Fix sentinel edge cases: hallucination combo guard + UI formatting

Replace ad-hoc refusal regexes with NOT IN DOCUMENTS sentinel

Fix refusal detector missing 'not able to' and 'outside scope' phrases

Show violation details in flagged response banner

Fix Dockerfile: replace HHEM pre-warm with nli-deberta-v3-small

Replace HHEM with sentence-level NLI, add claim decomposition and drift detection

Fix compat, bugs, and types; expand retail KB

Switch faithfulness to text_pair encoding, promote score logging to INFO

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

Fix Vectara label check and input format

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

Add joke short-circuit and reset attempt handler

Load T5-small tokenizer for Vectara HHEM v2

Add sentencepiece dependency for T5Tokenizer

Use T5Tokenizer directly for Vectara HHEM v2

Fix Vectara pipeline: explicitly load tokenizer before pipeline init

Pin transformers<4.46.0 to fix Vectara HHEM v2 compatibility

Load Vectara model via transformers pipeline, not CrossEncoder

Speed up Docker builds: .dockerignore + merge model download layers

Add trust_remote_code=True for Vectara hallucination model

Switch faithfulness grader to Vectara hallucination evaluation model

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

Faithfulness: mean sentence scoring, strip chunk title prefix, lower threshold to 0.35

Pre-build KB indexes at startup, not on first query

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

Add 15 drug profiles to pharma KB from Kaggle dataset

Add Kaggle drug CSV → features.yaml conversion script

UX: welcome message with example questions, specific failure details in verdict

Address Gate 5 audit gaps

Inject client terminology into system prompt

Fix faithfulness: score per chunk, take max entailment

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

Replace Anthropic with free-tier stack

Add .env and .DS_Store to gitignore

Update NOTES.md

Update ARCHITECTURE.md and README.md to reflect client library and test suite

Add typed client library, unit + integration tests, mypy, ruff, NOTES.md

Add Makefile, HTML eval report generator, gitignore for reports

Add L2 batch evaluator and architecture documentation

Add full RAG evaluation pipeline with L1 metrics and UI

initial commit