Replace ad-hoc refusal regexes with NOT IN DOCUMENTS sentinel

Fix compat, bugs, and types; expand retail KB

Add telemetry layer: in-memory counters + HF Dataset persistence

Add /refresh-cache endpoint, bi-encoder comparison, eval results, Ollama/Prometheus notes

Add joke short-circuit and reset attempt handler

Exclude pinned glossary doc from faithfulness grading context

Replace enforce_terminology with pinned glossary doc in RAG context

Add enforce_terminology: deterministic post-processing corrective gate

Load all KB formats merged — drop CSV directly, no conversion needed

Address Gate 5 audit gaps

Inject client terminology into system prompt

Switch generation model to Llama-3-8B-Instruct

Replace Anthropic with free-tier stack

Add full RAG evaluation pipeline with L1 metrics and UI