* feat(mcp): add external MCP client with daemon-managed OAuth and 17 design-focused templates
Open Design now acts as an MCP CLIENT and surfaces tools from third-party
MCP servers to the underlying agent (Claude Code, Hermes, Kimi).
Daemon
- New mcp-config / mcp-oauth / mcp-tokens modules: persist server entries
to .od/mcp-config.json, run the OAuth dance for HTTP/SSE servers
end-to-end on the daemon (so cloud deployments work and tokens
survive across turns), and inject Authorization: Bearer headers into
the per-spawn .mcp.json the daemon writes for Claude Code (or the
ACP mcpServers map for Hermes/Kimi).
- /api/mcp/servers and /api/mcp/oauth/{start,status,disconnect}
endpoints, plus spawn-time wiring in agents that hands the configured
servers to the active agent CLI.
- System-prompt directive for connected external MCPs so the model
does not chase Claude Code's synthetic *_authenticate /
*_complete_authentication tools when the Bearer is already pinned.
Web
- Settings -> External MCP servers panel with per-row OAuth Connect /
Disconnect / Refresh affordances and per-row template hints.
- New "Add server" picker categorized into 7 groups
(image-generation, image-editing, web-capture, ui-components,
data-viz, publishing, utilities) with a search box, sticky close
button, collapsible <details> sections (auto-expand on search),
60vh capped scroll region, and a pinned Custom-server footer.
- ChatComposer /mcp slash and MCP picker button forward to the new
Settings tab; AssistantMessage renders MCP tool calls inline;
markdown autolinker handles bare http(s) URLs (incl. OAuth links)
before italic markers so OAuth callback URLs do not get
italic-fragmented mid-token.
Contracts
- packages/contracts/src/api/mcp.ts owns the wire shapes
(McpServerConfig, McpTemplate with stable McpTemplateCategory
enum, McpServersResponse, OAuth start/status/disconnect bodies, the
postMessage payload from the OAuth callback).
Templates (17 built-in)
- image-generation: Higgsfield (OpenClaw, OAuth HTTP), Pollinations,
Allyson (animated SVG), AWS Bedrock Image (uvx).
- image-editing: Imagician, ImageSorcery.
- web-capture: just-every screenshot-website-fast, ScreenshotOne.
- ui-components: 21st.dev Magic, shadcn/ui, FlyonUI.
- data-viz: AntV Chart, Mermaid.
- publishing: EdgeOne Pages.
- utilities: Filesystem, GitHub, Fetch.
Tests
- apps/daemon/tests/mcp-{config,oauth,tokens,spawn}.test.ts cover
storage round-trip, OAuth helpers, token persistence, spawn-time
wiring, every template's transport / command / args / env-field
invariants, and the canonical category enum.
- apps/web/tests/runtime/markdown.test.tsx covers the new autolinker
ordering rules.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(mcp): add 21 more design-focused templates and a `design-systems` category
Expands the built-in MCP picker from 17 to 38 templates so users can compose
the full Open Design craft loop (design-system intake → generate → edit →
audit → publish) without leaving the Settings dialog. Every install spec is
verified live against the upstream README; templates that needed Go binaries,
multi-step `init` ceremonies, or massive runtime stacks (PostgreSQL + Redis
+ Ollama) are intentionally deferred so picking a template still resolves to
a working server in one click.
New `design-systems` category between `web-capture` and `ui-components`
(reflects the upstream-of-components position in the workflow). Mirrored in
`McpTemplateCategory` on both contracts and daemon, and `CATEGORY_ORDER` on
the web side.
New templates by category:
- image-generation (+4): prompt-to-asset (icons / favicons / OG / logos with
free-tier routing across Cloudflare AI / NVIDIA NIM / HF / Stable Horde),
Nano Banana (hosted streamable HTTP, virtual try-on + product placement),
Seedream (hosted streamable HTTP, ByteDance Seedream v3-v5 + SeedEdit),
fal.ai (uvx, 600+ models incl. FLUX / Kling / Hunyuan / MusicGen).
- image-editing (+3): Photopea (34 layered-editor tools — closes the PSD
gap), Topaz Labs (AI upscale / denoise / sharpen), Transloadit (86+ media
pipeline robots).
- web-capture (+1): Pagecast (browser → demo GIF / MP4 with auto-zoom).
- design-systems (+4, NEW category): Figma-Context (Framelink, designs →
code), Design Token Bridge (Tailwind ⇄ CSS ⇄ Figma ⇄ M3 / SwiftUI / W3C
DTCG + WCAG contrast), Design System Extractor (Storybook scrape),
Aesthetics Wiki (cottagecore / dark-academia / y2k / … moodboards).
- data-viz (+2): MCP Dashboards (45+ chart types + KPI dashboards),
Excalidraw Architect (hand-drawn architecture diagrams).
- publishing (+6): PageDrop, PDFSpark, OGForge, QRMint, Slideshot
(HTML → PDF / PPTX / PNG with 7 themes), Deckrun (Markdown → PDF / video,
hosted free tier with no key required).
- utilities (+1): A11y axe-core (WCAG 2.0/2.1/2.2 + color-contrast + ARIA).
Tests cover every new template's wiring (command, args, env / header
required-vs-optional, secret flag), the category enum invariant, and
in-category declaration order for image-generation, design-systems and
publishing buckets where the order is what users see in the picker. 21 new
test cases pass; full mcp-config suite is green.
Templates intentionally deferred (documented in PR body): figma-use
(needs Figma desktop with --remote-debugging-port=9222), m-moire (multi-step
`memi suite init` + daemon ceremony), gemini-media-mcp + trident-mcp (Go
binaries — no npx / uvx path), Pixelle-MCP (full app with web UI + ComfyUI
backend), storybook-addon-mcp (lives inside user's Storybook, not standalone),
primitiv (multi-step init / build / serve), ReftrixMCP (PostgreSQL + Redis +
Ollama + DINOv2), narasimhaponnada/mermaid (overlap with peng-shawn).
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(mcp): add figma-use template (write designs from chat) under design-systems
figma-use is the natural counterpart to Figma-Context already in this PR:
where Framelink reads Figma designs into the model, figma-use writes back
into the canvas (90+ tools — create frames / text / components / variants,
render JSX into Figma, export PNG/SVG, query nodes via XPath, lint for
WCAG / auto-layout / hardcoded colors, analyze design systems).
Wired as an HTTP MCP template (`http://localhost:38451/mcp`) because
`figma-use mcp serve` only exposes HTTP — there's no stdio mode in the
upstream `serve.ts`. No API key. Two prerequisites the user owns are
spelled out in the description so picking the template still resolves to
a working server: (1) start Figma with `--remote-debugging-port=9222`
(or `figma-use daemon start --pipe` on Figma 126+), and (2) leave
`npx figma-use mcp serve` running in a terminal.
Inserted between `design-system-extractor` and `aesthetics-wiki` so the
design-systems category reads as a workflow: read existing design (Figma
Context) → translate tokens (Token Bridge) → extract from Storybook
(Extractor) → write back to Figma (figma-use) → break creative block
(Aesthetics Wiki).
Tests cover the new template's transport (`http`), endpoint URL, the
empty header-fields invariant (no auth required), and bump the
design-systems group order to include it.
Co-authored-by: Cursor <cursoragent@cursor.com>
* feat(settings): i18n the External MCP / MCP server / Connectors sidebar entries and make the dialog header track the active section
The External MCP sidebar entry this PR introduces was hardcoded English
("External MCP / Add MCP tools (Higgsfield, GitHub…)"). Same for the
adjacent Connectors and MCP server entries. The dialog header was also
pinned to "Execution & model" copy, so opening Settings → External MCP
showed a header that lied about which section the user was on.
Adds six translation keys — `settings.connectorsTitle/Hint`,
`settings.mcpServerTitle/Hint`, `settings.externalMcpTitle/Hint` — and
translates them across all 17 locales (ar, de, en, es-ES, fa, fr, hu, id,
ja, ko, pl, pt-BR, ru, tr, uk, zh-CN, zh-TW).
`SettingsDialog` now derives the header title/subtitle from the active
section (11 sections total) instead of a single hardcoded pair, so each
section renders an honest header.
Co-authored-by: Cursor <cursoragent@cursor.com>
* test(e2e): pin level: 3 on dialog heading lookups for Pets and Connectors
CI's Validate workspace job (#1479) failed two Playwright cases with the
strict-mode violation:
getByRole('dialog').getByRole('heading', { name: 'Pets' })
resolved to 2 elements:
1) <h2>Pets</h2>
2) <h3>Pets</h3>
Same root cause as the unit-test fix already in this PR: the dynamic
dialog `<h2>` now echoes the section's own `<h3>` because the dialog
header tracks the active section. Disambiguate to `level: 3` so each
assertion still pins the section heading specifically (which is what
the test intends to verify).
Audit of the rest of e2e/ for `dialog.getByRole('heading', ...)` —
settings-api-protocol.test.ts looks for "OpenAI API" / "Anthropic API"
section h3s which never appear in the dialog `<h2>` (always
"Execution & model"), so those stay safe.
Co-authored-by: Cursor <cursoragent@cursor.com>
* fix(mcp): bind OAuth refresh to the issuing client and skip stale tokens
Persist the OAuth client context (token endpoint, client_id, client_secret,
issuer, redirect_uri, resource) alongside the bearer token so refresh hits
the same client the refresh_token was bound to (RFC 6749 §6). The previous
refresh path re-ran beginAuth with a dummy OOB redirect URI, which kept
getOrRegisterClient from finding the original DCR client and made
providers reject the refresh on the next chat turn. Refreshes now reuse
the persisted endpoint/client pair directly.
Also stop injecting expired access tokens at spawn time when refresh is
unavailable or fails. Pinning a stale Bearer made every Claude MCP call
401 while the prompt still treated the server as connected; on that path
we now skip the entry and let the UI surface a reconnect.
Generated-By: looper 0.6.1 (runner=fixer, agent=claude-code)
---------
Co-authored-by: Cursor <cursoragent@cursor.com>
* Optimize Windows packaged web output
* Fix packaged contracts runtime build
* Optimize Windows packaged size pruning
* Prune Windows root Next payload
* Remove Windows bundled Node runtime
* Prune Windows standalone duplicate Next
* Add tools-pack cache foundation
* Cache Windows packaged build layers
* Cache Windows workspace builds
* Cache Electron-ready Windows app
* Split Windows tools-pack module
* Cache Windows dir build outputs
* Split Windows pack build modules
* Document Windows NSIS smoke namespace limits
* Move Windows NSIS smoke note to agents guide
* Optimize Windows beta packaging
* Bump packaged beta base version
* Improve Windows installer namespace UX
* Improve Windows tools-pack cache keys
* Stabilize Windows beta cache version keys
* Cache Windows workspace build outputs
* Optimize windows release beta cache layers
* Cache windows release dependencies
* Trim windows release cache before save
* Refresh windows tools-pack cache key
* Improve windows installer preflight prompts
* Fallback NSIS installer strings to English
* Fix Windows installer cleanup and preflight
* Improve Windows NSIS state logging
* Fix system NSIS Persian language alias
* Use long-path removal for Windows uninstall
* Fix mac tools-pack tests on Windows
* Address Windows packaging review feedback
* Fix Windows installer cache namespace isolation
* Include web output mode in Windows tarball cache key
* Use unique Windows release cache save keys
* chore: enforce test directory conventions
Move package, app, and tool tests out of src and add guard enforcement so source directories stay source-only.
* ci: use guard and package-scoped tests
Run the new repository guard in CI and keep test execution aligned with package-scoped commands after removing root aliases.
* ci: align stable release guard check
Use the new repository guard in stable release verification after replacing the residual-JS-only script.
* chore: tighten test layout enforcement
Enforce sibling tests directories, typecheck moved test suites with dedicated configs, and refresh remaining guidance that pointed at src-based tests.
* chore: clarify no-emit test tsconfigs
Explicitly disable declaration-only emit in test tsconfigs so review tooling sees they are no-emit typecheck configs.
* docs: add Brazilian Portuguese (pt-BR) translations
Translate README, CONTRIBUTING, QUICKSTART, and the e2e/cases,
e2e/reports, skills/html-ppt, skills/guizang-ppt READMEs into pt-BR.
Add the pt-BR entry to the language switcher in every existing locale
variant (en, de, fr, ko, ja-JP, ru, uk, zh-CN, zh-TW for README; en,
de, fr, ja-JP, zh-CN for CONTRIBUTING; en, de, fr, ja-JP for
QUICKSTART) so readers in any language can jump to the Portuguese
version. Code blocks, file paths, identifiers, license attribution
links and brand names are kept verbatim with the source.
* docs(pt-BR): use repo-relative links in e2e READMEs
Replace author-local absolute paths (/Users/mac/...) with repo-relative links so the translated docs navigate correctly on GitHub and other checkouts.
* docs(pt-BR): fix README badge anchor and skill reference link
- Update Agents badge href to the Portuguese fragment (#agentes-de-código-suportados) so the badge jumps to the translated heading.
- Restore the [`SKILL.md`][skill] reference-link syntax in the comparison table; the opening bracket was lost in translation, breaking the row.
* fix(web): keep Design Files view active after deleting a file (#115)
Deleting a file from the Design Files panel was navigating the user
into another file's tab (typically the previously-opened file such as
`index.html`). Two unrelated symptoms contributed:
- `FileWorkspace.handleDelete` always called
`setActiveTab(nextActive ?? DESIGN_FILES_TAB)`, which yanked the user
out of the Design Files panel whenever `tabsState.active` still
pointed at a real file (clicking the Design Files tab only updates
local `activeTab`; it does not touch persisted `tabsState.active`).
- The row popover had `onMouseDown` propagation guard but no
corresponding `onClick` guard on the destructive action path.
Fix in `FileWorkspace.handleDelete`:
- If the deleted file is the one being viewed (`activeTab === name`),
fall back to another open tab (or Design Files if none remain) — the
prior behavior, which is correct in this case.
- Otherwise (deletion came from the Design Files panel, the typical
path), leave `activeTab` alone so the user stays in the list view.
Only null out `tabsState.active` when it referenced the deleted file
to avoid leaving a dangling pointer for the hydration `useEffect` to
resync against.
Defensive cleanup in `DesignFilesPanel`:
- Add `onClick` propagation guard on the popover wrapper (mirrors the
existing `onMouseDown` guard).
- Stop propagation on each popover button (Open / Download / Delete)
and on the download `<a>` so destructive/menu actions can't bubble
into row click handlers under any DOM arrangement.
Closes#115
* fix(web): address review feedback + add multi-tab delete regression E2E
Review feedback (#329):
- Drop the redundant `onClick={(e) => e.stopPropagation()}` on the
download `<a>` wrapper; the inner `<button>` is the actual click
target and already stops propagation.
- Expand the comment in `handleDelete`'s else branch to explicitly
state that `activeTab` is preserved because the user is in a
different context (Design Files panel or another tab) and shouldn't
be navigated away.
Regression coverage:
- Extend `runDesignFilesDeleteFlow` to upload a sibling file
(`keep-me.png`) before `trash-me.png`, so deletion has a fallback
tab that the buggy code would have navigated to. After deletion,
assert the Design Files tab still has `aria-selected="true"` and
the sibling tab is still present (just not auto-activated).
* fix(daemon): emit tool_use from tool_execution_start in pi-rpc
The pi-rpc adapter emitted tool_use from message_end, which fires
before tool execution starts. The web UI pairs tool results to prior
tool_use events, so receiving tool_result without a preceding tool_use
broke tool card rendering and file auto-open behavior.
Move tool_use emission to tool_execution_start, matching the pattern
in copilot-stream.ts. Remove redundant tool call extraction from
message_end (tool_use is now emitted at execution time, usage is
already emitted from turn_end).
Extract mapPiRpcEvent as a pure exported function so tests exercise
the real event mapping logic instead of an inlined copy that can
diverge from production.
Ref: mrcfps review comments on PR #117
* docs(daemon): clarify mapPiRpcEvent mutability contract
The function mutates ctx.sentFirstToken to track streaming state.
Calling it "pure" is misleading; revised the doc comment to say
no I/O or child process interaction instead.
* fix(pi-rpc): remove redundant status(tool) emission from tool_execution_start
Now that tool_use fires inline from tool_execution_start, the
accompanying status(tool) event is redundant: tool_use already
carries the tool name, and the UI renders running state from the
tool card. The extra status pill breaks consecutive tool_use
grouping in AssistantMessage.buildBlocks. Aligns with
copilot-stream, which emits only tool_use from
tool.execution_start with no status event.
Closes#141.
When the user clicked the Fullscreen button, requestFullscreen() put the
stage element into native browser fullscreen and React's `fullscreen`
state was set true. Pressing Esc was meant to exit the overlay, but in
browsers like Firefox the browser consumes Esc to drop its native
fullscreen element without delivering keydown to JS. The React state
stayed true, the `ds-modal-fullscreen` class lingered, and only a second
Esc reached the keydown handler that flipped the state.
Subscribe to `fullscreenchange` so the React state mirrors the native
state. When the browser exits its fullscreen element, the overlay drops
on the same keystroke. The keydown handler is still needed for the
fallback path (no native fullscreen API support, where requestFullscreen
is undefined and only React state is set).
Adds three regression tests in e2e/tests/preview-modal-fullscreen.test.tsx
covering the bug fix path, the keydown fallback, and a non-collapse
guard for transitions where another element is still fullscreen.
Co-authored-by: d 🔹 <258577966+voidborne-d@users.noreply.github.com>
* feat(daemon): add pi coding agent adapter
Add pi (https://pi.dev) as a supported coding agent, using its
--mode rpc JSON-RPC protocol over stdio for structured event streaming.
Changes:
- apps/daemon/pi-rpc.js: new RPC session handler that drives pi's
--mode rpc protocol, translating typed agent events (text_delta,
thinking_delta, tool_use, tool_result, usage, status) into the
daemon's UI event format. Auto-resolves extension UI requests
(fire-and-forget consumed, dialogs auto-approved) so pi stays
unblocked in the headless web UI. Kills the process after agent_end
since pi's RPC process is designed for multi-prompt sessions.
- apps/daemon/agents.js: add pi agent definition with custom
fetchModels (pi --list-models outputs to stderr, not stdout),
575+ models from 20+ providers, reasoning/thinking level support
via --thinking flag, and streamFormat 'pi-rpc'.
- apps/daemon/server.js: wire pi-rpc stream format to
attachPiRpcSession; skip stdin.end() for pi-rpc since the RPC
session manages stdin bidirectionally.
- apps/daemon/acp.js: export createJsonLineStream for reuse by
pi-rpc.js.
- apps/daemon/pi-rpc.test.mjs: 19 unit tests covering model list
parsing (TSV, dedup, edge cases), RPC event translation (text,
thinking, tools, usage, compaction, retry), sendCommand wire
format, extension UI auto-resolution.
- e2e/tests/structured-streams.test.ts: add pi RPC tool_use/tool_result
event mapping test alongside existing Claude/Copilot fixtures.
Verified end-to-end: daemon /api/chat → pi RPC → SSE stream with
status, text_delta, usage, and tool events. Live E2E test passes
(OD_E2E_RUNTIMES=pi). All 59 project tests green.
* refactor(daemon): migrate pi-rpc to TypeScript
Follow upstream #118 TypeScript migration convention: rename
pi-rpc.js → pi-rpc.ts and pi-rpc.test.mjs → pi-rpc.test.ts
with @ts-nocheck header (same as all other daemon modules).
Import paths remain ./pi-rpc.js per NodeNext module resolution.
* fix(daemon): avoid duplicate usage events in pi-rpc handler
Pi emits both message_end and turn_end per turn, both carrying
usage data. Emitting from both handlers caused double-counting
in the UI and any consumer that aggregates usage.
Remove usage emission from the message_end branch since turn_end
is the canonical per-turn usage source. Keep tool call extraction
in message_end (unique data not available in turn_end).
Add regression test confirming exactly one usage event is emitted
when both message_end and turn_end carry usage for the same turn.
Addresses Copilot P2 review on PR #117.
* fix(daemon): scope pi RPC id counter per session, bump graceful shutdown
Move nextRpcId and sendCommand inside attachPiRpcSession as local
state, matching the pattern in acp.ts where nextId is scoped per
session. Prevents RPC id collisions across concurrent /api/chat
requests.
Bump post-agent_end SIGTERM grace period from 2s to 5s and make it
configurable via PI_GRACEFUL_SHUTDOWN_MS env var for resource-
constrained machines.
Add test confirming concurrent sessions get independent id sequences.
* fix(daemon): wrap parser.feed in try-catch in pi-rpc
Catch errors from parser.feed and route them through the
existing fail() handler instead of letting them propagate
as unhandled exceptions.
* feat(dev): add desktop tools-dev control plane
* refactor(sidecar): split Open Design contracts
Move Open Design-specific sidecar protocol definitions into @open-design/contracts so sidecar and platform can remain descriptor-driven primitives.
* refactor(daemon): organize package sources
Keep daemon app code, tests, and sidecar entrypoints in separate package directories so each layer can be built and verified independently.
* chore(repo): streamline maintenance entrypoints
Centralize agent guidance by directory and reduce root command chains while preserving the existing build scope.
* docs: translate agent guidance to English
* fix(sidecar): tolerate stale IPC sockets
Remove stale Unix socket files only after confirming no listener is active, so tools-dev can restart after unclean shutdowns.
* test: add e2e ui automation suite
* fix review feedback for ui e2e suite
Resolved the FileWorkspace.tsx merge-marker issue and kept the intended combination of multiple, accept="image/*", and data-testid.
Updated the e2e port handling so the test config no longer relies on a single hardcoded app port. It now resolves an available port first and passes the same port selection through the dev server and Playwright base URL. Since main has moved to the Next.js dev stack, this was also adapted from the old Vite-based flow to NEXT_PORT.
Kept test:ui serialized so cleanup completes before Playwright starts.
Updated reset-e2e-artifacts.mjs so cleanup failures are surfaced with a warning instead of being silently swallowed, except for the expected ENOENT case.
