Releases · ZSeven-W/openpencil

26 Apr 11:23

v0.7.5

5e6b747

v0.7.5 — Quiet bugs, loud now Pre-release

Pre-release

A maintenance pre-release focused on three quietly broken behaviors. All three are user-reported issues from 0.7.4. Binaries for macOS, Windows, and Linux are attached below once the build matrix finishes.

🐛 Fixes

AI providers — `fetch failed` is now actionable (#121)

Custom OpenAI-compatible providers used to surface Node's opaque TypeError: fetch failed for every network failure — DNS lookup, TLS handshake, connection refused, timeout — all collapsed into one useless string. The real reason was already on error.cause but never reached the UI.

formatFetchError() now walks the cause chain (including the AggregateError undici emits when multiple A records all fail) and prefixes the SystemError code, so the AI Settings dialog and chat stream show:

ENOTFOUND: getaddrinfo ENOTFOUND api.example.com
ECONNREFUSED: connect ECONNREFUSED 127.0.0.1:8080
self-signed certificate in certificate chain

…instead of fetch failed.

Electron — agent-native binary now ships on every platform

The Zig NAPI provisioner had a silent failure mode that bit any matrix entry without a matching prebuilt release: the source-build fallback dropped agent_napi.node at zig-out/napi/…, but electron-builder only ships from packages/agent-native/napi/. Affected installs (commonly Windows) launched fine but died at the dynamic @zseven-w/agent-native import the moment chat was used.

Always source-build on the runner — mlugg/setup-zig is provisioned for every workflow
Always copy the built binary into napi/agent_napi.node so electron-builder packages it
Cross-compile per platform via `ZIG_TARGET` — `mac-x64` on arm64 runners now produces an x86_64 binary, not a wrong-arch arm64 one
Strict mode (`OPENPENCIL_REQUIRE_AGENT_NATIVE=1`) plus a dedicated Verify agent-native binary workflow step fails the build loudly if the binary is missing

📚 Docs

Issue	What changed
#116	Removed obsolete `op export` references from 15 root READMEs, 15 `apps/cli/` READMEs, AGENTS.md, and CLAUDE.md. The export command was retired in favor of the multi-stage `codegen:plan / submit / assemble` pipeline.
#117	Rewrote `packages/pen-mcp/README.md`. The previous `npx @zseven-w/pen-mcp` quick-start never worked — the package ships TypeScript source against workspace-only deps with no `bin` entry. New section explains how to run the server from the monorepo and how external MCP clients connect over HTTP at `http://localhost:3100/mcp\`.

🧪 Verification

1525 / 1525 unit tests passing (Vitest, 151 files)
0 lint warnings (oxlint, 818 files)
0 TypeScript errors (strict mode)
14 new tests covering `formatFetchError` cause-chain unwrapping and AggregateError handling

⚠️ Pre-release notice

This build is published for early testing of the agent-native packaging fix — particularly on Windows where it most often regressed. If you're on a stable distribution channel and only want shipped releases, wait for v0.7.6 stable.

Full Changelog: v0.7.4...v0.7.5

Assets 19

17 Apr 11:27

github-actions

v0.7.4

a1a03ba

v0.7.4-enhance Pre-release

Pre-release

Summary

OpenPencil v0.7.4 focuses on reliable AI design generation on dark themes, smarter incremental edits, and
a hardened native agent runtime (MiniMax tool_use, Windows, openai-compat streaming).

Changes

AI / Design generation

fix(ai): stop white section bands on dark-themed pages — skip fixSectionAlternation when parent
fill luminance < 0.5, and strip stale SAFE_LIGHT_HEXES from earlier runs
feat(ai): design.md-driven background + sidebar color pipeline (orchestrator planning, sub-agent
prompts, and MCP all share the palette policy)
feat(ai): append-intent detection — "continue"/"add more" prompts reuse the existing content root,
and sub-agents get an APPEND MODE preamble listing existing siblings
feat(ai): snapshot_layout now emits an overlaps array; when the parent is layout: "none" the
reason points at absolute x/y stacking so agents fix the parent instead of resizing children
docs(ai): horizontal scroll card-row pattern with full clipContent + nested fit_content example
chore(ai): enable incremental-add skill in the generation phase

Canvas / Editor

fix(canvas): require explicit role:'overlay' to escape auto-layout — badge/pill/tag are
inline roles again and flow normally instead of collapsing to (0,0). isBadgeOverlayNode renamed to
isOverlayNode; a deprecated re-export keeps external consumers of @zseven-w/pen-core building
fix(canvas): render synchronously on resize to prevent the one-frame white flash when flex layout
shifts (e.g. right panel mount on first selection)
feat(editor): paste anchors to the selected container (or as sibling) instead of always landing at
document root

Renderer

feat(renderer): enable local OS fonts with vector rendering and proper permission handling (#110)

Agent (native)

chore(agent): bump agent-native to v0.4.0 — absorbs upstream v0.2.0/v0.3.0 (openai-compat
tool_calls streaming, HTTP error diagnostics), MiniMax tool_use 400 fix (placeholder text block when
assistant turn is tool_use-only), auto-detected MiniMax Anthropic-compat quirk, and Windows N-API symbol
export

MCP / Tooling

fix(mcp): run codex via shell on Windows so PATHEXT resolves .cmd/.bat shims (works around the
Node CVE-2024-27980 execFileSync restriction)
ci(publish): check-before-publish; package names derived from each manifest so workflow/manifest
drift is impossible — fixes the spurious CLI-step 404 on re-runs
style(lint): clear 22 oxlint warnings across repo
chore: ignore .omx/

Type

feat — New feature
fix — Bug fix
docs — Documentation
chore — Build / tooling / dependencies

Checklist

npx tsc --noEmit passes
bun --bun run test passes
No unrelated changes included
Commit messages follow Conventional Commits

Assets 19

15 Apr 14:42

Kayshen-X

v0.7.3

0154873

v0.7.3-enhance Pre-release

Pre-release

Summary

v0.7.3 introduces incremental "append mode" for AI design generation — when the user
asks the AI to add content to an existing canvas, the planner now detects append intent and
reuses the current content root instead of redrawing from scratch. Also ships local OS
font support via the Local Font Access API with vector rendering, a design.md-driven
background/sidebar theming pipeline, and a handful of editor, CLI, and cross-platform
fixes.

Changes

AI / design generation

feat(ai): append-mode detection before generate_design dispatch —
detectAppendIntent parses continue/append prompts against the active page
feat(ai): sub-agent preamble describes existing sibling sections so added nodes
integrate seamlessly
feat(ai): planner reuses existing content-root in append mode instead of creating a new
root frame
feat(ai): applyAppendContextToPlan helper wires context into the orchestrator plan
feat(types): AppendContext + SubTask.existingSectionLabels
feat(ai): design.md-driven background + sidebar color pipeline; auto-derives neutral
page background when design.md has no explicit background role
fix(ai): stop white section bands on dark-themed pages
docs(ai): horizontal scroll card-row pattern taught to the generation phase;
overflow.md example fleshed out

Fonts

feat(renderer): enable local OS fonts with vector rendering via the Local Font Access
API; includes permission handling (prompt / granted / denied / unavailable),
canvas-width heuristic for unknown local fonts, and blob-based registration into CanvasKit
(#110)

Editor

fix(canvas): render synchronously on resize to prevent a one-frame white flash when
RightPanel mounts on the first selection after idle
feat(editor): Cmd/Ctrl+V now pastes into the selected container (if it can hold
children) or immediately after the selected node as a sibling, falling back to the root
when nothing is selected

CLI / cross-platform

fix(mcp): on Windows, run the Codex CLI through execSync so PATHEXT resolves
.cmd/.exe/.ps1 shims (works around Node 18.20/20.12 execFileSync EINVAL from
CVE-2024-27980)

Code hygiene

style: apply oxfmt formatting drift across web, renderer, and AI modules
style(lint): clear 22 oxlint warnings (useless spread fallbacks, useless spread into
arrays, control-char regex → \P{ASCII}, unused catch params / imports, unnecessary
escapes, new Array(n).fill) — repo now lints with 0 warnings, 0 errors
chore: ignore .omx/ build artifact directory

Related Issues

Merges #110 (local OS fonts with vector rendering and permission handling)

Type

feat — New feature
fix — Bug fix
refactor — Code refactoring (no behavior change)
docs — Documentation

Checklist

npx tsc --noEmit passes
bun --bun run test passes — 1515 tests in apps/web + 47 in packages/pen-mcp,
all green
No unrelated changes included
Commit messages follow Conventional Commits
bun run lint — 0 warnings, 0 errors (added as a bonus of this rollup)

What's Changed

Enable local OS fonts with vector rendering and proper permission handling by @1MochaChan1 in #110

New Contributors

@1MochaChan1 made their first contribution in #110

Full Changelog: v0.7.2...v0.7.3

Contributors

1MochaChan1

Assets 19

14 Apr 13:47

Kayshen-X

v0.7.2

904c033

v0.7.2-bugfix Pre-release

Pre-release

Summary

v0.7.2 is a stability release focused on multi-provider AI agent loops,
Mac CLI discovery across managed shells, and drag / reparent / clipping
correctness on the canvas. It also ships bounded AI codegen handoff so chat
payloads stop hitting provider request-size limits silently.

Changes

AI agent loops — multi-provider correctness

OpenAI-compatible providers: fix the second turn. Before, the request
builder forwarded the message store's Anthropic-style content blocks
verbatim, so tool-result turns 400'd on GLM / dashscope / StepFun.
@zseven-w/agent-native v0.3.0 now translates tool_use + tool_result
blocks into OpenAI's tool_calls + role="tool" form, injects
system_prompt, and drops unsupported thinking blocks.
Tool-call streaming for OpenAI-compat. The SSE parser now accepts
delta.tool_calls and emits content_block_start / tool_use_delta /
content_block_stop so tool invocations from GLM / DeepSeek / Qwen /
dashscope flow through the same pipeline as Anthropic.
StepFun step_plan/v1 support. Accept delta.reasoning alongside
reasoning_content so StepFun's reasoning-heavy stream renders instead of
stalling the client-side first-text watchdog into an abort → std.http
panic → Bun segfault cascade.
HTTP 451 / content-safety surfacing. Map StepFun's 451 to
error.InvalidRequest with a specific "Content blocked by provider safety
filter" message; /api/ai/chat now forwards result.errors[0] so users
see the real reason instead of Provider error: error_server.
firstTextTimeout relaxes on thinking activity. When the model is
streaming reasoning, the "no first text yet" watchdog stands down —
noTextTimeout + hardTimeout still bound genuinely runaway reasoning.

Orchestrator sub-agent resilience

Minimal-skills fallback. After the full-skills attempt and its retry
both produce zero nodes, the orchestrator re-runs just the failing subtask
with a ~3KB kernel prompt (schema + jsonl-format only). Successful earlier
subtasks are preserved; only the failing one retries.
Skip deterministic refusals. Responses matching HTTP 400/401/429/451,
"content blocked", "censorship", or "authentication failed" short-circuit
the retry ladder so users aren't charged a second 4-minute StepFun safety
scan.

Local CLI discovery — Mac / managed-shell users

Login-shell probe. New probeViaLoginShell() asks $SHELL (or a zsh /
bash / fish fallback) -ilc 'command -v <cli>' to source the user's
real rc/profile. This catches nvm / fnm / pnpm / bun / mise / asdf / volta
shims that Electron's scrubbed PATH hides.
Expanded candidate paths. posixUserBinDirs() now includes
~/.bun/bin, ~/.volta/bin, ~/Library/pnpm, ~/.pnpm-global/bin,
~/.local/share/mise/shims, ~/.asdf/shims, ~/.cargo/bin, plus
dynamically enumerated ~/.nvm/versions/node/<ver>/bin and
~/.fnm/node-versions/<ver>/installation/bin.
Uniform ladder across every resolver. claude / codex / opencode /
copilot / gemini all run the same PATH → login-shell → npm-prefix →
user-bin candidates sequence, each step logged to
~/.openpencil/logs/server-YYYY-MM-DD.log for remote diagnosis.

Built-in providers

Add "StepFun Coding Plan" preset (https://api.stepfun.com/step_plan/v1).

Electron / dev-sync stability (#104)

Stabilize Electron dev startup after the upstream sync.
Keep localhost probing resilient without relying on proxy-friendly fetch
behavior.
Unblock incomplete local workspaces and keep Codex-related env passthrough
working.

Drag / reparenting / nested clipping (#104)

Preserve absolute/world position when layer moves change parent containers
— nodes no longer jump visually after reparenting.
Stop nested frame / group / shape drags from auto-ejecting to root during
canvas drags.
Promote previously root-only frame clipping to explicit clipContent when
nested, so corner radius and clip visuals stay intact.

AI handoff / codegen context quality (#104)

Export bounded AI codegen asset bundles and structure bundles so chunk /
assembly prompts reference stable ./assets paths instead of inline
base64.
Enrich sanitized AI consumer views with reusable image / gradient / layout
/ component semantics.
Restore code-panel AI bundle and ZIP export affordances.
Preserve cropped image fill transform metadata alongside original image
size through the Figma import path.
Guard oversized chat payloads with a client-side rejection before the
request leaves the browser.

Server / sync plumbing (#104)

Harden MCP document sync behavior and related tests.
Keep the server-side handoff path consistent with the richer AI bundle
payloads.

Type

feat — StepFun Coding Plan preset, login-shell CLI probe, consumer-view enrichment, minimal-skills fallback
fix — OpenAI-compat tool-call streaming, turn-2 request shape, StepFun reasoning + 451, drag reparent, firstTextTimeout, Electron dev sync
perf — Bounded AI chat payloads, retry short-circuit on deterministic refusals

Verification

npx tsc --noEmit -p apps/web ✓
bun --bun run test — 1492 / 1492 passed across 151 files
bun --bun run build ✓
bun run electron:build:mac-arm64 ✓ — produces signed DMG + zip +
latest-mac-arm64.yml
Manual: GLM-5 via dashscope /chat/completions end-to-end design flow,
StepFun step_plan/v1 reasoning stream, Mac login-shell CLI detection
against nvm / fnm / pnpm / bun / mise / fish

Submodule

packages/agent-native 0.2.0 → 0.3.0
(feat(openai-compat): tool_calls streaming, content-block translation, reasoning + 451)

Workspaces bumped

All 14 workspace package.json files bumped 0.7.1 → 0.7.2.

Breaking changes

None.

What's Changed

Stabilize synced main for AI handoff, drag nesting, and Electron dev by @raiscui in #104

New Contributors

@raiscui made their first contribution in #104

Full Changelog: v0.7.1...v0.7.2

Contributors

raiscui

Assets 19

13 Apr 13:43

Kayshen-X

v0.7.1

7271a03

v0.7.1-bugfix Pre-release

Pre-release

Summary

v0.7.1 introduces first-class ACP (Agent Client Protocol) support, a skill-installable CLI, and a suite of production-stability fixes. Users can now connect external ACP-compatible agents (e.g. claude-agent-acp) directly from Settings → Agents and have them operate on the live canvas through OpenPencil's MCP tools.

Changes

ACP (Agent Client Protocol) integration

New @zseven-w/pen-acp client package wrapping the ACP TypeScript SDK
Settings → Agents → ACP Agents section with local-process + remote-WebSocket support
Server-side connection manager with lazy reconnect + globalThis persistence across Vite HMR
/api/ai/agent?providerType=acp branch wires session/prompt + session/update into the existing SSE chat stream
Auto-starts the OpenPencil MCP server, passes it to ACP via session/new, and auto-approves tool permissions
Custom system prompt enforces layered design pipeline (design_skeleton → design_content → design_refine) for higher quality output
Desktop-only guard for local process spawning (rejected outside Electron / dev mode)

op install CLI

New op install / op uninstall commands with target auto-detection (Claude Code, Codex, Cursor, Gemini CLI, OpenCode)
Skill files bundled into the CLI binary at build time — no GitHub access required at install time

Production build fixes

@zseven-w/agent-native package + native .node binary properly placed under server/node_modules/ so Nitro can resolve it
Electron before-quit + dev-script SIGINT handlers kill the detached MCP server (no more orphan processes)
webUtils.getPathForFile capture on drag-drop so recent files entries stay clickable after reopening

batch_design robustness (MCP)

Multi-line JSON support via bracket/quote-balanced splitter
Auto-normalize fill / stroke shorthand (string / single-object forms → canonical arrays)
Per-line error collection instead of whole-batch abort; repairs empty keys, trailing commas, smart quotes
Bindless I(parent, data) form supported (auto-generated binding)

Codegen / chat polish

Compact JSON + strip noise fields (id, parentId, layout-managed x/y, default values) — 60–70% smaller request body to avoid proxy 403 Request not allowed
CRUD intent detection routes to lightweight prompt + tool set (no design skills); insert_node supports after parameter for sibling placement
agent-native: reset StreamingToolExecutor between turns (fixes tool_use ID mismatch on multi-turn MiniMax / third-party providers); surface upstream HTTP error body via new Provider.lastError() VTable
Strip h3 JSON error wrapper on the client so chat shows clean error messages

Layer panel

Rectangle nodes now accept drag-to-reparent (they inherit ContainerProps — the restriction was UI-only)

i18n

Full ACP translation keys for all 15 locales

Docs

MIT LICENSE, README, and CLAUDE.md added/refreshed for every package

Related Issues

#93

Type

feat — New feature
fix — Bug fix

Checklist

npx tsc --noEmit passes
bun --bun run test passes
No unrelated changes included
Commit messages follow Conventional Commits

New Contributors

@raiscui made their first contribution in #99

Full Changelog: v0.7.0...v0.7.1

Contributors

raiscui

Assets 19

28 Mar 15:13

Kayshen-X

v0.6.0

3c697d8

v0.6.0-Embrace Pre-release

Pre-release

v0.6.0 introduces a built-in AI Agent SDK with multi-provider support, Agent Team mode for specialized
design delegation, and significant improvements to AI-powered design generation reliability.

Changes

AI Agent SDK & Multi-Provider Support

Add built-in agent SDK (packages/agent) with web integration and SSE streaming
Add 9+ builtin provider presets (OpenAI, Anthropic, Google Gemini, Mistral, DeepSeek, etc.) with region
switcher
Add Google Gemini support with 3.x series models
Support Anthropic API format in custom provider settings
Dynamic system prompt via pen-ai-skills for context-aware AI responses
Add keep-alive pings for long-running LLM calls (5s interval for Bun compatibility)
Add API error classification and auto-retry without tools
Add i18n for builtin provider settings (15 locales)

Agent Team Mode

Add Team section UI with dedicated design model selector
Wire team mode in chat handlers with member delegation events
Add source field and team events to AgentEvent type for multi-agent tracing
Auto team mode using current chat model when design model is set
Make team mode visually distinct in chat UI

Design Generation Pipeline

Replace insert_node with generate_design as primary design tool (uses internal CLI design pipeline)
Align insert_node with batch_design capability for consistent node creation
Auto-replace empty root frames and auto-zoom to fit after insert
Clean up partial nodes on generate_design failure
Sanitize node data, deep-clone before post-processing to avoid Zustand mutation
Prevent duplicate root-level inserts from weaker models

Renderer & Canvas

Guard against undefined fill entries in resolveFillColor/resolveStrokeColor
Rasterize paragraph image cache at 2x minimum for crisp text on low-DPR displays
Skip paragraph image cache when zoomed out below 0.5x or zoomed in
Enhance syncFromDocument error handling and normalize document structure

MCP & Live Sync

Implement sync URL caching for improved performance
Enhance live sync diagnostics and port file management
Clear stale sync cache on page load to prevent false dirty state
Wire openpencil codex install to config TOML

CI/CD & Distribution

Add Homebrew Cask update workflow for OpenPencil releases
Fix Scoop/Homebrew tap auto-update in CI
Streamline version publishing process

Agent Reliability Fixes

Fix SSE timeout, routing, and message format issues
Fix sliding window from splitting assistant+tool groups
Strip <think> tags from model text output in chat UI
Fix tool call args always {} and turn>0 retry
Properly serialize non-Error objects in error messages
Scope designer tools, streamline delegation, add model hint
Route resolveToolResult to correct agent in team mode
Clean up pending tool calls on exit and improve error handling

Related Issues

Fixes #85
Fixes #86 — 无法拉起MCP服务 (MCP service fails to start and doesn't persist)
Fixes #87 — "spawn EINVAL" error when connecting GitHub Copilot on Windows

Type

Checklist

npx tsc --noEmit passes
bun --bun run test passes
No unrelated changes included
Commit messages follow Conventional Commits

What's Changed

fix(mcp): wire openpencil codex install to config toml by @Smile232323 in #85

New Contributors

@Smile232323 made their first contribution in #85

Full Changelog: v0.5.2...v0.6.0

Contributors

Smile232323

Assets 19

23 Mar 15:00

Kayshen-X

v0.5.1

2592bf1

v0.5.1-enhance Pre-release

Pre-release

Summary

v0.5.1 introduces the OpenPencil CLI (op) for terminal control of the design tool, adds a text rendering
performance optimization via paragraph image caching, and fixes Docker multi-platform builds.

New Features

CLI tool (apps/cli) — New op command-line tool to control the desktop app or web server from the
terminal. Commands include app lifecycle (start, stop, status), document operations (open, save, get,
selection), node manipulation (insert, update, delete, move, copy, replace), design DSL (design),
multi-platform code export (export), and more. Published as @zseven-w/openpencil-cli on npm.
(#75)
npm publish workflow — New GitHub Actions workflow (publish-cli.yml) for publishing all @zseven-w/*
packages in topological order, plus a publish:beta script.

Performance

Paragraph image caching — Pre-rasterized paragraph images are now cached (128 MB LRU) in the CanvasKit
renderer, replacing per-frame glyph shaping with drawImageRect on cache hit. Significant frame-time improvement
for text-heavy documents. (#76)
Frame label zoom stability — Frame labels now render in screen-space after viewport transform, eliminating
flicker at integer zoom boundaries. Shadow rendering is skipped during active zoom for smoother performance.

Bug Fixes

Docker multi-platform builds — Fixed monorepo paths and added multi-platform support to the Docker workflow.

Documentation

Updated all 15 language README files with CLI installation instructions, usage examples, and expanded
multi-platform code export documentation.
Added README files for all packages (pen-core, pen-codegen, pen-figma, pen-renderer, pen-sdk,
pen-types).
Added apps/cli/CLAUDE.md for CLI development guidance.

Related Issues

Closes #75
Relates to #74

Full Changelog: v0.5.0...v0.5.1

Assets 19

22 Mar 02:15

Kayshen-X

v0.5.0

6c89c6d

v0.5.0-Promise Pre-release

Pre-release

Summary

OpenPencil v0.5.0 — Introduces the Design System (design.md) as a specification-driven approach to AI generation. Also adds Electron desktop app, image search & generation pipeline, Gemini CLI integration, and rendering performance improvements.

Changes

Design System Panel (design.md) — Release Highlight

A new markdown-driven design system specification that ensures AI-generated designs strictly follow your design language.

Add draggable, resizable floating Design System panel with expandable sections (theme, colors, typography, component styles, layout principles)
Import/export .md files in Google Stitch format — shareable and version-controllable across teams
One-click auto-generate design.md from existing canvas designs (AI analyzes the node tree → structured spec)
Sync color palette to design variables ($primary, $secondary, etc.) individually or in bulk — directly usable in documents and code generation
AI generation automatically injects design.md context — colors, fonts, component styles, and layout rules all take effect, replacing the default style policy
MCP tool support: get_design_md / set_design_md / export_design_md — external agents can read and write the design system
Per-document persistence via localStorage — switching files automatically restores the associated design.md
Full i18n support (Chinese, English, Japanese, etc.)

Electron Desktop App

Implement desktop application structure with auto-updater
Extract IPC handlers to a dedicated module
Enhance Windows process spawning for CLI scripts
Warn before closing with unsaved changes

Image Search & Generation

Add dual-source image search (Openverse + Wikimedia) with results grid UI
Add multi-provider image generation endpoint and popover UI
Auto-search pipeline: automatically fill images after AI design generation completes
MCP: add G() operation for image search in batch design DSL
Add Images tab in agent settings for API key and provider configuration
Split imageSearchQuery / imagePrompt for better search vs generation precision

Gemini CLI Integration

Add Gemini CLI as a supported AI agent (with Docker support and multi-language docs)

Performance

Viewport culling: skip draw calls for nodes outside the visible area (#64)
Text cache: replace count-based limits with memory-based eviction (#66)

Bug Fixes

Fix icon node selection crash caused by string fill values (fixes #61)
Fix Claude Code CLI exit code 1 on Windows (fixes #63)
Fix 1-frame delay when resizing canvas (#60)

Related Issues

Fixes #61, Fixes #63, Closes #65

Type

feat — New feature
fix — Bug fix
perf — Performance improvement

Checklist

npx tsc --noEmit passes
bun --bun run test passes
No unrelated changes included
Commit messages follow Conventional Commits

New Contributors

@leinaldo made their first contribution in #60

Full Changelog: v0.4.4...v0.5.0

Contributors

leinaldo

Assets 19

Uh oh!

Releases: ZSeven-W/openpencil

v0.7.5 — Quiet bugs, loud now

🐛 Fixes

AI providers — fetch failed is now actionable (#121)

Electron — agent-native binary now ships on every platform

📚 Docs

🧪 Verification

⚠️ Pre-release notice

Uh oh!

v0.7.4-enhance

Summary

Changes

Type

Checklist

Uh oh!

v0.7.3-enhance

Summary

Changes

Related Issues

Type

Checklist

What's Changed

New Contributors

Contributors

Uh oh!

v0.7.2-bugfix

Summary

Changes

AI agent loops — multi-provider correctness

Orchestrator sub-agent resilience

Local CLI discovery — Mac / managed-shell users

Built-in providers

Electron / dev-sync stability (#104)

Drag / reparenting / nested clipping (#104)

AI handoff / codegen context quality (#104)

Server / sync plumbing (#104)

Type

Verification

Submodule

Workspaces bumped

Breaking changes

What's Changed

New Contributors

Contributors

Uh oh!

v0.7.1-bugfix

Summary

Changes

Related Issues

Type

Checklist

New Contributors

Contributors

Uh oh!

v0.7.0-Devotion

Summary

Changes

Headline features

Design quality

Performance

Refactors

Infra

Notable fixes

Related Issues

Type

Checklist

New Contributors

Contributors

Uh oh!

v0.6.0-Embrace

Changes

AI Agent SDK & Multi-Provider Support

Agent Team Mode

Design Generation Pipeline

Renderer & Canvas

MCP & Live Sync

CI/CD & Distribution

Agent Reliability Fixes

Related Issues

AI providers — `fetch failed` is now actionable (#121)

New: `pen-ai-skills` package

New: CLI (`apps/cli/`)