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

feat: pre-create named session on widget load via /api/session/init

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

Update chat-loader2.js with DOMContentLoaded safety wrapper

Add/update chat-loader2.js script

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

Update employee handbook to latest version and remove old documents

Update static/chat-loader.js

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

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

fix(addon): implement infinite zero-overhead name resolution with storage and focus events

fix(addon): use infinite lightweight background polling for username resolution and prevent API spam

fix(addon): improve user session name resolution with 3-option fallback chain and race condition fixes

chore: ignore and untrack backup folders

Merge branch 'main' of https://huggingface.co/spaces/joedown11/chatRAG

fix: resolve admin refresh logout issue by checking credentials dynamically

Update static/chat-loader.js

Hardening admin security: moving credentials to environment variables

Update static/chat-loader.js

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

Synchronizing chat-loader.js changes

Update chat-loader.js with cleaned version from backup

Restore original proven localStorage scan + add Bearer token API fallback + retry

Fix: use Bearer token auth for profile API name resolution

Hardened user name discovery with background retry and profile API prioritization

Update static/chat-loader.js

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