ltcai 10.10.0 → 11.1.0

package/README.md

@@ -11,7 +11,7 @@
 [![CI Status](https://github.com/TaeSooPark-PTS/LatticeAI/actions/workflows/ci.yml/badge.svg?branch=main)](https://github.com/TaeSooPark-PTS/LatticeAI/actions/workflows/ci.yml)
 [![License](https://img.shields.io/badge/license-MIT-green)](LICENSE)
 
-![v10.10.0 Living Brain walkthrough](output/release/v10.10.0/gifs/v10.10.0-living-brain-walkthrough.gif)
+![v11.1.0 Living Brain walkthrough](output/release/v11.1.0/gifs/v11.1.0-living-brain-walkthrough.gif)
 
 Chat, files, folders, notes, and web pages all flow into one durable knowledge
 graph on your computer. Any model — local MLX or cloud — can speak with that
@@ -24,10 +24,10 @@ memory. Nothing leaves your machine without explicit consent.
 
 | | |
 | --- | --- |
-| **Chat with a Brain that remembers** — every conversation grows durable, source-linked memory ![Brain Chat](output/release/v10.10.0/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v10.10.0/screenshots/05-memory-graph.png) |
-| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v10.10.0/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v10.10.0/screenshots/12-review-center.png) |
-| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v10.10.0/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v10.10.0/screenshots/10-admin-console.png) |
-| **Watch a file become memory** — three named steps, not a pipeline diagram ![Material to memory](output/release/v10.10.0/screenshots/11-knowledge-journey.png) | **Say how much it may do alone** — one dial in plain words; dangerous actions stay blocked either way ![Settings](output/release/v10.10.0/screenshots/08-system.png) |
+| **Chat with a Brain that remembers** — every conversation grows durable, source-linked memory ![Brain Chat](output/release/v11.1.0/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v11.1.0/screenshots/05-memory-graph.png) |
+| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v11.1.0/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v11.1.0/screenshots/12-review-center.png) |
+| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v11.1.0/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v11.1.0/screenshots/10-admin-console.png) |
+| **Watch a file become memory** — three named steps, not a pipeline diagram ![Material to memory](output/release/v11.1.0/screenshots/11-knowledge-journey.png) | **Say how much it may do alone** — one dial in plain words; dangerous actions stay blocked either way ![Settings](output/release/v11.1.0/screenshots/08-system.png) |
 
 ## Why Lattice AI
 
@@ -58,52 +58,64 @@ First-run flow — wake the Brain, pick the owner, load a recommended model:
 
 | | | |
 | --- | --- | --- |
-| ![Login](output/release/v10.10.0/screenshots/01-login.png) | ![Model install](output/release/v10.10.0/screenshots/03-install-load-progress.png) | ![Model library](output/release/v10.10.0/screenshots/07-model-library.png) |
+| ![Login](output/release/v11.1.0/screenshots/01-login.png) | ![Model install](output/release/v11.1.0/screenshots/03-install-load-progress.png) | ![Model library](output/release/v11.1.0/screenshots/07-model-library.png) |
 
 Screenshot index and capture notes:
-[output/release/v10.10.0/SCREENSHOT_INDEX.md](output/release/v10.10.0/SCREENSHOT_INDEX.md)
+[output/release/v11.1.0/SCREENSHOT_INDEX.md](output/release/v11.1.0/SCREENSHOT_INDEX.md)
 
 ## Current Release
 
-The current release is **10.10.0 — Quiet Station**:
-
-The Brain chat home used to greet you with everything at once — a stats
-sentence, six capture chips, a model banner, an autonomy strip, and two
-shelves stacked under the composer. 10.10.0 rebuilds it around one idea: the
-canvas holds the composer; everything else blooms on demand.
-
-- **Stats became a badge.** "기억 13 · 주제 299" sits as a chip beside the
-  greeting; hovering (or clicking) it opens a summary popover with a small
-  memory/topics/links graph and the memory-map shortcut. The sentence left the
-  reading line.
-- **Capture folds behind one +.** 문서 · 이미지 · 파일 · 폴더 · 노트 · 웹 live
-  in the composer's Add menu — hover opens it, click pins it, Escape and
-  outside-click close it, and an in-flight upload keeps it open.
-- **The model banner became a status pill.** "모델 준비 필요" now sits on the
-  hero's right edge with the one accented CTA; the full sentence rides on the
-  tooltip and the accessible name.
-- **The shelves became a dock.** 대화 · 통계 · 기억 지도 sit on a quiet rail —
-  a left column on desktop, a row above the fold elsewhere — and open a
-  focus-trapped drawer over the screen instead of stacking cards under it.
-- **Borders got quieter, colour got scarcer.** Cards float on soft shadow
-  instead of rules, and the warm accent appears exactly twice: the send
-  button and the model CTA.
-- **The frontend test floor is 100%.** Every statement, branch, function and
-  line under `frontend/src` is covered, `vitest` enforces the thresholds, and
-  CI runs the coverage gate — a claim the suite fails loudly if it drifts.
-- **Release history starts at 9.0.0.** The 8.x notes left the tree; README,
-  the notes index, RELEASE.md and the changelog all begin the public story at
-  9.0.0.
+The current release is **11.1.0 — Product Intelligence**:
+
+The v9–v11.0 line hardened the foundation — proposal-first trust, honest
+signals, a 100% line-and-branch test floor. 11.1.0 builds the intelligence
+layer on top of it: **the Brain gets fast at scale, notices things on its
+own, remembers pictures and recordings, learns who you are, and connects to
+the tools you already use.**
+
+- **Fast at scale.** A pluggable vector-index layer (brute-force default,
+  int8 quantized and HNSW opt-in via the `hnsw` extra) plus a durable
+  background embed queue. Measured on Apple Silicon: hybrid search p50 at
+  10k vectors went from 299 ms to **10.1 ms**, and stays at 43.9 ms at 50k
+  (recall@10 0.987) — the plan's <50 ms target met at 5× the target corpus.
+  Approximate results say `approx: true`; quantized's honest verdict (no RAM
+  win here, ~2.2× slower) is printed, not hidden.
+- **Alive, not just searchable.** Contradiction detection now files
+  review-queue proposals with plain-language resolutions; approving one
+  stamps the temporal model (`valid_from`/`valid_to`/`superseded_by`, with
+  `as_of(timestamp)` slicing). Event-driven synthesis proposes parent
+  concepts, missing links and a proactive Brain Brief after every 25th
+  ingest — every write goes through the proposal path, asserted by tests.
+- **Pictures and recordings are memories.** Behind `allow_multimodal`
+  (default off, off ⇒ byte-identical): images become first-class `Image`
+  nodes with OCR text, real captions only when a vision model produced one
+  (the caption-fabricating stub was deleted), separate image vectors with
+  late fusion, and inline thumbnails in the Evidence panel that never bypass
+  the local-file approval gate. Recordings are first-class `Audio` nodes
+  with honest transcription degradation.
+- **It knows you — transparently.** A Self-Model subgraph (Self /
+  Preference / Decision / Habit / Relationship) built only from proposals
+  you approve, injected into answer context under a strict token budget,
+  fully listable and deletable. Agents can propose whole-folder
+  reorganizations — structurally incapable of proposing deletions.
+- **Connected, selectively.** An approval-gated Obsidian vault bridge
+  (wikilinks become edges, idempotent re-runs) and a signed, encrypted
+  subgraph-share prototype where received knowledge arrives as proposals —
+  off by default behind `LATTICEAI_BRAIN_NETWORK`.
+
+All of it lands with the floor intact: **6,261 tests, 100.00% of 37,590
+statements and 10,658 branches**, verified on macOS 3.14, a fresh-resolve
+python 3.11 environment, and a clean linux python:3.14 container.
 
 Release notes: [RELEASE.md](RELEASE.md) · Full history: [docs/CHANGELOG.md](docs/CHANGELOG.md)
 
-Expected artifacts for 10.10.0 release must use exact filenames:
+Expected artifacts for 11.1.0 release must use exact filenames:
 
-- `dist/ltcai-10.10.0-py3-none-any.whl`
-- `dist/ltcai-10.10.0.tar.gz`
-- `ltcai-10.10.0.tgz`
-- `dist/ltcai-10.10.0.vsix`
-- `src-tauri/target/release/bundle/dmg/Lattice AI_10.10.0_aarch64.dmg`
+- `dist/ltcai-11.1.0-py3-none-any.whl`
+- `dist/ltcai-11.1.0.tar.gz`
+- `ltcai-11.1.0.tgz`
+- `dist/ltcai-11.1.0.vsix`
+- `src-tauri/target/release/bundle/dmg/Lattice AI_11.1.0_aarch64.dmg`
 
 Do not use wildcard artifact uploads. Package registry publishing remains owner-run.
 
@@ -138,6 +150,9 @@ See [ARCHITECTURE.md](ARCHITECTURE.md) for details and
 
 | Version | Theme |
 | --- | --- |
+| 11.1.0 | Product Intelligence |
+| 11.0.1 | Both Branches |
+| 11.0.0 | Full Measure |
 | 10.10.0 | Quiet Station |
 | 10.9.0 | Never Blocks |
 | 10.8.0 | Within Reach |

package/docs/CHANGELOG.md

@@ -4,6 +4,74 @@ The top entry is either the current unreleased main-branch work or the current
 release line. Older entries are historical and may describe behavior as it
 existed at that release.
 
+## [11.1.0] - 2026-08-10 — Product Intelligence Layer
+
+### Added
+- 플러그형 벡터 인덱스 레이어(`lattice_brain/graph/vector_index/`):
+  BruteForce 기본, int8 Quantized·HNSW(`ltcai[hnsw]`) 옵트인, 영속 배경
+  임베딩 큐(`vector_jobs`), `vector_freshness_breakdown()`, RRF 융합·이웃
+  후보 확장 옵션. 하이브리드 p50 10k 299ms → 10.1ms, 50k 43.9ms
+  (recall@10 0.987, docs/PERFORMANCE.md).
+- Temporal 지식 모델: `valid_from`/`valid_to`/`superseded_by`(멱등 제자리
+  승급, NULL 규약) + `as_of(timestamp)` 슬라이스. 모순 감지 → 리뷰 제안
+  → 승인 시 temporal 스탬프. 이벤트 기반 합성(상위 개념·누락 엣지·
+  proactive Brief 제안, 25개 인제스트마다, 격리 배선) + 중요도/정리 제안.
+  새 API: `/api/brain/proactive-brief|importance|synthesize|contradictions/*`.
+- 멀티모달 1등 시민(`allow_multimodal`, 기본 꺼짐 — 꺼짐=바이트 동일):
+  Image/Audio 1등 노드, OCR·실캡션만(`caption_status`), 별도 이미지 벡터
+  공간+late fusion, Evidence 인라인 썸네일(승인 게이트 비우회), 비디오는
+  정직 거부.
+- Self-Model 서브그래프(제안-우선 생성, 사용자 직접 소유), 컨텍스트
+  예산 주입, 삭제 불가능 구조의 폴더 재구성 제안,
+  `/api/memory/self-model*` 5종.
+- Obsidian vault 브릿지(`POST /api/ingestion/obsidian`, 승인 게이트,
+  위키링크→엣지, 멱등) + 서명·암호화 선택적 서브그래프 공유 프로토타입
+  (`LATTICEAI_BRAIN_NETWORK` 기본 꺼짐, 수신=리뷰 제안).
+
+### Removed
+- `VisionStub`/`get_vision_embedder` — 파일명으로 캡션을 합성하고 그
+  문자열의 해시를 이미지 임베딩으로 저장하던 경로(정직성 위반) 삭제.
+
+## [11.0.1] - 2026-08-10
+
+### Fixed
+- 11.0.0 릴리스 노트가 기록한 결함 11건 전부: Telegram `send_web_link`의
+  서버 토큰 유출과 전체 언로드 성공 조작, `inspect_html` 스타일시트 데드
+  수집, 리뷰 아이템 id 초 단위 충돌, vLLM 좀비 재확인(침묵 성공 → 409),
+  보안 대시보드 목록/상세 마스킹 갭과 invalid-JSON 내보내기, 임베딩
+  `model_id` 차원 동결, fast-path `X-Model`/SSE 본문 불일치, 워크스페이스
+  응답의 죽은 `"ok"` 리터럴과 미도달 404 arm. 각 수정은 결함을 고정하던
+  테스트를 반전하고 회귀 테스트를 추가했습니다.
+
+### Changed
+- 커버리지 게이트가 분기까지 잡습니다: `[tool.coverage.run] branch = true`,
+  9,828아크 전부 실행, `fail_under = 100`은 이제 라인+분기 합산.
+  테스트 5,426 → 5,798개. `pragma: no branch`는 사유 명시 2줄.
+
+### Removed
+- 참조-0 증명 후 죽은 코드 삭제: `tool_registry._wa()`,
+  `workspace_os_utils._snapshot_graph_import_payload`, 워크스페이스 404
+  arm 2개, vLLM 침묵 성공 분기, 증명된 죽은 조건 3곳
+  (model_catalog 버전 가드 · model_compat MLX 조건 · retrieval_docgen
+  blank-query 가드).
+
+## [11.0.0] - 2026-08-10
+
+### Changed
+- Python 테스트 커버리지 72.80% → **100.00%**, CI 게이트 `fail_under = 100`.
+  테스트 2,269 → 5,426개(+3,157, 신규 파일 145개). 제외는 도달 불가 사유가
+  명시된 `pragma: no cover` 8줄뿐이며, MLX/Windows/watchdog 등 플랫폼 잠금
+  분기는 페이크 모듈·시임 패치로 ubuntu CI에서도 실행됩니다.
+- `build_phases` 후반 4개 페이즈가 `test_security.py`의 server-import
+  부수효과 없이 전용 테스트(RuntimeContext 직접 구동)로 커버됩니다.
+- ARCHITECTURE.md 검증 다이어그램이 실측값으로 갱신되고 "보고만 되고 강제
+  안 되는" 점선 상자가 사라졌습니다(양쪽 커버리지 모두 100% 플로어).
+
+### Internal
+- 커버리지 작업이 드러낸 실제 결함·죽은 분기 11건은 동작 변경 없이
+  RELEASE_NOTES_v11.0.0.md에 기록되고, 현재 동작을 그대로 단언하는
+  테스트로 고정됐습니다(수정은 다음 릴리스 후보).
+
 ## [10.10.0] - 2026-08-06
 
 ### Changed

package/docs/COMMUNITY_AND_PLUGINS.md

@@ -1,6 +1,6 @@
 # Community And Plugins
 
-Current release: **10.10.0 — Quiet Station**.
+Current release: **11.1.0 — Product Intelligence**.
 
 LatticeAI defines the path from a strong local-first framework (8.4.0
 action-aware baseline, 8.5.0 registry+DI hardening, 8.6.0 capture/navigation

package/docs/DEVELOPMENT.md

@@ -3,7 +3,7 @@
 > **Status: canonical** — current contributor guidance, kept in sync with the
 > current release.
 
-Current release: **10.10.0 — Quiet Station**.
+Current release: **11.1.0 — Product Intelligence**.
 
 This document is for contributors working on the local-first Digital Brain
 codebase. Product positioning and quick start stay in `README.md`; release

package/docs/ONBOARDING.md

@@ -1,6 +1,6 @@
 # Lattice AI Onboarding
 
-Current release: **10.10.0 — Quiet Station**.
+Current release: **11.1.0 — Product Intelligence**.
 
 The first-run goal is a five-minute path from "I opened the app" to "my Brain
 has a source, a question, and proof." This page is the product contract behind

package/docs/OPERATIONS.md

@@ -1,4 +1,4 @@
-# Lattice AI — Operations Guide (v10.10.0)
+# Lattice AI — Operations Guide (v11.1.0)
 
 > **Status: canonical** — kept in sync with the current release. Storage layout
 > below reflects the SQLite live Brain store and workspace scoping, not the

package/docs/PERFORMANCE.md

@@ -1,12 +1,11 @@
 # Knowledge Graph Performance Baseline
 
-> **Status: reference** — a synthetic regression baseline, not a
-> current-release measurement. The numbers below were last captured on the
-> v9.6.0 working tree (see provenance line) and are carried forward as the
-> comparison reference. The 9.7.0-9.8.0 line added graph-layer paths
-> (`hybrid_search`, vector freshness, extraction-quality scoring), so
-> regenerate with `scripts/profile_kg.py` on the current tree before treating
-> these as 9.8.0 numbers.
+> **Status: mixed provenance — read the date on each table.** The
+> `scripts/profile_kg.py` tables were last captured on the v9.6.0 working tree
+> and are carried forward as the regression reference; regenerate them before
+> treating them as current. The **vector index backend** table is a fresh
+> 11.1.0 measurement (2026-08-10) from `scripts/bench_vector_index.py`, and
+> says so inline.
 
 Synthetic performance and memory baseline for `KnowledgeGraphStore`
 (`lattice_brain/graph/`). Measured with `scripts/profile_kg.py`.
@@ -92,16 +91,141 @@ Keyword search p50 grew ~3.6x but stays under 5 ms.
 Regenerate with `.venv/bin/python scripts/profile_kg.py` after graph-layer
 changes and compare against these tables.
 
+## Vector index backends (11.1.0)
+
+`scripts/bench_vector_index.py` measures the three selectable backends
+(`LATTICEAI_VECTOR_INDEX`) against each other. It answers two questions
+together, because either one alone is misleading: **how fast** each backend
+answers, and **how much of the exact answer it returns** (recall@10 against
+the brute-force scan, which is ground truth by construction).
+
+Methodology, and what it does not cover:
+
+- The corpus is synthetic — deterministic pseudo-text from a fixed vocabulary
+  (English + Korean) embedded with the built-in hash embedder. Real embeddings
+  cluster differently, so the recall figures are an upper bound for a
+  well-separated corpus, not a promise about your notes.
+- Rows are written straight into `vector_embeddings`. This measures the
+  **search** path only; ingestion throughput stays in the tables above.
+- Latency and memory are measured in separate passes. tracemalloc roughly
+  triples Python allocation cost, so timing under it would measure the
+  profiler — the `peak MB` column comes from one extra traced query.
+- `peak MB` counts **Python** allocations only. hnswlib keeps its graph in C++
+  memory, which tracemalloc cannot see, so that column understates HNSW by the
+  size of the graph itself. Read it as "what the query costs the interpreter",
+  not as the process's resident size.
+- `first ms` is the *first* query after the corpus changed. For `hnsw` that is
+  where the graph gets built and the `.hnsw` sidecar written; for the other two
+  it is an ordinary query.
+- `hybrid p50` is `hybrid_search` (lexical + vector fusion) on that backend —
+  the number a user's question actually pays.
+- The candidate cap is **lifted** (`--max-candidates 0`). This matters more
+  than it sounds: with the product default of 10 000, the exact scan on a
+  larger index silently becomes "the newest 10 000 rows", and recall@10 would
+  then be measured against a baseline that never looked at most of the corpus.
+  The first 50k run made exactly that mistake and scored HNSW at 0.18 — not
+  because it missed anything, but because the two backends had searched
+  different candidate sets. The `trunc` column now reports whether any query
+  hit a cap.
+
+Run it:
+
+```bash
+.venv/bin/python scripts/bench_vector_index.py                  # 10k vectors
+.venv/bin/python scripts/bench_vector_index.py --nodes 1000     # quick
+.venv/bin/python scripts/bench_vector_index.py --json           # machine-readable
+```
+
+### Measured, 2026-08-10 — 10 000 vectors, 30 queries, top_k 10
+
+macOS 27 (arm64, Apple Silicon), Python 3.14.5, SQLite 3.53.1,
+hnswlib 0.8.0, uncapped candidates, corpus build 2.19 s.
+
+| backend | p50 ms | p95 ms | first ms | peak MB | recall@10 | hybrid p50 ms |
+|-----------|-------:|-------:|---------:|--------:|----------:|--------------:|
+| brute     | 293.25 | 299.31 |   293.91 |   39.72 |    1.000  |        299.17 |
+| quantized | 640.58 | 650.15 |   636.87 |   38.38 |    0.987  |        653.33 |
+| hnsw      |   7.01 |   7.50 |   799.95 |    0.05 |    0.953  |         10.07 |
+
+What the table says, plainly:
+
+- **The default is exact and slow.** 293 ms per query at 10k, and hybrid
+  inherits nearly all of it (299 ms) — the vector channel *is* the cost.
+- **HNSW meets the 11.1.0 target and prices it.** Hybrid p50 **10.1 ms** at 10k
+  (target: < 50 ms), a 30x improvement, in exchange for **4.7% of the exact
+  top-10 going missing**. That is the trade, stated as a number rather than as
+  the word "approximate".
+- **The 800 ms first query is the graph build**, paid once per index generation
+  and then persisted to the `.hnsw` sidecar (and held in memory for the rest of
+  the process). Any write to `vector_embeddings` invalidates the fingerprint
+  and buys that cost again, which is why `brute` stays the default for a
+  continuously-ingesting brain.
+- **Quantized is currently the wrong choice on every axis.** ~2.2x the latency
+  for 0.987 recall, and its RAM advantage does not materialise (38.4 vs
+  39.7 MB): the exact scan already feeds the index in bounded batches, so
+  resident vectors were never the dominant term — the fetched SQLite rows are.
+  It ships as an honest, exhaustive backend and as the representation a held
+  cross-query index would need. It is not a recommendation.
+
+### Measured, 2026-08-10 — 50 000 vectors, 15 queries, top_k 10
+
+Same machine and settings; corpus build 11.19 s.
+
+| backend | p50 ms | p95 ms | first ms | peak MB | recall@10 | hybrid p50 ms |
+|-----------|--------:|--------:|---------:|--------:|----------:|--------------:|
+| brute     | 1515.31 | 1522.94 |  1520.89 |  194.92 |    1.000  |       1514.75 |
+| quantized | 3254.76 | 3275.69 |  3253.54 |  195.05 |    0.967  |       3441.13 |
+| hnsw      |   35.58 |   38.19 |  6114.60 |    0.04 |    0.987  |         43.90 |
+
+- **The exact scan is linear and unusable at this size**: 1.5 s per query, and
+  ~195 MB of Python allocation to score one question.
+- **HNSW still clears the 50 ms budget at 5x the target corpus** — hybrid p50
+  43.9 ms — and its recall here is 0.987, higher than the 10k run's 0.953
+  (15 queries is a small sample; treat the two as "around 0.95–0.99", not as a
+  trend).
+- **The remaining HNSW cost is not the search.** 7 ms at 10k → 36 ms at 50k is
+  suspiciously linear for a graph index, and it is: every query first runs the
+  freshness check (`SELECT COUNT(*), MAX(indexed_at) FROM vector_embeddings
+  WHERE embedding_model=? AND embedding_dim=?`), which has no covering index
+  and walks the table. A named follow-up, not a mystery: an index on
+  `(embedding_model, embedding_dim)` would remove it. The budget is met either
+  way, so it was not worth a schema change in this release.
+- **The 6.1 s first query is the 50k graph build.** It is paid once per index
+  generation, and the sidecar means a restart does not pay it again.
+
+### A measurement mistake worth keeping
+
+The first 50k run reported HNSW recall of **0.18** and was wrong. The default
+candidate cap (10 000) was still in force, so the "exact" baseline had scored
+only the newest 10 000 of 50 000 rows while HNSW searched all of them — the
+disagreement was the baseline's blind spot, not the ANN's error. The bench now
+lifts the cap by default and prints a `trunc` column. Recorded here because
+the failure mode is generic: *any* recall number measured against a truncated
+baseline is measuring the truncation.
+
+### Not measured
+
+- **100k+ vectors.** Nothing is claimed beyond the 50k run above.
+- **sqlite-vec ANN.** The optional `ann` extra was not installed, so
+  `vector_search_backend` reported `bruteforce-cosine` throughout. Its numbers
+  are unknown, not zero.
+- **A real embedding provider.** Everything here uses the deterministic hash
+  embedder. With a model- or network-backed embedder, query-embedding cost
+  moves into the foreground and these ratios change.
+- **Resident process memory.** See the tracemalloc caveat above: the HNSW graph
+  lives outside Python's allocator and is not in the `peak MB` column.
+
 ## Observations
 
 - Keyword `search()` / `context_for_query()` stay low-millisecond thanks to
   the FTS5 trigram index; they are not the scaling bottleneck.
 - `traverse(depth=2)` cost grows with edge fan-out (synthetic corpus creates
   dense shared-concept hubs); p95 is ~5 ms at 500 sources and ~16 ms at 5000.
-- `vector_search()` is a brute-force scan over every stored embedding
-  (O(index size) per query). It is the dominant cost at scale and the first
-  candidate for an ANN/pruning optimization if vector recall becomes a hot
-  path. The profiler caps vector queries at 10 for this reason.
+- `vector_search()` on the default backend is a brute-force scan over every
+  stored embedding (O(index size) per query). It is the dominant cost at scale
+  — which is what the 11.1.0 backend table above measures, and what
+  `LATTICEAI_VECTOR_INDEX=hnsw` addresses. `profile_kg.py` still caps vector
+  queries at 10 for this reason.
 - `rebuild_vector_index(full=True)` embeds documents and chunks with the hash
   embedder; with a real embedding provider expect this phase to be slower by
   the provider's per-call latency times the item count.

package/docs/TRUST_MODEL.md

@@ -1,6 +1,6 @@
 # Lattice AI Trust Model
 
-Current release: **10.10.0 — Quiet Station**.
+Current release: **11.1.0 — Product Intelligence**.
 
 Lattice AI is local-first, explicit about external communication, and honest
 when a capability is unavailable.

package/docs/WHY_LATTICE.md

@@ -1,6 +1,6 @@
 # Why Lattice AI Exists
 
-Current release: **10.10.0 — Quiet Station**.
+Current release: **11.1.0 — Product Intelligence**.
 
 **Lattice AI is a local-first Digital Brain that keeps your knowledge durable
 across any AI model.**

package/docs/kg-schema.md

@@ -1,6 +1,6 @@
 # Knowledge Graph Schema
 
-Current release: **10.10.0 — Quiet Station**.
+Current release: **11.1.0 — Product Intelligence**.
 
 명세 출처: `lattice_ai_full_spec.pptx` 슬라이드 20·21·22
 구현: `lattice_brain/graph/schema.py`