ltcai 9.9.2 → 9.9.4

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)
 
-![v9.9.2 Living Brain walkthrough](output/release/v9.9.2/gifs/v9.9.2-living-brain-walkthrough.gif)
+![v9.9.4 Living Brain walkthrough](output/release/v9.9.4/gifs/v9.9.4-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/v9.9.2/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v9.9.2/screenshots/05-memory-graph.png) |
-| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v9.9.2/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v9.9.2/screenshots/12-review-center.png) |
-| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v9.9.2/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v9.9.2/screenshots/10-admin-console.png) |
+| **Chat with a Brain that remembers** — every conversation grows durable, source-linked memory ![Brain Chat](output/release/v9.9.4/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v9.9.4/screenshots/05-memory-graph.png) |
+| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v9.9.4/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v9.9.4/screenshots/12-review-center.png) |
+| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v9.9.4/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v9.9.4/screenshots/10-admin-console.png) |
 
 ## Why Lattice AI
 
@@ -57,49 +57,52 @@ First-run flow — wake the Brain, pick the owner, load a recommended model:
 
 | | | |
 | --- | --- | --- |
-| ![Login](output/release/v9.9.2/screenshots/01-login.png) | ![Model install](output/release/v9.9.2/screenshots/03-install-load-progress.png) | ![Model library](output/release/v9.9.2/screenshots/07-model-library.png) |
+| ![Login](output/release/v9.9.4/screenshots/01-login.png) | ![Model install](output/release/v9.9.4/screenshots/03-install-load-progress.png) | ![Model library](output/release/v9.9.4/screenshots/07-model-library.png) |
 
 Screenshot index and capture notes:
-[output/release/v9.9.2/SCREENSHOT_INDEX.md](output/release/v9.9.2/SCREENSHOT_INDEX.md)
+[output/release/v9.9.4/SCREENSHOT_INDEX.md](output/release/v9.9.4/SCREENSHOT_INDEX.md)
 
 ## Current Release
 
-The current release is **9.9.2 — Artifact Trust**:
-
-- **A clean core.** The historical repo-root compatibility shims are gone
-  (only `server.py` remains for `uvicorn server:app`); packaging ships exactly
-  the `latticeai.*` / `lattice_brain.*` packages, and a legacy debt gate in
-  `npm run lint` plus a dedicated test suite keep the root clean for good.
-- **Your first five minutes matter.** A guided "First 5 minutes" card on the
-  empty Brain home walks a new user through asking a first question, adding a
-  first file or note, and seeing what the Brain learned — wired to real
-  features, with progress that persists and a briefing that loads immediately.
-- **Proactive intelligence you can actually see.** Today's briefing now lives
-  on the Brain home instead of a double-collapsed drawer, and Cmd+K opens with
-  proactive quick actions (open briefing, review pending items, ask the Brain)
-  before you type a single letter.
-- **Review Center at product quality.** Proposal cards translate risk and
-  change class into human language, frame diffs with file targets and honest
-  truncation counts, tuck raw IDs into a "Technical details" disclosure, and
-  every approve/reject failure shows a friendly message first.
-- **Errors that speak your language.** The API error pipeline is localized
-  (ko/en): timeouts, unreachable-service, and backend failures produce plain,
-  helpful copy instead of raw `statusText` or English literals, across chat,
-  admin, care, and intelligence panels.
-- **Scenario-first tests, smaller evidence footprint.** 37 version-named test
-  files were renamed to behavior-named suites, and `output/release/` now keeps
-  only the newest three evidence sets (~70MB reclaimed) via an automated
-  retention policy.
+The current release is **9.9.4 — Durable Loops**:
+
+- **Loops that survive restarts.** Paused `awaiting_approval` runs are
+  persisted to disk (hashed tokens, wall-clock expiry) and resume after a
+  server restart; expired approvals answer with a one-click replan hint, and
+  `GET /agent/approvals` re-surfaces pending runs. Approval cards show a live
+  TTL countdown.
+- **You can watch the loop work.** Streamed agent runs emit named
+  `agent_step` SSE events (plan → tools → verify → terminal) rendered as a
+  live step timeline; weak-model parse repairs are counted and surfaced
+  honestly ("모델 응답을 N회 보정했어요").
+- **One retrieval policy.** A single `RetrievalPolicy` module (rule-based
+  query rewrite, query-class weights, 14-day recency age-decay in a
+  [0.5, 1.0] band) feeds both the service and graph fusion layers, gated by
+  the benchmark CI test; embedder swaps now report `stale_embedder` instead
+  of silently emptying the vector channel.
+- **Retrieval quality at the chunk level.** Markdown chunks at heading
+  boundaries (with `heading_path` provenance), code at function boundaries,
+  PDF chunks carry page numbers, plain text stays byte-identical — and
+  cited source cards click through to the stored chunk text.
+- **Grounded answers, cited sources.** When retrieved context exists the
+  answer prompt instructs [1]-style citations; a synthetic grounding bench
+  gates the verdict heuristic in CI; briefings suggest periodic graph noise
+  curation, and an opt-in review mode stages curator promotions for human
+  approval.
+- **A wider harness.** Manifest-aware plan rewriting plus React/Vite and
+  Python-package manifests, a bounded executor context window, five
+  deterministic workflow scenarios, a funnel soft gate, and a weekly
+  fail-open real-model agent smoke with a report artifact.
 
 Release notes: [RELEASE.md](RELEASE.md) · Full history: [docs/CHANGELOG.md](docs/CHANGELOG.md)
 
-Expected artifacts for 9.9.2 release must use exact filenames:
+Expected artifacts for 9.9.4 release must use exact filenames:
 
-- `dist/ltcai-9.9.2-py3-none-any.whl`
-- `dist/ltcai-9.9.2.tar.gz`
-- `ltcai-9.9.2.tgz`
-- `dist/ltcai-9.9.2.vsix`
-- `src-tauri/target/release/bundle/dmg/Lattice AI_9.9.2_aarch64.dmg`
+- `dist/ltcai-9.9.4-py3-none-any.whl`
+- `dist/ltcai-9.9.4.tar.gz`
+- `ltcai-9.9.4.tgz`
+- `dist/ltcai-9.9.4.vsix`
+- `src-tauri/target/release/bundle/dmg/Lattice AI_9.9.4_aarch64.dmg`
 
 Do not use wildcard artifact uploads. Package registry publishing remains owner-run.
 
@@ -119,7 +122,7 @@ 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 9.9.2.
+  live local Brain store in 9.9.4.
 - 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
@@ -131,6 +134,8 @@ See [ARCHITECTURE.md](ARCHITECTURE.md) for details and
 
 | Version | Theme |
 | --- | --- |
+| 9.9.4 | Durable Loops |
+| 9.9.3 | Closed Loops |
 | 9.9.2 | Artifact Trust |
 | 9.9.1 | Clean Foundations |
 | 9.9.0 | Fail-Closed Trust |

package/docs/CHANGELOG.md

@@ -4,6 +4,115 @@ 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.
 
+## [9.9.4] - 2026-07-26
+
+### Added
+- Durable approval/run store (`latticeai/core/run_store.py`): paused
+  `awaiting_approval` runs are mirrored to `data/agent_runs/` (one JSON file
+  per run, SHA-256 token hashes, wall-clock expiry) and resume across server
+  restarts; expired resumes answer 410 with a one-click replan hint;
+  `GET /agent/approvals` lists pending runs (memory ∪ disk).
+- Single retrieval policy (`lattice_brain/graph/retrieval_policy.py`):
+  rule-based query rewrite (env kill-switch `LATTICEAI_QUERY_REWRITE=0`),
+  query-class fusion weights, and a 14-day recency half-life consumed by both
+  the 3-channel service fusion and the 2-channel graph fusion; responses
+  carry `policy {search_query, rewrite_rules}` and recency-class matches a
+  `scores.age_decay` multiplier in the [0.5, 1.0] band.
+- Live agent step streaming: `AgentDeps.on_step` / per-run `ctx.on_step`
+  observers emit plan/approval/execute/verify/rollback/terminal events;
+  streamed agent chats send named `event: agent_step` SSE frames
+  (`agent_live_stream`) before the unchanged final payload frames; the UI
+  renders a live step timeline with a collapsed post-run summary.
+- Type-aware chunking: markdown chunks at heading boundaries with
+  `heading_path` provenance, code chunks at function/blank-line boundaries,
+  plain text byte-identical to the legacy chunker (same chunk ids); every
+  chunk records `strategy` + `start_char`; PDF chunks carry a 1-based `page`
+  derived from per-page extraction offsets (omitted when implausible).
+- Embedder fingerprint: the vector index records the embedder model id +
+  dimension; a swap surfaces `stale_embedder` in `index_status().embedder`,
+  vector freshness, and hybrid `vector_degraded` instead of silently empty
+  vector channels.
+- Citation-instructed answers: one `_compose_system` helper (all four prompt
+  paths) appends `CITATION_INSTRUCTION` whenever retrieved context exists; a
+  deterministic synthetic grounding bench gates `assess_answer_grounding`
+  verdict accuracy in CI.
+- Graph hygiene cadence: Command Center briefing gains a `hygiene` section +
+  one-click dry-run quick action suggesting `/knowledge-graph/curate/noise`
+  when the graph exceeds 200 nodes and no curation ran in 7 days
+  (`last_noise_curate_at` in graph_meta).
+- Review-before-promote: `LATTICEAI_GRAPH_PROMOTION_REVIEW=1` (or the
+  `GRAPH_PROMOTION_REVIEW` enterprise capability) stages curator topic
+  promotions as `pending_promotions` instead of writing them;
+  `GET /knowledge-graph/promotions` + `apply`/`reject` endpoints.
+- Project manifests beyond web: React/Vite starter (package.json, module-entry
+  index.html, src/main.jsx, src/App.jsx, src/App.css) and Python package
+  (`pkg/__init__.py`, `core.py`, `cli.py`, README.md); `normalize_plan`
+  rewrites empty/partial pure-file plans to the manifest
+  (`manifest_steps`/`manifest_rewrite` plan fixes).
+- Harness: five deterministic workflow/multi-agent scenarios;
+  `scripts/funnel_soft_gate.py` (advisory code_only/needs_review thresholds,
+  `--strict` opt-in); `approval_pauses`/`approval_resumes` counters +
+  `approval_resume_rate`; `scripts/bench_agent_smoke.py` weekly fail-open
+  real-model agent smoke + `agent-smoke.yml` workflow (report artifact, never
+  a gate).
+- Frontend: agent step timeline, source-card → stored-chunk modal, folder
+  watch health card, approval TTL countdown with expiry replan, generated-file
+  "remembered in Brain" chips, demo-corpus → "connect your own data" CTA,
+  parse-repair count note — all ko/en parity and bundle-budget clean.
+- `docs/SURFACE_PARITY.md`: per-surface capability matrix with honest gaps.
+
+### Changed
+- Executor prompts use a sliding transcript window (recent 8 steps full,
+  older steps one-line summaries, per-string truncation caps, last 3
+  corrections); the critic sees every step with capped string bodies
+  (`TranscriptBudget`, `LATTICEAI_AGENT_TRANSCRIPT_*`).
+- Agent memory learnings now record the actual terminal status (ok /
+  needs_review / failed) and prompt for what-went-wrong on non-DONE runs.
+
+## [9.9.3] - 2026-07-22
+
+### Added
+- Multi-file Artifact Loop: `infer_project_manifest` → per-file
+  generate/validate → cross-file reference repair → bundle validation →
+  `artifacts[]` + `project.zip_url`; safe `GET /tools/download_zip`.
+- Interactive approval: governed plans pause as `awaiting_approval` with a
+  single-use 10-minute token; `POST /agent/resume` approves, edits, or
+  cancels. Inline approval card in chat.
+- First Value Loop: `POST/GET/DELETE /api/setup/demo-corpus` (3 built-in demo
+  documents, `demo://` provenance, idempotent) + the "30초 체험" home track
+  with suggested-question chips.
+- Answer grounding: `grounding {status, source_ids, overlap}` on chat
+  responses; 근거 있음/근거 없음 badge.
+- Retrieval fusion: query-class detection (fact/code/person/recency) with
+  per-class channel weights and a benchmark-threshold CI gate
+  (`tests/unit/test_retrieval_fusion_gate.py`).
+- Opt-in folder watch (`/api/ingestion/watch`, polling + persisted consent),
+  capture-quality CTA (`capture_quality` on browser captures), graph noise
+  curation job (`POST /knowledge-graph/curate/noise`, dry-run default).
+- Automation visibility: `POST /api/automation/run-now` (dry-run-first),
+  `last_execution` on overview/briefing, failed runs → Review queue; Act-panel
+  "지금 한 번 실행" cards.
+- UX: inline file preview (sandboxed iframe / modal), folder job report card,
+  global drag-and-drop capture, 409 proposal rebase flow, focus traps, graph
+  keyboard navigation, reduced-motion coverage, success pulse / inflow motes.
+- Harness: agent_eval 23 scenarios (dirty-write filegen paths), golden
+  sanitize fixtures, `bench_models.py --filegen` (fail-open), deterministic
+  knowledge-pipeline E2E test, funnel metrics
+  (`GET /api/admin/funnel-metrics`), `PhaseBudgets` per-phase token caps,
+  `.ts/.tsx/.jsx/.vue/.svelte` filegen validation and Python `ast.parse`.
+
+### Changed
+- Approval-requiring agent runs return `awaiting_approval` instead of FAILED;
+  legacy `context_id` resume with `approved: true` now executes the gated
+  steps.
+- Hybrid search responses expose `query_class`; chat responses expose
+  `grounding`; automation overview exposes `last_execution`.
+
+### Fixed
+- Fenced/chatty CSS is now sanitized before write (`.css` validation rejects
+  Markdown fences) — caught by the new golden fixtures.
+- A legacy approved resume no longer re-fails at the approval gate.
+
 ## [9.9.2] - 2026-07-21
 
 ### Added

package/docs/COMMUNITY_AND_PLUGINS.md

@@ -1,6 +1,6 @@
 # Community And Plugins
 
-Current release: **9.9.2 — Artifact Trust**.
+Current release: **9.9.4 — Durable Loops**.
 
 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: **9.9.2 — Artifact Trust**.
+Current release: **9.9.4 — Durable Loops**.
 
 This document is for contributors working on the local-first Digital Brain
 codebase. Product positioning and quick start stay in `README.md`; release

package/docs/ONBOARDING.md

@@ -1,6 +1,6 @@
 # Lattice AI Onboarding
 
-Current release: **9.9.2 — Artifact Trust**.
+Current release: **9.9.4 — Durable Loops**.
 
 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 (v9.9.2)
+# Lattice AI — Operations Guide (v9.9.4)
 
 > **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/SURFACE_PARITY.md

@@ -0,0 +1,47 @@
+# Lattice AI — Surface Parity Matrix
+
+> **Status: reference**
+> 도입: v9.9.4 (2026-07-25, 리뷰 Wave 1.4 "표면 패리티 체크리스트").
+> 목적: 각 표면(서피스)이 Brain 계약의 어디까지를 제공하는지 **정직하게** 기록한다.
+> "앱마다 다른 Lattice"를 방지하는 기준표이며, 기능을 과장하지 않는다.
+
+## 표면 정의
+
+| 표면 | 진입점 | 성격 |
+| --- | --- | --- |
+| Web `/app` | FastAPI sidecar가 서빙하는 SPA (`static/app`) | 1차 표면 — 모든 기능의 기준 |
+| Desktop | Tauri 셸 (`src-tauri/`) | 동일 SPA를 감싸는 셸 — 웹과 구조적 동일 |
+| VS Code | `vscode-extension/` (`ltcai.*` 커맨드) | 에디터 보조 표면 |
+| Browser | `browser-extension/` (Send to Lattice) | 캡처 전용 표면 |
+| Telegram | 봇 어댑터 | 대화 전용 표면 |
+
+## 네 가지 루프 순간 × 표면
+
+✅ 제공 · ◐ 부분 제공 · — 미제공(의도) · ✖ 갭(백로그)
+
+| 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 회상 (Recall) | ✅ 하이브리드 검색 + grounding 배지 + 출처→청크 | ✅ (동일) | ◐ `askCurrentFile` — 배지 없음 ✖ | — | ◐ 답변만, 배지 없음 |
+| 첫 산출물 (Artifact) | ✅ artifacts[] 카드·미리보기·Brain 기억 칩 | ✅ (동일) | ◐ `createFile` — 검증 파이프라인 경유, 카드 UI 없음 | — | ◐ 파일 전송만 |
+| 첫 보호 (Approval) | ✅ 승인 카드 + TTL 카운트다운 + 재시작 생존 | ✅ (동일) | ✖ 승인 UI 없음 — 웹으로 유도 | — | ✖ 승인 불가 — 웹으로 유도 |
+
+## 기능 상세 × 표면
+
+| 기능 | Web `/app` | Desktop | VS Code | Browser | Telegram |
+| --- | --- | --- | --- | --- | --- |
+| 에이전트 스텝 타임라인 (v9.9.4) | ✅ 라이브 SSE | ✅ | — | — | — |
+| 승인 재개 (`/agent/resume`) | ✅ | ✅ | ✖ | — | ✖ |
+| 대기 중 승인 목록 (`GET /agent/approvals`, v9.9.4) | ✅ | ✅ | ✖ | — | — |
+| Watch 상태 신호 (v9.9.4) | ✅ 홈 카드 | ✅ | — | — | — |
+| Review Center (제안 승인/거절) | ✅ | ✅ | ✖ | — | — |
+| 데모 코퍼스 First Value Loop | ✅ | ✅ | — | — | — |
+| 모델 로드/추천 | ✅ | ✅ | ◐ `loadModel` | — | — |
+| 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.** 현재 갭: VS Code/Telegram 승인 흐름(웹으로 유도하는 안내만 존재), VS Code 회상 배지.
+4. 릴리스마다 이 표를 검토한다 (release checklist의 docs 단계).

package/docs/TRUST_MODEL.md

@@ -1,6 +1,6 @@
 # Lattice AI Trust Model
 
-Current release: **9.9.2 — Artifact Trust**.
+Current release: **9.9.4 — Durable Loops**.
 
 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: **9.9.2 — Artifact Trust**.
+Current release: **9.9.4 — Durable Loops**.
 
 **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: **9.9.2 — Artifact Trust**.
+Current release: **9.9.4 — Durable Loops**.
 
 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__ = "9.9.2"
+__version__ = "9.9.4"
 
 __all__ = [
     "AgentRuntime",