- USB CDC 경로 복원: #define Serial Serial1 우회 제거
- rp2040js/avr8js/codemirror/xterm/monaco-editor vendor화
- /vendor 정적 라우팅 추가 (Express 5 catch-all 우회)
- 부팅 완료 타임아웃 감지 (Serial 출력 없어도 8초 후 RAF 전환)
- 리셋 시 Simulator 재생성으로 주변 장치 상태 초기화
- 시리얼 패널의 내부 메시지를 console.log로 이동
- RP2040(Pico) 보드 감지·컴파일·에뮬레이션 지원 추가
- Serial → Serial1(UART0) 자동 리다이렉트 (#define 삽입)
- .uf2 파일 우선 추출, bootrom 자동 다운로드·캐싱
- ELF .text 추출: arm-none-eabi-objcopy 대신 Node.js 내장 파서
- HTTP 302 리다이렉트 자동 팔로우 (_httpsGetFollow)
- rp2040js 에뮬레이터: fast-path 초기화 루프, 피코 SVG 보드, GPIO25 LED
- 예외 처리: HardFault(#3)만 중지, 나머지 IRQ/SysTick 정상 통과
- UART onByte: TextDecoder stream 모드로 한글 UTF-8 정상 출력
- heartbeat 메시지 제거
- WiFi scan mock: WSCN 프로토콜로 C++ ↔ 브라우저 동기화, UI 편집 지원
- 에뮬레이터 팝업 → 코드 에디터 인라인 iframe 패널로 전환
- CDN 의존성 → /vendor/ 로컬 서빙 (xterm, Monaco)
- SSE 세션 idle timer (창 닫힘 후 5분 자동 종료)
- 업로드: 속도 자동 재시도(921600→460800→230400) + FlashMode fallback
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
컴파일 에러에서 'fatal error: Foo.h: No such file or directory' 파싱 →
arduino-cli lib search로 최적 라이브러리 찾기 → 자동 설치 → 재컴파일.
성공 시 autoInstalled[] 포함하여 반환, 클라이언트는 "📦 자동 설치" 시스템 메시지 표시.
에러 지속 시 sendCompileErrorToAI()로 AI 채팅에 전달.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
오류 발생 시 codeAiAppend(system) 대신 sendCompileErrorToAI()로
에러 메시지 + 코드 컨텍스트를 AI 입력창에 넣고 즉시 전송.
arduino / esp32 / 에뮬레이터 버튼 세 경로 모두 적용.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
aspect-ratio:2/1 미지원 브라우저에서 캔버스가 64px 자연 높이로
렌더링되어 가로로만 늘어나 '줄만 몇 개'로 보이는 버그 수정.
- canvas 128×64 → 256×128 (물리 픽셀 2배)
- JS 렌더러: 논리 픽셀 1개 → 2×2 물리 픽셀로 직접 기록
- CSS: image-rendering:pixelated + aspect-ratio 제거
→ max-width:100%; height:auto 로 브라우저 자연 스케일링
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- 캔버스 width:256px → width:100%; aspect-ratio:2/1
(보드 패널 280px 기준 오버플로우·클리핑 해소)
- OLED 섹션 항상 표시, 연결 전 플레이스홀더:
"OLED 연결 대기 / 0x3C / 0x3D" + 점선 격자
- 파란 점(dot) 인디케이터: 연결 전=꺼짐, displayOn=켜짐
- display.display() 수신 시 플레이스홀더 숨김·캔버스 표시
- display off(0xAE) 시 플레이스홀더 복원
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- AVRTWI connectToSlave에서 LCD(0x27/0x3F)와 OLED(0x3C/0x3D) 동시 지원
- SSD1306 프로토콜 파서:
- control byte (0x00=cmd stream, 0x40=data stream)
- 주요 명령: addressing mode, set col/page addr, display on/off,
inverse, page/col low/high nibble, 2바이트 명령 처리
- horizontal/vertical/page 어드레싱 모드 모두 지원
- GDDRAM(128×8 pages) 유지 → canvas 128×64 px 렌더링
(픽셀 2× 스케일, 청백색 톤)
- displayOn 명령 수신 시 OLED 패널 자동 표시
- runFrame마다 dirty 플래그로 효율적 canvas flush
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- web-ui/arduino-emulator.html: avr8js 기반 ATmega328P 에뮬레이터
(핀 상태 패널, 보드 LED, 시리얼 모니터, 속도 조절)
- cpu.tick() 누락 수정: delay()/millis()/Serial 동작 안 하던 버그
- 시리얼 라인 추적(serialLineSpan): D13 sys 메시지 끼어들 때 줄 깨짐 수정
- web-ui/esp32-flasher.html: Web Serial로 merged.bin 플래시
- POST /api/arduino/compile: arduino-cli로 uno/nano hex, esp32 merged.bin 컴파일
- POST /api/code/round: 클라이언트 주도 코드 에디터용 1라운드 SSE 엔드포인트
- code.js: 실행 모드에 Arduino 에뮬레이터 / ESP32 플래시 추가
Co-Authored-By: Claude Fable 5 <noreply@anthropic.com>
- 🧠 Karpathy 코딩 가이드라인 토글 버튼 추가 (시스템 프롬프트 주입)
- 모델 셀렉터를 AI 패널 헤더 내부로 이동 (채팅창 너비 연동)
- CSS Grid 레이아웃으로 전환: AI 패널이 파일 탭 상단까지 연장
- 오른쪽 공백 수정: auto 컬럼 → CSS 변수(--ai-panel-w) 제어
- 입력창 소실 수정: #code-ai-panel에 overflow:hidden 추가
- 터미널 불작동 수정: .code-bottom-panels overflow:hidden 제거
- body padding/gap 초기화로 전체 여백 제거
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- requestAnimationFrame → setTimeout(60ms): 패널 레이아웃 계산 후 xterm 초기화
- ptyReady 스냅샷 버그 수정: codeTermShells 대신 xtermInstances 참조
- 터미널 열릴 때 cls/clear 자동 실행 (Windows: cls, Linux: clear)
- companionPlatform 타이밍 버그 수정: clearCmd를 shell_ready 수신 후 평가
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Add alternating block background colors (ff-block-even/odd) for functions/classes
- Add ¶빈줄숨김 / ▓블록색상 toggle buttons to file panel sidebar (below file tree)
- Fix terminal error send: filter Windows prompt+command lines, only send last Traceback block, strip pygame header noise
- Show live server log bubble during AI tool calls, fade out on completion
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Per-file streaming: text shows while AI works, collapses on tool call, ✅완료 at end
- Options UI: numbered choice buttons with number/keyword input selection
- Number input in chat (1~6) selects corresponding option chip
- Terminal error 🤖 button permanently visible in header bar
- Model card moved to tabs bar top-right, synced with panel width
- Removed 코드 저장 디렉토리 from settings; merged save/folder into sidebar
- Removed language selector from chat header
- Bottom cards anchored to sidebar bottom
- Simplified planInstruction prompt
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Move code editor to standalone page; remove from main index/app mode switcher
- Add diff-active tab highlight and diff bar CSS to styles
- Add markdown table styles for chat messages
- PubMed: try NCBI FTP link before Unpaywall for PDF download
- Login: also persist token to localStorage for cross-tab auth
- Update skills state and config
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
/api/show가 cloud 모델의 PARAMETER num_ctx를 반환 안 하는 문제 해결.
매니페스트 → params 레이어 블롭 직접 파싱해서 num_ctx 우선 사용.
kimi-k2.6:cloud 1M으로 Modelfile 수정 후 정확히 표시됨.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
chat, generate, chatStream 모두 /api/show에서 읽은 context_length를
num_ctx 기본값으로 사용. 결과는 모델별로 캐시됨.
엔드포인트 변경 시 캐시 자동 무효화.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
GET /api/model-context?model=<name> 엔드포인트 추가.
Claude → 200k 고정, Ollama → /api/show 쿼리 후 model_info 또는
num_ctx 파라미터에서 실제 컨텍스트 크기 추출.
클라이언트: 모델 변경 및 초기 부팅 시 자동 fetch.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
세션 바에 현재 컨텍스트 토큰 추정치 / 모델 최대값 표시.
글자 수 ÷ 4 로 토큰 추정, 50% 이하 초록 / 50~80% 노랑 / 80%+ 빨강 색상 진행 바.
메시지 전송·응답 완료 시 즉시 업데이트.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- 오케스트레이터 auto-trigger 경로에 !isCodeAiSession/!isProjSession 누락 수정
(code_ai_ 세션에서 tool failure 쌓이면 memory_read 등 엉뚱한 도구 호출로 멈추던 문제)
- 로컬 셸 시작/프로젝트 전환 시 프로젝트 폴더로 자동 cd
- companion.py: shell_ready에 platform/home 정보 포함
- Windows/Unix 경로 처리: cd /d "경로" vs cd "경로"
- localTermPath 미설정 시 companionHome fallback, 둘 다 없으면 cd 안 함
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
터미널 패널이 닫힌 상태에서 로컬 셸을 열면 레이아웃 계산 전에
fitAddon.fit()이 실행돼 rows=0/cols=0으로 companion에 전달됨.
300ms 타임아웃 안에서 fit을 재실행하고 최솟값(24x80) 보장.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- 로컬 모드 shell 차단: error:true로 변경, 시스템 프롬프트에 명시적 금지 문구 추가
- 로컬 모드 파일 자동 저장: 새 파일 생성 시 승인 팝업 없이 즉시 디스크 저장 + "💾 저장" 알림
- 계획 단계 프롬프트 강화: 파일별 주요 함수/로직/데이터흐름/주의사항 포함
- 프로젝트 마법사 디폴트화: 새 세션 생성 시 자동으로 계획 단계 진입
- _isNewProjectIntent / _isSingleFileIntent 제거: 수동 프로젝트 생성으로 대체
- 채팅 히스토리 버그 수정: codeAiClear에서 history 지우기 전 saveProjectSession 호출
- 초기 로드 버그 수정: restoreLocalDirHandle에서 채팅 패널 렌더링 누락 수정
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- 코드 에디터 저장: 서버 API → File System Access API로 전환
- codeSaveFileById에 저장 성공/실패/폴더미선택 피드백 메시지 추가
- 프로젝트 생성 형식: project-files JSON → @@FILE/@@ENDFILE 델리미터로 변경
- JSON 이스케이프 오류(Unterminated string) 근본 해결
- 계획 단계 시스템 프롬프트 강화: JSON 출력 절대 금지 명시
- 프로젝트 생성 세션 ID: 계획 세션 재사용 (서버가 history 파라미터 무시하므로)
- _projFileCreated async화: 파일 쓰기 완료 후 사이드바 리프레시
- 헤더/드롭다운 폴더명 표시 동적 업데이트 (workspace/code/ 하드코딩 제거)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- PDF: skip references/bibliography section from text extraction
- PDF: add minimal system prompt for translate sessions (translation-only, no tool calls)
- Wizard: image download button per card + bulk download all
- Wizard: translation modal download button (saves as _ko.txt / _en.txt)
- Wizard: save papers.json immediately on upload, after text extraction, and before outline step
- Wizard: short image directory names (22 chars + timestamp suffix)
- Wizard: project-images scans workspace root dir alongside pptx/ folder
- Server: pptx/list scans only pptx/ folder (workspace root scanning removed after file migration)
- create_presentation: save output to workspace/pptx/{slug}/ instead of workspace root
- edit_presentation: fuzzy path search includes pptx/ subfolder
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Server:
- download-pdf-stream: check if PDF already exists (size > 1KB) → return
cached path immediately, skip all network requests
Client (startPrep):
- save pdfPaths from prepLog before reset → skip PMC download if path known
- skip text extraction if paperTexts[key] already loaded in memory
- text from project open (onOpenProjChange) now survives "다시 실행"
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Image extraction now immediately followed by per-figure mistral analysis
no manual button click needed: extract → analyze runs as one atomic flow
- Progress shows "이미지 분석 1/5..." inline with prep step
- Captions + 제외 filtering available before outline generation
- "🔍 재분석" button retained for manual uploads / re-run on failures
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
gpt-oss:120b-cloud refuses even short medical texts with "텍스트가 너무 길어...".
Add model:'mistral-large-3:675b-cloud' explicitly to three wizard /api/chat calls:
- translateAbstract() — abstract Korean translation
- chatStream() — PDF text chunk translation (used by translatePdfText)
- generateOutline() — slide outline generation
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- pptx-wizard: add "🔍 이미지 분석" button in Step 2 image panel
* calls /api/pptx/analyze-image per figure via mistral vision
* shows per-image progress (1/10, 2/10...)
* "제외" caption → dimmed card + filtered from outline prompt
* captions shown below each thumbnail in the grid
- server: POST /api/pptx/analyze-image endpoint
* resolves /api/files/ path to workspace file, thumbnails if >300KB
* calls orchestration.secondary vision model (mistral-large-3:675b-cloud)
* caches results in project/.image-captions.json (skips on re-analysis)
- pptx-wizard: generateOutline() includes captions in imgList
* "제외" images filtered out before sending to LLM
* format: "/api/files/... (figure_p2_1) — 카플란-마이어 생존곡선 3그룹"
- skills-manager: fix getModelOverrideForUser() trigger filtering
* was returning skill model for ALL messages regardless of trigger keywords
* now only overrides when message matches skill triggers (same logic as buildPromptContext)
* presenter model (mistral) now only applies for 발표/pptx/슬라이드 keywords
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- config: primary model → gpt-oss:120b-cloud (faster general chat, 2.72s median)
- server-v2: fix vision regex to exclude gpt-oss (gpt(?!-oss) negative lookahead)
* gpt-oss was incorrectly matching /gpt/ → image data sent to non-vision model
* applied at all 3 _supportsVision check sites (lines 5204, 6362, 7832)
- server-v2: vision fallback routing — when primary lacks vision support and user
message contains images, automatically route to orchestration.secondary
(mistral-large-3:675b-cloud, 4.27s avg, fastest vision cloud model)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- skills-manager: conditional skill injection via triggers frontmatter field
(skills only sent to model when message matches trigger keywords)
- skills: added triggers to all skill SKILL.md files; cleaned up headers/disclaimers
- anthropic-adapter: toAnthropicContent() converts OpenAI image_url → Anthropic image blocks
- multi-agent: vision flag in SecondaryProfile; secondarySupportsVision() checks config
- config: secondary set to mistral-large-3:675b-cloud with vision:true
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
The 💻 코드 sidebar tab now opens a dedicated code.html page in a new tab,
mirroring how the slide wizard opens pptx-wizard.html.
- Add web-ui/code.html: standalone code editor page reusing styles.css and
the same CodeMirror/xterm/Monaco head as the main app.
- Add web-ui/code.js: self-contained code-view logic — inlined shared helpers
(api/authHeaders/escHtml/getCookie) + the extracted code-editor block +
a bootstrap that inits Monaco and loads models/dir. It mirrors the code
block in app.js (kept duplicated so the main app stays untouched).
- index.html: tab-code now window.open('/code.html'). The in-page code mode
(top mode button) is unchanged, so chat→editor live streaming still works.
Verified with Playwright: Monaco initializes, editor/sidebar/toolbar/Coder AI
render, no JS errors.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
The slide editor draws a title slide's image as a full-bleed darkened
background, but pptx_gen.py's make_title_slide ignored image_path entirely
and only drew the skin background — so photo backgrounds showed in the
editor but vanished from the generated PPTX / preview.
- make_title_slide now renders image_path full-bleed (cover) with a dark
overlay and white title/subtitle, matching the editor preview.
- Add set_shape_fill_opacity() that injects OOXML <a:alpha>, since
python-pptx's fill.transparency is a silent no-op (the overlay was
rendering as fully opaque black). Apply it to the fullscreen bottom bar too.
- Pass project_dir/workspace_path/warnings into make_title_slide.
- Bump version to 2.8.2.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- Fix pptx-wizard slide editor modal opening off-screen (header clipped)
when a saved drag position is restored on a fresh page load: clear the
CSS centering transform and clamp coordinates into the viewport.
- Add pptx-wizard.html and python-runner.html web UIs.
- Bump version to 2.8.1.
Co-Authored-By: Claude Opus 4.8 <noreply@anthropic.com>
- All skill toggles are now per-user (except multi-agent-orchestrator
which remains global). Admin toggle without a target username defaults
to their own per-user state instead of the global file.
- GET /api/skills defaults to the requesting user's own state (previously
returned global state when no ?username= param was given).
- Add SkillsManager.initUserSkillsState(): creates per-user
skills_state.json from global defaults if missing — called on user
creation and on every login as a safety net for existing accounts.
- Create initial per-user skills_state.json for cherry and jasmine.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
New skill:
- .smallclaw/skills/meteorologist/SKILL.md — 기상 전문가 스킬 (Windy iframe 규칙 포함)
New weather tools (src/tools/weather.ts):
- weather_airpollution: OpenWeather 대기질 (AQI, PM2.5/PM10/O3/NO2)
- weather_openmeteo: Open-Meteo 시간별 예보 (ECMWF/GFS, 키 불필요)
- weather_kma: 기상청 공식 API (초단기실황·단기예보)
- weather_airkorea: 에어코리아 실시간 대기질
- weather_nasa_power: NASA POWER 기후 데이터 (MERRA-2, 키 불필요)
- weather_era5: ERA5 재분석 과거 데이터 (Open-Meteo Historical, 키 불필요)
- weather_cds: Copernicus CDS 정식 API (ERA5·CMIP6 SSP 시나리오)
- weather_cmip6: CMIP6 기후 모델 (Open-Meteo Climate API, 키 불필요)
Scripts:
- scripts/era5_cds_fetch.py — CDS/CMIP6 Python 헬퍼 (ZIP→NetCDF 처리 포함)
web-ui:
- Windy URL → iframe 자동 렌더링 (standalone URL + 마크다운 링크 모두 감지)
- windyToEmbedUrl: windy.com comma 형식 URL 파싱 개선
server-v2.ts:
- BROWSER RULE: "열어줘" 제거 → 오용 방지
- weather context: 9개 도구 선택 기준 추가
- JSON schema 8개 추가
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
These skills only added prompt instructions — no gateway tools or
unique capabilities. The system prompt already covers their domains.
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Remove blanket regex that stripped ALL image markdown from AI responses,
which was breaking dental-dict images. The [IMAGE COMPLETE] prompt reminder
already tells the model not to duplicate image_edit/image_read results.
- Remove coder skill (SKILL.md)
- Remove dental-dict skill (now handled by MCP server description alone)
- Remove broken external URL for 볼튼분석 (Open-i link dead)
- investor skill enabled in skills_state
Co-Authored-By: Claude Opus 4.7 <noreply@anthropic.com>
- Fix settings save bug: primaryModel captured before _modelSettingsLoaded guard → wiped model roles when models tab not opened
- Fix server: filter empty-string roles before saving to prevent role wipe
- Add Voice and Session settings tabs to UI
- Add OpenWeather API key field to Credentials tab
- Add GET/POST endpoints: /api/settings/voice, /api/settings/session, /api/settings/openweather
- Fix Mistral parallel tool calls: model embeds tool calls as text instead of tool_calls array; parseEmbeddedToolCalls() detects and converts
- Add Anthropic provider adapter (anthropic-adapter.ts)
- Weather tool vault key resolution fix
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
사이드바에 💻 코드 탭 추가:
- Monaco Editor (vs-dark/light 테마 자동 연동)
- 파일 탭 관리 (새 파일, 전환, 닫기), Ctrl+S 저장
- 오른쪽 AI 채팅 패널 (Coder 세션, SSE 스트리밍)
- "선택 코드 → AI 전송" 버튼
- "▶ 실행" → 하단 터미널 패널로 명령 전송
- 에디터/AI 패널 수직 드래그 리사이즈
- 스킬 탭 이모지 버그 수정 (조건 반전, 커스텀 이모지 표시 안 되던 문제)
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
풀스택 시니어 엔지니어 어시스턴트:
- 도구: python_eval, bash_eval, file_read/write, web_search
- 코드 실행 후 결과 검증 원칙
- 공식 문서 우선 참조 사이트 (MDN, PyPI, React, FastAPI 등)
- 코드 리뷰 체크리스트 (보안→정확성→성능→가독성)
- Python/JS/백엔드/DB/DevOps 언어별 핵심 포인트
- skills_state.json에 coder: true 등록
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- investor skill: TradingView 실시간 주가 차트 렌더링 지원
- ```tradingview SYMBOL|INTERVAL``` 블록 → 차트 위젯 자동 생성
- JSON 형식 출력 시 HTML 언이스케이프 후 파싱 (symbol/interval 추출)
- renderTVChart(): tv.js 동적 로드, 다크/라이트 테마 연동, RSI·MACD 기본 포함
- musician skill: MIDI 다운로드 사이트 4개 추가 (freemidi, bitmidi, piano-midi, midiworld)
- MIDI 탭 닫기 버그: window.open에 noopener,noreferrer 추가
- beforeunload/pagehide 시 midiRouter.stop() 호출
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- music-renderer: saveMidiFile export (JSON, no LilyPond), getRenderFile prefers original.midi, fix self-copy bug
- server-v2: POST /api/music/midi now saves to workspace/music/<name>/ and returns JSON immediately; new SSE endpoint /api/music/midi-score for on-demand LilyPond
- index.html: buildMidiPickerWidget with color-coded buttons (green/purple/amber), MIDI download moved inside player tab, score panel default closed
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- web-ui/midi-editor.html: full piano roll MIDI editor (new tab)
- all tracks simultaneously, color-coded per channel
- note add/delete/move/resize, multi-select, copy/paste
- velocity lane, track panel (mute/solo/instrument), undo/redo
- GM reset + bank select on playback, MIDI output device select
- export to .mid, open via ?url= param or file picker
- web-ui/index.html: add ✏ 편집 button to MIDI widget (opens editor)
- GM SysEx reset + bank select before note playback
- 200ms note delay for synth init time
- getRenderFile: prefer original.midi over LilyPond output.midi
- src/gateway/music-renderer.ts: getRenderFile returns original.midi first
- LilyPond SVG render overwrites output.midi (no Program Changes)
- original.midi preserved from upload, served via /api/music/file/:id/midi
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- session.ts: Replace fixed maxMessages limit with token-based trimHistory;
resolveNumCtx() now queries Ollama API for actual model context length (cached).
maxMessages raised to 2000 as safety ceiling only.
- session.ts: Boot sessions (boot-*) never saved to disk — ephemeral by design.
- session.ts: New sessions not written to disk until first message is added.
- session.ts: Add cleanupEmptySessions() called at startup to auto-remove empty files.
- session.ts: migrateGlobalSessionsToUser() deletes global original after copying to user dir.
- server-v2.ts: Call cleanupEmptySessions() at startup.
- server-v2.ts: User creation API accepts optional telegramId for immediate channel mapping.
- config.json: Remove explicit maxMessages (now uses dynamic token-based default).
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Replace piper TTS with edge-tts (Microsoft neural Korean voice)
- piper ko_KR-kss-medium uses pygoruut phoneme type unsupported by C++ binary,
causing Chinese-sounding output; edge-tts solves this via online neural TTS
- Added src/tools/edge_tts_synth.py Python helper script
- Server TTS endpoint now dispatches by provider (edge_tts vs piper)
- Config updated: voice.tts.provider = "edge_tts", voice = "ko-KR-SunHiNeural"
- Add TTS toggle switch to web UI (chat input bar)
- Toggles visibility of all 🔊 buttons and stops active playback
- State persisted in localStorage (default: on)
- Mic input now auto-submits after speech recognition completes
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- STT: Replace MediaRecorder+Whisper with browser Web Speech API (ko-KR)
Whisper base model hallucinated English for Korean speech; Chrome's
built-in Google STT is far more accurate for Korean
- TTS: Skip ffmpeg OGG conversion, return WAV directly from Piper
Avoids OGG/Opus codec compatibility issues in browsers
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- POST /api/voice/stt: Whisper-cpp transcription of webm/ogg audio
- POST /api/voice/tts: Piper Korean TTS returning ogg audio
- Web UI: 🎤 mic button in chat input; click to start/stop recording
MediaRecorder → /api/voice/stt → auto-fills chat input
- Web UI: 🔊 TTS button on each AI message; click to play/stop
- config.json: add absolute model/binary paths for whisper-cli and piper
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
- Luckysheet modal: 8-direction resize handles (edge + corner), title bar drag-to-move
- First drag/resize converts from flex-centered to absolute positioning
- Minimize/close reset to centered state on reopen
- New xlsx-viewer.html: standalone Luckysheet page for opening xlsx in separate window
- Added "↗ 새 창" button on xlsx cards to open viewer in a resizable popup window
- Viewer shares session cookies so auth works transparently
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
Skills:
- Add accountant (CPA) and investor (CFA) skills with site: hints
- Add site: hints to lawyer, psychiatrist, musician skills
- Allow multiple skills active simultaneously (remove exclusive mode)
Tools:
- Add excel_read / excel_write tools (openpyxl-based)
- Fix python_eval packages: retry with --break-system-packages on PEP 668 failure
- Fix email_read: spaces→underscores in filenames, return /api/files/ links,
remove absolute savedPaths from data, send SSE 'files' event for attachments
Server:
- FILE_OP v2: fall through to primary when secondary model unavailable
- Add PUT /api/files/{*filePath} endpoint for xlsx editor save
UI:
- xlsx viewer: Luckysheet modal (lazy CDN load, ~3MB on first use)
with edit mode, 💾 save button, Nanum Gothic font
- Email attachment preview: SSE 'files' event appends file links to final reply
- ✏️ 편집 button (blue) for xlsx cards
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
스캔 PDF에서 텍스트 추출 실패 시 자동으로 OCR 실행.
PyMuPDF로 300DPI 이미지 렌더링 후 tesseract kor+eng 적용.
ocr: true 파라미터로 강제 OCR 가능. method 필드로 추출 방법 표시.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
사용자가 업로드한 PDF는 이미 갖고 있으므로 저장 버튼 불필요.
renderMarkdown/renderLinkButton에 hideDownload 옵션 추가,
유저 메시지 렌더링 시 적용. 미리보기 버튼은 유지.
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
스캔 악보 PDF 처리 절차 추가:
pdf_read 시도 → 실패 시 pdf_extract_images로 페이지 추출 → image_read로 시각 분석.
도구 목록에 pdf_extract_images, image_read 추가.
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>
When no explicit output path is given and source is JPEG/WebP, output
defaults to PNG (lossless). This avoids cumulative quality loss on
repeated edits (brightness → contrast → filter → ...).
Exception: 'convert' operation keeps the original format so explicit
format-change requests still work. Explicit output path always honored.
Also fix quality default mismatch: TS params was 85, Python was 92.
Now both are 92 for when JPEG/WebP output is explicitly requested.
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>
- Add Korean search keywords to WEB category (뉴스, 검색해, etc.) so
Korean news queries trigger web_search instead of ollama_web_search
- Show ✓ SearXNG in startup banner when searxng_url is configured
- Update dental dict databases scripts and DB
- Clean up stale sessions and workspace runtime files
Co-Authored-By: Claude Sonnet 4.6 <noreply@anthropic.com>
image_edit:
- speech_bubble operation with Korean font, rounded rect, tail
- sketch quality: CLAHE pre-processing for better line contrast
- output filename with timestamp to prevent overwrites
- anime/painting stylize timeout 30s→600s (AnimeGANv2 model download)
- remove_bg PNG output fix
server-v2.ts:
- resolveToolImageContent: embed edited image as base64 in tool results
so vision models can see the output (3 execution paths covered)
- _activeModelName: fix vision support detection for Ollama-hosted models
(kimi/gemini run via Ollama — provider='ollama' was masking vision capability)
- Synthetic tool call ID generation to prevent Gemini function_response empty name error
- image_edit path hint format changed to English to prevent Gemini hallucination
- userRequestedImageEdit: expanded keyword list (풍선, 달아, 붙여 등)
- image_read OCR failure returns success:true with visual description hint
- TOOL_BLOCKS photo: image_edit workflow documentation updated
web-ui/index.html:
- renderFileDownloads: skip download buttons for image file extensions
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>
kim
