fix: sort sessions and chat threads by latest activity time

fix: make Default-name Run now clickable and show progress

fix: Run now soft-deletes all default-name sessions immediately

feat: auto soft-delete default-name sessions with 24h undo

fix: reduce log flood — downgrade high-frequency per-request logs to DEBUG, silence uvicorn.access + httpx, upgrade OTP log to WARNING for visibility

chore: push latest codebase to chatRAG - includes all fixes (escalation, notifications, WA debug)

fix: revert to bare number format, add Baileys session connection pre-check to test endpoint

fix: send Baileys WA with + prefix (international format), 30s timeout, fix number stripping in save handler

fix: send Baileys WA with full JID format (number@s.whatsapp.net) - most Baileys wrappers require this

debug: capture and surface Baileys API raw response body to diagnose delivery failure

fix: revert Baileys provider to original working version, remove response body validation

feat: per-admin targeted notifications, dedicated Escalation settings, QoL pulse animation, rules rewrite

fix: add response body validation to Baileys provider, add diagnostics to test endpoint

fix: WA number stored without +, fix ProviderFactory.get_provider and send_message calls

feat: claim-based escalation, admin transfer, per-admin WhatsApp, profile settings

feat: show admin display name instead of 'Live Agent (Admin)' during takeover

feat: Multi-Admin RBAC system - admin_store, router, frontend

Add manager emails to llm service

Update EBook Manager and PM VP names in system prompt

fix: Robust intent matching for personal leave balances and tag stripping

feat: Show View Leave Summary button instead of auto-opening dashboard

feat: Add Prorata Dashboard auto-trigger on leave balance requests

feat: implement full rating system - empty stars, hover preview, per-thread storage, admin badge

fix: response quality improvements and injection sanitization

Switch org query handling from hardcoded dict to intent-based reasoning

Add indirect org query reasoning to LLM prompt

Add new management personnel to LLM prompt

Add Baileys WhatsApp provider and UI configurations

Update system prompt with leadership names and update URLs for testing space

perf: remove unnecessary asyncio lock in get_session to improve read performance (file writes are already atomic via os.replace)

fix: resolve race condition in get_session by adding async lock to prevent reading partially written JSON files

fix: strengthen FORMAT C-SUMMARY (forbidden headings + wrong example) + add 'I want leave' → FORMAT D

feat: LLM-based confirmation intent + rotating handover prompts

chore: update llm.py - expanded FORMAT table, C-SUMMARY/C-PROCEDURE split, PROCESS/PROCEDURE rule

Revert all changes to app/services/rag_pipeline.py to match original RAG v1

Add pipeline phase timing logs to help debug Hugging Face space speed

Integrate RAG v1.2 admin panel and handoff features

Update addon.html: replaced FAB close button with top bar minimize button

Enforce strict rule: all leaves taken during probation are unpaid

Fix intent map: compound keywords, follow-up starters, prorata robustness

Fix follow-up detection: add prepositional starters for context continuity

Fix prorata and single-word HR term retrieval robustness

Fix inconsistent leave and per-annum responses

Update RAG application

Update system prompt to handle 'ok' and 'okay' with a shorter acknowledgment

Update LLM system prompt: Add FORMAT E for structured multi-level topics

Replace all em dashes with hyphens in llm.py

Fix acceptability retrieval; shorten redirect responses

Fix retrieval for prorata queries

Improve bot: self-identity, non-English redirect, privacy-tone for personal data, no hallucination on people/org, varied fallbacks