daveadmin
e32ee60e78
- Add 4-step year inference rule for DD.MM. entries (scan backward/forward for anchor year) - Add Norwegian month-name formats (18. september, den 18. september 2025, etc.) with month lookup table - Add $relativeInstruction to tell LLM upfront when relative dates are excluded (not just PHP-filtered post-hoc) - Define confidence calibration criteria explicitly (high/medium/low) - Improve source_excerpt guidance: most diagnostic phrase, not just any verbatim phrase - Add actor normalization for Norwegian institutions (Barnevernstjenesten, Fylkesnemnda, Statsforvalteren, etc.) - Add deduplication rule for events appearing across multiple documents - Add end_date field for date_type=period events - Improve what_we_found schema hint to require count/range/actors/gaps - Increase max_tokens to 8000 for azure_full (gpt-4o) to avoid truncation on large documents - Tighten system prompt with Norwegian CPS legal chain context Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Do Better Norge Legal Tools Hub
MVP docroot for tools.dobetternorge.no.
Required environment
- CaveauAI client access for
DBN_CAVEAU_CLIENT_SLUGandDBN_CAVEAU_PACKAGE_SLUG DBN_AZURE_OPENAI_ENDPOINTDBN_AZURE_OPENAI_API_KEYDBN_AZURE_OPENAI_API_VERSIONDBN_AZURE_OPENAI_CHAT_DEPLOYMENTDBN_AZURE_OPENAI_EMBEDDING_DEPLOYMENT
Optional:
DBN_AI_PORTAL_ROOT(defaults to siblingai-portal)DBN_CAVEAU_CLIENT_SLUG(defaults todobetter)DBN_CAVEAU_PACKAGE_SLUG(defaults tofamily-legal)DBN_TOOLS_SUPPORT_DIRDBN_TOOLS_METADATA_LOG
Authentication
The login form authenticates against Caveau client_users for the configured
client slug. The client must be active, the user must be active, and the client
must have an active subscription to the configured corpus package.
Use scripts/setup-caveau-access.php for repeatable local/production setup of
the Do Better Norge Caveau owner account, family-legal subscription, and
white-label domain mappings. Pass the account password through
DBN_SETUP_PASSWORD at runtime only; do not commit it.
The APIs process pasted text in memory and write only metadata such as tool name, latency, language, source count, chunk count, deployment, and anonymous session id.