)) score += 12;
|
|
5022
|
+
if (/\b(premium|total due|tax|fee|producer|broker)\b/i.test(text)) score += 10;
|
|
5023
|
+
if (/\b(endorsement\s+(?:no\.?|number|#)?\s*[A-Z0-9]|attached at inception|forms? and endorsements?)\b/i.test(text)) score += 8;
|
|
5024
|
+
if (/\b(definitions?|exclusions?|conditions?|duties in the event|action against|cancellation by)\b/i.test(text)) score -= 12;
|
|
5025
|
+
if (score > 0) scores.set(page, (scores.get(page) ?? 0) + score);
|
|
5026
|
+
}
|
|
5027
|
+
return new Set(
|
|
5028
|
+
[...scores.entries()].filter(([, score]) => score >= 18).sort((left, right) => right[1] - left[1] || left[0] - right[0]).slice(0, 12).map(([page]) => page)
|
|
5029
|
+
);
|
|
5030
|
+
}
|
|
5293
5031
|
function operationalProfileEvidence(sourceTree, sourceSpans) {
|
|
5294
5032
|
const sorted = [...sourceSpans].sort(
|
|
5295
5033
|
(left, right) => (spanPageStart(left) ?? Number.MAX_SAFE_INTEGER) - (spanPageStart(right) ?? Number.MAX_SAFE_INTEGER) || (left.location?.charStart ?? Number.MAX_SAFE_INTEGER) - (right.location?.charStart ?? Number.MAX_SAFE_INTEGER) || left.id.localeCompare(right.id)
|
|
5296
5034
|
);
|
|
5035
|
+
const selectedPages = operationalEvidencePages(sorted);
|
|
5297
5036
|
const selected = /* @__PURE__ */ new Set();
|
|
5298
5037
|
const selectedTableIds = /* @__PURE__ */ new Set();
|
|
5299
5038
|
for (let index = 0; index < sorted.length; index += 1) {
|
|
5300
|
-
const
|
|
5039
|
+
const span = sorted[index];
|
|
5040
|
+
const score = operationalEvidenceScore(span);
|
|
5301
5041
|
if (score < 8) continue;
|
|
5302
|
-
if (!isOperationalEvidenceAnchor(
|
|
5303
|
-
const
|
|
5304
|
-
if (
|
|
5305
|
-
const
|
|
5306
|
-
|
|
5042
|
+
if (!isOperationalEvidenceAnchor(span)) continue;
|
|
5043
|
+
const page = spanPageStart(span);
|
|
5044
|
+
if (selectedPages.size > 0 && typeof page === "number" && !selectedPages.has(page) && score < 30) continue;
|
|
5045
|
+
const tableId2 = spanTableId(span);
|
|
5046
|
+
if (tableId2 && !isTableCellSpan(span)) selectedTableIds.add(tableId2);
|
|
5047
|
+
const neighborWindow = score >= 24 ? 2 : 1;
|
|
5048
|
+
for (let offset = -neighborWindow; offset <= neighborWindow; offset += 1) {
|
|
5307
5049
|
const neighborIndex = index + offset;
|
|
5308
5050
|
const neighbor = sorted[neighborIndex];
|
|
5309
5051
|
if (!neighbor || spanPageStart(neighbor) !== page) continue;
|
|
5052
|
+
if (selectedPages.size > 0 && typeof page === "number" && !selectedPages.has(page) && operationalEvidenceScore(neighbor) < 30) continue;
|
|
5310
5053
|
const neighborText = cleanText(neighbor.text, "");
|
|
5311
|
-
if (!neighborText || neighborText.length >
|
|
5054
|
+
if (!neighborText || neighborText.length > 3e3) continue;
|
|
5312
5055
|
selected.add(neighborIndex);
|
|
5313
5056
|
}
|
|
5314
5057
|
}
|
|
@@ -5317,7 +5060,7 @@ function operationalProfileEvidence(sourceTree, sourceSpans) {
|
|
|
5317
5060
|
const tableId2 = spanTableId(span);
|
|
5318
5061
|
if (!tableId2 || !selectedTableIds.has(tableId2) || isTableCellSpan(span)) return;
|
|
5319
5062
|
const text = cleanText(span.text, "");
|
|
5320
|
-
if (text && text.length <=
|
|
5063
|
+
if (text && text.length <= 3e3) selected.add(index);
|
|
5321
5064
|
});
|
|
5322
5065
|
}
|
|
5323
5066
|
const nodeIdsBySpanId = sourceNodeIdsBySpanId(sourceTree);
|
|
@@ -5335,12 +5078,12 @@ function operationalProfileEvidence(sourceTree, sourceSpans) {
|
|
|
5335
5078
|
pageEnd: spanPageEnd(span),
|
|
5336
5079
|
sourceUnit: spanSourceUnit(span),
|
|
5337
5080
|
formNumber: span.formNumber,
|
|
5338
|
-
text: text.slice(0, span.sourceUnit === "page" ?
|
|
5081
|
+
text: text.slice(0, span.sourceUnit === "page" ? 900 : 700)
|
|
5339
5082
|
}];
|
|
5340
5083
|
});
|
|
5341
5084
|
const detailEntries = entries.filter((entry) => entry.sourceUnit !== "page");
|
|
5342
5085
|
const pageEntries = entries.filter((entry) => entry.sourceUnit === "page");
|
|
5343
|
-
return [...detailEntries, ...pageEntries
|
|
5086
|
+
return [...detailEntries.slice(0, 80), ...pageEntries.slice(0, 8)];
|
|
5344
5087
|
}
|
|
5345
5088
|
function sourceTreeRootId(sourceTree) {
|
|
5346
5089
|
return sourceTree.find((node) => node.kind === "document")?.id;
|
|
@@ -5388,7 +5131,8 @@ Rules:
|
|
|
5388
5131
|
- A coverage schedule row's coverage name should come from the "Coverage Part" or equivalent row label. Limit, deductible, aggregate, sublimit, retention, and retroactive-date values belong as nested terms under that coverage, not in the coverage title.
|
|
5389
5132
|
- If a coverage schedule continues onto the next page before the next item marker, include the continuation rows in the same coverage or declaration item.
|
|
5390
5133
|
- If one schedule row or continuation row states the same amount with multiple bases, such as "$1,000,000 Each Claim / Aggregate", return separate limit terms for each basis using the same value instead of one combined "Each Claim / Aggregate" term.
|
|
5391
|
-
-
|
|
5134
|
+
- LiteParse text can fragment visual table cells into adjacent lines. Before extracting coverage terms, mentally join adjacent lines in the same declaration item or schedule row. For example, "$2,000,000 Policy Each Claim" followed immediately by "Aggregate" means "$2,000,000 Policy Aggregate"; a line ending with "/" followed by "Aggregate ..." means the limit cell continues, not a new coverage.
|
|
5135
|
+
- Forms-and-endorsements schedules are form schedule evidence, not coverage limits. Do not turn form schedule rows into coverage units unless the row also states a coverage-specific limit or deductible.
|
|
5392
5136
|
- Keep each coverage unit tied to one evidence scope: a declaration/core schedule row, a core policy form section, or one specific endorsement schedule. Do not merge declaration facts and endorsement schedule facts into the same coverage unit, even when they use the same coverage name.
|
|
5393
5137
|
- If the declarations schedule and an endorsement schedule both list Network Security, Social Engineering Fraud, Regulatory Proceedings, or another same-named coverage, return separate coverage units for each supported source scope.
|
|
5394
5138
|
- Use the declaration coverage name for declaration/core schedule rows. Use the endorsement title or endorsement schedule coverage name for endorsement rows, and include formNumber and endorsementNumber when source-backed.
|
|
@@ -5627,8 +5371,8 @@ async function cleanupOperationalCoverageSchedules(params) {
|
|
|
5627
5371
|
}
|
|
5628
5372
|
async function runSourceTreeExtraction(params) {
|
|
5629
5373
|
const sourceSpans = normalizeSourceSpans(params.sourceSpans);
|
|
5630
|
-
const formHints =
|
|
5631
|
-
let sourceTree = applySemanticPageGrouping(
|
|
5374
|
+
const formHints = [];
|
|
5375
|
+
let sourceTree = applySemanticPageGrouping(buildDocumentSourceTree(sourceSpans, params.id));
|
|
5632
5376
|
const warnings = [];
|
|
5633
5377
|
let modelCalls = 0;
|
|
5634
5378
|
let callsWithUsage = 0;
|