- USER.md/SOUL.md 문자캡 잘림 보완용 벡터 검색(Chroma, EmbeddingGemma) 신설
- 일별 대화로그 LLM 추출 파이프라인(user_facts/daily_extracts 컬렉션 분리)
- 검증-강제 게이트(isFactualInfoRequest 등)를 prompt-gates.ts로 분리, 개인 인프라
별명(지서버/클로서버) 관련 불필요한 web_search 강제 호출 버그 수정
- Qwen3-Embedding-8B는 실측 결과 이미지생성 GPU와 자원 충돌 확인되어 폐기,
EmbeddingGemma(경량+다국어)로 최종 선택
Co-Authored-By: Claude Sonnet 5 <noreply@anthropic.com>
- mobToggle 가드 640→1024: 음악·슬라이드·코드·날씨·언어·치과·ESP32·아두이노 앱
(CSS max-width:1024px인데 JS guard가 >640으로 남아 폴드 내부화면에서 토글 불가)
- #mob-tabbar z-index 400/490→600, 패널 bottom 0→52px, backdrop inset 0 0 52px 0
(backdrop이 탭바를 가려 열린 상태에서 다른 탭 전환 불가 문제 해결)
- 모든 innerWidth<=640 자동트리거 →<=1024 통일 (9개 앱)
- 탐정앱: 네트워크 분석 패널 (IP조회/Traceroute/Nmap/DNS/WHOIS/SSL/취약점/해시/웹스캔/배너/CVE)
- voice-utils.js 분리 — 서브앱 공통 음성입력+TTS 유틸
- app.js: 컨텍스트 토큰 게이지 (세션 목록에 tok/max 표시), usage 이벤트 처리
- routes-music.ts: Demucs 보컬분리 + YouTube 다운로드 잡 관리 (TTL 자동정리)
- server-v2.ts: 탐정 네트워크 API (traceroute/dns/whois/ssl/nmap/vuln/hash/webscan/cve)
- session.ts: resolveNumCtx export, /api/agent/session contextTokenEstimate 노출
- config.json: 카카오 채널 설정, ITS 교통 API 키 vault 참조
- styles.css: app-mic-btn / app-tts-btn 공통 스타일
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Settings that were silently lost on reinstall:
- Track .smallclaw/heartbeat/config.json (active hours 8-22, interval 30m)
- Track .smallclaw/skills_state.json (multi-agent-orchestrator enabled)
- Fix gitignore: heartbeat/ → heartbeat/runs/ (only ignore run logs, not config)
- Fix gitignore: remove skills_state.json from ignored list
Vault (contains channel tokens, passwords) cannot go in git — instead:
- Add scripts/backup-vault.sh: backs up vault+credentials to ~/.smallclaw-backup/
keeping last 5 snapshots. Run manually or via cron (0 3 * * *).
- Run initial backup now → ~/.smallclaw-backup/vault_20260518_232441
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add per-user session/workspace paths to .gitignore so runtime data
(sessions, uploads, memory, attachments, pubmed) is no longer tracked
- Narrow ollama_web_search description to prevent it being chosen over
web_search for news/info queries — it's now explicitly a fallback only
- Add scripts/install-image-deps.sh to install Pillow/torch/rembg deps
- Remove stray root files (1, pdf-pptx.txt, eng.traineddata)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Reorganize .smallclaw/databases/ around a single entry point with
subcommands (add-terms / add-images / verify / reassign / stats),
absorb pmc_reassign.py into reassign, and route every image source
through inline vision-model verification before commit.
Layout
config.py paths, endpoints, API-key locations (no more
hard-coded absolute paths in source files)
manage.py argparse dispatcher
workflow_terms.py seed-JSON import (JSONC supported, dedupes on
korean/english)
workflow_images.py renamed from dental_image_workflow.py; main()
converted to run(verify=True, ...)
workflow_verify.py validate_image() / verify_db() + verify_updates()
gate used by every add-images source
seeds/ recovered seed_all.json, seed_periodontics.json
scratch/ ad-hoc work area replacing the /tmp habit
(only README.md is tracked)
docs/howto.md moved + expanded
docs/archive_image_rounds/ one-off round scripts + their results
docs/archive_validation/ model-comparison + validation history
Verification
- VERIFY_MODEL defaults to qwen3.5:397b-cloud (50-image test on
procedure-heavy sample: 9.8s/img avg, zero timeouts, Kimi-level
rigor — see archive_validation/).
- Prompt strengthened: in-image text/captions are not valid grounds
for "적합"; technique terms require visible procedure steps, not
generic device/anatomy photos.
- All 9 add-images sources gated through verify_updates() before
commit; --no-verify escape hatch for bulk runs.
.gitignore: API key files, dental_images/, __pycache__/, scratch/*
(README.md kept).
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
kimandClaude Sonnet 5