@claritylabs/cl-sdk 3.1.7 → 3.1.9

package/README.md

@@ -12,7 +12,7 @@ npm install @claritylabs/cl-sdk pdf-lib zod
 
 ## What It Does
 
-- **Document Extraction** — Source-tree extraction that turns parser-provided PDF spans into a canonical hierarchy of document, page group, form, endorsement, section, schedule, clause, table, row, cell, and text nodes. Form-inventory page ranges and parser title elements guide the hierarchy, but every node remains backed by real source spans. Operational policy facts are projections from that tree, not the canonical source of truth.
+- **Document Extraction** — Source-tree extraction that turns parser-provided PDF spans into a canonical hierarchy of document, page group, form, endorsement, section, schedule, clause, table, row, cell, and text nodes. Form-inventory page ranges and parser title elements guide the hierarchy, but every node remains backed by real source spans. Operational policy facts are model-extracted, source-cited projections from that tree, not the canonical source of truth.
 - **Source Grounding** — Shared source spans, source nodes, hierarchical table row/cell evidence, source stores, quoted evidence validation, and deterministic evidence ordering across extraction, query, application, PCE, and case workflows.
 - **Query Agent** — Citation-backed question answering over stored source nodes, exact source spans, and inbound photos/PDFs/text with sub-question decomposition, bounded retrieval planning, attachment-only reasoning when retrieval is unnecessary, and grounding verification.
 - **Application Processing** — Bounded workflows handle intake with deterministic planning — versioned question graphs, conditional/repeatable question projection, prior-answer backfill, context auto-fill, source-backed document backfill, topic-based question batching, reply parsing, context proposals, packet assembly, and PDF mapping helpers
@@ -53,7 +53,7 @@ console.log(result.chunks);              // [] on v3 source-tree extraction path
 
 ### Optional Docling input
 
-If your host pre-processes a PDF with [Docling](https://github.com/docling-project/docling), pass the serialized `DoclingDocument` JSON instead of a PDF. CL-SDK does not install or run Python Docling; it consumes the parsed document, builds source spans, constructs the same source tree, and projects operational facts from cited nodes. Docling tables are represented as table, row, and cell source spans; row spans are treated as the canonical evidence for extracted table facts.
+If your host pre-processes a PDF with [Docling](https://github.com/docling-project/docling), pass the serialized `DoclingDocument` JSON instead of a PDF. CL-SDK does not install or run Python Docling; it consumes the parsed document, builds source spans, constructs the same source tree, and asks the configured model to extract operational facts with citations to those nodes and spans. Docling tables are represented as table, row, and cell source spans; row spans are treated as the canonical evidence for extracted table facts.
 
 ```typescript
 const result = await extractor.extract({
@@ -81,7 +81,7 @@ const extractor = createExtractor({ generateText, generateObject, sourceStore })
 const result = await extractor.extract(pdfBase64, "policy-123", { sourceSpans });
 ```
 
-When source spans are available, extraction returns `sourceTree`, `sourceSpans`, `operationalProfile`, `warnings`, `tokenUsage`, and `performanceReport`. The source tree is canonical for policy wording and hierarchy. The extractor uses form/page-range hints to group declarations, policy forms, and endorsements, then promotes title elements into section/schedule nodes that can span page breaks. The operational profile contains policy metadata, parties, coverage units, nested coverage limit terms, deductibles/retentions, premiums, key dates, and endorsement-support facts, each with `sourceNodeIds` and `sourceSpanIds`. Source-backed identity records such as insurer, producer, contacts, named insured rows, endorsement parties, and standalone insured addresses must include non-empty `sourceSpanIds`. After projection, a bounded model cleanup pass may keep, drop, or update existing coverage rows and terms by index; the SDK enforces the schema and rejects source IDs that are not present in the current source tree/spans. Endorsement schedules are modeled as whole endorsement coverage units with their own `limits[]` terms instead of unrelated flat rows like `Aggregate Limit`.
+When source spans are available, extraction returns `sourceTree`, `sourceSpans`, `operationalProfile`, `warnings`, `tokenUsage`, and `performanceReport`. The source tree is canonical for policy wording and hierarchy. The extractor uses form/page-range hints to group declarations, policy forms, and endorsements, then promotes title elements into section/schedule nodes that can span page breaks. The operational profile contains model-extracted policy metadata, parties, coverage units, nested coverage limit terms, deductibles/retentions, premiums, key dates, and endorsement-support facts, each with `sourceNodeIds` and `sourceSpanIds`. Source-backed identity records such as insurer, producer, contacts, named insured rows, endorsement parties, and standalone insured addresses must include non-empty `sourceSpanIds`. After extraction, a bounded model cleanup pass may keep, drop, or update existing coverage rows and terms by index; the SDK enforces the schema and rejects source IDs that are not present in the current source tree/spans. Endorsement schedules are modeled as whole endorsement coverage units with their own `limits[]` terms instead of unrelated flat rows like `Aggregate Limit`.
 
 Store `result.sourceTree` in a retrievable node index and embed node `description` values for search. Keep `result.sourceSpans` as the exact PDF highlighting layer. `result.document` and its `documentOutline` remain compatibility projections for existing host screens; do not treat broad structured policy JSON as canonical extraction truth.
 

package/dist/application.d.mts

@@ -1,2 +1,2 @@
-export { s as AcroFormMapping, t as AcroFormMappingSchema, u as AnswerParsingResult, v as AnswerParsingResultSchema, w as ApplicationClassifyResult, x as ApplicationClassifyResultSchema, y as ApplicationContextProposal, z as ApplicationContextProposalSchema, E as ApplicationEmailReviewSchema, F as ApplicationField, H as ApplicationFieldSchema, J as ApplicationListFilters, K as ApplicationNextQuestions, N as ApplicationPacket, O as ApplicationPacketAnswer, R as ApplicationPacketAnswerSchema, V as ApplicationPacketSchema, W as ApplicationPipelineConfig, X as ApplicationQualityArtifactSchema, Y as ApplicationQualityIssueSchema, Z as ApplicationQualityReportSchema, _ as ApplicationQualityRoundSchema, $ as ApplicationQuestionCondition, a0 as ApplicationQuestionConditionSchema, a1 as ApplicationQuestionGraph, a2 as ApplicationQuestionGraphSchema, a3 as ApplicationQuestionNode, a4 as ApplicationQuestionNodeSchema, a5 as ApplicationRepeat, a6 as ApplicationRepeatSchema, a7 as ApplicationState, a8 as ApplicationStateSchema, a9 as ApplicationStore, aa as ApplicationTemplate, ab as ApplicationTemplateListFilters, ac as ApplicationTemplateSchema, ad as ApplicationTemplateStore, ae as AutoFillMatch, af as AutoFillMatchSchema, ag as AutoFillResult, ah as AutoFillResultSchema, ak as BackfillProvider, al as BuildApplicationPacketInput, am as BuildApplicationPacketResult, aq as ContextProposalResult, au as CreateApplicationRunInput, aM as FieldExtractionResult, aN as FieldExtractionResultSchema, aO as FieldType, aP as FieldTypeSchema, aQ as FlatPdfPlacement, aR as FlatPdfPlacementSchema, aT as LookupFill, aU as LookupFillResult, aV as LookupFillResultSchema, aW as LookupFillSchema, aX as LookupRequest, aY as LookupRequestSchema, b7 as ParsedAnswer, b8 as ParsedAnswerSchema, bg as PriorAnswer, bh as ProcessApplicationInput, bi as ProcessApplicationResult, bj as ProcessReplyInput, bk as ProcessReplyResult, bl as QuestionBatchResult, bm as QuestionBatchResultSchema, bp as ReplyIntent, bq as ReplyIntentSchema, bN as applyApplicationAnswers, bO as buildApplicationPacket, bP as buildQuestionGraphFromFields, bQ as createApplicationPipeline, bR as createApplicationRun, bS as extractQuestionGraphFromFields, bT as flattenQuestionGraph, bU as getActiveApplicationFields, bV as getNextApplicationQuestions, bW as normalizeApplicationQuestionGraph, bX as planNextApplicationQuestions, bY as proposeContextWrites, b_ as validateApplicationPacket } from './index-C-jIqJru.mjs';
+export { s as AcroFormMapping, t as AcroFormMappingSchema, u as AnswerParsingResult, v as AnswerParsingResultSchema, w as ApplicationClassifyResult, x as ApplicationClassifyResultSchema, y as ApplicationContextProposal, z as ApplicationContextProposalSchema, E as ApplicationEmailReviewSchema, F as ApplicationField, H as ApplicationFieldSchema, J as ApplicationListFilters, K as ApplicationNextQuestions, N as ApplicationPacket, O as ApplicationPacketAnswer, R as ApplicationPacketAnswerSchema, V as ApplicationPacketSchema, W as ApplicationPipelineConfig, X as ApplicationQualityArtifactSchema, Y as ApplicationQualityIssueSchema, Z as ApplicationQualityReportSchema, _ as ApplicationQualityRoundSchema, $ as ApplicationQuestionCondition, a0 as ApplicationQuestionConditionSchema, a1 as ApplicationQuestionGraph, a2 as ApplicationQuestionGraphSchema, a3 as ApplicationQuestionNode, a4 as ApplicationQuestionNodeSchema, a5 as ApplicationRepeat, a6 as ApplicationRepeatSchema, a7 as ApplicationState, a8 as ApplicationStateSchema, a9 as ApplicationStore, aa as ApplicationTemplate, ab as ApplicationTemplateListFilters, ac as ApplicationTemplateSchema, ad as ApplicationTemplateStore, ae as AutoFillMatch, af as AutoFillMatchSchema, ag as AutoFillResult, ah as AutoFillResultSchema, ak as BackfillProvider, al as BuildApplicationPacketInput, am as BuildApplicationPacketResult, aq as ContextProposalResult, au as CreateApplicationRunInput, aM as FieldExtractionResult, aN as FieldExtractionResultSchema, aO as FieldType, aP as FieldTypeSchema, aQ as FlatPdfPlacement, aR as FlatPdfPlacementSchema, aT as LookupFill, aU as LookupFillResult, aV as LookupFillResultSchema, aW as LookupFillSchema, aX as LookupRequest, aY as LookupRequestSchema, b7 as ParsedAnswer, b8 as ParsedAnswerSchema, bg as PriorAnswer, bh as ProcessApplicationInput, bi as ProcessApplicationResult, bj as ProcessReplyInput, bk as ProcessReplyResult, bl as QuestionBatchResult, bm as QuestionBatchResultSchema, bp as ReplyIntent, bq as ReplyIntentSchema, bN as applyApplicationAnswers, bO as buildApplicationPacket, bP as buildQuestionGraphFromFields, bQ as createApplicationPipeline, bR as createApplicationRun, bS as extractQuestionGraphFromFields, bT as flattenQuestionGraph, bU as getActiveApplicationFields, bV as getNextApplicationQuestions, bW as normalizeApplicationQuestionGraph, bX as planNextApplicationQuestions, bY as proposeContextWrites, b_ as validateApplicationPacket } from './index-CTxWtbqE.mjs';
 import 'zod';

package/dist/application.d.ts

@@ -1,2 +1,2 @@
-export { s as AcroFormMapping, t as AcroFormMappingSchema, u as AnswerParsingResult, v as AnswerParsingResultSchema, w as ApplicationClassifyResult, x as ApplicationClassifyResultSchema, y as ApplicationContextProposal, z as ApplicationContextProposalSchema, E as ApplicationEmailReviewSchema, F as ApplicationField, H as ApplicationFieldSchema, J as ApplicationListFilters, K as ApplicationNextQuestions, N as ApplicationPacket, O as ApplicationPacketAnswer, R as ApplicationPacketAnswerSchema, V as ApplicationPacketSchema, W as ApplicationPipelineConfig, X as ApplicationQualityArtifactSchema, Y as ApplicationQualityIssueSchema, Z as ApplicationQualityReportSchema, _ as ApplicationQualityRoundSchema, $ as ApplicationQuestionCondition, a0 as ApplicationQuestionConditionSchema, a1 as ApplicationQuestionGraph, a2 as ApplicationQuestionGraphSchema, a3 as ApplicationQuestionNode, a4 as ApplicationQuestionNodeSchema, a5 as ApplicationRepeat, a6 as ApplicationRepeatSchema, a7 as ApplicationState, a8 as ApplicationStateSchema, a9 as ApplicationStore, aa as ApplicationTemplate, ab as ApplicationTemplateListFilters, ac as ApplicationTemplateSchema, ad as ApplicationTemplateStore, ae as AutoFillMatch, af as AutoFillMatchSchema, ag as AutoFillResult, ah as AutoFillResultSchema, ak as BackfillProvider, al as BuildApplicationPacketInput, am as BuildApplicationPacketResult, aq as ContextProposalResult, au as CreateApplicationRunInput, aM as FieldExtractionResult, aN as FieldExtractionResultSchema, aO as FieldType, aP as FieldTypeSchema, aQ as FlatPdfPlacement, aR as FlatPdfPlacementSchema, aT as LookupFill, aU as LookupFillResult, aV as LookupFillResultSchema, aW as LookupFillSchema, aX as LookupRequest, aY as LookupRequestSchema, b7 as ParsedAnswer, b8 as ParsedAnswerSchema, bg as PriorAnswer, bh as ProcessApplicationInput, bi as ProcessApplicationResult, bj as ProcessReplyInput, bk as ProcessReplyResult, bl as QuestionBatchResult, bm as QuestionBatchResultSchema, bp as ReplyIntent, bq as ReplyIntentSchema, bN as applyApplicationAnswers, bO as buildApplicationPacket, bP as buildQuestionGraphFromFields, bQ as createApplicationPipeline, bR as createApplicationRun, bS as extractQuestionGraphFromFields, bT as flattenQuestionGraph, bU as getActiveApplicationFields, bV as getNextApplicationQuestions, bW as normalizeApplicationQuestionGraph, bX as planNextApplicationQuestions, bY as proposeContextWrites, b_ as validateApplicationPacket } from './index-C-jIqJru.js';
+export { s as AcroFormMapping, t as AcroFormMappingSchema, u as AnswerParsingResult, v as AnswerParsingResultSchema, w as ApplicationClassifyResult, x as ApplicationClassifyResultSchema, y as ApplicationContextProposal, z as ApplicationContextProposalSchema, E as ApplicationEmailReviewSchema, F as ApplicationField, H as ApplicationFieldSchema, J as ApplicationListFilters, K as ApplicationNextQuestions, N as ApplicationPacket, O as ApplicationPacketAnswer, R as ApplicationPacketAnswerSchema, V as ApplicationPacketSchema, W as ApplicationPipelineConfig, X as ApplicationQualityArtifactSchema, Y as ApplicationQualityIssueSchema, Z as ApplicationQualityReportSchema, _ as ApplicationQualityRoundSchema, $ as ApplicationQuestionCondition, a0 as ApplicationQuestionConditionSchema, a1 as ApplicationQuestionGraph, a2 as ApplicationQuestionGraphSchema, a3 as ApplicationQuestionNode, a4 as ApplicationQuestionNodeSchema, a5 as ApplicationRepeat, a6 as ApplicationRepeatSchema, a7 as ApplicationState, a8 as ApplicationStateSchema, a9 as ApplicationStore, aa as ApplicationTemplate, ab as ApplicationTemplateListFilters, ac as ApplicationTemplateSchema, ad as ApplicationTemplateStore, ae as AutoFillMatch, af as AutoFillMatchSchema, ag as AutoFillResult, ah as AutoFillResultSchema, ak as BackfillProvider, al as BuildApplicationPacketInput, am as BuildApplicationPacketResult, aq as ContextProposalResult, au as CreateApplicationRunInput, aM as FieldExtractionResult, aN as FieldExtractionResultSchema, aO as FieldType, aP as FieldTypeSchema, aQ as FlatPdfPlacement, aR as FlatPdfPlacementSchema, aT as LookupFill, aU as LookupFillResult, aV as LookupFillResultSchema, aW as LookupFillSchema, aX as LookupRequest, aY as LookupRequestSchema, b7 as ParsedAnswer, b8 as ParsedAnswerSchema, bg as PriorAnswer, bh as ProcessApplicationInput, bi as ProcessApplicationResult, bj as ProcessReplyInput, bk as ProcessReplyResult, bl as QuestionBatchResult, bm as QuestionBatchResultSchema, bp as ReplyIntent, bq as ReplyIntentSchema, bN as applyApplicationAnswers, bO as buildApplicationPacket, bP as buildQuestionGraphFromFields, bQ as createApplicationPipeline, bR as createApplicationRun, bS as extractQuestionGraphFromFields, bT as flattenQuestionGraph, bU as getActiveApplicationFields, bV as getNextApplicationQuestions, bW as normalizeApplicationQuestionGraph, bX as planNextApplicationQuestions, bY as proposeContextWrites, b_ as validateApplicationPacket } from './index-CTxWtbqE.js';
 import 'zod';