Integrate RAG v1.2 admin panel and handoff features

Hardening admin security: moving credentials to environment variables

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

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

Upgrade: Professional intelligent retrieval pipeline with robust tokenization and LLM query expansion

Migrate from Groq to OpenAI 4o-mini

Optimize RAG pipeline for speed: persistent HTTP client, faster reranker, and result caching

Refine RAG pipeline for comprehensive leave retrieval, improve system prompt, and fix Gradio HTML rendering

Optimize token usage to resolve 413 Payload Too Large error

Fix Groq 413 Payload Too Large by strictly capping context and tokens

Optimize for Intelligent Completeness: 10 context chunks and dense system prompt

Fix latency: switch to bge-small and bge-reranker-base for CPU optimization

Fix Groq 413 Payload Too Large by reducing max_tokens and context chunks

Update Groq Qwen model ID to qwen/qwen3-32b

Switch entirely to qwen-2.5-32b due to DeepSeek-R1 string deprecations

Update DeepSeek-R1 model alias to deepseek-r1-distill-qwen-32b

Update decommissioned DeepSeek-R1 model alias to specdec

Implement DeepSeek-R1, BGE-Large, and Hybrid Search

Upgraded RAG pipeline for ChatGPT-level depth and intelligence (Multi-query, larger context, smarter prompts)

Upload 47 files

wipe space

Implement Clarification Intelligence: Ambiguity detection and multi-turn clarification protocol

Implement Deep Intelligence: Query Expansion, Reranking, and High-Precision Chunking

Switch to SMTP_SSL on port 465 for better reliability on Hugging Face

Implement email-based OTP and enforce verification state

Fix database persistence: added sessions volume and robust path handling for /data

Enable persistent storage for sessions and index

feat: add secure admin panel, session store, localStorage tracking