ltcai 11.7.0 → 11.9.0

package/README.md

@@ -11,23 +11,24 @@
 [![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)
 
-![v11.7.0 Living Brain walkthrough](output/release/v11.7.0/gifs/v11.7.0-living-brain-walkthrough.gif)
+![v11.9.0 Living Brain walkthrough](output/release/v11.9.0/gifs/v11.9.0-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
-memory. Nothing leaves your machine without explicit consent.
+graph on your computer. The default is local. Cloud is optional — an
+OAuth-authenticated CLI (`agy` / `grok`) or an API key you configure — and
+nothing leaves your machine without explicit consent.
 
-대화·파일·폴더·웹페이지가 전부 내 컴퓨터 안의 지식 그래프로 쌓이고, 어떤
-모델이든 그 기억을 이어받아 대화합니다.
+대화·파일·폴더·웹페이지가 전부 내 컴퓨터 안의 지식 그래프로 쌓입니다.
+기본은 로컬이고, 클라우드는 선택입니다 (OAuth CLI 지원).
 
 ## What You Can Do
 
 | | |
 | --- | --- |
-| **See your Brain's story in time** — a growth curve, an activity heatmap, and each day's story, rewindable to any past moment ![Brain Chronicle](output/release/v11.7.0/screenshots/13-chronicle.png) | **Chat with a Brain that remembers** — every conversation grows durable, source-linked memory ![Brain Chat](output/release/v11.7.0/screenshots/04-brain-chat-home.png) |
-| **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v11.7.0/screenshots/05-memory-graph.png) | **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v11.7.0/screenshots/06-capture.png) |
-| **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v11.7.0/screenshots/12-review-center.png) | **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v11.7.0/screenshots/02-recommended-models.png) |
-| **Watch a file become memory** — three named steps, not a pipeline diagram ![Material to memory](output/release/v11.7.0/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/v11.7.0/screenshots/08-system.png) |
+| **See your Brain's story in time** — a growth curve, an activity heatmap, and each day's story, rewindable to any past moment ![Brain Chronicle](output/release/v11.9.0/screenshots/13-chronicle.png) | **Chat with a Brain that remembers** — every conversation grows durable, source-linked memory ![Brain Chat](output/release/v11.9.0/screenshots/04-brain-chat-home.png) |
+| **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v11.9.0/screenshots/05-memory-graph.png) | **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v11.9.0/screenshots/06-capture.png) |
+| **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v11.9.0/screenshots/12-review-center.png) | **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v11.9.0/screenshots/02-recommended-models.png) |
+| **Watch a file become memory** — three named steps, not a pipeline diagram ![Material to memory](output/release/v11.9.0/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/v11.9.0/screenshots/08-system.png) |
 
 ## Why Lattice AI
 
@@ -58,67 +59,49 @@ First-run flow — wake the Brain, pick the owner, load a recommended model:
 
 | | | |
 | --- | --- | --- |
-| ![Login](output/release/v11.7.0/screenshots/01-login.png) | ![Model install](output/release/v11.7.0/screenshots/03-install-load-progress.png) | ![Model library](output/release/v11.7.0/screenshots/07-model-library.png) |
+| ![Login](output/release/v11.9.0/screenshots/01-login.png) | ![Model install](output/release/v11.9.0/screenshots/03-install-load-progress.png) | ![Model library](output/release/v11.9.0/screenshots/07-model-library.png) |
 
 Screenshot index and capture notes:
-[output/release/v11.7.0/SCREENSHOT_INDEX.md](output/release/v11.7.0/SCREENSHOT_INDEX.md)
+[output/release/v11.9.0/SCREENSHOT_INDEX.md](output/release/v11.9.0/SCREENSHOT_INDEX.md)
 
 ## Current Release
 
-The current release is **11.7.0 — Clean Sweep**:
+The current release is **11.9.0 — Working Order**:
 
-11.6.0 left a disclosed backlog and a visual language that still used
-glass. This release closes that backlog, fixes regressions One Door did
-not know it had shipped, and restyles every captured surface on an
-elevation ladder — ink night, paper day, no glass. The door is unchanged:
+11.8.0 took weight off the door. This release puts the remaining Current
+stubs and the half-wired lanes in working order. The door is unchanged:
 `lattice-host` still serves **420 operations across 41 route families**,
-and the Python package is still a **28-route AI worker** (LLM, embed,
-extract, parse, four renderers, ASR, multimodal, catalog, `sysinfo`,
-`/health`). The allowlist still includes `/worker/parse` and
-`/worker/render/*`; nothing product-shaped moved back into Python.
-
-- **The three oracle bugs 11.6.0 ported as-is are fixed.** Command-search
-  knowledge now reads `matches` and returns nodes. Review snooze accepts
-  offset-aware datetimes (unparseable `until` → 422). Double-reject is
-  409, byte-identical to its dismiss sibling. Fixture bodies that pinned
-  the old faults were updated and marked as divergences from the oracle.
-- **The §5.3 holes are closed.** Binary uploads go through `/worker/parse`.
-  Per-chunk supplied vectors land at the four ingest doors. User hooks
-  fire on native tools (`HooksStore` → `HookSink`) and write the same run
-  log the HTTP route writes. `sanitize_write_content` runs on the loop
-  path and on `POST /tools/write_file`. Every mutating review route records
-  `review_item_created` / `review_item_updated`. `workspace_os.json` has
-  one writer (`WorkspaceOsStore` + registry + ports).
-- **Regressions One Door did not know it had.** Self-Model writes were
-  100% dead (five routes posted into the retired `/worker/graph/mutate`;
-  `resolve_contradiction` claimed "applied" while writing nothing) —
-  restored natively, nine recorded bodies byte-identical. The security
-  xlsx export 502'd because it posted to a product route; it now uses
-  `/worker/render/xlsx`. Chat `ingest_generated` was a schema 400 even
-  against a live 11.5.2 worker. Vault-watch had fixtures and no poller —
-  it is a real native ingest loop now. A decoy-proven static gate keeps
-  this class from shipping again.
-- **Time bombs defused.** Chronicle `@today`, briefing freshness, and the
-  insights/garden/proactive/health/quality cutoffs now take a frozen
-  clock. Falsifier tests fail on the next run if a fuse is re-armed.
-- **The UI is one language.** Token-native elevation and gradients replace
-  backdrop-filter. Cytoscape reads theme tokens (comma-form `hsl()`).
-  Layout and a11y contracts stay; the first-paint bundle is still ~103 KiB
-  gzip.
-
-What this release still carries openly — `open_keys` pending-only, no
-extraction refiner, `delete_node` leaving `PART_OF`, review events silent
-without an owner, text-only KG-api ingest, two store cycles per review
-mutation, raw-English snooze 422 — is listed in
-[RELEASE_NOTES_v11.7.0.md](RELEASE_NOTES_v11.7.0.md).
-
-Expected artifacts for 11.7.0 release must use exact filenames:
-
-- `dist/ltcai-11.7.0-py3-none-any.whl`
-- `dist/ltcai-11.7.0.tar.gz`
-- `ltcai-11.7.0.tgz`
-- `dist/ltcai-11.7.0.vsix`
-- `src-tauri/target/release/bundle/dmg/Lattice AI_11.7.0_aarch64.dmg`
+and the AI worker is still **19 routes** (`/worker/sysinfo` gained
+additive `capabilities` and `python_version`). Cloud is optional; the
+default is local; OAuth CLI (`agy` / `grok`) is supported.
+
+- **Thirteen documented-Current stubs now answer.** Model
+  recommendations probe RAM and the worker catalog. Setup scan/auto are
+  real probes; install is real-or-manual (brew/pip stay manual).
+  Computer-use status reads worker capabilities. `/agent/eval` is a
+  deterministic skill eval. `/agents/api/run` is a live single-agent
+  pass. Automation mines `conversation_messages`. Workflow run is a
+  per-step executor; `build`/`deploy_project` run governed scripts.
+- **Hybrid cloud is wired.** ReviewSink and a shape-only egress audit
+  are bound in production. Dual credentials: `api_key` (mock-verified
+  only) and `cli_oauth` (live OAuth E2E at zero billing). Escalation is
+  `auto` / `manual` / `always`; `local_only` on the request always wins.
+- **MCP is a real JSON-RPC server** at `POST /mcp`. Chat file generation
+  — the v9.2.0 headline deleted in the 11.6.0 port — is restored. The
+  8GB-tier default (gemma-4-e2b) actually runs.
+
+What this release does not close — 2B agent-run quality, the mock-only
+`api_key` path, restore needing a restart, brew/pip staying manual,
+`/mcp` outside the OpenAPI contract, the ad-hoc-signed dmg — is listed
+in [RELEASE_NOTES_v11.9.0.md](RELEASE_NOTES_v11.9.0.md).
+
+Expected artifacts for 11.9.0 release must use exact filenames:
+
+- `dist/ltcai-11.9.0-py3-none-any.whl`
+- `dist/ltcai-11.9.0.tar.gz`
+- `ltcai-11.9.0.tgz`
+- `dist/ltcai-11.9.0.vsix`
+- `src-tauri/target/release/bundle/dmg/Lattice AI_11.9.0_aarch64.dmg`
 
 Do not use wildcard artifact uploads. Package registry publishing remains owner-run.
 
@@ -131,21 +114,24 @@ every product route, owns every write to the Brain, and supervises a Python
 **AI worker** it reaches over loopback for the things a model does — inference,
 embedding, extraction, parsing, rendering, speech-to-text. The React/Vite
 frontend and the Tauri desktop shell sit on top of that one door. Local-first
-by default — cloud model calls, downloads, Brain Network, and update checks are
-opt-in.
+by default — cloud is optional (OAuth CLI or an API key you configure),
+and downloads, Brain Network, and update checks are opt-in.
 
 See [ARCHITECTURE.md](ARCHITECTURE.md) for details and
 [docs/DEVELOPMENT.md](docs/DEVELOPMENT.md) for the developer workflow
-(`npm install && npm run dev`, validation via `npm run lint`,
-`npm run test:unit`, `npm run test:visual`).
+(`npm start` / `bin/ltcai.js` is the product; `npm run dev` is the
+19-route worker). Validation via `npm run lint`, `npm run test:unit`,
+`npm run test:visual`.
 
 ## Known Limitations
 
 - External package registries are owner-published and can lag behind GitHub.
 - SQLite is the live local Brain store. The optional PostgreSQL/pgvector
-  migration tooling is not part of the 11.6.0 worker.
+  migration tooling is not part of the 11.9.0 worker.
 - Docker, model downloads, cloud model calls, Brain Network, and update checks
-  require explicit user action.
+  require explicit user action. Cloud is optional: `cli_oauth` (`agy` /
+  `grok`) was live-checked at zero billing; the `api_key` path is
+  mock-verified only.
 - **The Telegram bridge was removed in 11.6.0** — it lived in the platform code
   that became the AI worker. **SSO/OIDC login and callback flows were removed
   with it**; the configuration surface remains and password login is native.
@@ -157,11 +143,26 @@ See [ARCHITECTURE.md](ARCHITECTURE.md) for details and
   required dependency as of 11.6.0 (it used to be an undeclared lazy import
   that raised a 500; `ltcai[pdf]` remains as an empty alias for older
   install instructions).
+- The multimodal image and video analysis functions have no HTTP door as of
+  11.8.0: their only route wrapped a native image ingest that was never
+  built. The observation code stays in Brain Core under unit test, and its
+  module header says so.
+- The Python coverage gate is a **line floor of 90** since 11.8.0 (the
+  100%-lines-and-branches gate was removed). 11.9.0 measures 99.97%; the
+  enforced floor is the smaller claim.
+- **2B agent-run quality is gated honestly.** gemma-4-e2b writes the
+  requested file and can still fail the critic on the summary.
+- Restore in a long-lived process may serve pre-restore bytes until
+  connections recycle — restart after restore. brew/pip setup items stay
+  manual. `/mcp` is a real JSON-RPC server and is outside the OpenAPI
+  contract by design.
+- The macOS dmg is ad-hoc signed — effectively unsigned — so first launch
+  needs the usual Gatekeeper step.
 - Pointer-control tools still execute in the worker. Remaining honest gaps
   (`open_keys` pending-only, no Self-Model refiner, `PART_OF` left on
   delete, review events silent without an owner, KG-api ingest text-only,
   two store cycles per review mutation) are listed with their reasons in
-  [RELEASE_NOTES_v11.7.0.md](RELEASE_NOTES_v11.7.0.md).
+  [RELEASE_NOTES_v11.9.0.md](RELEASE_NOTES_v11.9.0.md).
 
 ## Release History
 
@@ -172,6 +173,8 @@ same boundary. Earlier notes stay in the tree as `RELEASE_NOTES_v*.md` files.
 
 | Version | Theme |
 | --- | --- |
+| 11.9.0 | Working Order |
+| 11.8.0 | Travel Light |
 | 11.7.0 | Clean Sweep |
 | 11.6.0 | One Door |
 | 11.5.2 | Tight Ship |

package/docs/BENCHMARKS.md

@@ -1,8 +1,15 @@
 # Model Robustness Benchmarks
 
 > Status: reference 2026-07-21
-
-Methodology and results for `scripts/bench_models.py`, a harness that measures
+>
+> **Dated snapshot.** The harness this page documents no longer exists in the
+> tree: `scripts/bench_models.py` went with the Python agent loop when 11.5.1
+> ported it to Rust, and `latticeai.core.agent_eval` / `scripts/agent_eval.py`
+> followed (the last of them deleted in 11.8.0). The methodology and the
+> honesty notes below are kept as the record of how these numbers were produced
+> and what they did and did not mean — not as instructions you can run today.
+
+Methodology and results for `scripts/bench_models.py`, a harness that measured
 how well the agent loop turns model output into executable actions across model
 quality tiers. Companion to [CI & Release Gates](CI_AND_RELEASE_GATES.md).
 

package/docs/CHANGELOG.md

@@ -4,6 +4,163 @@ 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.
 
+## [11.9.0] - 2026-08-17 — Working Order
+
+### Added
+- 이중 클라우드 자격증명: `<data_dir>/cloud_provider.json` →
+  `LATTICEAI_CLOUD_API_KEY` → CLI 자동감지(`agy` / `grok`). `api_key`는
+  OpenAI 호환 어댑터(모의 서버만 검증, 실과금 없음). `cli_oauth`는 로컬
+  OAuth CLI(`agy` → gemini-3.7-flash, `grok` → grok-4.6). 중립 temp cwd,
+  120초 타임아웃.
+- `GET /api/cloud/status` — `{configured, mode, provider, model, detail}`.
+- 하이브리드 에스컬레이션 `always` / `auto`(기본) / `manual`
+  (`hybrid_policy.json`). `auto`는 로컬 모델 없음 / 로컬 컨텍스트가 얇음
+  / 명시적 `/cloud `·`클라우드:` 접두사일 때만. 요청
+  `network_mode:"local_only"`가 항상 이김.
+- 호스트가 Review Center + egress 감사 싱크를 바인딩. 클라우드 턴이
+  `kg_cloud_expansion` 제안을 올리고 형태만 있는 egress 레코드를 남김
+  (provider / model / reason, 내용 없음).
+- `POST /mcp` streamable-HTTP JSON-RPC 실서버(`initialize` /
+  `tools/list` / `tools/call`). 큐레이트된 안전 도구 + 스키마가 파싱된
+  스킬 7개. `/mcp/call`이 실제로 디스패치. `/mcp/install`은 정직
+  (스킬/플러그인 활성화, 원격은 수동).
+- SPA 클라우드 투명성: ☁️ 클라우드 답변 칩, 컴포저 경계 힌트, 「이번
+  대화는 로컬만」 토글, System 패널 provider 상태 행.
+- 채팅 파일 생성 복원(v9.2.0 헤드라인, 11.6.0 포트에서 삭제됨). 확장자별
+  앵커 프롬프트, judge + 1회 교정, 정직한 sanitize 배지, 프로젝트는
+  최대 3파일 순차, 워커 렌더 시임의 실제 docx/pdf.
+- `/worker/sysinfo`에 `capabilities`(pointer_tools)와 `python_version`
+  (가산, 라우트 수는 19 유지).
+- 통합 로컬 승인 토큰(`LocalApprovals`) — `/permissions/approve`에서
+  상환.
+
+### Changed
+- 문서에만 있던 13개 Current 스텁이 실동작: `/models/recommendations`,
+  `/setup/scan`+`auto`, `/setup/install`, computer-use 상태,
+  `/agent/eval`, `/agents/api/run`, 자동화 패턴/제안, 워크플로 run·
+  resume, 리뷰 `run_now`, `build`/`deploy_project`, 백업 blob.
+- 클라우드 모델은 provider 설정에서 오고, 로컬 MLX id를 쓰지 않음.
+  로컬 모델이 없어도 클라우드 턴이 가능.
+- 하이브리드 토큰 프레임은 도착하는 대로 스트림. `stream: false`는
+  JSON.
+- 채팅 쓰기의 스코프가 비면 `workspace_id = personal`. null workspace
+  읽기는 personal 가시성.
+- 2B(gemma-4-e2b-it-4bit) compact 프로파일: 태그 스트립·balanced·
+  truncated_close·labeled·fence_rescue 파서, v10.8.0 salvage 삼종
+  복원, COMPACT 컨텍스트 <2k, EXECUTE 온도 고정(compact 0.1 /
+  standard 0.2). MLX가 temperature + stop string을 존중.
+- 백업 = `VACUUM INTO` 스냅샷 + blob + 정직한 매니페스트 + 원자적 복원.
+  export가 edges/chunks를 실음.
+- `POST /agent`가 네이티브 루프에 닿고 제품 정책 표를 실음.
+
+### Fixed
+- 라이브 감사 N1–N9: 에이전트 루프 호스트 바인딩, 빈 Brain 메모리
+  API 500(`conversation_messages` 부트스트랩), chat/memory/chronicle/
+  command가 지식을 봄, brain health의 빈 100점, 백업/복원 정직성,
+  export의 없는 컬럼 조회, 폴더 ingest 승인, 보이스 메모 텍스트 저장.
+- 워크플로 resume 승인 게이트. `write_file`이 비어 있는 content를
+  교정 에러로 거절. critic 판정 복구(verdict-shape + 보수적 토큰,
+  fail-closed 유지).
+- 이전에 고장 나 있던 22항목을 신선한 Brain·실모델로 재검증.
+
+### Known issues
+- 2B 에이전트 루프의 *내용 품질*은 정직하게 게이트된다. gemma-4-e2b는
+  요청한 파일을 기계적으로 쓰지만(마감 테이프 5/5) 요약이 critic에서
+  떨어져 FAILED/NEEDS_REVIEW로 끝날 수 있다. 퍼널은 에이전트 런에 더
+  큰 모델을 권한다.
+- `api_key` 클라우드 경로는 모의 서버만 검증했다. 계약 테스트는 있고
+  실호출은 없다(과금 예산 없음).
+- 오래 떠 있는 프로세스에서 복원하면 커넥션이 재활용되기 전까지
+  복원 전 바이트를 줄 수 있다 — 재시작이 필요하다.
+- brew/pip 셋업 항목은 설계상 수동이다.
+- `/mcp`는 설계상 OpenAPI 제품 계약 밖이다.
+- DMG는 ad-hoc 서명(미서명)이다.
+- 11.8.0이 열어 둔 항목(커버리지 바닥 라인 90, 멀티모달 이미지/비디오
+  HTTP 문 없음, 11.7.0 leftover)은 그대로다. 전문은
+  [RELEASE_NOTES_v11.9.0.md](../RELEASE_NOTES_v11.9.0.md).
+
+## [11.8.0] - 2026-08-16 — Travel Light
+
+### Added
+- 골든 드리프트 가드: 축소된 agent 대표행 세트가 커널의 새 판정 클래스를
+  덮지 않으면 실패. 축소가 조용한 커버리지 손실이 되지 않게 하는 장치.
+- 삭제된 아홉 워커 라우트에 대한 네거티브 테스트 — 게이트웨이가 더 이상
+  전달하지 않음을 Rust KEEP 표와 allowlist 양쪽에서 고정.
+- `rust/fixtures/chunking/FROZEN.md`. 이제 모든 픽스처 계열이 FROZEN.md를
+  가짐.
+- `PhaseBudgets` 토큰 상한(MIN 128 / MAX 8192). 이전에는 하한만 있었음.
+- 모든 GitHub Actions 워크플로에 `concurrency` 그룹과 `timeout-minutes`.
+- Brain Chat Home 재설계: 히어로 컴포저, 3배 커진 LivingBrain(1440에서
+  60px → 179px)과 금빛/옥빛 성장 링, 준비도에 묶인 '기억이 자라고 있어요'
+  캡션, 풀캔버스 그리드, 바닥 연속성 바(지난 대화·현황·기억 지도·기능),
+  `prefers-reduced-motion` 폴백.
+
+### Changed
+- 워커 표면 **28 → 19 라우트**. `rust/fixtures/worker_allowlist.json`도 19.
+- 로컬 lint 체인 **13 → 10 게이트**. 순서와 남은 열 개는 그대로.
+- Python 커버리지 게이트가 `fail_under = 100`(문+분기) → **라인 90**.
+  분기 측정은 꺼짐. 실측은 이번 릴리스에서도 100%.
+- `ci.yml` 중복 스텝 제거 — 4레그 매트릭스는 유지하되 OpenAPI ·
+  product-readiness · 확장 테스트는 3.11+ubuntu 레그에서만, 커버리지 레그는
+  `pytest tests/`를 두 번 돌리지 않음. `release.yml`은 릴리스 스텝만.
+  dependency-audit은 cron 전용, visual은 push+nightly(PR 제외),
+  e2e-sidecar는 nightly 전용.
+- Rust: `lattice-{platform,retrieval,ingest,jobs}`의 약 191개 파일 blanket
+  `#![allow]` 헤더 제거, 약 650건의 clippy/rustc 진단을 원인에서 수정.
+  워크스페이스 수준 허용 0건 추가, 남긴 억제는 이유가 붙은 지역
+  `#[allow(clippy::too_many_arguments)]` 8개.
+- 통합 테스트 파일(= 링크되는 테스트 바이너리) **98 → 56**
+  (lattice-platform 43 → 11). 테스트 함수 삭제 없이 주제별 통합.
+- `ROLE_CAPABILITIES`가 `lattice-auth` 단일 출처. `lattice-agent`가 의존.
+- agent 골든 `decisions__strict` · `calls`가 702 → **171 대표행**
+  (등가류당 한 행).
+- product-readiness 증거를 Rust 픽스처로 재지정. 판정은 COMPLETE 10/10.
+
+### Fixed
+- `SessionStore`가 조회 미스 시 `sessions.json`을 다시 읽음. v11.6.0부터
+  writer는 `lattice-auth`인데 워커는 `__init__`에서 한 번만 읽어, **워커
+  기동 이후의 로그인이 워커에게 보이지 않았음** —
+  `trusted_local_owner`에서는 조용히, `LATTICEAI_REQUIRE_AUTH=true`에서는
+  파일 안에 있는 토큰에 대해 401. `mtime_ns`/`size` 가드 + 1초 throttle을
+  같은 락 아래에서 적용해 추측 버스트가 읽기 버스트가 되지 않게 함.
+  테스트 9개 추가.
+
+### Removed
+- 호출자 0인 워커 라우트 아홉 개: `GET /api/embeddings/providers`,
+  `POST /tools/read_document`, `GET /tools/pdf_pages`,
+  `POST /worker/multimodal/describe`, `GET /api/ingestion/multimodal`,
+  `POST /models/switch/{model_id}`, `DELETE /models/unload-all`,
+  `POST /engines/pull-model`, `GET /api/capture/voice/status`. 파일로는
+  `latticeai/api/{tools,local_files,voice_capture}.py`와
+  `lattice_brain/ingestion/pipeline.py`. `pypdfium2` 의존성도 함께.
+- `latticeai/core/agent_permission.py`; 죽은 보안 헬퍼(`hash_password` /
+  `verify_password`, `check_ip_rate_limit`, `configure_trusted_proxies`,
+  `client_ip`, `bytes_match_extension`); `_kg_common/text.py`의 죽은 청커와
+  호출자 0 함수 9개; 렌더 시임의 `_safe_filename` 이중 살균.
+- 얼어붙은 픽스처의 생성기 2종(`generate_agent_parity_fixtures.py`,
+  `generate_chunking_parity_fixtures.py`),
+  `scripts/{brain_quality_eval,agent_eval,check_python,bench_agent_smoke}.py`,
+  `scripts/check_legacy_debt.mjs`(드리프트한 거울 — 파이썬 테스트가 권위).
+- `.github/workflows/agent-smoke.yml` — 모델 없는 러너에서 이중 fail-open.
+- Rust 죽은 코드: `workspace_scope` 모듈, `WORKSPACE_OS_VERSION` 상수,
+  호출자 0 항목 16개.
+- agent 골든 `decisions__trusted` · `decisions__bypass` 그리드(각 702행) —
+  모든 판정 클래스를 덮는 이름 붙은 단위 테스트로 대체.
+- 죽은 프론트 컴포넌트 `FeedbackState.tsx`, `DepthEmergence.tsx`.
+
+### Known issues
+- 커버리지 **강제 바닥이 100 → 90(라인)** 으로 내려갔고 분기 게이트가
+  없어졌습니다. 실측은 100%지만 게이트가 지키는 것은 바닥입니다.
+- `lattice_brain` 멀티모달의 이미지/비디오 절반에 HTTP 문이 없습니다
+  (관찰 함수는 Brain Core에 남아 단위 테스트를 받고, 모듈 헤더에 명시).
+- DMG는 ad-hoc 서명(미서명)입니다.
+- 삭제된 라우트의 메시지 카탈로그 키는 얼어붙은 패리티 픽스처에 의도적으로
+  남습니다 — 픽스처는 녹화 당시의 표면을 고정하는 기록입니다.
+- `tests/visual/mock_server`가 고아 mock 라우트 하나를 아직 서빙합니다
+  (현재 증거가 해시로 묶여 있어 다음 캡처 사이클에 정리).
+- 11.7.0이 열어 둔 항목은 그대로입니다. 전문은
+  [RELEASE_NOTES_v11.8.0.md](../RELEASE_NOTES_v11.8.0.md).
+
 ## [11.7.0] - 2026-08-15 — Clean Sweep
 
 ### Added

package/docs/CI_AND_RELEASE_GATES.md

@@ -1,6 +1,6 @@
 # CI & Release Gates
 
-> Status: reference 2026-07-21
+> Status: reference 2026-08-16
 
 Reference for the GitHub Actions workflows that guard `main` and releases, the
 supply-chain hardening applied to them, and the recommended branch-protection
@@ -11,13 +11,79 @@ configuration. Companion to [SECURITY_AUDIT.md](SECURITY_AUDIT.md) and
 
 | Workflow | File | Triggers | Purpose |
 |----------|------|----------|---------|
-| CI | `.github/workflows/ci.yml` | push/PR to `main` | Lint, typecheck, unit + integration tests, brain/agent eval gates, build + wheel smoke |
-| Release | `.github/workflows/release.yml` | tags `v*` / `[0-9]*` | Build & validate all artifacts (no publish) |
-| Visual Smoke | `.github/workflows/visual.yml` | push/PR, nightly cron, dispatch | Playwright visual smoke |
-| **Dependency Audit** | `.github/workflows/dependency-audit.yml` | push/PR, weekly cron, dispatch | pip-audit + npm audit + CycloneDX SBOMs |
-| **Postgres Integration** | `.github/workflows/postgres-integration.yml` | weekly cron, dispatch | Live SQLite→Postgres/pgvector migration test |
+| CI | `.github/workflows/ci.yml` | push/PR to `main` | Lint, typecheck, unit + coverage + integration tests, product-readiness, build + wheel smoke, Rust workspace |
+| Release | `.github/workflows/release.yml` | tags `v*` / `[0-9]*` | Build & validate artifacts (no publish; does not re-run CI lint/tests) |
+| Visual Smoke | `.github/workflows/visual.yml` | push to `main`, nightly cron, dispatch | Playwright visual smoke (not on PRs) |
+| Sidecar E2E | `.github/workflows/e2e-sidecar.yml` | nightly cron, dispatch | Live sidecar Playwright first-value loop |
+| Dependency Audit | `.github/workflows/dependency-audit.yml` | weekly cron, dispatch | pip-audit + npm audit + CycloneDX SBOMs |
+| Postgres Integration | `.github/workflows/postgres-integration.yml` | weekly cron, dispatch | Live SQLite→Postgres/pgvector migration test |
 
-The last two were added for the P2 deployment-trust / supply-chain workstream.
+There is no `agent-smoke.yml`. Hosted runners have no MLX models; a fail-open
+weekly smoke cannot report anything actionable.
+
+Every workflow sets `concurrency.group` to `<workflow-file-stem>-${{ github.ref }}`
+and cancels in-progress runs except on `main` (`cancel-in-progress: false` on
+`release.yml`, which runs on tags). Job timeouts: test 40, integration 25,
+build 20, rust 40, visual 15, sidecar 20, audit 15, release build 40,
+postgres 20.
+
+## CI matrix (`ci.yml`)
+
+Four legs. Job names are `Test (Python <ver> on <os>)`:
+
+| Leg | OpenAPI generate + upload | Full lint + typecheck + docs | Extension tests | Vitest | `pytest tests/unit/` | Coverage pytest (`tests/` + `--cov`) | Product readiness |
+|-----|---------------------------|------------------------------|-----------------|--------|----------------------|--------------------------------------|-------------------|
+| 3.11 + ubuntu-latest | yes | yes (`npm run lint`, `typecheck`, `docs:check-current`, `docs:check-links`) | yes (`test:browser-extension` && `test:vscode-extension`) | yes | yes | no | yes |
+| 3.12 + ubuntu-latest | no | Python only (`lint:python`) | no | yes | yes | no | no |
+| 3.14 + ubuntu-latest | no | Python only | no | yes | **no** (coverage invocation is the only pytest) | yes, line floor ≥90 | no |
+| 3.11 + macos-latest | no | Python only | no | yes | yes | no | no |
+
+Downstream jobs (after `test`): `Integration smoke test` (25 min), then
+`Build package` (20 min). `Rust workspace` is independent (40 min).
+
+Removed from CI **and deleted from the tree** in 11.8.0 — a script that is not
+a gate is a script that looks like one:
+
+- `scripts/check_python.py` — ruff parses every file on every test leg
+- `scripts/brain_quality_eval.py`
+- `scripts/agent_eval.py`
+- `scripts/bench_agent_smoke.py`
+
+## Local lint chain (`npm run lint`)
+
+Ten members, in order:
+
+1. `lint:python` (ruff + mypy)
+2. `lint:visual`
+3. `lint:frontend`
+4. `frontend:openapi:check`
+5. `scripts/check_i18n_literals.mjs`
+6. `check:i18n-namespaces`
+7. `check:bundle`
+8. `check:server-i18n`
+9. `scripts/check_release_evidence_bound.mjs`
+10. `check:max-file-lines`
+
+Not in the lint chain (CI calls the extension tests directly on the 3.11+ubuntu
+leg; the Python legacy-shim test is authoritative):
+
+- `test:browser-extension` / `test:vscode-extension` (script entries remain)
+- `check:legacy-debt` (script entry and `scripts/check_legacy_debt.mjs` both
+  removed — the mjs mirror had drifted from the Python test)
+- `check:python` (script entry and `scripts/check_python.py` both removed)
+
+`npm run typecheck` is frontend-only (`typecheck:frontend`). The VS Code
+extension is built by `test:vscode-extension` in CI and by `build_vsix.mjs`
+at release.
+
+## Coverage floor
+
+Python: `[tool.coverage.report] fail_under = 90` (line coverage). Branch
+measurement is off (`branch` is not set under `[tool.coverage.run]`). The
+coverage step runs only on 3.14 + ubuntu-latest.
+
+Frontend: `vitest.config.ts` still pins 100% thresholds on all four metrics;
+that is unchanged and still runs on every CI test leg.
 
 ## Supply-chain hardening: pinned actions
 
@@ -36,30 +102,22 @@ from the authoritative upstream refs via `git ls-remote --tags` on 2026-07-21.
 | actions/upload-artifact | v4.6.2 | `ea165f8d65b6e75b540449e92b4886f43607fa02` |
 
 Pinning coverage: **100% of current `uses:` entries** across `ci.yml`,
-`release.yml`, `visual.yml`, `dependency-audit.yml`, and
-`postgres-integration.yml`. All are first-party `actions/*`. If a third-party
-action is added later, resolve and pin its SHA the same way before merge.
+`release.yml`, `visual.yml`, `e2e-sidecar.yml`, `dependency-audit.yml`, and
+`postgres-integration.yml`. First-party `actions/*` plus pinned
+`Swatinem/rust-cache` and `dtolnay/rust-toolchain` on the Rust/integration
+legs. If a third-party action is added later, resolve and pin its SHA the same
+way before merge.
 
-## Dependency-audit gate posture (conservative)
+## Dependency-audit gate posture
 
-The audit workflow is intentionally **non-blocking on day-to-day PRs** and
-**strict on the scheduled/dispatch run**:
-
-- `push` / `pull_request`: `pip-audit` and `npm audit` run with
-  `continue-on-error` keyed on the event name, so a newly-disclosed CVE in a
-  transitive dependency never reddens an unrelated PR. Findings still appear in
-  the job summary and uploaded report artifacts.
-- `schedule` (weekly) / `workflow_dispatch`: the same steps run **strict** —
-  `pip-audit --strict` fails on any known vuln; `npm audit --audit-level=high`
-  fails on high/critical. This is the loud channel for triage.
+The audit workflow is **schedule + dispatch only** (not on push/PR). Both
+`pip-audit --strict` and `npm audit --audit-level=high` fail the job on
+findings. This is the loud channel for triage; a newly-disclosed CVE cannot
+redden an unrelated change.
 
 CycloneDX SBOMs (`sbom-python.json`, `sbom-npm.json`) are produced every run and
 uploaded as artifacts. Regenerate locally with `scripts/generate_sbom.py`.
 
-**To promote to a required blocking PR check:** remove the `continue-on-error`
-expressions in `dependency-audit.yml` and add `python-audit` / `npm-audit` to
-the required-checks list below.
-
 ## Postgres integration gate
 
 `postgres-integration.yml` runs the migration-integrity suite
@@ -70,31 +128,58 @@ the workflow sets that variable, and the test itself starts and tears down a
 GitHub-hosted `ubuntu-latest`). It is deliberately kept off the PR path (slow,
 image pull, needs Docker) and runs weekly + on demand.
 
+## Visual smoke and sidecar E2E
+
+This repository typically commits straight to `main`.
+
+- `visual.yml` runs on push to `main`, the nightly cron, and dispatch. It does
+  **not** run on pull requests.
+- `e2e-sidecar.yml` is nightly + dispatch only (no push, no PR).
+
 ## Recommended branch protection for `main`
 
-Required status checks (blocking):
+Required status checks (blocking). Names match the job `name:` fields:
+
+- `Test (Python 3.11 on ubuntu-latest)`
+- `Test (Python 3.12 on ubuntu-latest)`
+- `Test (Python 3.14 on ubuntu-latest)`
+- `Test (Python 3.11 on macos-latest)`
+- `Integration smoke test`
+- `Build package`
+- `Rust workspace`
 
-- `CI / Test (Python 3.11)`
-- `CI / Test (Python 3.12)`
-- `CI / Integration smoke test`
-- `CI / Build package`
-- `Visual Smoke / Playwright visual smoke`
+`Playwright visual smoke` is **not** a PR-blocking check: `visual.yml` no
+longer has a `pull_request` trigger. It still runs on every push to `main`.
 
-Advisory / non-blocking today (promote when the team is ready):
+Advisory / non-blocking (schedule + dispatch only):
 
-- `Dependency Audit / Python dependency audit (pip-audit)`
-- `Dependency Audit / npm dependency audit`
+- `Python dependency audit (pip-audit)`
+- `npm dependency audit`
 
-Additional recommended settings: require PRs before merge, require branches to
-be up to date, require linear history, and dismiss stale approvals on new
-commits.
+Additional recommended settings if pull requests are used: require PRs before
+merge, require branches to be up to date, require linear history, and dismiss
+stale approvals on new commits.
 
 ## Release gate (publication safety)
 
-`release.yml` builds and validates artifacts only — it never publishes. Package
-publication (PyPI / npm / VS Code Marketplace / Open VSX) is a manual step
-(`npm run publish:*`) using **exact version filenames**, never a `dist/*` glob,
-so pushing a tag can never publish by accident. See
+`release.yml` builds and validates artifacts only — it never publishes. A tag
+is only pushed on a commit that already passed CI, so the workflow does **not**
+re-run `npm run lint`, `npm run typecheck`, `docs:check-links`, frontend tests,
+or `pytest tests/unit/`.
+
+It still runs:
+
+- checkout / setup / installs
+- `npm run docs:check-current` (release-specific current-version docs gate)
+- `npm run build:assets`
+- `python scripts/product_readiness.py` (safety net)
+- `python -m build`, `wheel_smoke.py`, `twine check`
+- `npm pack`, vsce package
+- `validate_release_artifacts.py <v> --require-vsix --require-tgz`
+
+Package publication (PyPI / npm / VS Code Marketplace / Open VSX) is a manual
+step (`npm run publish:*`) using **exact version filenames**, never a `dist/*`
+glob, so pushing a tag can never publish by accident. See
 [../RELEASE.md](../RELEASE.md) for the full procedure.
 
 ## Limitations (honest)

package/docs/COMMUNITY_AND_PLUGINS.md

@@ -1,6 +1,6 @@
 # Community And Plugins
 
-Current release: **11.7.0 — Clean Sweep**.
+Current release: **11.9.0 — Working Order**.
 
 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