Implements a state machine to filter streaming tokens:
- Only stream tokens from the 'answer' field to the frontend
- Skip tokens from 'reasoning', 'citations', 'confidence', 'follow_up' fields
- Remove DSPy field markers like '[[ ## answer ## ]]' from streamed content
This fixes the issue where raw DSPy signature field markers were being
displayed in the chat interface instead of clean answer text.
- Add sparqlQuery field to CachedResponse interface
- Extract SPARQL query before cache storage (not after)
- Include sparqlQuery in cache HIT message objects
- Handle both snake_case (server) and camelCase field names
SPARQL queries are now displayed for both fresh API responses
and cached responses, improving debugging and transparency.
- CZ: 2,170 processed (26% of 8,432)
- JP: 2,075 processed (17% of 12,096)
- AR: Started processing
- Total checkpoint: 9,762 files across all countries
- Using crawl4ai favicon extraction
- Added logo_enrichment to 771 Czech custodian files
- 87% logo hit rate using crawl4ai favicon extraction
- Total checkpoint: 9,257 files across all countries
- CZ remaining: 6,642 files
- Remove onFaceClick prop from CustodianTypeIndicator3D in class/slot/enum detail views
to prevent accidental filtering when clicking decorative cubes (Bug 3)
- Add parseCustodianTypesAnnotation() helper to handle JSON-stringified arrays like '["A"]'
in YAML annotations, fixing Bug 2 where all 19 letters appeared on every cube
- Legend bar retains onTypeClick for intentional filtering functionality
- Use hc: <https://w3id.org/heritage/custodian/> prefix
- Use hc:institutionType with single-letter codes (M, L, A, etc.)
- Use Wikidata URIs for countries (Q55=NL, Q31=BE, etc.)
- Update all SPARQL examples to use correct ontology
- Align with actual RDF data in Oxigraph
- Use crm:E39_Actor instead of glam:HeritageCustodian
- Use hc:institutionType with single-letter codes (M, L, A, etc.)
- Use Wikidata URIs for countries (Q55=NL, Q31=BE, etc.)
- Use skos:prefLabel for institution names
- Update ONTOLOGY_CONTEXT with correct examples
- Update HeritageSPARQLGenerator docstring with correct prefixes
- Change main class from hc:Custodian to crm:E39_Actor
- Change type property from hcp:institutionType to org:classification
- Update type values from single letters to full names (MUSEUM, ARCHIVE, etc.)
- Add rate limit handling with exponential backoff for 429 errors
- Fix test_live_rag.py sample queries to use correct ontology
- Update optimized_models instructions with correct prefixes
- Update SPARQL CONSTRUCT query to use correct ontology namespaces:
- hc: https://w3id.org/heritage/custodian/ (was nde)
- Use nde:Custodian type (was crm:E39_Actor)
- Use schema:location + geo:lat/long (was crm predicates)
- Remove LIMIT 500 clause to fetch all results
- Show all node types by default instead of random single type
- Fixes issue where Knowledge Graph showed incomplete/random data
