ltcai 0.1.29 → 0.1.30

package/README.md

@@ -1,7 +1,9 @@
 <div align="center">
   <img src="https://raw.githubusercontent.com/TaeSooPark-PTS/LatticeAI/main/docs/images/logo.svg" alt="Lattice AI" width="280"/>
   <br/>
-  <strong>Your personal AI workspace server — local & cloud, one stack.</strong>
+  <strong>One install. Your personal AI workspace.</strong>
+  <br/>
+  Local LLMs, cloud models, VS Code / Cursor, Telegram, MCP tools, files, admin controls, and a knowledge graph in one self-hosted stack.
   <br/><br/>
 
 [![PyPI](https://img.shields.io/pypi/v/ltcai?label=PyPI&color=blue)](https://pypi.org/project/ltcai/)
@@ -9,35 +11,61 @@
 [![npm](https://img.shields.io/npm/v/ltcai?label=npm)](https://www.npmjs.com/package/ltcai)
 [![VS Code](https://vsmarketplacebadges.dev/version-short/parktaesoo.ltcai.svg)](https://marketplace.visualstudio.com/items?itemName=parktaesoo.ltcai)
 [![Open VSX](https://img.shields.io/open-vsx/v/parktaesoo/ltcai?label=Open%20VSX)](https://open-vsx.org/extension/parktaesoo/ltcai)
+[![CI](https://github.com/TaeSooPark-PTS/LatticeAI/actions/workflows/ci.yml/badge.svg)](https://github.com/TaeSooPark-PTS/LatticeAI/actions/workflows/ci.yml)
 [![License: MIT](https://img.shields.io/badge/License-MIT-green)](./LICENSE)
 [![Python 3.11+](https://img.shields.io/badge/python-3.11+-blue)](https://www.python.org/)
 
+<br/>
+
+<img src="https://raw.githubusercontent.com/TaeSooPark-PTS/LatticeAI/main/docs/images/lattice-ai-demo.gif" alt="Lattice AI demo showing chat, knowledge graph, and admin dashboard" width="100%"/>
+
 </div>
 
 ---
 
 ## What is Lattice AI?
 
-**Lattice AI** is a self-hosted AI server that unifies local and cloud LLMs into one workspace — web chat, VS Code extension, Telegram bot, and MCP tools, all from a single `pip install`.
+**Lattice AI** is a self-hosted AI server that unifies local and cloud LLMs into one practical workspace. Install once, then use the same AI from the web UI, VS Code / Cursor, Telegram, MCP clients, files, and your personal knowledge graph.
 
 - 🖥️ **Web UI** — chat, file upload, admin dashboard, data graph
 - 🧩 **VS Code / Cursor extension** — edit, explain, generate commands inline
 - 📱 **Telegram bot** — access your AI from anywhere
 - 🔌 **MCP server** — use Lattice tools inside Claude Desktop / Cursor
 - 🔒 **Zero telemetry** — all data stays in `~/.ltcai/` on your machine
+- ⚡ **30-second start** — `pip install ltcai` or `npm install -g ltcai`
 
 ---
 
-## 📸 Screenshots
+## 📸 Product Preview
+
+Real screens from the local web app:
 
 <table>
 <tr>
-<td width="33%"><b>Chat UI</b><br/><img src="https://raw.githubusercontent.com/TaeSooPark-PTS/LatticeAI/main/docs/images/screenshot-chat.png" alt="Lattice AI Chat" width="100%"/></td>
-<td width="33%"><b>Admin Dashboard</b><br/><img src="https://raw.githubusercontent.com/TaeSooPark-PTS/LatticeAI/main/docs/images/screenshot-admin.png" alt="Admin Dashboard" width="100%"/></td>
-<td width="33%"><b>Data Graph (Graph RAG)</b><br/><img src="https://raw.githubusercontent.com/TaeSooPark-PTS/LatticeAI/main/docs/images/screenshot-graph.png" alt="Knowledge Graph" width="100%"/></td>
+<td align="center" width="33%">
+  <b>💬 Workspace Chat</b><br/>
+  <img src="https://raw.githubusercontent.com/TaeSooPark-PTS/LatticeAI/main/docs/images/screenshot-chat.png" alt="Lattice AI workspace chat" width="100%"/>
+  <sub>Web chat with local LLM, file upload, pipeline status</sub>
+</td>
+<td align="center" width="33%">
+  <b>🛡️ Admin Dashboard</b><br/>
+  <img src="https://raw.githubusercontent.com/TaeSooPark-PTS/LatticeAI/main/docs/images/screenshot-admin.png" alt="Lattice AI admin dashboard" width="100%"/>
+  <sub>User management, audit log, security monitoring</sub>
+</td>
+<td align="center" width="33%">
+  <b>🕸️ Knowledge Graph</b><br/>
+  <img src="https://raw.githubusercontent.com/TaeSooPark-PTS/LatticeAI/main/docs/images/screenshot-graph.png" alt="Lattice AI knowledge graph" width="100%"/>
+  <sub>Auto-built Graph RAG from chats &amp; documents</sub>
+</td>
 </tr>
 </table>
 
+What this gives users after install:
+
+- A single local workspace for chat, files, models, runtime setup, and tool control
+- A graph view that turns chats and documents into searchable knowledge
+- Admin screens for users, model status, VPC settings, SSO, audit logs, and security monitoring
+
 ---
 
 ## ⚡ Quick Start (30 seconds)
@@ -45,16 +73,9 @@
 **Python / PyPI**
 
 ```bash
-# Install (cloud models)
 pip install ltcai
-
-# Install (+ Apple Silicon local models)
 pip install "ltcai[local]"
-
-# Verify environment
 LTCAI doctor
-
-# Start server
 LTCAI
 # → http://localhost:4825
 ```
@@ -298,7 +319,7 @@ Or: `./start_ai.sh` (auto-restart + caffeinate)
 | VS Code Marketplace | [marketplace.visualstudio.com](https://marketplace.visualstudio.com/items?itemName=parktaesoo.ltcai) |
 | Open VSX | [open-vsx.org](https://open-vsx.org/extension/parktaesoo/ltcai) |
 
-Current version: **0.1.29** — [Changelog](docs/CHANGELOG.md)
+Current version: **0.1.30** — [Changelog](docs/CHANGELOG.md)
 
 ---
 

package/docs/CHANGELOG.md

@@ -1,5 +1,32 @@
 # Changelog
 
+## [0.1.30] - 2026-05-25
+
+### 코드 품질 및 리팩토링
+
+- **`server.py` 모듈 분리** — 7,568줄 → 6,798줄
+  - MCP 레지스트리 상수 + 원격 레지스트리 페치 + 스킬 마켓플레이스 + 플러그인 디렉터리 로직을 `mcp_registry.py`(791줄)로 분리
+  - `server.py`의 가독성과 유지보수성 대폭 향상
+
+- **버그 수정 6건**
+  - `requirements.txt`에 누락된 `pymupdf` 추가 (Docker 빌드 실패 방지)
+  - 비밀번호 해싱 로그 메시지 "bcrypt" → 실제 알고리즘 "scrypt"로 수정
+  - HuggingFace 모델 캐시 경로 `~/.latticeai/` → `~/.ltcai/`로 통일 (DATA_DIR과 일치)
+  - OpenRouter 모델 카탈로그: Claude 3.5 → Claude 4.x, Gemini 2.0 → 2.5 업데이트
+  - `.gitignore`에 임시 파일, 로그, 세션 파일 패턴 8개 추가
+  - 고아 파일 정리 (구버전 GIF, 캡처 스크립트 삭제)
+
+- **README 개선**
+  - v0.1.29 실제 UI에서 새로 찍은 스크린샷 3장 + 애니메이션 데모 GIF 추가
+  - GitHub Actions CI 배지 추가
+  - 스크린샷에 이모지 레이블 + 설명 캡션 추가
+
+### Release
+- 배포 버전을 `0.1.30`으로 상향
+- 대상 채널: `npm` · `PyPI` · `VS Code Marketplace` · `Open VSX`
+
+---
+
 ## [0.1.29] - 2026-05-25
 
 ### 관리자 UX 및 거버넌스 개선

package/llm_router.py

@@ -128,12 +128,12 @@ PROVIDER_MODEL_CATALOG = {
     ],
     "openrouter": [
         {"id": "openai/gpt-4o-mini", "name": "GPT-4o Mini via OpenRouter", "family": "GPT"},
-        {"id": "anthropic/claude-3.5-sonnet", "name": "Claude 3.5 Sonnet via OpenRouter", "family": "Claude"},
-        {"id": "anthropic/claude-3.5-haiku", "name": "Claude 3.5 Haiku via OpenRouter", "family": "Claude"},
+        {"id": "anthropic/claude-sonnet-4-6", "name": "Claude Sonnet 4.6 via OpenRouter", "family": "Claude"},
+        {"id": "anthropic/claude-haiku-4-5", "name": "Claude Haiku 4.5 via OpenRouter", "family": "Claude"},
         {"id": "x-ai/grok-2", "name": "Grok 2 via OpenRouter", "family": "Grok"},
         {"id": "meta-llama/llama-3.3-70b-instruct", "name": "Llama 3.3 70B via OpenRouter", "family": "Llama"},
         {"id": "qwen/qwen-2.5-72b-instruct", "name": "Qwen 2.5 72B via OpenRouter", "family": "Qwen"},
-        {"id": "google/gemini-2.0-flash-exp", "name": "Gemini 2 Flash via OpenRouter", "family": "Gemini"},
+        {"id": "google/gemini-2.5-flash", "name": "Gemini 2.5 Flash via OpenRouter", "family": "Gemini"},
     ],
     "groq": [
         {"id": "llama-3.1-8b-instant", "name": "Llama 3.1 8B Instant", "family": "Llama"},
@@ -174,7 +174,7 @@ def parse_model_ref(model_id: str) -> tuple[str, str]:
         return "local_mlx", model_id.split(":", 1)[1]
     return "local_mlx", model_id
 
-HF_MODELS_ROOT = Path.home() / ".latticeai" / "hf-models"
+HF_MODELS_ROOT = Path.home() / ".ltcai" / "hf-models"
 
 def hf_model_dir(repo_id: str) -> Path:
     return HF_MODELS_ROOT / repo_id.replace("/", "__")