fix: route conversational queries early in stream_answer to bypass RAG retrieval and ensure correct greeting/identity responses

feat: enhance conversational query prompts and fallback handlers to support Risu Solutions / BAMS curriculum identity

debug: run llama-server logging to file, do not block uvicorn, expose server log in debug endpoint

debug: add /debug/llm endpoint to diagnose completions traceback

tune: raise context budget 700->1400 tokens + max_tokens 1200->1800 for 600-800 word answers

feat: complete BAMS syllabus database ingestion & local LLM config

feat: complete BAMS syllabus database ingestion & local LLM config

feat: optimize deployment payload using zipped database index