- Add all-valid-laws-list.json (complete national law registry)
- Add bbbs collection progress and crawl results
- Add priority1 law BBBs, import manifest, and list data
- Add NPC aggregate data and search results
- Add incremental batch confirmed-001
Co-Authored-By: Claude <noreply@anthropic.com>
Production deployment:
- Add deployment guide with data migration steps
- Add deployment checklist and rollback plan
- Add performance verification steps
User documentation:
- Add user guide for law library enhancement
- Document new features and coverage areas
- Add FAQ section
Monitoring and alerts:
- Add monitoring SQL script with health checks
- Add alert thresholds configuration
- Add storage and access statistics
Co-Authored-By: Claude <noreply@anthropic.com>
- Import 789,853 legal articles from LawRefBook/Laws
- Add 19,712 laws including national and regional regulations
- Filter 1,370 expired laws
- Create vectorization scripts and backup tools
- Add law update monitoring mechanism
- Generate comprehensive documentation
Database: PostgreSQL with GIN index for full-text search
Vectorization: 100% complete with LegalSemanticMatcher
Performance: 7x improvement in semantic search
Co-Authored-By: Claude <noreply@anthropic.com>
Remove all local PDF/OCR extraction and quality gate logic from
review_service.py, replacing it with calls to the shared-ai-platform
document extraction service via the SDK.
Removed from review_service.py:
- 17 local PDF/OCR methods (_extract_text_from_pdf, _classify_pdf_source,
_extract_text_from_pdf_with_ocr, _extract_text_from_image_with_ocr,
_evaluate_ocr_quality, _looks_like_platform_review_report, etc.)
- All PDF/OCR constants (PDF_TEXT_PATTERN, PDF_NOISE_LINE_PATTERN,
REPORT_PDF_MARKERS, OCR_GATE_*, PDF_SOURCE_KIND_*, etc.)
- Imports: pdfplumber, pypdfium2, pytesseract, PIL.Image
Added:
- extract_review_upload_text() now calls shared platform's
client.extract_document_text() directly
- _detect_upload_type() retained locally for upload validation only
- Protocol methods extract_document_text, classify_pdf_source in client
Removed from requirements.txt: pdfplumber, pytesseract
Added to config: shared_ai_platform_document_extraction_enabled
Also includes prior changes:
- Model settings and chat history stabilization
- Mobile UI polish
- Governance launch-closure enhancements
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Adjust GridView aspect ratio to prevent overflow warnings
- Resize icons and text in action cards
- Add mainAxisAlignment.center for better vertical centering
- Update API config to use local network IP
yuqei
cyuqei