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

feat: maintenance banner as full-screen overlay

feat: enable maintenance banner

fix: hide contextualizing stage message from upload UI

fix: deselect deleted doc from filter in Sidebar handleDelete

feat: sidebar doc filter chips scope retrieval to selected documents

fix: citation toggle stopPropagation + absolute UPLOAD_DIR path

feat: wire citation popover — click [N] in answer to view source chunk

feat: add CitationPopover component for citation highlighting

fix: show full chunk content in SourceExpander (remove 200-char truncation)

fix: ensure setLoading(false) runs in finally after streamChat

feat: stream tokens into chat UI via SSE

feat: add streamChat SSE client to api.js

fix: guard against undefined documents in upload poll callback

feat: async embed upload — return 202 immediately, poll status for stage labels

feat: disable maintenance banner — migrated to HF Spaces

feat(frontend): config-driven maintenance banner in src/config.js

feat(frontend): add maintenance banner for slow upload warning

feat(frontend): show Violet v1.3 version badge in sidebar footer

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

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

fix: remount ChatArea on workspace switch to clear stale messages

feat: multi-workspace frontend — workspace switcher, per-workspace doc list and chat

feat: add inline citation UI — [N] superscripts scroll to source cards

fix: null-safe briefing arrays, exhaustive useEffect deps, chip button type

feat: add briefing UI — summary card + clickable suggested questions after upload

fix: sanitize upload_url error messages, handle embed failure, add timeout

feat: add URL ingestion endpoint + file/url tab UI in FileUpload

fix: update index.html title and benchmark script to Prism branding

feat: rebrand FinRAG → Prism (collection names, system prompt, UI branding)

chore: run full RAGAS eval — all 4 metrics now populated

chore: update RAGAS benchmark with real scores (faithfulness=1.0, answer_relevancy=0.90)

feat: RAGAS benchmark driven by JSON, local runner script

fix: Remove corpus footnote, add i-button to RAGAS Benchmark header

refactor: Remove live RAGAS eval, replace with static benchmark panel

fix: Graceful RAGAS 500 + info tooltips on eval metrics and faithfulness badge

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

frontend changes

Add Dockerfile and Render config