* feat(editor): add github releases auto update flow
Enable desktop auto-update checks and install prompt so packaged apps can update from published GitHub Releases.
* fix(canvas): keep frame labels aligned during zoom
Draw labels in viewport space with zoom-aware positioning so frame titles stay anchored while panning and zooming.
* fix(ai): disable chat interactions when no models connected
Prevent sending and shortcut actions when provider models are unavailable, and show a concise model picker hint to avoid false-available UI states.
* docs: refresh readme community and demo section
Embed the product demo video inline, add a styled Discord community entry, and update media assets for clearer README presentation.
* chore: update nitro external dependency settings
Align SSR bundling with current runtime usage by removing the unnecessary @opencode-ai external entries.
* feat(electron): enhance macOS build process and update auto-updater
- Added a new build script for macOS that allows building for both arm64 and x64 architectures.
- Updated GitHub Actions workflow to support separate build arguments for macOS arm64 and x64.
- Implemented a custom GitHub update provider for macOS to handle versioning based on architecture.
- Introduced a new icon for the electron app and removed the old logo image.
* feat(editor): enhance update ready banner with additional states and UI improvements
- Added new state management for checking updates and dismissed status.
- Improved visibility logic for the update banner based on update states.
- Enhanced UI to display current and latest version information, download progress, and error messages.
- Updated layout and styling for better user experience and accessibility.
* docs: replace stripped video embed with clickable cover link
GitHub sanitizes README HTML video tags, so the embedded demo player does not render on repository pages.
Use a clickable poster image and explicit watch link to preserve the demo entry point across GitHub README rendering.
---------
Co-authored-by: Fini <fini.yang@gmail.com>
* feat(editor): add github releases auto update flow
Enable desktop auto-update checks and install prompt so packaged apps can update from published GitHub Releases.
* fix(canvas): keep frame labels aligned during zoom
Draw labels in viewport space with zoom-aware positioning so frame titles stay anchored while panning and zooming.
* fix(ai): disable chat interactions when no models connected
Prevent sending and shortcut actions when provider models are unavailable, and show a concise model picker hint to avoid false-available UI states.
* docs: refresh readme community and demo section
Embed the product demo video inline, add a styled Discord community entry, and update media assets for clearer README presentation.
* chore: update nitro external dependency settings
Align SSR bundling with current runtime usage by removing the unnecessary @opencode-ai external entries.
* feat(electron): enhance macOS build process and update auto-updater
- Added a new build script for macOS that allows building for both arm64 and x64 architectures.
- Updated GitHub Actions workflow to support separate build arguments for macOS arm64 and x64.
- Implemented a custom GitHub update provider for macOS to handle versioning based on architecture.
- Introduced a new icon for the electron app and removed the old logo image.
---------
Co-authored-by: Fini <fini.yang@gmail.com>
* chore(docs): add video demo to README.md for enhanced project visibility
* refactor(ai): centralize Claude Agent SDK env resolution with debug logging and model retry
Extract shared buildClaudeAgentEnv() and getClaudeAgentDebugFilePath() into
resolve-claude-agent-env.ts to eliminate duplicated env setup across all
server endpoints. Add model fallback retry logic (retry without explicit
model on exit code 1) and diagnostic hints from debug log tail on failures.
* fix(canvas): normalize layout justify/align values from CSS aliases
AI-generated nodes may use CSS-style values like "flex-start",
"space-between", "middle" etc. Add normalizeJustifyContent and
normalizeAlignItems to map these to internal enum values in both
the layout engine and the property panel.
* fix(canvas): improve text and path rendering accuracy
- Remove icon-specific bounding box override on path scaling to prevent
pathOffset drift that visually offsets icons in logo containers
- Only use Textbox for explicit fixed-width text modes instead of any
node with width > 0, preventing unwanted word wrapping on auto-width text
- Add widthSafetyFactor for Latin text estimation (1.14x vs 1.06x CJK)
to reduce accidental line wraps from font width variation
* feat(ai): add input icon affordance rules and trailing icon alignment
Prompt AI to include semantic icons in form inputs (search, password,
email). Add normalizeInputTrailingIconAlignment post-pass in
role-resolver to auto-set justifyContent="space_between" on input
frames with a trailing icon node.
* feat(ai): persist model selection across sessions via localStorage
Add preferredModel and selectModel to ai-store with localStorage
read/write. Hydrate on mount to restore user's last chosen model.
Add isHydrated flag to agent-settings-store to prevent race
conditions during provider list construction.
* chore(package): update version to 0.0.2 and add new build scripts for mac architectures
---------
Co-authored-by: Fini <fini.yang@gmail.com>
* chore(docs): add video demo to README.md for enhanced project visibility
* refactor(ai): centralize Claude Agent SDK env resolution with debug logging and model retry
Extract shared buildClaudeAgentEnv() and getClaudeAgentDebugFilePath() into
resolve-claude-agent-env.ts to eliminate duplicated env setup across all
server endpoints. Add model fallback retry logic (retry without explicit
model on exit code 1) and diagnostic hints from debug log tail on failures.
* fix(canvas): normalize layout justify/align values from CSS aliases
AI-generated nodes may use CSS-style values like "flex-start",
"space-between", "middle" etc. Add normalizeJustifyContent and
normalizeAlignItems to map these to internal enum values in both
the layout engine and the property panel.
* fix(canvas): improve text and path rendering accuracy
- Remove icon-specific bounding box override on path scaling to prevent
pathOffset drift that visually offsets icons in logo containers
- Only use Textbox for explicit fixed-width text modes instead of any
node with width > 0, preventing unwanted word wrapping on auto-width text
- Add widthSafetyFactor for Latin text estimation (1.14x vs 1.06x CJK)
to reduce accidental line wraps from font width variation
* feat(ai): add input icon affordance rules and trailing icon alignment
Prompt AI to include semantic icons in form inputs (search, password,
email). Add normalizeInputTrailingIconAlignment post-pass in
role-resolver to auto-set justifyContent="space_between" on input
frames with a trailing icon node.
* feat(ai): persist model selection across sessions via localStorage
Add preferredModel and selectModel to ai-store with localStorage
read/write. Hydrate on mount to restore user's last chosen model.
Add isHydrated flag to agent-settings-store to prevent race
conditions during provider list construction.
---------
Co-authored-by: Fini <fini.yang@gmail.com>
- Translated code style guidelines from Chinese to English for better accessibility.
- Revised Git commit conventions section for clarity and consistency in language.
- Updated README.md to reflect the correct GitHub repository and added a demo screenshot.
- Added new demo screenshot file to enhance visual representation of the project.
- icon-resolver: refactor ICON_PATH_MAP with shared IconEntry constants
and s()/f() helpers to eliminate duplicate path strings; fix timer and
pencil icon paths which were incorrectly aliased to clock/edit
- icon-resolver: remove BRAND_PLACEHOLDER_MAP — brand icons now go
straight to async resolution (simple-icons) without a Feather placeholder
- icon-resolver: add tryImmediateIconResolution() — fires a 600ms-timeout
fetch during streaming so brand icons appear without waiting for
post-stream resolution; pending queue remains as fallback on timeout
- design-canvas-ops: normalize gradient stops in insertStreamingNode to
catch AI-generated nodes before they reach the store
- design-canvas-ops: call resolveAllPendingIcons() after all non-streaming
apply paths (applyNodesToCanvas, animateNodesToCanvas)
Install @iconify-json/lucide and @iconify-json/simple-icons as server-only
dependencies. Rewrite /api/ai/icon to read from local bundled JSON instead
of fetching from api.iconify.design, eliminating the external network
dependency that caused brand icons to silently fail.
Search order: simple-icons first (brand logos only — no UI name collisions),
then lucide (UI icons). Covers 3670 brand icons and 1729 Lucide icons
with sub-millisecond lookup. No impact on client bundle size.
All icons in icon-resolver.ts now carry iconId (e.g. feather:search),
so after AI generation each node automatically maps to the correct
library in the property panel picker. The built-in "OpenPencil"
collection in the picker is no longer needed.
Removes BUILTIN_ICONS import, BUILTIN_ICON_MAP, buildBuiltinSvg,
getIconColorRaw, and all openpencil-specific branches from the dialog.
AI sometimes omits the offset field on gradient stops, causing
Math.round(undefined * 100) = NaN in the UI. Fix at two layers:
- normalize-pen-file.ts: auto-distribute missing offsets evenly across
[0,1] and convert percentage-format offsets (>1) to 0-1 range
- fill-section.tsx: defensive guard in the stop percentage display
featherBodyToPathD was missing <line>, <polyline>, and <polygon>
support. Feather icons heavily use these elements — e.g. arrow-right,
menu, check, x all use <line> or <polyline>. Without this support,
many common icons returned d=null and were never added to ICON_PATH_MAP,
causing them to fall back to async Iconify fetch or the generic star
placeholder instead of rendering correctly.
Now all 286 Feather icons are fully parsed and available offline.
- Export AVAILABLE_FEATHER_ICONS list from icon-resolver
- Add findPrefixFallback() for compound icon name resolution
- Fix rawName="" edge case when node is named exactly "Icon"
- Inject full Feather icon list into AI prompts so the model
only picks names guaranteed to resolve locally without network
Install @iconify-json/feather and populate ICON_PATH_MAP at module init time
by parsing the bundled SVG body strings (handles <path>, <circle>, <ellipse>,
<rect> elements). Both kebab-case ("arrow-right") and normalized ("arrowright")
keys are registered so the icon name resolver finds them immediately without
any Iconify API calls.
- Add ~40 more common Lucide icons to ICON_PATH_MAP (phone, calendar, clock,
bookmark, edit, trash, chat, shield, zap, camera, chart, filter, etc.)
so they resolve instantly without relying on the Iconify async fetch
- Fix rawName="" bug: when a node is named exactly "Icon" or "Logo", stripping
the suffix leaves an empty string causing the async queue guard to silently
skip it; now falls back to the full normalized name for the queue key
For icon nodes (PathNode with iconId), expand Fabric's logical bounding box to
the declared w×h so selection handles always form a perfect square, while the
path content remains centered via Fabric's natural pathOffset.
- Add IconSection panel shown when a path node with iconId is selected
- Add IconPickerDialog: anchored popover with collection browsing, search,
current icon highlight, and outside-click/Escape to close
- Add iconId field to PathNode to track Iconify icon identity
- Fix canvas path sync to update d in-place (no object recreation/focus loss)
- Fix multi-element SVG icons: convert circles, rects, lines to path commands
so shapes like emoji face circles are not dropped during icon replacement
- Filter invisible bounding-box paths (Tabler's M0 0h24v24H0z) before merging
- Preserve original node width/height on icon replace; carry over display color
- Populate iconId in AI icon resolver and server-side Iconify proxy
- Introduced a layout engine for auto-layout computation, including padding resolution and fit-content size calculations.
- Added a node creator for various drawing tools (rectangle, frame, ellipse, line, text) to streamline object creation.
- Implemented object modification handling to sync changes back to the document store, improving interaction with Fabric.js.
- Enhanced text measurement utilities for better width and height estimation, including support for CJK characters.
- Added new API endpoints for AI icon retrieval and validation, supporting multimodal content analysis.
- Differentiate text defaults by parent layout direction in insertStreamingNode (vertical=fill, horizontal=fit_content)
- Add shouldDemoteHorizontalTextFillInLayout to prevent short labels from stretching in horizontal rows
- Add countVisibleChildren utility for accurate sibling-aware text demotion
- Add isLikelyCenteredColumnContext, shouldCenterTextInCenteredColumn, shouldCenterButtonRowInContext
- Add isDenseCardPrimaryVisualCandidate to protect primary visual icons during dense card compaction
- Integrate text demotion and centered column logic into Fix 1 and applyTextFillContainerInLayout
- Apply shouldCenterButtonRowInContext in Fix 11 and applyFormChildFillContainer
- Add dense card row compaction (5+ cards): aggressively shorten text,
limit to 2 text blocks per card, remove non-essential decorative elements
- Flatten redundant single "Inner" wrapper layers to keep hierarchy shallow
- Add phone placeholder and divider frame detection and normalization
- Add isCompactButtonLikeFrame/isCompactControlFrame to prevent badge
heuristics from mis-targeting buttons and CTA elements
- Improve text width promotion logic with shouldPromoteTextWidthToFillInLayout
- Add long-text padding adjustment to prevent excessive horizontal padding
from squeezing body text in narrow containers
- Simplify horizontal overflow fix: remove fit_content strategy, prefer
parent expansion
- Reduce minimum section padding from 40px to 24px for desktop layouts
- Tune CJK lineHeight defaults (body 1.55, heading 1.35) and auto-height
estimation with paragraph-aware line wrapping
- Add shallow hierarchy and dense card row rules to AI prompts
- Skip invisible nodes (visible=false) in layout computation, flattenNodes,
and document bounds calculation
- Add getRootFillWidthFallback() to resolve fill_container width when parent
is unavailable, preventing frames from collapsing to content width
- Increase CJK glyph width estimate from 1.08 to 1.12 for more accurate sizing
- Pass parentAvail through fitContentWidth for better nested width resolution
- Remove reverse() in layer panel tree rendering to fix display order
- Use invisible fallback path (M0 0 L0 0) instead of dot for empty d attr
- Track __sourceD on path objects to detect d changes requiring recreation
- Generalize textRecreated to objectRecreated for path recreation support
- Tighten isBadgeLikeFrame: max height 40px, max 3 children, 1 icon max,
exclude explicit button names, width cap 260px, CJK label limit 10 chars
- Use full capsule radius (height/2) instead of clamped range for badges
Add COPYWRITING section to CHAT_SYSTEM_PROMPT, DESIGN_GENERATOR_PROMPT,
and SUB_AGENT_PROMPT enforcing concise text in generated designs:
headlines 2-6 words, descriptions ≤20 words, no 3+ sentence paragraphs.
- Add splitByGrapheme for CJK text to enable natural character-level wrapping
- Add optical vertical centering offset for single-line text in horizontal layouts
- Use fallback path data when SVG d attribute is empty to prevent render errors
- Fix stroke-only path detection to check for visible stroke (non-zero width)
- Add isBadgeLikeFrame heuristic for badge/chip/tag detection
- Enhance badge sizing: auto corner-radius, icon normalization, CJK-aware padding
- Fix fill-style icon resolution to always apply visible fill color
- Add dot/bullet/point/circlefill to icon path map
Refactor text measurement to use per-glyph width estimation with distinct
ranges for CJK, uppercase, lowercase, and digits. Add letter-spacing support
and paragraph-aware line wrapping to fix under-estimated text dimensions.
* feat(canvas,panels): multi-selection drag, shift-key selection, and chat pipeline UI
- Preserve multi-selection when clicking a selected object without Shift,
enabling drag-move of the whole set
- Set selectionKey to shiftKey so only Shift+click toggles multi-select
- Refactor chat-message step rendering: extract step blocks with regex,
add pipeline checklist progress UI, separate step display from markdown
- Adjust AI chat panel selection count display and layout
* feat(opencode): integrate OpenCode SDK for enhanced AI interactions
- Add support for OpenCode as a new AI provider, allowing users to connect to a local OpenCode server.
- Implement new API endpoints for generating and streaming chat responses via OpenCode.
- Update UI components to include OpenCode in provider selection and display.
- Introduce OpenCode logo and enhance the agent settings dialog to manage OpenCode connections.
- Refactor existing chat and generation logic to accommodate provider-specific routing.
- Include type definitions for OpenCode SDK to ensure type safety and improve developer experience.
* feat(electron): integrate Electron framework for desktop application support
- Add Electron configuration and main process setup for building a desktop application.
- Implement IPC communication for file operations (open, save) between the renderer and main processes.
- Create a preload script to expose Electron APIs to the renderer.
- Update package.json to include Electron and related dependencies.
- Enhance the build process with electron-builder for packaging the application.
- Introduce a new electron-builder.yml configuration file for build settings.
- Modify Vite configuration to support Electron-specific builds.
- Update UI components to accommodate Electron's window management and drag regions.
* fix(canvas): multi-selection drag reparenting and infinite recursion guard
- Add re-entry guard to object:modified handler to prevent infinite
recursion caused by discardActiveObject() firing object:modified
via _finalizeCurrentTransform
- Extend drag-into detection to non-layout root frames (rootFrameBounds)
in addition to layout containers (layoutContainerBounds)
- Add checkReparentIntoFrame() fallback for root-level objects dragged
into frames, handling both layout and non-layout targets
- Redirect _currentTransform to ActiveSelection in mouse:down so the
whole group moves/scales/rotates together
- Support same-container reorder in commitDragIntoMulti
- Fix guide-utils getEdges() for center-origin ActiveSelection objects
- Track selection descendants for visual drag-follow during multi-drag
- Show position coordinates during multi-selection drag in dimension label
* feat(store,canvas): add reusable component and instance system
add makeReusable/detachComponent store methods, RefNode resolution in
canvas sync with component/instance selection borders, virtual child ID
handling in selection context, purple/instance-colored frame labels,
and collision avoidance when duplicating nodes
* feat(panels): add component/instance UI to layer and property panels
layer panel shows diamond icon and purple/#9281f7 styling for
components/instances with context menu actions; property panel resolves
RefNode display, routes instance overrides, adds header with go-to and
detach buttons, and supports inline name editing on click
* feat(canvas): match hover outline to selection style for components and instances
hover outlines now use purple solid for reusable components and #9281f7
dashed for instances, consistent with their selection border styling
* fix(editor): save directly without dialog for previously opened files
prioritize fileName check over File System Access API so opened files
save via download without showing a file picker; also add Cmd+Alt+K
shortcut for creating reusable components
* refactor(canvas): remove dimension label overlay
remove the blue dimension/position label that appeared on selection,
drag, and scale interactions
* feat(export): add export section for raster image export functionality
- Introduce a new ExportSection component to facilitate exporting layers as raster images in various formats (PNG, JPEG, WEBP) with adjustable scale options.
- Integrate the ExportSection into the PropertyPanel for easy access during design editing.
- Enhance export utility functions to support exporting layers and managing descendant nodes.
* feat(assets): add new icon files for application branding
- Introduce new icon files in various formats (ICNS, ICO, PNG) for application branding.
- Add logo image for the Electron interface to enhance visual identity.
- Update canvas selection logic to allow programmatic selection from the layer panel.
* feat(electron): enhance Electron app integration and CI/CD workflows
- Add new commands for Electron development, compilation, and building processes in CLAUDE.md.
- Update README.md to reflect the availability of the application as both a web and desktop app.
- Introduce a FixedChecklist component in the AI chat panel for better user interaction with generated tasks.
- Implement CI/CD workflows for automated testing and Electron builds in GitHub Actions.
- Refactor design generator prompts to support element-by-element streaming for improved performance.
* feat(ai): enhance chat functionality and orchestration capabilities
- Introduce context optimization to manage chat history size and prevent unbounded growth.
- Implement complexity assessment for design prompts to determine orchestration needs.
- Add orchestrator functionality for parallel design generation, improving performance and responsiveness.
- Update chat message parsing to include explicit status handling for orchestrator steps.
- Refactor design generator to support orchestration and streamline context building.
* refactor(ai): streamline orchestration and remove complexity classifier
- Remove the complexity classifier as its functionality is no longer needed.
- Update design generator to always route through the orchestrator, simplifying the logic.
- Enhance error handling during orchestration to ensure fallback to direct generation is clear.
- Introduce a new sub-agent prompt for improved output formatting and clarity in design generation.
* feat(ai): refine orchestrator prompt and timeout settings
- Update the ORCHESTRATOR_PROMPT to allow for more granular task division, specifying 4-15 atomic sections.
- Enhance the JSON output structure by adding new subtasks for the hero section.
- Adjust ORCHESTRATOR_TIMEOUTS to extend hard and no-text timeout values for improved orchestration performance.
* feat(docs): update CLAUDE.md and README.md for new features and improvements
- Expand the Fabric.js integration section in CLAUDE.md to include new files and functionalities.
- Highlight new features such as double-click frame entry, advanced drag-and-drop capabilities, and per-layer export options in README.md.
- Add context optimization and multi-provider support for AI in README.md.
- Update the project structure descriptions for clarity and completeness.
* refactor(config): update Vite configuration import for Vitest compatibility
* chore(ci): update GitHub Actions workflow to trigger on main branch pushes
* feat(uikit): introduce UIKit browser and component management features
- Add a new ComponentBrowserPanel for browsing and managing UI components.
- Implement ComponentBrowserGrid and ComponentBrowserCard for displaying components.
- Integrate UIKit store for managing component kits, search queries, and active categories.
- Enhance editor layout to support toggling the UIKit browser with keyboard shortcuts.
- Include import/export functionality for UIKit components.
* feat(types): add clipContent to ContainerProps
Allow frames to explicitly clip overflowing children, essential for
cards with cornerRadius + image children.
* feat(canvas): wire letterSpacing, textGrowth and clipContent to Fabric.js
- Convert letterSpacing (px) to Fabric charSpacing (1/1000 em) in
factory and sync
- Select IText vs Textbox based on textGrowth mode, restore canvas
selection after text object recreation
- Add multi-line text height estimation with CJK character support
- Honor clipContent flag in clipping logic
* feat(panels): split text Layout and Typography into separate sections
- Add readOnly prop to NumberInput for non-editable dimension display
- Extract text Layout section (dimensions, fill/hug, resizing toggles)
into text-layout-section.tsx
- Enhance Typography section with line height, letter spacing, vertical
alignment controls
- Reorder property panel: Size → Layout → Appearance → Fill → Stroke →
Typography → Effects
- Add hideWH prop to SizeSection to avoid duplicate W/H inputs
* feat(panels): rewrite layout-section with full Flex Layout panel
- 3x3 alignment grid with context-aware behavior per layout direction
- Gap section with numeric/space-between/space-around radio modes
- Multi-mode padding: single, 2-axis (V/H), 4-individual (T/R/B/L)
with gear popover
- Dimensions (W/H) and sizing checkboxes (fill/hug/clip) integrated
into layout panel
* feat(panels): improve layer panel with auto-collapse and scroll-to-selection
- Collapse all layers by default, auto-collapse newly added nodes
- Auto-expand ancestor layers when a child is selected on canvas
- Scroll selected layer item into view after expansion
* fix(panels): improve AI chat panel overflow and color picker styling
- Fix chat panel overflow with proper flex layout and min-h-0
- Cap checklist height with scrollable overflow
- Adjust color picker input sizing
* feat(codegen): add textGrowth, textAlignVertical and clipContent to code generation
- textGrowth: auto → whitespace-nowrap, fixed-width-height → overflow-hidden
- textAlignVertical: middle/bottom → vertical-align CSS
- clipContent: true → overflow-hidden on containers
* feat(ai): integrate text typography properties into design prompts
- Add textGrowth, lineHeight, letterSpacing, textAlignVertical, fontStyle
to PEN_NODE_SCHEMA and sub-agent prompt
- Add typography scale guidelines with lineHeight/letterSpacing defaults
- Update examples with lineHeight, clipContent, fill_container usage
- Add phone placeholder and clipContent rules
* feat(ai): enhance streaming service with runtime config and thinking modes
- Extract timeout constants to ai-runtime-config.ts
- Add thinking mode control (adaptive/disabled/enabled) to stream options
- Add StyleGuide interface for orchestrator visual consistency
- Add ping timeout and first-text timeout options
* feat(ai): improve design generator with typography defaults and phone placeholder
- Set default lineHeight on text nodes (1.2 for headings, 1.5 for body)
- Expand phone/mockup placeholder detection with shape-based fallback
- Flatten nested phone-shaped frames in post-streaming tree fixes
- Increase CJK character width estimation and button padding buffer
* feat(ai): enhance orchestrator with style guide and prompt optimizer
- Pass style guide from orchestrator plan to sub-agent prompts
- Add orchestrator-prompt-optimizer for context-aware prompt tuning
- Improve parallel sub-task generation and error recovery
* feat(ai): add thinking mode and Codex provider support to server API
- Support thinkingMode/effort params in chat and generate endpoints
- Add Codex (OpenAI) provider streaming via codex-client utility
- Forward thinking config to both Anthropic SDK and Agent SDK paths
* feat(mcp): implement OpenPencil file format and MCP server integration
- Introduce support for .op file format alongside .pen
- Add MCP server functionality for document management and tool operations
- Implement batch processing tools for design and variable management
- Enhance save and open dialogs to accommodate new file format
- Update dependencies and scripts for MCP server compilation and execution
* feat(build): update electron build configuration and resource handling
- Add mcp-server.cjs to extraResources in electron-builder.yml for production packaging
- Modify package.json build script to include MCP server compilation
- Enhance main.ts to set ELECTRON_RESOURCES_PATH for resource access
- Update mcp-install.ts to resolve MCP server path from resources in production
---------
Co-authored-by: Fini <fini.yang@gmail.com>
- Add mcp-server.cjs to extraResources in electron-builder.yml for production packaging
- Modify package.json build script to include MCP server compilation
- Enhance main.ts to set ELECTRON_RESOURCES_PATH for resource access
- Update mcp-install.ts to resolve MCP server path from resources in production
- Introduce support for .op file format alongside .pen
- Add MCP server functionality for document management and tool operations
- Implement batch processing tools for design and variable management
- Enhance save and open dialogs to accommodate new file format
- Update dependencies and scripts for MCP server compilation and execution
- Support thinkingMode/effort params in chat and generate endpoints
- Add Codex (OpenAI) provider streaming via codex-client utility
- Forward thinking config to both Anthropic SDK and Agent SDK paths
- Pass style guide from orchestrator plan to sub-agent prompts
- Add orchestrator-prompt-optimizer for context-aware prompt tuning
- Improve parallel sub-task generation and error recovery
- Set default lineHeight on text nodes (1.2 for headings, 1.5 for body)
- Expand phone/mockup placeholder detection with shape-based fallback
- Flatten nested phone-shaped frames in post-streaming tree fixes
- Increase CJK character width estimation and button padding buffer
- Collapse all layers by default, auto-collapse newly added nodes
- Auto-expand ancestor layers when a child is selected on canvas
- Scroll selected layer item into view after expansion
- 3x3 alignment grid with context-aware behavior per layout direction
- Gap section with numeric/space-between/space-around radio modes
- Multi-mode padding: single, 2-axis (V/H), 4-individual (T/R/B/L)
with gear popover
- Dimensions (W/H) and sizing checkboxes (fill/hug/clip) integrated
into layout panel
- Convert letterSpacing (px) to Fabric charSpacing (1/1000 em) in
factory and sync
- Select IText vs Textbox based on textGrowth mode, restore canvas
selection after text object recreation
- Add multi-line text height estimation with CJK character support
- Honor clipContent flag in clipping logic
- Add a new ComponentBrowserPanel for browsing and managing UI components.
- Implement ComponentBrowserGrid and ComponentBrowserCard for displaying components.
- Integrate UIKit store for managing component kits, search queries, and active categories.
- Enhance editor layout to support toggling the UIKit browser with keyboard shortcuts.
- Include import/export functionality for UIKit components.
- Expand the Fabric.js integration section in CLAUDE.md to include new files and functionalities.
- Highlight new features such as double-click frame entry, advanced drag-and-drop capabilities, and per-layer export options in README.md.
- Add context optimization and multi-provider support for AI in README.md.
- Update the project structure descriptions for clarity and completeness.
- Update the ORCHESTRATOR_PROMPT to allow for more granular task division, specifying 4-15 atomic sections.
- Enhance the JSON output structure by adding new subtasks for the hero section.
- Adjust ORCHESTRATOR_TIMEOUTS to extend hard and no-text timeout values for improved orchestration performance.
- Remove the complexity classifier as its functionality is no longer needed.
- Update design generator to always route through the orchestrator, simplifying the logic.
- Enhance error handling during orchestration to ensure fallback to direct generation is clear.
- Introduce a new sub-agent prompt for improved output formatting and clarity in design generation.
- Introduce context optimization to manage chat history size and prevent unbounded growth.
- Implement complexity assessment for design prompts to determine orchestration needs.
- Add orchestrator functionality for parallel design generation, improving performance and responsiveness.
- Update chat message parsing to include explicit status handling for orchestrator steps.
- Refactor design generator to support orchestration and streamline context building.
