@claritylabs/cl-sdk 1.3.7 → 1.3.8

package/README.md

@@ -13,7 +13,7 @@ npm install @claritylabs/cl-sdk pdf-lib zod
 ## What It Does
 
 - **Document Extraction** — Deterministic extraction pipeline with focused model calls that turns insurance PDFs or host-provided Docling documents into structured data with page-level provenance, quality gates, first-class definitions and covered reasons, referential coverage resolution, cost-aware formatting, and automatic declarations-to-schema promotion (limits, deductibles, locations, broker, loss payees, premium, taxes/fees, summary)
-- **Source Grounding** — Shared source spans, source chunks, source stores, quoted evidence validation, and deterministic evidence ordering across extraction, query, application, PCE, and case workflows
+- **Source Grounding** — Shared source spans, hierarchical table row/cell evidence, source chunks, 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 documents, 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 — field extraction, prior-answer backfill, context auto-fill, document lookup gating, topic-based question batching, reply parsing, source-backed field provenance, and PDF mapping
 - **Policy Change Endorsements** — PCE intake, evidence collection, missing-info handling, quality gates, execution mode selection, and reviewable submission packets
@@ -52,7 +52,7 @@ console.log(result.reviewReport); // Quality gate results
 
 ### 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, and runs the same focused structuring pipeline over Docling page text.
+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, and runs the same focused structuring pipeline over Docling page text. 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({
@@ -80,7 +80,7 @@ const extractor = createExtractor({ generateText, generateObject, sourceStore })
 const result = await extractor.extract(pdfBase64, "policy-123", { sourceSpans });
 ```
 
-When source spans are available, section and endorsement extraction returns a compact index with page ranges, short excerpts, and `sourceSpanIds`/`sourceTextHash` instead of asking the model to reproduce full policy wording. Store `result.sourceSpans`/source chunks as the canonical evidence corpus for Q&A and source viewers; use `result.chunks` for structured facts and navigation metadata.
+When source spans are available, section and endorsement extraction returns a compact index with page ranges, short excerpts, and `sourceSpanIds`/`sourceTextHash` instead of asking the model to reproduce full policy wording. Table-derived records prefer parent row spans over isolated cells, and coverage schedule rows can be recovered deterministically when the model misses explicit table evidence. Store `result.sourceSpans`/source chunks as the canonical evidence corpus for Q&A and source viewers; use `result.chunks` for structured facts and navigation metadata.
 
 See the [full documentation](https://cl-sdk.claritylabs.inc/docs) for architecture, provider setup, API reference, and more.