fix: disable HyDE + MQ for free-tier stability; restore app to live

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

feat: add v1.2.0 (MQ) and v1.3.0 (CTX) eval runs to dashboard

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

eval: v1.3.0 clean run (25 samples) — recall=0.627, relevancy=0.837; fix eval script max_tokens+print

eval: v1.4.0 semantic chunking — recall -9.8pp, reverted to fixed splits

feat(eval-dashboard): show version name + date on chart X-axis

feat(eval-dashboard): version label format Violet(v1.0) + release notes per version

eval: v1.3.0 Violet — contextual retrieval results (recall=0.601, P@5=0.956, p50=4161ms)

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

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

chore: rename v1.0 tag baseline → Violet

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

feat: v2.0 baseline eval run (50 samples) + metric methodology tooltips

fix: update eval dashboard subtitle

feat: remove eval sections from main UI, add eval dashboard link

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