Strict cleanup: remove internal handoff docs, neutralize teammate/sprint naming in public docs

Diversity probe sweep + V1->V4 narrative README + HF Spaces entry + DV/incomplete fixes

V4.3: prompt-injection audit, input length cap, per-layer ablation, unguarded baseline, limitations restored

V4.2 part 3: sycophancy guard, F-1 flag decay, incomplete-message handler

V4.2 part 1: fix broken ISSS URL, ship URL audit + Karthik data brief

V4: streaming, controlled paraphrasing, support plan, voice, sweeps

Add Eval B safety supplement

Ingest Core dataset and harden router policy

Prepare Core dataset intake and resource registry

Polish peer helper and scope handling

Add Core safety metadata and eval summaries

Implement EmpathRAG Core hybrid router

Add Karthik eval harness and safety patches

Start V2.5 support navigator hardening

Checkpoint V2 curated support navigator

Add curated corpus integration scaffold

Start v2 safety hardening

Clean repo: fix README with verified metrics, pin requirements, update gitignore, remove log from tracking

Add conversation memory, fix Gradio stack, improve SYSTEM_PROMPT, log human eval turns

Fix Condition C ablation - pure FAISS order, no safety score bias - mean=0.50

Add ablation Condition C eval - mean alignment 0.40 vs D=0.88

fix: MistralJudge schema detection for truths/claims/verdicts — matches DeepEval 3-call pattern (Day 15)

fix: MistralJudge uses from_json_schema grammar — correct structure for claim extraction and verification (Day 15)

fix: GBNF grammar-constrained JSON sampling in MistralJudge — eliminates DeepEval JSON parse errors (Day 15)

fix: MistralJudge JSON extraction for DeepEval faithfulness, commit Wilcoxon results (Day 15)

fix: wilcoxon sys.path for condition_a import, zero_method=pratt for binary scores (Day 15)

fix: Wilcoxon uses stub guardrail — tests retrieval quality on all 50 prompts not 13 (Day 15)

feat: DeepEval FaithfulnessMetric with Mistral judge, async_mode=False (replaces RAGAS, Day 15)

fix: guardrail dual-import path, bertscore key names, ragas reuse pipeline.llm (Day 14)

eval: save adversarial results at both t=0.50 and t=0.85, reset production threshold to 0.50 (Day 14)

fix: threshold sweep — calibrate DeBERTa guardrail threshold, patch eval imports (Day 14)

feat: eval scripts — BM25 baseline, adversarial probes, BERTScore, RAGAS, Wilcoxon (Day 14)

feat: Gradio demo app, DeBERTa Colab notebook, updated smoke test results (Day 13)

Add eval suite: test prompts, adversarial probes, BERTScore references (Day 12)

Add pipeline orchestrator + smoke test — 4/5 emotion predictions correct (Day 12)

Day 1: data pipeline, session tracker, query router, adversarial probes, Colab training notebooks