John SmithandClaude b9539dc8c3 feat(lore): Qdrant-backed compendium RAG with honest provenance (iteration 32) ...

Multi-tenant retrieval per GOALS.md Pillar 7: compendium spells/
monsters/magic items indexed into the qdrant_rules collection named
and dimensioned by the repo's own collections config, payload-filter
namespacing (category + system_id + tags), deterministic UUID5 point
ids, keyword indexes on filter fields — all over raw httpx REST so the
transport stays trivially mockable. Embedding is a documented
lexical-hash embedder (MD5-bucketed, L2-normalized), not semantic;
real models are a single-function swap. lore-lookup gains semantic=true
with provenance retrieval: qdrant | substring | substring_fallback,
zero network when disabled, one honest warning when unreachable,
read-path degradation only (canon-write strictness unchanged).
29 red-first tests; suite at 279.

Co-Authored-By: Claude <[email protected]>

2026-08-24 03:41:46 -04:00

..

tests

feat(lore): Qdrant-backed compendium RAG with honest provenance (iteration 32)

2026-08-24 03:41:46 -04:00

vtt_orchestrator

feat(lore): Qdrant-backed compendium RAG with honest provenance (iteration 32)

2026-08-24 03:41:46 -04:00

pyproject.toml

feat(wave13): UI/UX hardening — code splitting, dice history, a11y & honest ambience

2026-08-23 15:16:15 -04:00