ltcai 10.0.0 → 10.3.0

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)
 
-![v10.0.0 Living Brain walkthrough](output/release/v10.0.0/gifs/v10.0.0-living-brain-walkthrough.gif)
+![v10.3.0 Living Brain walkthrough](output/release/v10.3.0/gifs/v10.3.0-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 +24,9 @@ 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/v10.0.0/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v10.0.0/screenshots/05-memory-graph.png) |
-| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v10.0.0/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v10.0.0/screenshots/12-review-center.png) |
-| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v10.0.0/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v10.0.0/screenshots/10-admin-console.png) |
+| **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) |
 
 ## Why Lattice AI
 
@@ -57,41 +57,47 @@ First-run flow — wake the Brain, pick the owner, load a recommended model:
 
 | | | |
 | --- | --- | --- |
-| ![Login](output/release/v10.0.0/screenshots/01-login.png) | ![Model install](output/release/v10.0.0/screenshots/03-install-load-progress.png) | ![Model library](output/release/v10.0.0/screenshots/07-model-library.png) |
+| ![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) |
 
 Screenshot index and capture notes:
-[output/release/v10.0.0/SCREENSHOT_INDEX.md](output/release/v10.0.0/SCREENSHOT_INDEX.md)
+[output/release/v10.3.0/SCREENSHOT_INDEX.md](output/release/v10.3.0/SCREENSHOT_INDEX.md)
 
 ## Current Release
 
-The current release is **10.0.0 — Plain Language**:
-
-- **The first screen is four things.** Your Brain, one input box, the autonomy
-  dial, and the capture controls — file, folder, note, web — now sit inside the
-  composer instead of a separate panel. The knowledge graph opens by clicking
-  the Brain, so the home shows no diagram at all.
-- **Korean and English, everywhere.** A language switch sits in the top bar on
-  every screen, and the interface is fully translated in both directions:
-  memory tiers, agent roles, automation recipes, entity types, and every
-  backend payload label read in the language you picked.
-- **Numbers say what they counted.** "출처 반영률 12%" is now "출처가 남은
-  기억 · 35 / 291개" with the sentence that explains it. Model names read
-  "Gemma 4 26B A4B Instruct", never `mlx-community/gemma-4-26b-a4b-it-4bit`.
-- **Defects found by using it with a model loaded.** The conversation header
-  Brain rendered at 311px and covered 46% of the viewport; the sticky composer
-  hid the end of every answer; a nested payload printed its field names where
-  its values belonged; the folder button never opened a picker in a browser.
-  All fixed, each with a test.
+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.
 
 Release notes: [RELEASE.md](RELEASE.md) · Full history: [docs/CHANGELOG.md](docs/CHANGELOG.md)
 
-Expected artifacts for 10.0.0 release must use exact filenames:
+Expected artifacts for 10.3.0 release must use exact filenames:
 
-- `dist/ltcai-10.0.0-py3-none-any.whl`
-- `dist/ltcai-10.0.0.tar.gz`
-- `ltcai-10.0.0.tgz`
-- `dist/ltcai-10.0.0.vsix`
-- `src-tauri/target/release/bundle/dmg/Lattice AI_10.0.0_aarch64.dmg`
+- `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`
 
 Do not use wildcard artifact uploads. Package registry publishing remains owner-run.
 
@@ -111,7 +117,7 @@ See [ARCHITECTURE.md](ARCHITECTURE.md) for details and
 
 - External package registries are owner-published and can lag behind GitHub.
 - PostgreSQL/pgvector is optional scale/migration tooling. SQLite remains the
-  live local Brain store in 10.0.0.
+  live local Brain store in 10.3.0.
 - Docker, model downloads, cloud model calls, Telegram, Brain Network, and
   update checks require explicit user action.
 - Conversation does not fabricate answers when no model is loaded. Agent and
@@ -120,12 +126,17 @@ See [ARCHITECTURE.md](ARCHITECTURE.md) for details and
   model success.
 - Some backend-generated messages (for example the Postgres DSN notice) are
   produced server-side in English and are shown as-is; server-side i18n is not
-  part of 10.0.0.
+  part of 10.3.0.
 
 ## Release History
 
 | Version | Theme |
 | --- | --- |
+| 10.3.0 | Measured Ground |
+| 10.2.0 | Load-Bearing Fixes |
+| 10.1.1 | Reachable Boundary |
+| 10.1.0 | Hybrid Brain |
+| 10.0.1 | One Source of Truth |
 | 10.0.0 | Plain Language |
 | 9.9.9 | Lean Shell |
 | 9.9.8 | Autonomy Dial |

package/docs/CHANGELOG.md

@@ -4,6 +4,210 @@ 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.
 
+## [10.3.0] - 2026-07-29
+
+### Fixed
+- **Frontend coverage was not being measured.** Vitest reports only files a
+  test imports unless `all: true`; untested modules left the denominator
+  instead of counting against it. Reported 54%, actual **28.5%**.
+- **Python coverage was over-reported.** `omit = ["*/tests/*"]` does not match
+  the repo-relative `tests/...` paths coverage records, so the suite counted
+  itself. Reported 80%, actual **71.6%**.
+- `lattice_brain/runtime/hooks.py` referenced `self._path` (does not exist)
+  inside the handler for an unreadable registry, turning a recoverable failure
+  into `AttributeError`.
+- `lattice_brain/graph/_kg_fsutil.py` used `Iterable` in an annotation without
+  importing it.
+- `lattice_brain/runtime/agent_runtime.py` could call `.get` on `None`.
+- `pages/Library.tsx` printed the raw registry coordinate
+  (`mlx-community/gemma-4-…`) when a catalog entry had no display name; it now
+  falls through `humanizeModelId` like every other model surface.
+
+### Added
+- `latticeai/runtime/history_writer.py` — `save_to_history` extracted from the
+  `app_factory._build` closure with its ordering contract documented, plus 14
+  tests (`tests/unit/test_history_writer.py`).
+- `frontend/src/test/renderPage.tsx` — a page-level harness that stubs the
+  whole `latticeApi` surface, making error states, empty states and both
+  languages reachable in unit tests.
+- First unit tests for every page: `System` (11), `Library` (7), `Capture` (6),
+  `Act` (8), `Brain` (8). Frontend suite 154 → 208 tests.
+- Python tests for boundaries that had none: Telegram allowlist (26),
+  `run_command` containment (34), audit log and sensitivity report (22),
+  model-load consent gates (14), connection lifecycle guards. 1,786 → 1,896.
+- `docs/MYPY_BACKLOG.md` — the 77 modules still outside type checking with
+  per-module error counts, smallest first.
+- ARCHITECTURE.md "Verification Surface" diagram: which figures gate CI and
+  which are only reported.
+
+### Changed
+- mypy adopted set: 13 → **193 of 270** modules.
+- `vitest.config.ts` gains a coverage block with `all: true`.
+- `npm run test:frontend:coverage` added.
+
+### Known
+- `app_factory._build` remains ~1,300 lines; only the history writer was
+  extracted this release.
+- Frontend coverage (28.5%) is reported but not gated — flooring it at today's
+  figure would freeze it there.
+- 77 modules remain outside mypy; see the backlog.
+
+## [10.2.0] - 2026-07-29
+
+Response to a full code review of 10.1.1 (71/100). All twelve findings.
+
+### Fixed
+- **SQLite connections were committed but never closed** at 70+ sites.
+  `sqlite3.Connection.__exit__` commits or rolls back and leaves the connection
+  open; `KnowledgeGraphStore._connect`, `ConversationStore._connect`,
+  `WorkspaceOSStore._connect_state_db`, both storage engines, `portability`,
+  `archive`, `migration` and `users` all relied on it. Refcounting hid the leak
+  until something held a frame alive (profiler, logged traceback, coverage
+  tracer), at which point the process hit `EMFILE`. Added
+  `StorageEngine.session()` and made the store helpers closing context
+  managers; `tests/unit/test_connection_lifecycle.py` asserts it.
+- **The cloud sensitivity guard could not fire.** `HARD_BLOCK_NODE_TYPES` was
+  an empty set and nothing in the product could set the metadata flags
+  `is_node_blocked_for_cloud` matches on, so "sensitive memories are never
+  sent" was unfalsifiable. Populated the type list, added
+  `lattice_brain/sensitivity.py` (path rules, stamped at ingestion), added
+  `KnowledgeGraphStore.set_node_sensitivity` and
+  `POST /api/network-boundary/node-sensitivity`, and a per-memory hold-back
+  control in the boundary panel.
+- **Outbound cloud text was not redacted.** `redact_secret_text` ran on logs,
+  audit records and API previews but not on the payload that actually leaves.
+- **Vector similarity truncated silently on a dimension mismatch**, producing a
+  plausible but meaningless score. Now raises with both dimensions named.
+- **`tempfile.mktemp()` (TOCTOU race) in the Telegram bridge** replaced with
+  `mkstemp` at two sites.
+- **Three closures captured loop variables by reference** (`chat_agent_http`,
+  `computer_use`, `model_runtime`). Safe today because each is invoked within
+  its iteration; bound explicitly so deferring the call cannot break them.
+- **The cloud turn ran retrieval twice**, discarding the first result except
+  for its quality dict.
+
+### Added
+- `latticeai/services/cloud_egress_audit.py` — every cloud send and every
+  refusal writes an audit entry *before* the provider call, naming node ids,
+  count, token estimate, provider and mode. Shape, never content.
+- `latticeai/core/quiet.py` + `lattice_brain/quiet.py` — `quiet()` keeps the
+  behaviour of `except: pass` and records the exception with its file,
+  function and line at DEBUG. 112 handlers converted; `except: pass` is now a
+  lint error (S110/S112).
+- Coverage measurement: `pytest-cov` in the `dev` extra, `[tool.coverage]`
+  config, a **70% floor** in CI. Measured **71%** — the first known figure.
+- `tests/unit/test_cloud_egress_guard.py` — end-to-end proof that a flagged
+  memory never reaches the payload, that retrieval still carries `metadata`
+  (whose loss would silently disable the filter), and that egress is audited.
+- mypy over 13 trust-critical modules (`npm run typecheck:python`), wired into
+  `npm run lint:python`.
+- CI matrix: macOS runner (the platform the `.dmg` ships for, previously
+  untested) and Python 3.14 (the version this is developed on).
+
+### Changed
+- ruff widened from pyflakes-only to `E4,E7,E9,F,B,S,I,SIM,RET,C901`. Every
+  remaining finding is either fixed or carries a written reason; complexity
+  ceiling set to 30 with named exemptions.
+- `latticeai/core/workspace_os.py` 1354 → 1130 lines; vocabulary moved to
+  `workspace_os_constants.py` and state/migration to `workspace_os_state.py`,
+  with delegating methods so the public surface is unchanged.
+- Package classifiers now advertise Python 3.13 and 3.14, matching what CI tests.
+
+### Known
+- `app_factory._build` remains one 1,343-line function. Its sections share ~34
+  local bindings, so decomposition requires a runtime-context object rather
+  than a mechanical extraction; deferred rather than rushed, and named in the
+  C901 exemptions so the choice is visible.
+
+## [10.1.1] - 2026-07-28
+
+### Added
+- `NetworkBoundaryPanel` (`frontend/src/components/NetworkBoundaryPanel.tsx`),
+  mounted in the System settings tab beside `PermissionModePanel`. Renders the
+  server's mode catalog, gates `cloud_allowed` behind the acknowledgement the
+  server requires, and exposes the hybrid write-back policy switches only while
+  the boundary permits cloud.
+- Context preview in that panel: a question is sent to
+  `POST /api/network-boundary/preview` and the panel lists the actual node
+  titles that would leave, the token estimate, and the token guard's verdict.
+  Available in `local_only` too, labelled as hypothetical.
+- API client bindings and types: `networkBoundary`, `setNetworkBoundary`,
+  `setHybridPolicy`, `previewCloudContext`; `NetworkBoundaryOption`,
+  `NetworkBoundaryState`, `HybridPolicy`, `CloudContextPreview`,
+  `CloudTokenBudget`. The `networkBoundary` fallback is `local_only`, so a
+  failed read never renders as if cloud were already permitted.
+- 22 `system.network.*` copy keys in the `workspace` i18n namespace (ko + en).
+- `/api/network-boundary*` routes in `tests/visual/mock_server.cjs` so release
+  evidence shows the panel working rather than an unavailable state.
+- `NetworkBoundaryPanel.test.tsx` (12 tests) and two Playwright specs covering
+  the settings-tab route, the acknowledgement gate, and the preview.
+
+### Removed
+- `static/app/network-boundary-panel.js` — the unmounted standalone module
+  10.1.0 shipped as this feature's UI. Nothing referenced it, it was absent
+  from the asset manifest, and it lived in Vite's output directory, which
+  `npm run build:assets` wipes; it had in fact already been deleted by the
+  previous release's asset rebuild. The React panel replaces it.
+
+### Changed
+- ARCHITECTURE, FEATURE_STATUS, README, and the hybrid design doc no longer
+  carry the "API-only surface" caveat, and describe the in-app control instead.
+
+## [10.1.0] - 2026-07-28
+
+### Added
+- Local-first hybrid path: the Knowledge Graph stays on-device and cloud LLMs
+  are an opt-in worker. `NetworkBoundaryMode` and `MinimalContext` contracts
+  (`latticeai/core/network_boundary.py`, `latticeai/api/network_boundary.py`)
+  with a persisted dial wired via `latticeai/runtime/network_boundary_wiring.py`.
+- Cloud streaming worker: `latticeai/services/cloud_streaming.py`,
+  `cloud_extraction.py`, `cloud_token_guard.py`, and an OpenAI-compatible stream
+  adapter (`openai_compatible_adapter.py`) with token budgets and guardrails.
+- Hybrid chat pipeline: `latticeai/api/chat_hybrid.py` plus
+  `services/hybrid_chat.py`, `hybrid_context.py`, and `hybrid_policy.py`; the
+  `/chat` route branches through it and writes back through the Review Queue.
+- Multimodal streaming contracts (`services/multimodal_streaming.py`) and a
+  network-boundary control panel (`static/app/network-boundary-panel.js`).
+- Tests: `test_network_boundary.py`, `test_hybrid_phase2.py`,
+  `test_hybrid_phase3.py`.
+
+### Notes
+- Default network boundary is `local_only`; cloud requires explicit
+  acknowledgement. Minimal related nodes only leave the machine; streamed
+  answers expand the local Brain with provenance.
+
+## [10.0.1] - 2026-07-28
+
+### Changed
+- `latticeai/core/agent.py` holds only the state machine (1769 → 1326 lines).
+  Its pure functions move to `latticeai/core/agent_helpers.py`: action parsing
+  (`extract_action`, `extract_action_details`), plan normalization
+  (`normalize_plan`), learning filters, transcript compaction, artifact and
+  requirement reporting, and the `TranscriptBudget` / `PhaseBudgets` dataclasses.
+- `AgentState` and `AGENT_TERMINAL_STATES` move to a new
+  `latticeai/core/agent_state.py`. Both `agent.py` and `agent_helpers.py` import
+  from it, which is what lets the helpers reference the enum instead of a
+  literal state string.
+- `latticeai.core.agent` re-exports every moved name as the same object and
+  declares the set in `__all__`. No caller changed: the HTTP layer, `run_store`,
+  `computer_use`, `bench_agent_smoke`, `bench_models`, and eight test modules
+  import exactly as before.
+- The home's secondary control row is visually demoted (opacity, tighter gaps,
+  softer divider) and gets larger touch spacing under 640px. The sticky top bar
+  border is softened. CSS only.
+
+### Fixed
+- `files_written` and `artifact_checklist` matched transcript steps against the
+  literal `"EXECUTING"` instead of `AgentState.EXECUTING.value`. A rename of the
+  enum value would have made both silently return empty results with no failing
+  test. Both now reference the enum.
+
+### Verification
+- pytest 1747 passed / 11 skipped; `scripts/agent_eval.py` 23/23 (100%); ruff
+  clean across `latticeai/`, `lattice_brain/`, `scripts/`, `tests/`.
+- All 18 extracted symbols were AST-compared against their originals before the
+  originals were removed.
+
 ## [10.0.0] - 2026-07-28
 
 ### Changed

package/docs/COMMUNITY_AND_PLUGINS.md

@@ -1,6 +1,6 @@
 # Community And Plugins
 
-Current release: **10.0.0 — Plain Language**.
+Current release: **10.3.0 — Measured Ground**.
 
 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: **10.0.0 — Plain Language**.
+Current release: **10.3.0 — Measured Ground**.
 
 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/HYBRID_CLOUD_KG_STREAMING.md

@@ -0,0 +1,101 @@
+# Hybrid Cloud + Local Knowledge Graph Streaming
+
+> Status: **shipped in 10.1.0**; in-app control added in **10.1.1**  
+> Principle: **Local Brain is the asset. Cloud is an opt-in worker.**  
+> Surface: `환경설정 → 내 지식이 나가는 범위`
+> (`frontend/src/components/NetworkBoundaryPanel.tsx`), plus
+> `/api/network-boundary` and `LATTICEAI_NETWORK_MODE`.
+
+## Goal
+
+Local Knowledge Graph stays on-device. Cloud LLMs (and optional multimodal) are opt-in workers. Minimal related nodes leave the machine; streamed answers expand the local Brain with provenance and review gates.
+
+## Phase summary
+
+| Phase | Branch | Delivered |
+|-------|--------|-----------|
+| 0 | `feature/hybrid-cloud-kg-streaming` | Architecture + core contracts |
+| 1 | `…-phase1` | Dial, OpenAI adapter, hybrid helpers, basic expansion |
+| 2 | `…-phase2` | `/chat` branch, token guardrails, extraction, preview API |
+| **3** | `…-phase3` | **Policy, Review Queue write path, multimodal contracts, UI panel module** |
+
+## Phase 3 details
+
+### Hybrid policy (`HybridPolicyService`)
+Persisted dial for:
+- `blocked_node_types` / `blocked_metadata_flags` (unioned with hard circuit breakers)
+- `auto_commit` (default **false**)
+- `allow_multimodal` (default **false**)
+- `min_extraction_confidence`
+
+API:
+```
+GET  /api/network-boundary/policy
+POST /api/network-boundary/policy
+     { "auto_commit": false, "allow_multimodal": false, "blocked_node_types": ["Secret"] }
+```
+
+### Review Queue write path
+`CloudResponseIngestor` now:
+1. Always enqueues a `change_proposal` review item when a ReviewQueueService is bound
+2. Only auto-writes to the graph when `plan.auto_commit` is true **and** a store write API exists
+
+Users approve cloud-derived memory growth in the existing Review Center.
+
+### Multimodal / video
+`latticeai/services/multimodal_streaming.py`:
+- Same `NetworkBoundaryMode.CLOUD_ALLOWED` gate
+- Additional `allow_multimodal` policy flag
+- Adapter protocol for future Runway/Luma/Veo-compatible providers
+
+### UI
+`NetworkBoundaryPanel` (React) + `GET /api/network-boundary/ui-state`:
+- Toggle local ↔ cloud (with ack)
+- Transparency preview of nodes about to be sent
+- Shows current policy flags
+
+Mounted in `frontend/src/pages/System.tsx` beside `PermissionModePanel`, so it
+appears on the settings tab of every install. The standalone
+`static/app/network-boundary-panel.js` module 10.1.0 shipped was removed in
+10.1.1: nothing mounted it, and it lived in Vite's build output directory,
+which `npm run build:assets` wipes.
+
+## End-to-end flow (Phase 3)
+
+```
+User toggles cloud_allowed (UI panel or API)
+    → optional policy: auto_commit / multimodal / sensitivity
+User sends chat message
+    → /chat resolves mode
+    → if cloud_allowed: minimal KG context + token budget check
+    → cloud stream (SSE)
+    → rich extraction (Decision/Task/Concept)
+    → Review Queue item (change_proposal)
+    → optional auto-commit when policy allows
+```
+
+## Configuration
+
+```bash
+export LATTICEAI_CLOUD_API_KEY=sk-...
+export LATTICEAI_CLOUD_MODEL=gpt-4o-mini
+export LATTICEAI_NETWORK_MODE=local_only
+export LATTICEAI_CLOUD_MAX_TOKENS_PER_TURN=2500
+export LATTICEAI_CLOUD_MAX_TOKENS_PER_SESSION=50000
+```
+
+## Privacy (unchanged core rules)
+
+1. Default `local_only`
+2. Cloud requires explicit ack
+3. Only minimal compact context leaves the host
+4. Hard + user sensitivity filters
+5. Cloud-derived nodes go through Review Queue unless user opts into auto_commit
+6. Multimodal is off unless policy explicitly enables it
+
+## Success criteria (Phase 3)
+
+- User can configure sensitivity and auto-commit without code changes
+- Cloud KG growth appears in Review Center as actionable proposals
+- Multimodal path cannot fire without both cloud mode and policy flag
+- UI panel works without rebuilding the main React bundle

package/docs/MYPY_BACKLOG.md

@@ -0,0 +1,98 @@
+# 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.
+
+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.
+
+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.
+
+| 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 |
+
+Total outstanding: **1407** errors across **77** modules.

package/docs/ONBOARDING.md

@@ -1,6 +1,6 @@
 # Lattice AI Onboarding
 
-Current release: **10.0.0 — Plain Language**.
+Current release: **10.3.0 — Measured Ground**.
 
 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 (v10.0.0)
+# Lattice AI — Operations Guide (v10.3.0)
 
 > **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/TRUST_MODEL.md

@@ -1,6 +1,6 @@
 # Lattice AI Trust Model
 
-Current release: **10.0.0 — Plain Language**.
+Current release: **10.3.0 — Measured Ground**.
 
 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: **10.0.0 — Plain Language**.
+Current release: **10.3.0 — Measured Ground**.
 
 **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: **10.0.0 — Plain Language**.
+Current release: **10.3.0 — Measured Ground**.
 
 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__ = "10.0.0"
+__version__ = "10.3.0"
 
 __all__ = [
     "AgentRuntime",

package/lattice_brain/archive.py

@@ -16,17 +16,18 @@ import shutil
 import sqlite3
 import tempfile
 import zipfile
+from contextlib import closing
 from dataclasses import dataclass
 from pathlib import Path, PurePosixPath
 from typing import Any, Dict, Iterable, List, Optional
 
+from cryptography.exceptions import InvalidTag
 from cryptography.hazmat.primitives import hashes
 from cryptography.hazmat.primitives.ciphers.aead import AESGCM
-from cryptography.exceptions import InvalidTag
 from cryptography.hazmat.primitives.kdf.pbkdf2 import PBKDF2HMAC
 
-from .utils import sha256_file as _sha256_file, utc_now_iso as _now
-
+from .utils import sha256_file as _sha256_file
+from .utils import utc_now_iso as _now
 
 ARCHIVE_FORMAT = "latticebrain.encrypted"
 ARCHIVE_VERSION = 2
@@ -106,7 +107,7 @@ def _checkpoint_sqlite(db_path: Path) -> None:
     if not db_path.exists():
         return
     try:
-        with sqlite3.connect(str(db_path)) as conn:
+        with closing(sqlite3.connect(str(db_path))) as conn, conn:
             conn.execute("PRAGMA wal_checkpoint(FULL)")
     except sqlite3.Error:
         return