ltcai 10.10.0 → 11.0.1

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)
+![v11.0.1 Living Brain walkthrough](output/release/v11.0.1/gifs/v11.0.1-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/v11.0.1/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v11.0.1/screenshots/05-memory-graph.png) |
+| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v11.0.1/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v11.0.1/screenshots/12-review-center.png) |
+| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v11.0.1/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v11.0.1/screenshots/10-admin-console.png) |
+| **Watch a file become memory** — three named steps, not a pipeline diagram ![Material to memory](output/release/v11.0.1/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/v11.0.1/screenshots/08-system.png) |
 
 ## Why Lattice AI
 
@@ -58,52 +58,53 @@ 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/v11.0.1/screenshots/01-login.png) | ![Model install](output/release/v11.0.1/screenshots/03-install-load-progress.png) | ![Model library](output/release/v11.0.1/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/v11.0.1/SCREENSHOT_INDEX.md](output/release/v11.0.1/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 **11.0.1 — Both Branches**:
+
+11.0.0 put every line under test and documented, unfixed, the defects that
+work surfaced. 11.0.1 is the settling of that account: **all eleven
+documented defects are fixed, the code they proved dead is gone, and the CI
+floor now holds 100% of branch arcs as well as lines.**
+
+- **Every 11.0.0 finding is fixed.** The Telegram helper that sent the local
+  server's auth header to api.telegram.org, the unload-all that fabricated
+  success, the HTML inspector whose stylesheet collection could never fire,
+  the review-item id that collided within one second, the vLLM zombie that
+  read as "already running", the security dashboard's listing/detail
+  redaction gaps and invalid-JSON exports, the embedding `model_id` frozen at
+  the wrong dimension, the fast-path model-name mismatch, and the workspace
+  routes' dead literal and unreachable 404 arms. Each fix flipped the test
+  that had pinned the broken behaviour and gained a regression test.
+- **Branch coverage joined the floor.** `branch = true` is now in the
+  coverage config: both directions of all 9,828 conditionals execute under
+  the suite (5,798 tests, up from 5,426), and `fail_under = 100` fails CI on
+  a single missed arc. Exclusions stay honest: eight reasoned
+  `pragma: no cover` lines and two reasoned `pragma: no branch` lines.
+- **Dead code left the tree.** The unused auto-approved write-policy factory,
+  an unused snapshot-import normalizer, the workspace 404 arms shadowed by
+  the anti-enumeration 403, a provably-dead version guard, a provably-dead
+  MLX condition, and the vLLM silent-success recheck — each removal proved by
+  AST/reference scan before deletion.
+- **Verified where CI runs.** The full suite passes with the branch gate on
+  macOS 3.14, a fresh-resolve python 3.11 environment (fastapi 0.141), and a
+  clean linux python:3.14 container — the three environments that caught
+  11.0.0's release-day failures.
 
 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 11.0.1 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-11.0.1-py3-none-any.whl`
+- `dist/ltcai-11.0.1.tar.gz`
+- `ltcai-11.0.1.tgz`
+- `dist/ltcai-11.0.1.vsix`
+- `src-tauri/target/release/bundle/dmg/Lattice AI_11.0.1_aarch64.dmg`
 
 Do not use wildcard artifact uploads. Package registry publishing remains owner-run.
 
@@ -138,6 +139,8 @@ See [ARCHITECTURE.md](ARCHITECTURE.md) for details and
 
 | Version | Theme |
 | --- | --- |
+| 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 +4,46 @@ 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.
 
+## [11.0.1] - 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: **11.0.1 — Both Branches**.
 
 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: **11.0.1 — Both Branches**.
 
 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: **11.0.1 — Both Branches**.
 
 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 (v11.0.1)
 
 > **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`.
@@ -92,6 +91,78 @@ 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.
+- `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 2.12 s.
+
+| backend | p50 ms | p95 ms | first ms | peak MB | recall@10 | hybrid p50 ms |
+|-----------|-------:|-------:|---------:|--------:|----------:|--------------:|
+| brute     | 288.89 | 291.95 |   290.68 |   39.72 |    1.000  |        296.63 |
+| quantized | 639.47 | 645.93 |   653.31 |   38.38 |    0.987  |        639.83 |
+| hnsw      |  21.53 |  22.11 |   795.84 |    0.74 |    0.953  |         24.37 |
+
+What the table says, plainly:
+
+- **The default is exact and slow.** 289 ms per query at 10k, and hybrid
+  inherits nearly all of it (297 ms) — the vector channel *is* the cost.
+- **HNSW meets the 11.1.0 target and prices it.** Hybrid p50 **24.4 ms** at 10k
+  (target: < 50 ms), a 12x 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". Its 0.74 MB peak is the two-phase lookup: it reads
+  only the ten rows it returns, where the exact scan reads all 10 000.
+- **The 796 ms first query is the graph build**, paid once per index generation
+  and then persisted to the `.hnsw` sidecar. 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.
+
 ## Observations
 
 - Keyword `search()` / `context_for_query()` stay low-millisecond thanks to

package/docs/TRUST_MODEL.md

@@ -1,6 +1,6 @@
 # Lattice AI Trust Model
 
-Current release: **10.10.0 — Quiet Station**.
+Current release: **11.0.1 — Both Branches**.
 
 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: **11.0.1 — Both Branches**.
 
 **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: **11.0.1 — Both Branches**.
 
 명세 출처: `lattice_ai_full_spec.pptx` 슬라이드 20·21·22
 구현: `lattice_brain/graph/schema.py`