docs: Stage 18 — free-tier stability config + live/blocked eval status

docs: Stage 17 metadata filtering — evolution, decisions, architecture

docs: add metadata filtering implementation plan

docs: add metadata filtering design spec (Stage 17)

docs: update architecture.md to reflect current shipped state (v1.3.0 stack)

docs: audit learning.md — remove 6 non-GenAI concepts, update stale data, add Concept 21 contextual retrieval

docs: add Concept 20 — semantic chunking recall vs precision tradeoff

docs: update evolution, decisions for Stage 16 citation highlighting

fix: replace startswith with is_relative_to() for path traversal security

docs: add citation highlighting implementation plan

docs: add citation highlighting design spec

feat: HyDE re-eval (recall +21pp), briefing JSON fix, eval run cleanup

docs: update evolution.md with streaming responses (Stage 14)

docs: streaming responses implementation plan

docs: streaming responses design spec

docs: log Stage 13 async embed upload

docs: async embed upload design spec

docs: update all references Render → HF Spaces (Stage 12)

docs: Stage 11 — contextual prod + dashboard polish + concepts 18-19

docs: Stage 10 contextual retrieval results, update current state snapshot

docs: contextual retrieval implementation plan

docs: contextual retrieval design spec (eval-only, v1.3.0 target)

feat: multi-query retrieval + HyDE/MQ eval runs (v1.1.0, v1.2.0 Violet)

chore: name changes on MAJOR version only — all v1.x.x = Violet

chore: adopt semver for eval runs, rename v1.0 → v1.0.0 Violet

fix: pass methodology prop to MetricCard, rename v2.0 → Prism v1.0, update docs

docs: update evolution.md — Stage 8 TOC, current state URLs, HyDE done, next = multi-query

feat: Stage 8 — eval dashboard, mandatory web search, docs update

docs: add Prism v3 implementation plan (8 tasks: rebrand + URL ingest + briefing + citations + multi-workspace)

docs: add Prism v3 design spec (domain-agnostic rebrand + URL ingestion + briefing + citations + multi-workspace)

docs: update architecture and decisions for 2026-05-30 changes

feat: Migrate LLM to Groq, fix web search pipeline, add structured logging

feat: Add RAGAS eval, score passthrough, docs, and hybrid retrieval config