fix: resolve workflow linking on resume, update proposals auto-commit, and validation baseline rules

feat: add quick demo login, fix archived knowledge filter and workflow completion state

feat: render in-page interactive elements as Links to support right-click open in new tab

perf: optimize login transition and dashboard loading performance

fix: eliminate N+1 queries on knowledge list/search endpoints

perf: knowledge page loads 2x faster, filters are instant

fix: auto-commit used workspace_id as committed_by (FK violation)

feat: light/dark mode toggle, sharper text

fix: activity filter shows all event types per doc; knowledge filter persists on back

polling and sort by doc

fix: concurrency lock, full stage instrumentation, submission docs

docs update

fix forgot password

fix signup message

fix signup

mcp update

feat: use email OTP for password recovery

Remove demo mode from signup OTP verification flow

search box

feat: proposal archive/restore governance, knowledge derived status, documents live polling, yellow archive UI

fix: harden knowledge governance and reconciliation

fix: complete knowledge lifecycle and activity pagination

feat: improve knowledge extraction and wire knowledge labels

fix: restore knowledge extraction and token tracking

feat: multi-provider LLM (Ollama local + HuggingFace deployed + Groq), fix think-tag parsing, 15K batch

fix: 5K char batch — Groq free tier strict payload limit

restore: gpt-oss-120b model, 30K batch size, proper system prompt

debug: reduce max_tokens to 2048, add request size logging

fix: minimal prompt + 3K batch for Groq limits, optimistic delete in UI

fix: switch to gpt-oss-20b (faster, larger limits), reduce batch to 8K

fix: reduce batch size to 20K chars for Groq free tier TPM limits

fix: frontend link

docs: comprehensive README, fix delete button (204), retry on any status

fix: resolve LLM context limits and tool-calling errors using Qwen JSON batching

feat: batch knowledge extraction — processes all sections sequentially, no data loss

refactor: knowledge extraction uses native JSON mode, no tool calling, 50K char buffer

fix: reduce prompt size aggressively (6K cap, 4K retry, 3K fallback) for Groq limits

feat: auto-detect document type from file extension

fix: remove confirm dialog on document delete (caused double-click issue)

fix: auto-redirect to login on 401 (expired token)

fix: cap knowledge extraction prompt to 12K chars, reduce retry to 3 sections

feat: switch email service to Resend HTTP API (no SMTP port needed)

fix: use SMTP_SSL port 465 with timeout to prevent hanging on HF

feat: replace Settings footer with user profile + logout in sidebar

feat: real email OTP via SMTP, forgot password email, Settings on mobile nav

feat: mobile-responsive frontend (bottom nav, stacked layouts, scrollable tables)

fix: remove unsupported JsonPlusSerializer kwarg for deployed langgraph version

fix: replace PNG logo with SVG, fix workspace delete double-click, remove LFS

fix: create storage dir with proper permissions, fix static copy order

untrack PNG from LFS