ltcai 9.9.3 → 9.9.5

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)
 
-![v9.9.3 Living Brain walkthrough](output/release/v9.9.3/gifs/v9.9.3-living-brain-walkthrough.gif)
+![v9.9.5 Living Brain walkthrough](output/release/v9.9.5/gifs/v9.9.5-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/v9.9.3/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v9.9.3/screenshots/05-memory-graph.png) |
-| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v9.9.3/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v9.9.3/screenshots/12-review-center.png) |
-| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v9.9.3/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v9.9.3/screenshots/10-admin-console.png) |
+| **Chat with a Brain that remembers** — every conversation grows durable, source-linked memory ![Brain Chat](output/release/v9.9.5/screenshots/04-brain-chat-home.png) | **See how knowledge connects** — a real relationship graph, not a file list ![Memory Graph](output/release/v9.9.5/screenshots/05-memory-graph.png) |
+| **Capture anything** — files, whole folders, notes, screenshots, web pages ![Capture](output/release/v9.9.5/screenshots/06-capture.png) | **Automate with review** — agent changes become proposals you approve first ![Review Center](output/release/v9.9.5/screenshots/12-review-center.png) |
+| **Pick a model in one click** — recommended local models for your hardware ![Recommended Models](output/release/v9.9.5/screenshots/02-recommended-models.png) | **Stay in control** — audit, roles, retention in a separate admin surface ![Admin Console](output/release/v9.9.5/screenshots/10-admin-console.png) |
 
 ## Why Lattice AI
 
@@ -57,48 +57,47 @@ First-run flow — wake the Brain, pick the owner, load a recommended model:
 
 | | | |
 | --- | --- | --- |
-| ![Login](output/release/v9.9.3/screenshots/01-login.png) | ![Model install](output/release/v9.9.3/screenshots/03-install-load-progress.png) | ![Model library](output/release/v9.9.3/screenshots/07-model-library.png) |
+| ![Login](output/release/v9.9.5/screenshots/01-login.png) | ![Model install](output/release/v9.9.5/screenshots/03-install-load-progress.png) | ![Model library](output/release/v9.9.5/screenshots/07-model-library.png) |
 
 Screenshot index and capture notes:
-[output/release/v9.9.3/SCREENSHOT_INDEX.md](output/release/v9.9.3/SCREENSHOT_INDEX.md)
+[output/release/v9.9.5/SCREENSHOT_INDEX.md](output/release/v9.9.5/SCREENSHOT_INDEX.md)
 
 ## Current Release
 
-The current release is **9.9.3 — Closed Loops**:
-
-- **Multi-file projects, not single files.** "todo 앱 html+css+js" now infers
-  a project manifest, generates and validates every file through the same
-  sanitize pipeline, repairs cross-file references, verifies the bundle, and
-  offers a safe zip download — every file rides the `artifacts[]` contract.
-- **Approval is a conversation, not a dead end.** Runs that need human
-  approval pause as `awaiting_approval` with a plan summary and a short-TTL
-  token; an inline card lets you approve, edit the plan, or cancel — the
-  fail-closed guarantee is unchanged.
-- **First value in 30 seconds.** One click installs a 3-document demo corpus,
-  suggested questions prove recall with real sources, and answers carry an
-  honest grounding badge (근거 있음/근거 없음) bound to retrieved sources.
-- **Retrieval that knows what you asked.** Hybrid search classifies queries
-  (fact/code/person/recency) and fuses channels with per-class weights, gated
-  by a benchmark-threshold CI test; a graph noise-curation job and an opt-in
-  folder watch keep the Brain fresh and clean.
-- **Automation you can see and trust.** Per-automation "run now" with
-  dry-run-first, last execution surfaced on cards and the daily briefing,
-  failures routed to the Review queue — plus inline file previews, global
-  drag-and-drop capture, 409 conflict rebase, and a funnel-metrics endpoint.
-- **A deeper harness.** 23 agent_eval scenarios including dirty-write filegen
-  paths, golden sanitize fixtures, a multi-model filegen benchmark, a
-  deterministic knowledge-pipeline E2E test, per-phase token budgets, and
-  `.tsx/.vue/.svelte` support with `ast.parse` Python validation.
+The current release is **9.9.5 — Closed Gaps**:
+
+- **One approval path.** Legacy `human_in_loop` now rides the same durable
+  approval store as `awaiting_approval` (hashed tokens, restart-safe). The
+  old wire contract (`waiting_approval` + `context_id`) still works; the
+  separate in-memory `_pending` map is gone.
+- **Rollback that is honest.** File recovery is `git` → pre-write `snapshot`
+  → `none`, so non-git workspaces and newly created files can still be
+  restored. Each rollback entry reports its mode.
+- **Critic sees artifact truth.** Before judging file work, the critic gets a
+  deterministic checklist of written paths with sanitize/repair flags — an
+  auto-repaired scaffold cannot pass as fulfillment unchecked.
+- **Mid-run workspace awareness.** Later executor steps see files this run
+  already wrote, so multi-step "create then explain" work is not blind.
+- **Optional cross-encoder rerank.** Off by default; set
+  `LATTICEAI_CROSS_ENCODER_RERANK=1` to reorder hybrid matches (identity
+  fallback when the model is missing). Hybrid responses carry a `rerank`
+  meta block.
+- **Surface parity for approvals.** VS Code gains List/Approve/Reject
+  commands with token cache; Telegram handles both `waiting_approval` and
+  `awaiting_approval` with token-first resume.
+- **Live sidecar E2E.** Nightly Playwright first-value tests hit a real
+  FastAPI sidecar (`npm run test:e2e:sidecar`), not only the visual mock
+  server.
 
 Release notes: [RELEASE.md](RELEASE.md) · Full history: [docs/CHANGELOG.md](docs/CHANGELOG.md)
 
-Expected artifacts for 9.9.3 release must use exact filenames:
+Expected artifacts for 9.9.5 release must use exact filenames:
 
-- `dist/ltcai-9.9.3-py3-none-any.whl`
-- `dist/ltcai-9.9.3.tar.gz`
-- `ltcai-9.9.3.tgz`
-- `dist/ltcai-9.9.3.vsix`
-- `src-tauri/target/release/bundle/dmg/Lattice AI_9.9.3_aarch64.dmg`
+- `dist/ltcai-9.9.5-py3-none-any.whl`
+- `dist/ltcai-9.9.5.tar.gz`
+- `ltcai-9.9.5.tgz`
+- `dist/ltcai-9.9.5.vsix`
+- `src-tauri/target/release/bundle/dmg/Lattice AI_9.9.5_aarch64.dmg`
 
 Do not use wildcard artifact uploads. Package registry publishing remains owner-run.
 
@@ -118,7 +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 9.9.3.
+  live local Brain store in 9.9.5.
 - 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
@@ -130,6 +129,8 @@ See [ARCHITECTURE.md](ARCHITECTURE.md) for details and
 
 | Version | Theme |
 | --- | --- |
+| 9.9.5 | Closed Gaps |
+| 9.9.4 | Durable Loops |
 | 9.9.3 | Closed Loops |
 | 9.9.2 | Artifact Trust |
 | 9.9.1 | Clean Foundations |

package/docs/CHANGELOG.md

@@ -4,6 +4,106 @@ 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.
 
+## [9.9.5] - 2026-07-26
+
+### Added
+- Optional cross-encoder rerank (`lattice_brain/graph/rerank.py`): env
+  `LATTICEAI_CROSS_ENCODER_RERANK=1` (model via
+  `LATTICEAI_CROSS_ENCODER_MODEL`); hybrid_search returns additive `rerank`
+  meta; default path is identity with no model download.
+- Sidecar-backed Playwright first-value E2E: `tests/e2e/`,
+  `scripts/run_sidecar_e2e.mjs`, `npm run test:e2e:sidecar`, nightly
+  `.github/workflows/e2e-sidecar.yml`.
+- VS Code approval commands: `ltcai.listApprovals`, `ltcai.approveAgent`,
+  `ltcai.rejectAgent` with pause-token session cache.
+- Telegram approval handles both `waiting_approval` and `awaiting_approval`
+  with run_id+token resume preferred.
+- Agent loop L4/L5/L7 helpers: `artifact_checklist`, `files_written`,
+  snapshot rollback ports (`snapshot_file` / `restore_snapshot`) with
+  mode-tagged results (`git` | `snapshot` | `none`).
+- Knowledge-graph read surface decomposition:
+  `lattice_brain/graph/retrieval_reads.py` (`KnowledgeGraphReadsMixin`).
+
+### Changed
+- Legacy `human_in_loop` pauses now use the durable `AgentRunStore` path
+  (`legacy_context=True`); the separate in-memory `_pending` map is removed.
+  Wire contract (`status=waiting_approval`, `context_id`) is preserved.
+- Rollback recovers file-create actions via pre-write snapshots when git is
+  unavailable or not governed.
+- Critic verify prompts include a deterministic artifact checklist derived
+  from transcript sanitize/repair flags.
+- Executor prompts list files already written in the current run.
+- `docs/SURFACE_PARITY.md` marks VS Code/Telegram approval as provided.
+
+### Tests
+- `test_agent_loop_l4_l5_l7.py`, `test_cross_encoder_rerank.py`,
+  `test_snapshot_rollback_ports.py`, L1 approval flow extensions.
+
+## [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

package/docs/COMMUNITY_AND_PLUGINS.md

@@ -1,6 +1,6 @@
 # Community And Plugins
 
-Current release: **9.9.3 — Closed Loops**.
+Current release: **9.9.5 — Closed Gaps**.
 
 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: **9.9.3 — Closed Loops**.
+Current release: **9.9.5 — Closed Gaps**.
 
 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: **9.9.3 — Closed Loops**.
+Current release: **9.9.5 — Closed Gaps**.
 
 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 (v9.9.3)
+# Lattice AI — Operations Guide (v9.9.5)
 
 > **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 +1,53 @@
+# Lattice AI — Surface Parity Matrix
+
+> **Status: reference**
+> 도입: v9.9.4 (2026-07-25, 리뷰 Wave 1.4 "표면 패리티 체크리스트").
+> 갱신: v9.9.5 — VS Code/Telegram 승인 흐름 갭 해소.
+> 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) | ✅ List/Approve/Reject 커맨드 + 토큰 캐시 | — | ✅ 인라인 Done/Cancel + run_id/token 재개 |
+
+## 기능 상세 × 표면
+
+| 기능 | Web `/app` | Desktop | VS Code | Browser | Telegram |
+| --- | --- | --- | --- | --- | --- |
+| 에이전트 스텝 타임라인 (v9.9.4) | ✅ 라이브 SSE | ✅ | — | — | — |
+| 승인 재개 (`/agent/resume`) | ✅ | ✅ | ✅ `ltcai.approveAgent` / `rejectAgent` | — | ✅ callback → resume |
+| 대기 중 승인 목록 (`GET /agent/approvals`, v9.9.4) | ✅ | ✅ | ✅ `ltcai.listApprovals` | — | — (봇 로컬 pending map) |
+| 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 회상 배지, VS Code Review Center.
+4. 릴리스마다 이 표를 검토한다 (release checklist의 docs 단계).
+
+## VS Code / Telegram 승인 메모 (v9.9.5)
+
+- **토큰은 GET `/agent/approvals`에 다시 내려가지 않는다** (보안). Web은 일시 중지 응답의 토큰을 클라이언트에 보관하고, VS Code도 동일하게 pause 응답의 토큰을 확장 세션 캐시에 둔다. 캐시에 없으면 붙여넣기 또는 웹 UI로 유도한다.
+- **Telegram**은 `waiting_approval`(레거시 `human_in_loop`)과 `awaiting_approval`(토큰) 둘 다 인라인 키보드로 처리하며, resume 시 run_id+token을 우선한다.

package/docs/TRUST_MODEL.md

@@ -1,6 +1,6 @@
 # Lattice AI Trust Model
 
-Current release: **9.9.3 — Closed Loops**.
+Current release: **9.9.5 — Closed Gaps**.
 
 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: **9.9.3 — Closed Loops**.
+Current release: **9.9.5 — Closed Gaps**.
 
 **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: **9.9.3 — Closed Loops**.
+Current release: **9.9.5 — Closed Gaps**.
 
 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__ = "9.9.3"
+__version__ = "9.9.5"
 
 __all__ = [
     "AgentRuntime",