ltcai 10.3.0 → 10.5.0

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)
 
-![v10.3.0 Living Brain walkthrough](output/release/v10.3.0/gifs/v10.3.0-living-brain-walkthrough.gif)
+![v10.5.0 Living Brain walkthrough](output/release/v10.5.0/gifs/v10.5.0-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
@@ -24,9 +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/v10.3.0/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v10.3.0/screenshots/05-memory-graph.png) |
-| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v10.3.0/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v10.3.0/screenshots/12-review-center.png) |
-| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v10.3.0/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v10.3.0/screenshots/10-admin-console.png) |
+| **Chat with a Brain that remembers** — every conversation grows durable, source-linked memory ![Brain Chat](output/release/v10.5.0/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v10.5.0/screenshots/05-memory-graph.png) |
+| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v10.5.0/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v10.5.0/screenshots/12-review-center.png) |
+| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v10.5.0/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v10.5.0/screenshots/10-admin-console.png) |
+| **Watch a file become memory** — three named steps, not a pipeline diagram ![Material to memory](output/release/v10.5.0/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/v10.5.0/screenshots/08-system.png) |
 
 ## Why Lattice AI
 
@@ -57,47 +58,55 @@ First-run flow — wake the Brain, pick the owner, load a recommended model:
 
 | | | |
 | --- | --- | --- |
-| ![Login](output/release/v10.3.0/screenshots/01-login.png) | ![Model install](output/release/v10.3.0/screenshots/03-install-load-progress.png) | ![Model library](output/release/v10.3.0/screenshots/07-model-library.png) |
+| ![Login](output/release/v10.5.0/screenshots/01-login.png) | ![Model install](output/release/v10.5.0/screenshots/03-install-load-progress.png) | ![Model library](output/release/v10.5.0/screenshots/07-model-library.png) |
 
 Screenshot index and capture notes:
-[output/release/v10.3.0/SCREENSHOT_INDEX.md](output/release/v10.3.0/SCREENSHOT_INDEX.md)
+[output/release/v10.5.0/SCREENSHOT_INDEX.md](output/release/v10.5.0/SCREENSHOT_INDEX.md)
 
 ## Current Release
 
-The current release is **10.3.0 — Measured Ground**:
-
-10.2.0 answered a code review. 10.3.0 is about knowing where things actually
-stand: several numbers this project reported about itself turned out to be
-wrong, and those corrections matter more than the features around them.
-
-- **Frontend coverage was never really measured.** Vitest only reports files a
-  test already imports, so every untested module quietly left the denominator
-  and the tool read 54%. With `all: true` the honest figure is **28.5%** — and
-  208 tests now cover pages that had none, including every settings and memory
-  screen.
-- **Python coverage was reported as 80%. It is 71.6%.** The `omit` pattern did
-  not match the paths coverage records, so the suite was counting itself — and
-  test files run start to finish by construction.
-- **mypy went from 13 modules to 193 of 270**, finding three real defects on
-  the way: a log line inside an error handler referenced an attribute that does
-  not exist (turning a recoverable failure into a crash), an annotation used a
-  name that was never imported, and one call could dereference `None`.
-- **The chat-turn writer left the composition root.** 66 lines that decide what
-  a message looks like after redaction, and what the audit log records about
-  it, are now a module with 14 tests instead of a closure nothing could reach.
-- **What is not measured is written down.** `docs/MYPY_BACKLOG.md` lists the 77
-  modules still outside type checking with their error counts, so the boundary
-  is a fact rather than an intention.
+The current release is **10.5.0 — Everyday Words**:
+
+10.4.0 named the ground the code stands on. 10.5.0 renames the ground the
+*reader* stands on: every screen a first-time user lands on now says what
+Lattice is doing in the words that user would use. No feature was removed —
+the engine's own vocabulary moved behind the advanced mode switch, where it
+belongs to the people who asked for it.
+
+- **The autonomy dial is a sentence, not a mode name.** 엄격 / 신뢰 / 바이패스
+  became 먼저 물어보기 / 웬만하면 알아서 / 거의 다 알아서, each with one line
+  about what it will and will not do on its own. The home dial and Settings
+  now draw that copy from one module, so the same setting is never named two
+  ways — and a mode the server adds later still renders, from the server's own
+  label.
+- **The path from a file to a memory is three named steps.** 진행 상황 was
+  hidden from plain mode and held two raw API payloads. It now shows
+  내용 읽기 → 뜻 파악하기 → 기억에 연결하기 as a labelled ordered list, with
+  each step saying what it does to your file. 파싱 · 임베딩 · 인덱싱 are gone
+  from that screen.
+- **Automations are named the way you named them.** A run shows its workflow's
+  name rather than a database id, and its state is spoken — `awaiting_approval`
+  reads as "내 승인 기다리는 중". Unknown states say so instead of printing the
+  token. Advanced mode still shows the id.
+- **A model your machine cannot run says so in one sentence** instead of a
+  registry line half-translated word by word.
+- **The published screenshots were wrong before this release.** Capture ran in
+  `advanced`, so every README frame showed payload panels, storage engines and
+  hook logs that no first-run user is ever shown. Captures now run in the app's
+  real default, `basic` — this page's images are what you will actually see.
+- **Guarded, not asserted.** A visual sweep walks ten plain-mode routes and
+  fails if any of them renders empty or puts engine vocabulary in front of a
+  reader who never asked for it.
 
 Release notes: [RELEASE.md](RELEASE.md) · Full history: [docs/CHANGELOG.md](docs/CHANGELOG.md)
 
-Expected artifacts for 10.3.0 release must use exact filenames:
+Expected artifacts for 10.5.0 release must use exact filenames:
 
-- `dist/ltcai-10.3.0-py3-none-any.whl`
-- `dist/ltcai-10.3.0.tar.gz`
-- `ltcai-10.3.0.tgz`
-- `dist/ltcai-10.3.0.vsix`
-- `src-tauri/target/release/bundle/dmg/Lattice AI_10.3.0_aarch64.dmg`
+- `dist/ltcai-10.5.0-py3-none-any.whl`
+- `dist/ltcai-10.5.0.tar.gz`
+- `ltcai-10.5.0.tgz`
+- `dist/ltcai-10.5.0.vsix`
+- `src-tauri/target/release/bundle/dmg/Lattice AI_10.5.0_aarch64.dmg`
 
 Do not use wildcard artifact uploads. Package registry publishing remains owner-run.
 
@@ -132,6 +141,8 @@ See [ARCHITECTURE.md](ARCHITECTURE.md) for details and
 
 | Version | Theme |
 | --- | --- |
+| 10.5.0 | Everyday Words |
+| 10.4.0 | Named Ground |
 | 10.3.0 | Measured Ground |
 | 10.2.0 | Load-Bearing Fixes |
 | 10.1.1 | Reachable Boundary |

package/docs/CHANGELOG.md

@@ -4,6 +4,150 @@ 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.
 
+## [10.5.0] - 2026-08-03
+
+A UI/UX pass for the person who did not build this. No feature was removed;
+vocabulary, ordering, and the default mode a first-run user lands in changed.
+Backend behaviour is unchanged — `frontend/openapi.json` differs from 10.4.0
+only in `info.version`.
+
+### Changed
+- **Permission modes are named by what they do to you, not by their enum.**
+  엄격 / 신뢰 / 바이패스 → 먼저 물어보기 / 웬만하면 알아서 / 거의 다 알아서
+  (`Strict` / `Trusted` / `Bypass` → `Ask me first` / `Mostly on its own` /
+  `Almost everything on its own`), each with a one-line summary of what it does
+  without asking. The bypass warning now says which kind of action stays
+  blocked rather than naming the mode.
+- **`#/pipeline` is reachable in basic mode and named 진행 상황.** Its two raw
+  API payload panels are replaced (in basic mode) by an `aria-label`ed ordered
+  list of three steps — 내용 읽기 / 뜻 파악하기 / 기억에 연결하기 — with a
+  per-step waiting/working/done state. Advanced mode keeps both payload panels.
+- **Ingestion stage names describe the reader's file, not the machine's job**:
+  준비 → 파일 여는 중, 파싱 → 내용 읽는 중, 임베딩 → 뜻 파악하는 중, 인덱싱 →
+  기억에 연결하는 중, 메모리화 완료 → 기억 완료. The stale-embedding prompt
+  became "찾는 방식이 바뀌었어요 / 기억 다시 정리하기".
+- **Run rows are titled by workflow name** (then goal, then title/query, then
+  "n번째 작업" in basic mode) instead of a database id; the id moves to a
+  secondary line in advanced mode only.
+- **Run and trigger states are translated per token.**
+  `act.runStatus.<token>` covers ok/succeeded/completed/retried_ok/
+  awaiting_approval/waiting_approval/running/queued/pending/failed/error/
+  cancelled/stopped/interrupted/rejected/partial; an unmapped token renders
+  "알 수 없음" rather than itself.
+- **Brain stats answer a person's question** — 저장 위치 / 내 컴퓨터 and
+  가져가기 / 언제든 내보낼 수 있어요 in place of `schema_version` and the
+  storage engine name (both still shown in advanced).
+- **`scripts/capture_release_evidence.mjs` captures in `basic`**, the app's real
+  default, instead of `advanced`. Every README screenshot before this release
+  showed panels a first-run user never sees. `09-model-setup-status.png` (a
+  duplicate of the Brain home once captured in basic) is replaced by
+  `09-automation-runs.png`, and `11-knowledge-journey.png` is added.
+- **The walkthrough GIF is encoded against a palette generated from the clip**
+  (`palettegen=stats_mode=diff` + `paletteuse=dither=sierra2_4a`) instead of
+  ffmpeg's default 256-colour cube, which had been rendering the ivory
+  background as dithered yellow and the greens as olive. 1.5 MB → 2.8 MB.
+
+### Added
+- `frontend/src/lib/permissionCopy.ts` — one source for permission-mode copy,
+  shared by `BrainQuickControls` (home dial) and `PermissionModePanel`
+  (Settings), which had each been translating the server catalog separately.
+  Lookup is by mode id, falling back to the server's own localized label, so a
+  mode added server-side still renders; `PermissionModePanel.test.tsx` asserts
+  that fallback so the table cannot become an accidental allowlist.
+- A basic-mode "자동으로 실행되는 작업" summary on the workflows surface:
+  workflow name plus 새 자료가 들어오면 / 정해진 시간에 / 내가 눌렀을 때만 /
+  조건이 맞으면, and 켜져 있어요 / 지금은 멈춰 있어요. The node canvas and the
+  paste-JSON box are author tools and stay in advanced mode.
+- `tests/visual/v3.spec.js`: a sweep over ten plain-mode routes asserting each
+  renders, shows no service-unavailable banner, and contains none of a list of
+  engine terms; plus a test that the three journey steps render under their
+  accessible name. `#/runs` failed the vocabulary assertion before this pass.
+- `Library.test.tsx` covers registry prose that is English-only: a sentence with
+  no Hangul and six or more words is now replaced by a written Korean
+  explanation instead of being substituted term by term into word salad.
+
+### Known gaps
+- The approval card under 작업 → 실행 still labels raw payload fields `Action`,
+  `Action Label`, `User Email`. It is visible in `09-automation-runs.png` and is
+  published rather than cropped.
+
+## [10.4.0] - 2026-08-02
+
+### Changed
+- **`app_factory._build` is decomposed.** 1,318 lines → 26. The assembly now
+  lives in `latticeai/runtime/build_phases.py` as ten ordered phases sharing a
+  typed `latticeai/runtime/runtime_context.py::RuntimeContext`:
+  `platform → config → identity → brain → domain → web → services →
+  foundation_routes → platform_features → interaction`.
+  The single closure worked because closures resolve free variables at call
+  time; several sections depend on names bound far below them. The
+  RuntimeContext preserves that late binding while naming the shared state.
+  `tests/unit/test_runtime_context.py` fixes the phase order, which phase
+  produces which attribute, and that reading one early fails by name.
+- **mypy covers the whole tree: 274 of 274 modules, 0 errors** (was 193 of 270
+  with 1,407 outstanding). `pyproject.toml`'s `[tool.mypy] files` is no longer
+  a curated subset.
+- `lattice_brain/graph/_kg_common.py`'s `__all__` is a literal instead of a
+  comprehension over `globals()`. The computed form was invisible to a type
+  checker, so twelve modules resolved no names behind
+  `from ._kg_common import *` (~750 false `name-defined` errors).
+  `tests/unit/test_kg_common_exports.py` keeps the literal honest.
+- The star import of `._kg_fsutil` inside `_kg_common` is now an explicit list
+  for the same reason.
+- JSON-shaped payloads in `services/model_runtime.py`, `model_engines.py`,
+  `model_catalog.py`, `api/setup.py` and `api/models.py` are typed
+  `Dict[str, Any]` rather than `Dict[str, object]`, which forced a cast at
+  every nested access without catching anything.
+- Optional dependencies (`AsyncOpenAI`, `mx`, `vlm_load`, `lm_load`,
+  `pyautogui`) are aliased on import and re-exported as `Any`, so "installed"
+  and "absent" have one declared type.
+
+### Added
+- `lattice_brain/graph/_kg_contract.py` — the 23-member surface the eleven
+  graph mixins share, written down for the first time. Typing-only: `_Core` is
+  `object` at runtime, so `KnowledgeGraphStore`'s MRO is unchanged.
+  `tests/unit/test_kg_contract.py` asserts both the contract and that it never
+  becomes a real base class.
+- `AppContext.require(field)` — binds a dependency a router cannot run without,
+  so an absent one names itself at router construction instead of surfacing as
+  `'NoneType' object is not callable` inside a request handler.
+- VS Code `ltcai.captureFolder` — folder ingestion through the same
+  `/api/ingestion/folder` endpoint and the same local-read approval dance the
+  web Capture view uses.
+- VS Code `ltcai.showArtifacts` — `artifacts[]` rendered as cards with the
+  server's repair and validation flags, so a deterministically repaired
+  scaffold no longer looks identical to clean model output.
+- VS Code model picker now shows the hardware-derived recommendation from
+  `GET /setup/scan`, with the server's own reasoning. No scan, no banner.
+- Telegram sends the same `artifacts[]` card summary before the files.
+- Frontend tests for four previously untested modules with real logic:
+  `routes.ts`, `store/appStore.ts`, `api/base.ts` error translation, and
+  `pages/brain/graphExplorer.ts`.
+
+### Fixed
+- **`python -m latticeai.server_app` raised `AttributeError`.** `main` was a
+  local inside the old `_build` closure and was never on the export allowlist,
+  so `get_shared_runtime().main()` could never resolve it. `main()` now serves
+  the shared runtime directly and needs no export.
+- `core/workspace_os.py`: four lines duplicated after a `return` in
+  `remove_member` — dead since the merge that introduced them.
+- `models/router.py`: a `str` shadowed a `dict` in the custom cloud-model loop,
+  so those entries built their ids from the wrong variable.
+- `lattice_brain/context.py`: an unconfigured retrieval seam was called
+  unguarded and died as a `TypeError` inside failure isolation instead of
+  naming itself.
+- `runtime/review_wiring.py` declared its injected `HTTPException` as
+  `type[Exception]`, which does not accept `(status_code=, detail=)`.
+- `api/security_dashboard.py`: a defensive `isinstance(rows, list)` re-check
+  that every branch above already guaranteed.
+
+### Documentation
+- `docs/MYPY_BACKLOG.md` is now the record of how the boundary closed, not a
+  list of what is left — including the conventions the sweep settled on.
+- `docs/SURFACE_PARITY.md`: no ◐ remains in the matrix. A stale v9.9.6 note
+  claiming the live step timeline was web-only is corrected (v9.9.7's
+  `runAgentLive` provides it).
+
 ## [10.3.0] - 2026-07-29
 
 ### Fixed

package/docs/COMMUNITY_AND_PLUGINS.md

@@ -1,6 +1,6 @@
 # Community And Plugins
 
-Current release: **10.3.0 — Measured Ground**.
+Current release: **10.5.0 — Everyday Words**.
 
 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: **10.3.0 — Measured Ground**.
+Current release: **10.5.0 — Everyday Words**.
 
 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/MYPY_BACKLOG.md

@@ -1,98 +1,65 @@
 # mypy backlog
 
-`[tool.mypy] files` in `pyproject.toml` lists every module that type-checks
-today — **193 of 270** as of 10.3.0, up from 13 in 10.2.0.
-This file is the remainder, smallest first, so the boundary is a measured
-fact rather than an open-ended intention.
+> **Status: reference**
+> 10.2.0: 13 modules checked. 10.3.0: 193 of 270, with the remaining 77 listed
+> here by error count. **10.4.0: 274 of 274 — the backlog is empty.**
 
-Adding a module to the checked set is a decision to fix that module, not its
-dependencies (`follow_imports = silent`). Work from the top: the short ones
-are usually one missing annotation.
+`[tool.mypy] files` in `pyproject.toml` now lists **every** module in
+`lattice_brain/` and `latticeai/`. There is no "adopted set" any more; adding a
+module to the tree adds it to the checked set, and CI fails if it does not
+type-check.
 
-Three of these turned out to be real defects when 10.3.0 measured them:
-`hooks.py` referenced a non-existent `self._path` inside the handler for an
-unreadable registry, `_kg_fsutil.py` used `Iterable` without importing it,
-and `agent_runtime.py` called `.get` on a value that could be `None`. Those
-are fixed; the list below is what is left.
+This file stays as the record of how the boundary closed, because two of the
+1,407 errors 10.3.0 measured turned out to be worth more than the annotations.
 
-| errors | module | dominant codes |
-| ---: | --- | --- |
-| 1 | `lattice_brain/graph/_kg_fsutil.py` | `union-attr` ×1 |
-| 1 | `latticeai/api/admin.py` | `call-overload` ×1 |
-| 1 | `latticeai/api/computer_use.py` | `var-annotated` ×1 |
-| 1 | `latticeai/api/hooks.py` | `unreachable` ×1 |
-| 1 | `latticeai/api/local_files.py` | `arg-type` ×1 |
-| 1 | `latticeai/api/static_routes.py` | `assignment` ×1 |
-| 1 | `latticeai/core/marketplace.py` | `arg-type` ×1 |
-| 1 | `latticeai/core/model_compat.py` | `unreachable` ×1 |
-| 1 | `latticeai/core/plugins.py` | `unreachable` ×1 |
-| 1 | `latticeai/core/project_sessions.py` | `var-annotated` ×1 |
-| 1 | `latticeai/core/workspace_os.py` | `unreachable` ×1 |
-| 1 | `latticeai/core/workspace_os_state.py` | `arg-type` ×1 |
-| 1 | `latticeai/runtime/sso_config_runtime.py` | `arg-type` ×1 |
-| 1 | `latticeai/services/command_center.py` | `assignment` ×1 |
-| 1 | `latticeai/services/search_service.py` | `assignment` ×1 |
-| 1 | `latticeai/services/triggers.py` | `truthy-function` ×1 |
-| 1 | `latticeai/setup/auto_setup.py` | `attr-defined` ×1 |
-| 2 | `lattice_brain/ingestion.py` | `assignment` ×2 |
-| 2 | `latticeai/api/chat_stream.py` | `var-annotated` ×1, `arg-type` ×1 |
-| 2 | `latticeai/api/mcp.py` | `var-annotated` ×2 |
-| 2 | `latticeai/core/mcp_registry.py` | `index` ×1, `return-value` ×1 |
-| 2 | `latticeai/core/run_explain.py` | `union-attr` ×1, `call-overload` ×1 |
-| 2 | `latticeai/core/workspace_snapshots.py` | `var-annotated` ×2 |
-| 2 | `latticeai/runtime/review_wiring.py` | `call-arg` ×2 |
-| 2 | `latticeai/services/brain_intelligence.py` | `operator` ×1, `index` ×1 |
-| 2 | `latticeai/services/memory_service.py` | `misc` ×1, `index` ×1 |
-| 2 | `latticeai/services/model_loading.py` | `arg-type` ×1, `call-overload` ×1 |
-| 2 | `latticeai/services/multimodal_streaming.py` | `attr-defined` ×1, `arg-type` ×1 |
-| 2 | `latticeai/setup/wizard.py` | `attr-defined` ×1, `dict-item` ×1 |
-| 2 | `latticeai/tools/documents.py` | `arg-type` ×2 |
-| 3 | `lattice_brain/quality.py` | `var-annotated` ×2, `return-value` ×1 |
-| 3 | `latticeai/api/models.py` | `call-overload` ×2, `attr-defined` ×1 |
-| 3 | `latticeai/cli/entrypoint.py` | `operator` ×1, `union-attr` ×1, `arg-type` ×1 |
-| 3 | `latticeai/core/audit.py` | `assignment` ×1, `index` ×1, `operator` ×1 |
-| 3 | `latticeai/integrations/telegram_bot.py` | `union-attr` ×2, `arg-type` ×1 |
-| 3 | `latticeai/runtime/stages.py` | `arg-type` ×3 |
-| 3 | `latticeai/services/cloud_streaming.py` | `arg-type` ×2, `attr-defined` ×1 |
-| 3 | `latticeai/services/hybrid_chat.py` | `arg-type` ×3 |
-| 3 | `latticeai/services/tool_dispatch.py` | `arg-type` ×3 |
-| 4 | `lattice_brain/graph/_kg_common.py` | `misc` ×3, `return-value` ×1 |
-| 4 | `latticeai/api/chat_agent_http.py` | `arg-type` ×2, `misc` ×1, `assignment` ×1 |
-| 4 | `latticeai/api/chat_helpers.py` | `call-overload` ×2, `union-attr` ×1, `arg-type` ×1 |
-| 4 | `latticeai/api/security_dashboard.py` | `assignment` ×3, `unreachable` ×1 |
-| 4 | `latticeai/services/evidence_actions.py` | `union-attr` ×4 |
-| 5 | `lattice_brain/context.py` | `arg-type` ×4, `misc` ×1 |
-| 5 | `latticeai/api/permissions.py` | `arg-type` ×5 |
-| 5 | `latticeai/services/model_engines.py` | `attr-defined` ×2, `call-overload` ×2, `unreachable` ×1 |
-| 5 | `latticeai/services/run_executor.py` | `unreachable` ×3, `arg-type` ×1, `return-value` ×1 |
-| 6 | `lattice_brain/runtime/contracts.py` | `union-attr` ×6 |
-| 6 | `latticeai/core/agent.py` | `arg-type` ×4, `return-value` ×2 |
-| 7 | `lattice_brain/graph/proactive.py` | `assignment` ×2, `arg-type` ×2, `index` ×1 |
-| 7 | `latticeai/app_factory.py` | `arg-type` ×3, `assignment` ×2, `attr-defined` ×2 |
-| 7 | `latticeai/core/embedding_providers.py` | `unreachable` ×2, `assignment` ×2, `union-attr` ×2 |
-| 7 | `latticeai/services/openai_compatible_adapter.py` | `arg-type` ×7 |
-| 8 | `lattice_brain/graph/curator.py` | `operator` ×8 |
-| 8 | `lattice_brain/workflow.py` | `arg-type` ×5, `index` ×2, `assignment` ×1 |
-| 8 | `latticeai/api/setup.py` | `index` ×5, `attr-defined` ×3 |
-| 8 | `latticeai/services/local_knowledge.py` | `union-attr` ×3, `misc` ×2, `operator` ×2 |
-| 10 | `latticeai/api/tools.py` | `arg-type` ×10 |
-| 13 | `latticeai/api/search.py` | `return` ×12, `return-value` ×1 |
-| 15 | `lattice_brain/graph/store.py` | `name-defined` ×15 |
-| 16 | `latticeai/api/chat.py` | `arg-type` ×12, `misc` ×3, `call-overload` ×1 |
-| 16 | `latticeai/tools/computer.py` | `union-attr` ×16 |
-| 19 | `lattice_brain/graph/retrieval_docgen.py` | `name-defined` ×12, `attr-defined` ×7 |
-| 35 | `latticeai/services/model_runtime.py` | `index` ×15, `arg-type` ×8, `attr-defined` ×6 |
-| 45 | `lattice_brain/graph/retrieval_reads.py` | `name-defined` ×30, `attr-defined` ×15 |
-| 46 | `latticeai/models/router.py` | `arg-type` ×26, `assignment` ×7, `attr-defined` ×4 |
-| 57 | `lattice_brain/graph/write_master.py` | `name-defined` ×48, `attr-defined` ×9 |
-| 64 | `lattice_brain/graph/documents.py` | `name-defined` ×45, `attr-defined` ×19 |
-| 71 | `lattice_brain/graph/provenance.py` | `name-defined` ×59, `attr-defined` ×12 |
-| 77 | `lattice_brain/graph/retrieval.py` | `name-defined` ×61, `attr-defined` ×16 |
-| 79 | `lattice_brain/graph/discovery.py` | `name-defined` ×72, `attr-defined` ×7 |
-| 107 | `lattice_brain/graph/retrieval_vector.py` | `name-defined` ×68, `attr-defined` ×39 |
-| 108 | `latticeai/api/workspace.py` | `misc` ×105, `arg-type` ×2, `call-overload` ×1 |
-| 127 | `lattice_brain/graph/discovery_index.py` | `name-defined` ×98, `attr-defined` ×29 |
-| 143 | `lattice_brain/graph/projection.py` | `name-defined` ×122, `attr-defined` ×21 |
-| 177 | `lattice_brain/graph/ingest.py` | `name-defined` ×122, `attr-defined` ×55 |
+## Two root causes were 68% of the backlog
 
-Total outstanding: **1407** errors across **77** modules.
+**`_kg_common.__all__` was computed** (`[name for name in globals() if not
+name.startswith("__")]`). Correct at runtime, opaque to a checker: mypy could
+not resolve a single name behind `from ._kg_common import *`, so twelve graph
+modules reported **~750 false `name-defined` errors** and stayed unchecked.
+Freezing the list to a literal fixed all of them.
+`tests/unit/test_kg_common_exports.py` asserts the literal still equals what
+the expression would produce, so it cannot drift.
+
+**The eleven graph mixins had an unwritten contract.** `ingest` calls
+`_upsert_node` from `write_master`, which calls `_v2_project_node` from
+`projection`, and everything calls `_connect` — 229 `attr-defined` errors,
+because from a checker's position each mixin is a bare class calling methods it
+does not have. `lattice_brain/graph/_kg_contract.py` writes that contract down:
+23 declared members, typing-only (`_Core` is `object` at runtime, so the MRO is
+unchanged), verified by `tests/unit/test_kg_contract.py`.
+
+Neither was a typing problem. Both were *readability* problems that a reader
+had to solve by grepping eleven files.
+
+## Real defects the remaining work surfaced
+
+| defect | module | why it mattered |
+| --- | --- | --- |
+| four lines duplicated after a `return` | `core/workspace_os.py` | dead since the merge that introduced it; `remove_member` looked like it did its work twice |
+| `main` was never exported | `app_factory.py` | `python -m latticeai.server_app` raised `AttributeError` — the module entrypoint did not run |
+| `str` shadowed a `dict` in a loop | `models/router.py` | the custom-cloud-model branch built ids from the wrong variable |
+| `Optional` seam called unguarded | `lattice_brain/context.py` | an unconfigured retrieval port raised `TypeError` inside failure isolation instead of naming itself |
+
+(10.3.0 found three more the same way: `self._path` inside an error handler,
+`Iterable` used without importing it, and `.get` on a possible `None`.)
+
+## Conventions the sweep settled on
+
+* **JSON-shaped payloads are `Dict[str, Any]`, not `Dict[str, object]`.**
+  `object` forced a cast at every nested access without catching anything;
+  the value really is arbitrary JSON.
+* **Optional dependencies are aliased, then re-exported as `Any`**
+  (`AsyncOpenAI`, `mx`, `vlm_load`, `pyautogui`), so "installed" and "absent"
+  have the same declared type and call sites keep their historical name.
+* **Async generators in Protocols are declared with `def`, not `async def`.**
+  `async def … -> AsyncIterator[T]` says "a coroutine resolving to an
+  iterator", which no implementation does.
+* **A router dependency it cannot run without is bound through
+  `AppContext.require("name")`** — an absent dependency names itself at router
+  construction instead of surfacing as `'NoneType' object is not callable`
+  inside a request handler.
+* **A defensive `isinstance` check on a parameter means the annotation is
+  wrong.** Widen the parameter (`Any`, `Optional[str]`) rather than deleting
+  the guard: the guard is what the callers actually need.

package/docs/ONBOARDING.md

@@ -1,6 +1,6 @@
 # Lattice AI Onboarding
 
-Current release: **10.3.0 — Measured Ground**.
+Current release: **10.5.0 — Everyday Words**.
 
 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 (v10.3.0)
+# Lattice AI — Operations Guide (v10.5.0)
 
 > **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/PERMISSION_MODE.md

@@ -36,10 +36,21 @@ Env default: `LATTICEAI_PERMISSION_MODE=strict|trusted|bypass`.
 
 ## UI
 
-`PermissionModePanel` renders in **환경설정 → 에이전트 자율성** (`SystemPage`
-settings tab). It renders the catalog `/api/permission-mode` returns rather
-than a hardcoded mode list, so adding or renaming a mode server-side needs no
-frontend change, and it keeps the apply button disabled until
+`PermissionModePanel` renders in **설정 → 혼자 해도 되는 일** (`SystemPage`
+settings tab; the section was called 에이전트 자율성 before 10.5.0). The same
+dial is reachable on the home screen through `BrainQuickControls`.
+
+It still renders whatever modes the catalog `/api/permission-mode/catalog`
+returns rather than a hardcoded list, so a mode added server-side appears with
+no frontend change. Since 10.5.0 the *wording* is no longer taken from the
+server for modes the app knows: `frontend/src/lib/permissionCopy.ts` maps mode
+id → plain-language label and summary (`strict` → 먼저 물어보기, `trusted` →
+웬만하면 알아서, `bypass` → 거의 다 알아서), and both surfaces read that one
+module so the dial cannot be named two ways. The server's own localized label
+is the fallback for an id the map does not know — renaming a mode server-side
+therefore changes the UI only for ids the app has no copy for.
+
+The apply button stays disabled until
 
 * a *different* mode is selected, and
 * for a mode whose catalog entry sets `requires_ack`, the risk acknowledgement

package/docs/SURFACE_PARITY.md

@@ -2,7 +2,8 @@
 
 > **Status: reference**
 > 도입: v9.9.4 (2026-07-25, 리뷰 Wave 1.4 "표면 패리티 체크리스트").
-> 갱신: v9.9.7 — 표에 남아 있던 ✖ 갭을 **전부** 해소. Browser 확장도 캡처 전용 경계를 넘어 회상/승인 가시성을 갖췄다.
+> 갱신: v9.9.7 — 표에 남아 있던 ✖ 갭을 **전부** 해소.
+> 갱신: **v10.4.0 — 남아 있던 ◐(부분 제공)를 전부 해소.** 표에 ◐ 는 더 이상 없다.
 > 목적: 각 표면(서피스)이 Brain 계약의 어디까지를 제공하는지 **정직하게** 기록한다.
 > "앱마다 다른 Lattice"를 방지하는 기준표이며, 기능을 과장하지 않는다.
 
@@ -22,9 +23,9 @@
 
 | 루프 순간 | Web `/app` | Desktop | VS Code | Browser | Telegram |
 | --- | --- | --- | --- | --- | --- |
-| 첫 저장 (Capture) | ✅ DnD·폴더·웹 수집, 품질 경고 | ✅ (웹과 동일) | ◐ `sendToLattice` 선택 영역 전송 | ✅ 페이지 캡처 (단일 목적) | ◐ 메시지 수집 |
+| 첫 저장 (Capture) | ✅ DnD·폴더·웹 수집, 품질 경고 | ✅ (웹과 동일) | ✅ `sendToLattice` 파일/선택 + `captureFolder` 폴더 수집 (v10.4.0) | ✅ 페이지 캡처 (단일 목적) | ✅ 메시지 + 문서/사진 업로드 수집 |
 | 첫 회상 (Recall) | ✅ 하이브리드 검색 + grounding 배지 + 출처→청크 | ✅ (동일) | ✅ `askCurrentFile`/`askBrain` — 동일 `/chat` grounding 배지 | ✅ 팝업 질문 + 동일 grounding 배지 (v9.9.7) | ✅ 답변 + grounding 배지 (v9.9.7) |
-| 첫 산출물 (Artifact) | ✅ artifacts[] 카드·미리보기·Brain 기억 칩 | ✅ (동일) | ◐ `createFile` + `runAgent`/`runAgentLive` 스텝·파일 요약, 카드 UI 없음 | — (의도: 브라우저에서 파일 쓰기 없음) | ◐ 파일 전송만 |
+| 첫 산출물 (Artifact) | ✅ artifacts[] 카드·미리보기·Brain 기억 칩 | ✅ (동일) | ✅ `createFile` + `showArtifacts` 카드(보정/검증 플래그 포함, v10.4.0) | — (의도: 브라우저에서 파일 쓰기 없음) | ✅ 파일 + artifacts[] 카드 요약 (v10.4.0) |
 | 첫 보호 (Approval) | ✅ 승인 카드 + TTL 카운트다운 + 재시작 생존 | ✅ (동일) | ✅ List/Approve/Reject 커맨드 + 토큰 캐시 | ✅ 대기 건수 표시 (승인은 웹에서, v9.9.7) | ✅ 인라인 Done/Cancel + run_id/token 재개 |
 
 ## 기능 상세 × 표면
@@ -42,14 +43,14 @@
 | Watch 상태 신호 (v9.9.4) | ✅ 홈 카드 | ✅ | — | — | — |
 | Review Center (제안 승인/거절) | ✅ | ✅ | ✅ `ltcai.reviewCenter` (409 충돌 정직 보고) | — (의도: 승인은 웹/에디터/봇에서) | ✅ `/review` + 인라인 승인/거절 (v9.9.7) |
 | 데모 코퍼스 First Value Loop | ✅ | ✅ | — | — | — |
-| 모델 로드/추천 | ✅ | ✅ | ◐ `loadModel` | — | — |
+| 모델 로드/추천 | ✅ | ✅ | ✅ `loadModel` + 하드웨어 기반 추천·근거 (v10.4.0) | — (의도) | — (의도) |
 | 코드 편집 보조 (edit/explain/refactor/tests) | — | — | ✅ | — | — |
 
 ## 규칙
 
 1. **API 계약이 기준이다.** 모든 표면은 동일한 sidecar API를 소비한다. 표면별 전용 API를 만들지 않는다.
 2. **◐/✖ 는 문서화된 상태로만 존재한다.** 새 기능을 Web에 추가할 때 이 표를 갱신하고, 다른 표면에 제공하지 않을 경우 "—(의도)" 인지 "✖(갭)" 인지 명시한다.
-3. **✖ 갭은 릴리스 노트의 Honest Limitations 후보다.** v9.9.7 기준 표에 남은 ✖는 **없다**.
+3. **✖ 갭은 릴리스 노트의 Honest Limitations 후보다.** v9.9.7 이후 표에 남은 ✖는 **없고**, v10.4.0 이후 ◐ 도 **없다**.
    - 남은 "—"는 전부 **설계 경계**이며, 각 항목에 이유를 함께 적는다. 예: 브라우저 확장은 파일을 쓰지 않으므로 산출물 생성이 없고, 승인 *결정*은 서명된 토큰이 필요한 흐름이라 대기 건수만 보여 주고 승인은 웹/에디터/봇에서 한다.
    - 경계를 새로 만들 때는 "왜 제공하지 않는가"를 이 문서에 남긴다. 이유 없는 "—"는 갭이지 경계가 아니다.
 4. 릴리스마다 이 표를 검토한다 (release checklist의 docs 단계).
@@ -63,7 +64,7 @@
 
 - **회상 배지**: `askCurrentFile` / `askBrain`은 웹과 동일한 `POST /chat` 응답의 `grounding` 판정을 그대로 읽는다. 판정이 없으면 "근거 있음"으로 승격하지 않고 `unknown`으로 보고한다 (`vscode-extension/surface.ts::groundingBadge`).
 - **Review Center**: `ltcai.reviewCenter`는 웹과 같은 `/api/proposals` 표면을 쓴다. 승인은 검토한 내용 그대로 적용하고, 409(스테이징 이후 파일 변경)는 "아무것도 쓰지 않았다"고 정직하게 알린다.
-- **스텝 요약**: `ltcai.runAgent`는 실행 후 `steps`/`created_files`/`explanation`을 출력 채널에 요약한다. 라이브 SSE 타임라인은 아직 웹 전용이다 (◐).
+- **스텝 요약**: `ltcai.runAgent`는 실행 후 `steps`/`created_files`/`explanation`을 출력 채널에 요약한다. (라이브 SSE 타임라인은 v9.9.7의 `ltcai.runAgentLive`가 같은 `agent_step` 프레임으로 제공한다 — 이 메모는 v9.9.6 시점 기준이었다.)
 - 파싱 계약은 `tests/vscode-extension.test.cjs`가 sidecar 페이로드 모양 그대로 검증한다.
 
 ## v9.9.7 — 남은 갭을 닫은 방법
@@ -81,3 +82,29 @@
 - **Browser 확장**: 캡처 전용 경계를 넘어 `/chat` 질문과 `agent/approvals` 대기
   건수를 보여 준다. **판정을 로컬에서 계산하지 않는다** — 판정이 없으면
   "근거 확인 불가"이며 절대 "근거 있음"으로 승격하지 않는다.
+
+## v10.4.0 — 마지막 ◐ 셋을 닫은 방법
+
+세 갭 모두 **계약의 문제가 아니라 렌더링의 문제**였다. 사이드카는 이미 필요한
+데이터를 내고 있었고, 에디터/봇이 그것을 버리고 있었다.
+
+- **VS Code 폴더 수집** (`ltcai.captureFolder`): 웹 Capture 와 **같은**
+  `POST /api/ingestion/folder` 를 쓴다. 로컬 디스크를 읽으므로 승인 절차도
+  동일하다 — 토큰 없는 첫 호출은 `permission_required` 이고, 확장은 그것을
+  그대로 보여 준다(조용히 재시도하지 않는다). 백그라운드 job 으로 큐잉되며
+  진행 상황은 웹에서 본다.
+- **VS Code 산출물 카드** (`ltcai.showArtifacts`): `/agent` 응답의
+  `artifacts[]` 를 그대로 읽는다. 결정적으로 **보정된(repaired) 스캐폴드와
+  깨끗한 모델 출력이 구분된다** — 이전에는 평평한 경로 목록이라 둘이 같아
+  보였다. 서버의 `valid=false` 판정을 확장이 성공으로 승격하지 않는다.
+  구형 사이드카(`created_files` 만 있는 응답)는 "세부 정보 없음"이라고
+  정직하게 말한다.
+- **VS Code 모델 추천**: `GET /setup/scan` 의 `zero_config.recommend` 를
+  읽어 **이 기기에 왜 이 모델인지**를 근거와 함께 보여 준다. 스캔이 없으면
+  배너도 없다 — 이유를 지어내지 않는다.
+- **Telegram 산출물 카드**: 같은 `artifacts[]` 플래그를 파일 전송 직전에
+  요약한다. 8개까지 나열하고 나머지는 `… +N` 으로 정직하게 줄인다.
+
+계약 테스트: `tests/vscode-extension.test.cjs` (19), `tests/unit/test_telegram_security.py`.
+전부 사이드카 페이로드 모양 그대로 검증하며, 확장/봇이 서버 판정을 재계산하지
+않는지도 함께 고정한다.

package/docs/TRUST_MODEL.md

@@ -1,6 +1,6 @@
 # Lattice AI Trust Model
 
-Current release: **10.3.0 — Measured Ground**.
+Current release: **10.5.0 — Everyday Words**.
 
 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: **10.3.0 — Measured Ground**.
+Current release: **10.5.0 — Everyday Words**.
 
 **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: **10.3.0 — Measured Ground**.
+Current release: **10.5.0 — Everyday Words**.
 
 명세 출처: `lattice_ai_full_spec.pptx` 슬라이드 20·21·22
 구현: `lattice_brain/graph/schema.py`

package/lattice_brain/__init__.py

@@ -26,7 +26,7 @@ from .storage import (
     storage_from_env,
 )
 
-__version__ = "10.3.0"
+__version__ = "10.5.0"
 
 __all__ = [
     "AgentRuntime",