feat: kakao_send_message 에이전트 도구화 + 멀티기기 메인챗 세션 동기화 + 터미널 전체화면

- src/tools/kakao.ts: 기존 KakaoNotify를 kakao_send_message 도구로 노출, 코드에디터에서는 차단
- app.js/server-v2.ts: 메인챗 마지막 활성 세션을 서버에 기록해 새 기기에서 열 때 자동 이어보기
- code.html/code.js/styles.css: 서버 터미널 패널 전체화면 토글 (Esc로 종료)
- companion.py: .vbs 자동시작 시 cwd가 System32로 잡히는 문제 방지 위해 홈 디렉터리로 고정
- papa 워크스페이스: 우즈베크어 학습 진행상황, 서버 이름(지서버/클로서버) 메모 갱신

Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>

.smallclaw/users/papa/workspace/language/progress.json

@@ -1,5 +1,11 @@
 {
-  "known": [],
+  "known": [
+    "Salom",
+    "Xayr",
+    "Ha",
+    "Yoʻq",
+    "Iltimos"
+  ],
   "lessonsDone": {
     "1": true,
     "2": true,

.smallclaw/users/papa/workspace/prompts/SOUL.md

@@ -14,6 +14,8 @@
 - Name: (not yet assigned)
 - "I am SmallClaw, your local AI assistant."
 
+- The local LLM server (HP Z840) is officially named "지서버" (Z-Server). [2026-07-03] [2026-07-03]
+- Web server name: 클로서버 (Claw-Server). [2026-07-03] [2026-07-03]
 ## limits
 - Small model — best at structured tasks.
 - Limited context — rely on workspace files.

.smallclaw/users/papa/workspace/prompts/USER.md

@@ -14,4 +14,10 @@
 - Gemma 4 released March 2026 (12B in June 2026), native audio/video multimodal. [2026-06-21]
 
 ## hardware_history
-- RTX 5060 launched May 19, 2025 ($299); RTX 5060 Ti launched April 16, 2025 ($429 for 16GB). [2026-06-24]
+- RTX 5060 launched May 19, 2025 ($299); RTX 5060 Ti launched April 16, 2025 ($429 for 16GB). [2026-06-24]
+
+## projects
+- Local LLM Server: HP Z840, 2x RTX 5060 Ti, 64GB RAM, Crucial P310 1TB NVMe. [2026-07-03] [2026-07-03]
+- Local LLM Server: HP Z840, 2x RTX 5060 Ti (16GB each, total 32GB VRAM), 64GB RAM, Crucial P310 1TB NVMe. [2026-07-03] [2026-07-03]
+- Local LLM Server name: 지서버 (Z-Server). [2026-07-03] [2026-07-03]
+- Web server name: 클로서버 (Claw-Server). [2026-07-03] [2026-07-03]