openpencil/README.de.md
Kayshen Xu 8472d4ac04 V0.5.0 (#67)
* docs: add image search & generation design spec and implementation plan

- Spec: dual-source image search (Openverse + Wikimedia), multi-provider image generation
- Plan: 16 tasks covering types, server endpoints, settings UI, property panel, auto-search pipeline, MCP integration

* feat(types): add image service types and imagePrompt to ImageNode

* feat(server): add image service API key validation endpoint

Adds POST /api/ai/image-service-test that validates credentials for
openverse (client_credentials), openai/custom (Bearer + /v1/models),
gemini (API key + v1beta/models), and replicate (Bearer + /v1/models).

* feat(server): add multi-provider image generation endpoint

* feat(server): add dual-source image search endpoint (Openverse + Wikimedia)

POST /api/ai/image-search searches freely-licensed images via Openverse
with automatic fallback to Wikimedia Commons on 429 rate-limit responses.
Supports optional OAuth credentials for authenticated Openverse requests.

* feat(store): add imageSearchStatuses to canvas store for runtime status tracking

* feat(store): add image generation config and Openverse OAuth to agent settings

* feat(editor): add Images tab to agent settings dialog

Adds Popover primitive, ImagesPage component with Image Search (Openverse OAuth, test) and Image Generation (provider select, API key, model, base URL) sections, and wires them into the settings dialog sidebar.

* feat(panels): add image search popover with Openverse/Wikimedia results grid

* feat(panels): add image generate popover with multi-provider support

* feat(panels): add Search and Generate buttons to image property section

* feat(ai): update prompts to use imagePrompt instead of src for image nodes

* feat(ai): add auto-search pipeline with Openverse/Wikimedia fallback

* feat(ai): trigger auto image search after design generation completes

* feat(mcp): implement G() operation for image search in batch design DSL

Adds the G(parent, mode, prompt) operation to batch_design DSL that creates
an image node and optionally fetches a real image URL via the image-search
API when mode is "search". Converts executeLine to async to support the
network call.

* feat(mcp): auto-fill images after design refinement in layered pipeline

* feat(ai): split imageSearchQuery and imagePrompt for search vs generation

- ImageNode now has both imageSearchQuery (short keywords for search)
  and imagePrompt (long description for AI image generation)
- AI prompts instruct LLM to generate both fields
- Search pipeline and popovers use imageSearchQuery
- Generate popover uses imagePrompt
- Server-side simplifySearchQuery kept as fallback for manual input

* fix(ai): hook auto image search into orchestrator completion path

The primary generation path uses executeOrchestration -> insertStreamingNode,
not applyNodesToCanvas/animateNodesToCanvas. Added scanAndFillImages call
to orchestrator.ts after all sub-agents complete. Added debug logging.
Removed plan/spec docs from git.

* style(editor): remove provider names from image search ready status

* fix(panels): clean up image gen error display and settings UI

- Parse API error response to show concise message instead of raw JSON
- Limit error text to 2 lines with line-clamp
- Fix image gen test button sending wrong service name
- Inline Image Search ready indicator with section header
- Remove debug logging from image search pipeline

* style(panels): allow up to 4 lines for image gen error message

* fix: avoid 1-frame delay when resizing canvas (#60)

rAF callbacks run before ResizeObserver in the same frame.
Scheduling render in ResizeObserver via rAF defers it to the next frame.

Invoke render() synchronously to leverage ResizeObserver's pre-paint timing
and ensure immediate visual update.

* feat(electron): implement desktop application structure and auto-updater

- Introduced a new Electron desktop application with a structured directory for apps and packages.
- Added auto-updater functionality to manage application updates seamlessly.
- Created a comprehensive menu system for the desktop app.
- Implemented logging capabilities for better debugging and error tracking.
- Configured build settings for various platforms (macOS, Windows, Linux) using electron-builder.
- Established TypeScript configurations for both the desktop and web applications.
- Integrated Vite for the web application with support for React and Tailwind CSS.
- Added icons and assets for the desktop application.

* chore: update package versions to 0.5.0 across all package.json files and add pre-commit hook for version synchronization

- Bumped version to 0.5.0 in package.json files for the main project, desktop app, web app, and all packages.
- Introduced a pre-commit hook to automatically sync version numbers from branch names to all package.json files.

* chore: update package versions to 0.5.0 and refactor Skia components

- Bumped version to 0.5.0 in bun.lock and all relevant package.json files.
- Refactored Skia components to utilize shared functionality from @zseven-w/pen-renderer, including image loading, hit testing, and path utilities.
- Removed redundant code and improved modularity by re-exporting necessary functions and classes from the renderer package.

* fix(panels): handle string fill values in icon nodes (#61)

AI-generated icon/path nodes may have fill stored as a raw string
instead of a PenFill[] array, causing "Cannot use 'in' operator"
crash when selecting the node in the property panel.

* chore: update documentation and project structure for monorepo organization

- Added a new version bump command to synchronize all package.json files.
- Updated the project structure to reflect a monorepo setup with organized workspaces for apps and packages.
- Enhanced README files in multiple languages to include the new structure and commands.
- Adjusted image paths in documentation to point to the correct locations for the desktop application.

* feat(ai): incremental image search and improved image generation prompts

- Refactor image search from batch post-generation to incremental queue:
  enqueueImageForSearch() triggers as each image node is inserted during
  streaming, so images appear progressively instead of all at once after
  generation completes. scanAndFillImages() remains as a final sweep.
- Update imagePrompt guidance to avoid "transparent background" and
  similar phrases that many models cannot reliably produce.
- Pass node width/height from image panel to generation endpoint for
  aspect-ratio-aware output (Gemini aspect ratio mapping, OpenAI size
  selection, Replicate dimensions).

* feat(ai): multi-profile image generation config and cleaner error messages

- Support multiple image generation profiles with active selection;
  first configured profile becomes default. Old single-config migrated
  automatically on hydrate.
- Fix Gemini aspect ratio: move to generationConfig.imageConfig per API spec.
- Extract clean error messages from provider JSON responses (Gemini
  error.message, OpenAI error.message, Replicate detail) instead of
  returning raw JSON text.
- Remove destructive client-side regex that mangled error display.

* feat(design-md): integrate design system panel and functionality

- Added a new DesignMdPanel component for managing design system specifications.
- Implemented functionality to toggle the design system panel in the editor layout and toolbar.
- Introduced new commands for importing, exporting, and auto-generating design.md content.
- Updated AI chat handlers to utilize design.md data for enhanced design generation.
- Enhanced localization support for design system features across multiple languages.

* perf(canvas): skip draw calls for nodes outside the viewport (#64)

Add viewport culling in render() to avoid issuing CanvasKit draw calls
  for off-screen nodes. A 64px screen-space buffer is kept around the
  viewport edges so nearby nodes are pre-rendered, preventing pop-in
  during fast panning.

* feat(utils): enhance Windows process spawning for CLI scripts

- Updated the buildSpawnClaudeCodeProcess function to handle .cmd and .ps1 scripts appropriately.
- Implemented PowerShell invocation for .ps1 files and ensured safe defaults for .cmd and .exe files.
- Improved handling of command execution to avoid limitations of cmd.exe.

* feat(ai): add support for Gemini CLI integration

- Extended the AI provider options to include 'gemini' across various components and APIs.
- Implemented functions for generating, validating, and connecting to the Gemini CLI.
- Added Gemini-specific error handling and model fetching logic.
- Updated UI components to display Gemini as a selectable provider with appropriate icons and labels.
- Enhanced localization support for Gemini-related features in multiple languages.

* feat(editor): warn before closing with unsaved changes

Intercept window/tab close when isDirty is true:
- Electron: native dialog with Save / Don't Save / Cancel
- Web: beforeunload handler + confirm on New/Open actions
- i18n: close-confirm strings for all 15 locales

* feat(ipc): extract IPC handlers to a dedicated module

- Moved IPC dialog handling and updater functions from main.ts to ipc-handlers.ts for better organization and maintainability.
- Implemented file open/save dialogs, theme setting, and preferences management through IPC.
- Enhanced updater functionality with state management and auto-update settings.
- Improved code structure by separating concerns, making it easier to manage IPC-related logic.

* feat(docs): update CLAUDE documentation and add new files for desktop and web apps

- Enhanced CLAUDE.md with detailed module documentation references for `packages/` and `apps/`.
- Updated `pen-core` description to include clone utilities in `pen-core`.
- Added new documentation files for the desktop and web applications, outlining their structure, components, and functionalities.
- Included IPC handler details in the desktop app documentation for better clarity on file dialogs and theme synchronization.

* feat(docker): add Gemini CLI support and update documentation

- Introduced a new Docker build stage for the Gemini CLI, allowing users to install and run it.
- Updated the Dockerfile to include the installation of the Gemini CLI alongside existing CLI tools.
- Enhanced README files in multiple languages to document the new `openpencil-gemini` image variant.
- Added Gemini CLI connection instructions to the main README for better user guidance.

* feat(docs): add Gemini CLI connection instructions to multiple language READMEs

- Updated README files in German, Spanish, French, Hindi, Indonesian, Japanese, Korean, Portuguese, Russian, Thai, Turkish, Vietnamese, and both Traditional and Simplified Chinese to include connection instructions for the Gemini CLI.
- Enhanced documentation to improve user guidance for connecting the Gemini CLI in agent settings.

* perf(renderer): replace count-based text cache limits with memory-based eviction (#66)

previous limits (PARA_CACHE_MAX=200, TEXT_CACHE_MAX=300) were too small
  for scenes with many nodes, causing constant cache churn and paragraph
  rebuilds every frame, which dropped FPS significantly during canvas pan.

  - switch to byte-budget limits (64 MB paragraphs, 256 MB bitmaps)
  - bitmap size measured exactly as cw*ch*4; paragraph WASM heap estimated
    as content.length*64+4096
  - eviction uses Map insertion order (FIFO) instead of a separate string[]
    array, replacing O(n) array.shift() with O(1) Map.entries().next()
  - evict before insert so the budget check includes the incoming entry

---------

Co-authored-by: Fini <fini.yang@gmail.com>
Co-authored-by: leinaldo <60176594+leinaldo@users.noreply.github.com>
2026-03-22 09:44:04 +08:00

14 KiB

OpenPencil

OpenPencil

Das weltweit erste KI-native Open-Source-Vektordesign-Werkzeug.
Parallele Agententeams • Design-as-Code • Eingebauter MCP-Server • Multi-Modell-Intelligenz

English · 简体中文 · 繁體中文 · 日本語 · 한국어 · Français · Español · Deutsch · Português · Русский · हिन्दी · Türkçe · ไทย · Tiếng Việt · Bahasa Indonesia

Stars License CI Discord


OpenPencil — Klicken, um das Demo-Video anzusehen

Auf das Bild klicken, um das Demo-Video anzusehen


Warum OpenPencil

🎨 Prompt → Canvas

Beschreiben Sie jede UI in natürlicher Sprache. Beobachten Sie, wie sie in Echtzeit mit Streaming-Animation auf der unendlichen Canvas erscheint. Ändern Sie bestehende Designs, indem Sie Elemente auswählen und chatten.

🤖 Parallele Agententeams

Der Orchestrierer zerlegt komplexe Seiten in räumliche Teilaufgaben. Mehrere KI-Agenten arbeiten gleichzeitig an verschiedenen Bereichen — Hero, Features, Footer — alle parallel streamend.

🧠 Multi-Modell-Intelligenz

Passt sich automatisch an die Fähigkeiten jedes Modells an. Claude erhält vollständige Prompts mit Thinking; GPT-4o/Gemini deaktivieren Thinking; kleinere Modelle (MiniMax, Qwen, Llama) erhalten vereinfachte Prompts für zuverlässige Ausgabe.

🔌 MCP-Server

Ein-Klick-Installation in Claude Code, Codex, Gemini, OpenCode, Kiro oder Copilot CLIs. Designen Sie aus Ihrem Terminal — .op-Dateien über jeden MCP-kompatiblen Agenten lesen, erstellen und bearbeiten.

📦 Design-as-Code

.op-Dateien sind JSON — menschenlesbar, Git-freundlich, diff-fähig. Designvariablen generieren CSS Custom Properties. Code-Export nach React + Tailwind oder HTML + CSS.

🖥️ Läuft überall

Web-App + native Desktop-Anwendung auf macOS, Windows und Linux über Electron. Auto-Updates über GitHub Releases. .op-Dateizuordnung — Doppelklick zum Öffnen.

Schnellstart

# Abhängigkeiten installieren
bun install

# Entwicklungsserver auf http://localhost:3000 starten
bun --bun run dev

Oder als Desktop-App ausführen:

bun run electron:dev

Voraussetzungen: Bun >= 1.0 und Node.js >= 18

Docker

Mehrere Image-Varianten sind verfügbar — wählen Sie die passende für Ihre Anforderungen:

Image Größe Enthält
openpencil:latest ~226 MB Nur Web-App
openpencil-claude:latest + Claude Code CLI
openpencil-codex:latest + Codex CLI
openpencil-opencode:latest + OpenCode CLI
openpencil-copilot:latest + GitHub Copilot CLI
openpencil-gemini:latest + Gemini CLI
openpencil-full:latest ~1 GB Alle CLI-Tools

Ausführen (nur Web):

docker run -d -p 3000:3000 ghcr.io/zseven-w/openpencil:latest

Mit KI-CLI ausführen (z.B. Claude Code):

Der KI-Chat basiert auf Claude CLI OAuth-Login. Verwenden Sie ein Docker-Volume, um die Login-Sitzung beizubehalten:

# Schritt 1 — Login (einmalig)
docker volume create openpencil-claude-auth
docker run -it --rm \
  -v openpencil-claude-auth:/root/.claude \
  ghcr.io/zseven-w/openpencil-claude:latest claude login

# Schritt 2 — Starten
docker run -d -p 3000:3000 \
  -v openpencil-claude-auth:/root/.claude \
  ghcr.io/zseven-w/openpencil-claude:latest

Lokal bauen:

# Basis (nur Web)
docker build --target base -t openpencil .

# Mit einem bestimmten CLI
docker build --target with-claude -t openpencil-claude .

# Vollständig (alle CLIs)
docker build --target full -t openpencil-full .

KI-natives Design

Vom Prompt zur UI

  • Text-zu-Design — eine Seite beschreiben und sie wird in Echtzeit mit Streaming-Animation auf der Canvas generiert
  • Orchestrierer — zerlegt komplexe Seiten in räumliche Teilaufgaben zur parallelen Generierung
  • Design-Modifikation — Elemente auswählen und Änderungen in natürlicher Sprache beschreiben
  • Bildeingabe — Screenshots oder Mockups als Referenz für referenzbasiertes Design anhängen

Multi-Agenten-Unterstützung

Agent Einrichtung
Claude Code Keine Konfiguration — verwendet Claude Agent SDK mit lokalem OAuth
Codex CLI In den Agenteneinstellungen verbinden (Cmd+,)
OpenCode In den Agenteneinstellungen verbinden (Cmd+,)
GitHub Copilot copilot login dann in den Agenteneinstellungen verbinden (Cmd+,)
Gemini CLI In den Agenteneinstellungen verbinden (Cmd+,)

Modell-Fähigkeitsprofile — passt Prompts, Thinking-Modus und Timeouts automatisch pro Modellstufe an. Modelle der Vollstufe (Claude) erhalten vollständige Prompts; Standardstufe (GPT-4o, Gemini, DeepSeek) deaktiviert Thinking; Basisstufe (MiniMax, Qwen, Llama, Mistral) erhält vereinfachte verschachtelte JSON-Prompts für maximale Zuverlässigkeit.

MCP-Server

  • Eingebauter MCP-Server — Ein-Klick-Installation in Claude Code / Codex / Gemini / OpenCode / Kiro / Copilot CLIs
  • Automatische Node.js-Erkennung — falls nicht installiert, automatischer Fallback auf HTTP-Transport und automatischer Start des MCP-HTTP-Servers
  • Design-Automatisierung vom Terminal aus: .op-Dateien über jeden MCP-kompatiblen Agenten lesen, erstellen und bearbeiten
  • Mehrstufiger Design-Workflowdesign_skeletondesign_contentdesign_refine für hochwertigere mehrteilige Designs
  • Segmentierter Prompt-Abruf — laden Sie nur das benötigte Design-Wissen (Schema, Layout, Rollen, Icons, Planung usw.)
  • Mehrseitige Unterstützung — Seiten erstellen, umbenennen, neu ordnen und duplizieren über MCP-Tools

Codegenerierung

  • React + Tailwind CSS, HTML + CSS, CSS Variables
  • Vue, Svelte, Flutter, SwiftUI, Jetpack Compose, React Native

Funktionen

Canvas und Zeichnen

  • Unendliche Canvas mit Pan, Zoom, intelligenten Ausrichtungshilfslinien und Einrasten
  • Rechteck, Ellipse, Linie, Polygon, Stift (Bezier), Frame, Text
  • Boolesche Operationen — Vereinigung, Subtraktion, Schnittmenge mit kontextbezogener Werkzeugleiste
  • Icon-Auswahl (Iconify) und Bildimport (PNG/JPEG/SVG/WebP/GIF)
  • Auto-Layout — vertikal/horizontal mit Gap, Padding, Justify, Align
  • Mehrseitige Dokumente mit Tab-Navigation

Designsystem

  • Designvariablen — Farb-, Zahl- und Text-Tokens mit $variable-Referenzen
  • Multi-Theme-Unterstützung — mehrere Achsen, jeweils mit Varianten (Hell/Dunkel, Kompakt/Komfortabel)
  • Komponentensystem — wiederverwendbare Komponenten mit Instanzen und Überschreibungen
  • CSS-Synchronisierung — automatisch generierte benutzerdefinierte Eigenschaften, var(--name) in der Code-Ausgabe

Figma-Import

  • .fig-Dateien importieren mit erhaltenem Layout, Füllungen, Konturen, Effekten, Text, Bildern und Vektoren

Desktop-App

  • Natives macOS, Windows und Linux über Electron
  • .op-Dateizuordnung — Doppelklick zum Öffnen, Einzelinstanzsperre
  • Automatische Aktualisierung über GitHub Releases
  • Natives Anwendungsmenü und Dateidialoge

Technologie-Stack

Frontend React 19 · TanStack Start · Tailwind CSS v4 · shadcn/ui
Canvas CanvasKit/Skia (WASM, GPU-beschleunigt)
State Zustand v5
Server Nitro
Desktop Electron 35
KI Anthropic SDK · Claude Agent SDK · OpenCode SDK · Copilot SDK
Laufzeit Bun · Vite 7
Dateiformat .op — JSON-basiert, menschenlesbar, Git-freundlich

Projektstruktur

openpencil/
├── apps/
│   ├── web/                 TanStack Start Web-App
│   │   ├── src/
│   │   │   ├── canvas/      CanvasKit/Skia-Engine — Zeichnen, Sync, Layout
│   │   │   ├── components/  React-UI — Editor, Panels, gemeinsame Dialoge, Icons
│   │   │   ├── services/ai/ KI-Chat, Orchestrierer, Designgenerierung, Streaming
│   │   │   ├── stores/      Zustand — Canvas, Dokument, Seiten, Verlauf, KI
│   │   │   ├── mcp/         MCP-Server-Tools für externe CLI-Integration
│   │   │   ├── hooks/       Tastaturkürzel, Datei-Drop, Figma-Paste
│   │   │   └── uikit/       Wiederverwendbares Komponenten-Kit-System
│   │   └── server/
│   │       ├── api/ai/      Nitro-API — Streaming-Chat, Generierung, Validierung
│   │       └── utils/       Claude CLI, OpenCode, Codex, Copilot-Wrapper
│   └── desktop/             Electron-Desktop-App
│       ├── main.ts          Fenster, Nitro-Fork, natives Menü, Auto-Updater
│       ├── ipc-handlers.ts  Native Dateidialoge, Theme-Sync, Einstellungen-IPC
│       └── preload.ts       IPC-Brücke
├── packages/
│   ├── pen-types/           Typdefinitionen für das PenDocument-Modell
│   ├── pen-core/            Dokumentbaum-Operationen, Layout-Engine, Variablen
│   ├── pen-codegen/         Codegeneratoren (React, HTML, Vue, Flutter, ...)
│   ├── pen-figma/           Figma-.fig-Datei-Parser und -Konverter
│   ├── pen-renderer/        Eigenständiger CanvasKit/Skia-Renderer
│   └── pen-sdk/             Umbrella-SDK (re-exportiert alle Pakete)
└── .githooks/               Pre-Commit-Versionssynchronisierung vom Branch-Namen

Tastaturkürzel

Taste Aktion Taste Aktion
V Auswählen Cmd+S Speichern
R Rechteck Cmd+Z Rückgängig
O Ellipse Cmd+Shift+Z Wiederholen
L Linie Cmd+C/X/V/D Kopieren/Ausschneiden/Einfügen/Duplizieren
T Text Cmd+G Gruppieren
F Frame Cmd+Shift+G Gruppierung aufheben
P Stiftwerkzeug Cmd+Shift+E Exportieren
H Hand (Pan) Cmd+Shift+C Code-Panel
Del Löschen Cmd+Shift+V Variablen-Panel
[ / ] Reihenfolge ändern Cmd+J KI-Chat
Pfeiltasten 1px verschieben Cmd+, Agenteneinstellungen
Cmd+Alt+U Boolesche Vereinigung Cmd+Alt+S Boolesche Subtraktion
Cmd+Alt+I Boolesche Schnittmenge

Skripte

bun --bun run dev          # Entwicklungsserver (Port 3000)
bun --bun run build        # Produktions-Build
bun --bun run test         # Tests ausführen (Vitest)
npx tsc --noEmit           # Typprüfung
bun run bump <version>     # Version über alle package.json synchronisieren
bun run electron:dev       # Electron-Entwicklung
bun run electron:build     # Electron-Paketierung

Mitwirken

Beiträge sind willkommen! Siehe CLAUDE.md für Architekturdetails und Code-Stil.

  1. Forken und klonen
  2. Versionssynchronisierung einrichten: git config core.hooksPath .githooks
  3. Branch erstellen: git checkout -b feat/my-feature
  4. Prüfungen ausführen: npx tsc --noEmit && bun --bun run test
  5. Mit Conventional Commits committen: feat(canvas): add rotation snapping
  6. Pull Request gegen main öffnen

Roadmap

  • Designvariablen & Tokens mit CSS-Synchronisierung
  • Komponentensystem (Instanzen & Überschreibungen)
  • KI-Designgenerierung mit Orchestrierer
  • MCP-Server-Integration mit mehrstufigem Design-Workflow
  • Mehrseitige Unterstützung
  • Figma-.fig-Import
  • Boolesche Operationen (Vereinigung, Subtraktion, Schnittmenge)
  • Multi-Modell-Fähigkeitsprofile
  • Monorepo-Umstrukturierung mit wiederverwendbaren Paketen
  • Kollaboratives Bearbeiten
  • Plugin-System

Mitwirkende

Contributors

Community

Discord Unserem Discord beitreten — Fragen stellen, Designs teilen, Funktionen vorschlagen.

Star History

Star History Chart

Lizenz

MIT — Copyright (c) 2026 ZSeven-W