fix(voice+chat+llm+docs): KI-155 + KI-156 + KI-157 + KI-158 + KI-159 + KI-160 bundle

feat(deploy): KI-152 — upload_to_hf.py syncs deletions, not just adds

fix(routing): KI-154 — empty-profile QA must route to fact_find

fix(routing): KI-153 — profile-update utterances now route to fact_find

fix(chat+marketplace+voice): KI-145 + KI-148 + KI-149 + KI-150 bundle

fix(api): KI-145 — RENAME-vs-VARIANT smart dedup (final 164 cards)

fix(marketplace+voice+routing): KI-136 + KI-141 + KI-142 + KI-143 + KI-144 — full bundle

fix(deploy): bump DATASET_CACHE_BUST -> ki138-v2 — force rebuild to pull post-KI-138 Chroma + extracted

fix(rag+voice): KI-137 + KI-138 + KI-139 — ingest 21 curated policies into Chroma, canonicalize 84 policy names, fix voice VAD thresholds

fix(api): KI-135 — /api/coverage counts from disk same as /api/policies/all

fix(voice): KI-134 — 5 blind fixes for silent-fail mic capture

fix(api): KI-133 — dedup /api/policies/all to one card per policy product

fix(api): KI-132 — drop regulatory from /api/policies/all + complete insurer_meta

fix(voice): KI-131 — voice OFF by default + surface AudioWorklet failure

fix(api): KI-130 — drop 'regulatory' from /api/coverage marketplace tallies

fix(api): KI-129 — /api/coverage must not surface 'profile' as an insurer

fix(deploy): KI-128 — exclude _hf_dataset_backup + LFS pointers from Space push

fix(docs): KI-127 — correct cascade arithmetic, 224 -> 206 corpus PDFs

fix(corpus): KI-126 — drop 2 image-only PDFs + cascade docs across 3 repos

perf(ingest): KI-125 — bump MPS embedding batch 64→128 for bulk re-ingest

fix(admin): KI-122 — clear LLM availability + in-use indicators

fix(ui): KI-120 — unify policy/insurer counts from /api/coverage

fix(deploy): KI-119 — DATASET_CACHE_BUST arg forces HF dataset re-pull

chore: trigger HF rebuild — pull cleaned Chroma (1 UUID, 3799 chunks)

fix(deploy): KI-119 — disable persistent /data/vectors symlink

chore: trigger HF Space rebuild to pull clean Chroma from dataset

refactor(session): KI-118 — rip out session_id concept, name-based profiles only

fix(rag): KI-117 — boot-time cleanup of dangling profile chunks

fix(rag+admin): KI-112 hardening + KI-116 banner + admin copy

fix(voice): KI-113 + KI-114 + KI-115 — reject background noise, distant speech, mid-thought pauses

fix(indic): KI-110 — repair Hindi pipeline raising on every turn

fix(safety+closer): KI-108 + KI-109 — apply CoT strip to all reply paths + broaden closer regex

fix(rag): KI-111 — wrap collection.query() to survive corrupted Chroma index

docs: KI-101..KI-107 — audit + CLAUDE.md + ADR sync

feat(closer): KI-105 — wire ranked recommendation handoff on closer intent

fix(rag): KI-107 — graceful handling of Chroma get(ids=...) for missing ids

fix(safety): KI-106 — graceful timeout/exception handling on /api/chat

fix(safety): KI-104 — strip chain-of-thought / instruction-echo leakage from replies

fix(fact-find): KI-103 — break no_trailer fallback loop after 2 failed attempts

fix(privacy): KI-102 — scope profile-RAG retrieval to session_id only

fix(orchestrator): KI-101 — drop function-local 'import logging' to fix UnboundLocalError

fix(latency): KI-100 — outer wait_for(25s) around drive_fact_find

fix(latency): KI-099 — bound every per-turn LLM call

fix(admin): KI-096 + KI-097 — public /api/version + password-only admin

fix(safety): KI-095 — 5 defensive guards against profile-field clearing

docs: KI-091 + KI-094 — extractor gates + None-guard added to audit + CLAUDE + ADR-032

fix(orchestrator): KI-094 — extractor cannot clear a filled profile field

fix(fact-find): KI-092 — lenient name parser when slot explicitly awaiting name

fix(orchestrator): KI-091 — skip profile_extractor + faithfulness judge on fact-find turns (drop dependent LLM calls on saturated chains)

docs: backend/README — fix stale ADR-027 link on needs_finder + add fact_find_brain row + mark paraphraser deleted