- Add GLAMORCUBESFIXPHDNT heritage type detection for person profiles
- Two-stage classification: blocklist non-heritage orgs, then match keywords
- Special handling for Digital (D) type: requires heritage org context
- Add career_history heritage_relevant and heritage_type fields
- Add exponential backoff retry for Anthropic API overload errors
- Fix DSPy 3.x async context with dspy.context() wrapper
- Implemented a new script `test_pico_arabic_waqf.py` to test the GLM annotator's ability to extract person observations from Arabic historical documents.
- The script includes environment variable handling for API token, structured prompts for the GLM API, and validation of extraction results.
- Added comprehensive logging for API responses, extraction results, and validation errors.
- Included a sample Arabic waqf text for testing purposes, following the PiCo ontology pattern.
Add new endpoints for querying administrative boundaries:
- GET /boundaries/countries - List all countries with boundary data
- GET /boundaries/countries/{code}/admin1 - List provinces/states
- GET /boundaries/countries/{code}/admin2 - List municipalities
- GET /boundaries/lookup?lat=&lon= - Point-in-polygon lookup
- GET /boundaries/admin2/{id}/geojson - Get single boundary GeoJSON
- GET /boundaries/countries/{code}/admin2/geojson - Get all admin2 as GeoJSON
- GET /boundaries/stats - Get boundary statistics
Uses proper joins through country_id/admin1_id foreign keys.
