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

fix(llm): stop AI from addressing the user by name

fix(backend): allow renaming sessions before first message is sent

fix: implement session merging to allow multiple logins for the same user without splitting history

Fix: Broad HR queries + Anti-hallucination hardening (no fake careers page)

Fix: Conversational Intelligence - Natural greetings, varied responses, no robot loop

Production Intelligence: Graceful Guidance + Full Intent Coverage + Urdu Support

Upgrade: Hybrid Intelligence (LLM Query Rewriter + Local Expansion)

Upgrade: Intelligence & Reasoning (Added Format D + Expanded Intent Map)

Fix follow-up typo handling (then/them) + prevent specific leave type listing other types

Add conversational follow-up resolver: pronouns (them/it/this) now resolve to last topic for accurate retrieval

Hardening RAG Intelligence: Restoration of perfect format decision table, optimized thresholds, and query expansion logic for GPT-4o-mini

feat: institutional-grade intelligence upgrade with hybrid expansion, logical deduction, and core reference data

Restore: Revert codebase to stable May 14th 6 PM state

feat: hardcode leave entitlements in system prompt for guaranteed completeness

feat: reach 100% intelligence with broader retrieval and mandatory deduction rules

feat: improve list completeness and add conclusion logic

feat: further intelligence boost via multi-intent matching and relaxed rerank thresholds

feat: increase HR assistant intelligence via logical deduction and broader retrieval

Add OpenAI integration while preserving stable intelligence - 2026-05-15 18:05

Restore to latest backup from 13 May - 2026-05-15 17:56

Polish: Add step numbers to structured list format

Intelligence: Remove all hardcoded format rules, let LLM choose format by intent