* fix(web,daemon): make max_tokens configurable (closes#29)
BYOK users on custom Anthropic-compatible providers (e.g. Xiaomi MiMo)
hit the hardcoded 8192 cap and saw artifacts truncated mid-stream.
- AppConfig.maxTokens with Settings input (EN/CN + 8 other locales)
- ProxyStreamRequest.maxTokens contract field
- anthropic, anthropic-compatible, and openai-compatible providers all
forward cfg.maxTokens
- /api/proxy/anthropic/stream and /api/proxy/stream payloads honor it,
defaulting to 8192 when unset so prior clients are unaffected
Original sketch by @mashu in #78 (50a9d14); rebased to the apps/web
layout and extended to the proxy paths actually used when baseUrl is
set, which is where #29's user actually traffics.
* feat(web): per-model max_tokens defaults
Adds a hand-maintained MODEL_MAX_TOKENS table (Claude 4.5 line → 64k,
mimo-v2.5-pro → 32k) and an effectiveMaxTokens helper layered over the
override field added in 6a3ae5f, so #29's user — and others on supported
models — don't have to discover Settings to avoid mid-stream truncation.
- apps/web/src/state/maxTokens.ts: lookup + helpers
- providers/{anthropic,anthropic-compatible,openai-compatible}.ts:
forward effectiveMaxTokens(cfg) instead of cfg.maxTokens ?? 8192
- SettingsDialog: input becomes an optional override (blank = default,
shown as placeholder)
- 10 locale hint strings updated to the new semantics
* feat(web): vendor LiteLLM model metadata for max_tokens defaults
Replaces the 4-entry hand-rolled MODEL_MAX_TOKENS map from 544e67e with
a vendored slice of BerriAI/litellm's model_prices_and_context_window
JSON (1970 chat models, ~97KB raw / ~25KB gzip). Future model launches
land in maxTokens.ts via `pnpm sync-litellm-models` instead of manual
edits.
- scripts/sync-litellm-models.ts: fetches the upstream JSON, filters to
chat-mode entries, projects each entry to its max_output_tokens (or
max_tokens fallback), and writes a sorted, license-attributed JSON
- apps/web/src/state/litellm-models.json: generated artifact, committed
- apps/web/src/state/maxTokens.ts: lookup is now
OVERRIDES → LITELLM_MODELS → FALLBACK_MAX_TOKENS. The OVERRIDES table
shrinks to just `mimo-v2.5-pro` (LiteLLM only ships MiMo via
OpenRouter/Novita aliases, not the canonical id Xiaomi's API uses).
LiteLLM is MIT-licensed (BerriAI/litellm/blob/main/LICENSE); attribution
is preserved in both the script header and the generated JSON's
_license field.
* test(web,docs): cover maxTokens lookup + document sync workflow
- apps/web/src/state/maxTokens.test.ts: six vitest cases pinning the
three-tier lookup (override → LiteLLM → fallback) and the
effectiveMaxTokens user-override path. Guards against a future sync
silently dropping the Anthropic 4.5 entries we rely on.
- CONTRIBUTING.md / CONTRIBUTING.zh-CN.md: new "Updating model
max_tokens metadata" section pointing future maintainers at
scripts/sync-litellm-models.ts and explaining when OVERRIDES is
appropriate (it's the rare exception, not the default).
* fix(web): mark Max tokens label as optional in 10 locales
The Settings field is optional (blank means "use the per-model default")
but the label gave no visual cue, breaking the implicit pattern that
every other API-mode field (key/model/baseUrl) is required. Append
"(optional)" — using the locale's natural parenthetical convention
(Chinese full-width brackets, Japanese 任意, Russian опционально, etc.)
— so the field reads as discretionary at a glance.
* fix(web): validate maxTokens override against advertised UI bounds
Addresses Siri-Ray's review on commit 0d98185. The Settings input
declares min={1024}/max={200000}/step={1024}, but until now
effectiveMaxTokens trusted any defined cfg.maxTokens, so a stale or
hand-edited localStorage value (negative, zero, fractional, billions)
would pass straight to the Anthropic SDK on the direct path while the
daemon proxy quietly clamped it back to 8192 on the proxied path —
same config, divergent behavior depending on route.
- maxTokens.ts: add MIN_MAX_TOKENS / MAX_MAX_TOKENS exports and
isValidOverride helper. effectiveMaxTokens only honors the override
when it is a finite integer in [1024, 200000]; otherwise falls back
to modelMaxTokensDefault.
- SettingsDialog.tsx: input bounds now reference the same constants so
the UI promise can't drift from the runtime check.
- maxTokens.test.ts: six new cases pinning the rejection of negative,
zero, sub-MIN, super-MAX, non-integer (fractional / NaN / Infinity)
overrides plus the inclusive MIN/MAX boundaries.
The daemon proxy's existing `> 0` fallback stays as defense-in-depth.
* feat(skills): integrate lewislulu/html-ppt-skill as html-ppt + 15 per-template Examples cards
Bring the MIT-licensed lewislulu/html-ppt-skill upstream into skills/html-ppt/
with its full asset tree (36 themes, 31 single-page layouts, 27 CSS + 20
canvas-FX animations, runtime + presenter mode, all 15 full-deck templates,
and the upstream LICENSE preserved verbatim).
Surface each full-deck template as its own Examples gallery card via thin
wrapper skills under skills/html-ppt-<template>/. Each wrapper ships:
- SKILL.md with `od.mode=deck`, scenario, `featured: 20-34` (slotting after
the existing curated cards), an `od.example_prompt` tuned to the template,
and `od.upstream` pointing at the upstream repo. Clicking "Use this prompt"
on a card now wires up `kind=deck` + `speakerNotes=true` and seeds the
composer with the upstream's authoring flow so the prompt -> output path
matches the upstream demo.
- example.html baked self-contained (fonts/base/animations/style/theme CSS
inlined, runtime <script> stripped) so the gallery srcdoc iframe renders
the upstream look without external paths.
scripts/scaffold-html-ppt-skills.mjs and scripts/bake-html-ppt-examples.mjs
are idempotent generators — re-run after editing skills/html-ppt/ to re-sync
all per-template wrappers and their baked examples.
Add a Credits section + extend the License section in README.md /
README.zh-CN.md / README.ko.md to credit the upstream alongside the
already-cited op7418/guizang-ppt-skill.
* fix(scripts): allowlist html-ppt skill JS for residual-js check
Add scripts/bake-html-ppt-examples.mjs and scripts/scaffold-html-ppt-skills.mjs
to allowedExactPaths, and skills/html-ppt/assets/ to allowedPathPrefixes so
pnpm check:residual-js no longer flags the vendored upstream runtime JS or the
new maintainer-only .mjs scripts.
* fix(skills): keep all slides in baked html-ppt examples + correct asset guidance
The bake script's `STATIC_FALLBACK_CSS` set `.slide+.slide{display:none}`,
which silently truncated every baked `example.html` to slide 1. That artifact
is also served by `/api/skills/:id/example` and reused by the Examples
preview modal's share/export and print-to-PDF, so the rule dropped the rest
of the deck from those flows. Drop the rule — slides now stack in the
print-style flow the surrounding comment already described, the gallery
thumbnail iframe still naturally lands on slide 1 (each `.slide` is `100vh`),
and modal/share/export contains the full deck.
The wrapper SKILL.md authoring instructions told agents to copy
`index.html` + `style.css` into a project while keeping the upstream
`../../../assets/...` links, but those parent-relative URLs only resolve
in-tree (the template sits three folders deep). Once the file lives in a
project artifact, `base.css`, `animations.css`, and `runtime.js` 404 and
the deck never activates. Replace step 3 with two recipes — copy the
shared assets into a project-local `assets/` and rewrite the four tags,
or inline the CSS/JS directly — and re-emit all 15 wrapper SKILL.md
files via the scaffold generator.
* feat(prompt-templates): add dance storyboard and ancient-china MMO HUD templates
- social-media-post-sensational-girl-dance-storyboard-8-shots: 8-shot storyboard
prompt set with shared global style tokens, negative prompt, and character
lock, tuned for GPT-Image-2. Produces a continuous dance choreography as a
coherent 8-frame sequence.
- game-ui-ancient-china-open-world-mmo-hud: HUD mockup for a Black Myth: Wukong
style ancient-China open-world MMO, centered on a female swordswoman
protagonist. Covers character panel, minimap with bagua frame, skill hotbar,
quest tracker, chat window, and world-space nameplates with Chinese
typography rules.
- scripts/import-prompt-templates.mjs: preserve hand-authored templates on
re-run by keeping any JSON whose source.repo is not the upstream CC-BY
corpus. Previously clearDir wiped the whole directory, which would delete
first-party curated prompts on the next import.
Both templates carry source attribution to nexu-io/open-design under
Apache-2.0. Categories reuse the existing 'Social Media Post' and 'Game UI'
enum values already present in the gallery.
* feat(prompt-templates): add preview images for dance and MMO HUD templates
- assets/prompt-templates/image/social-media-post-sensational-girl-dance-storyboard-8-shots.jpg:
an 8-panel storyboard render produced from the template itself, downscaled to
1024x1536 JPEG for gallery thumbnails.
- assets/prompt-templates/image/game-ui-ancient-china-open-world-mmo-hud.jpg:
a reference HUD screenshot rendered from the template prompt via gpt-image-2,
downscaled to 1536x1024 JPEG.
- Both templates now reference these previews via a raw.githubusercontent.com
URL pointing at nexu-io/open-design main, matching the pattern used by the
existing YouMind-sourced seeds (cms-assets.youmind.com) so every card in the
Prompt Gallery carries a thumbnail once the PR merges.
---------
Co-authored-by: Joey <joey@open-design.local>
Postinstall assumed `npm_execpath` always points to pnpm's JS entry and
invoked it via `node $npm_execpath`. When pnpm is installed as a
standalone binary (e.g. `@pnpm/exe` via mise / volta), `npm_execpath`
points to an ELF/Mach-O/PE executable and Node fails with
"Invalid or unexpected token" parsing the binary as JS.
Branch on the executable's extension: keep wrapping `.js`/`.cjs`/`.mjs`
entries with `node`, but spawn other paths directly so standalone pnpm
binaries work too.
Co-authored-by: decker <decker502@qq.com>
* 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.
* Refactor project name from "Open Claude Design" to "Open Design"
- Updated project name in package.json, package-lock.json, and README files.
- Changed CLI commands and references from "ocd" to "od".
- Adjusted file structure references in documentation and code to reflect new naming conventions.
- Enhanced .gitignore to include new runtime data files.
- Updated metadata in LICENSE file to match new project name.
* chore: migrate frontend toolchain from Vite to Next.js 16 App Router
Replace the Vite SPA scaffold with Next.js 16 App Router while keeping
the existing daemon as the API/SSE/sqlite backend. The whole client
tree now mounts under a single optional catch-all route
(app/[[...slug]]) loaded with ssr:false; static export emits one shell
HTML the daemon serves as the SPA fallback for deep links. Dev uses
next.config rewrites to proxy /api, /artifacts, /frames to the daemon,
matching the previous Vite setup.
Made-with: Cursor
* fix: address Next migration review feedback
* fix: serve static export in preview script
---------
Co-authored-by: mrcfps <mrc@powerformer.com>
* Refactor project name from "Open Claude Design" to "Open Design"
- Updated project name in package.json, package-lock.json, and README files.
- Changed CLI commands and references from "ocd" to "od".
- Adjusted file structure references in documentation and code to reflect new naming conventions.
- Enhanced .gitignore to include new runtime data files.
- Updated metadata in LICENSE file to match new project name.
* Add contributing guidelines in English and Chinese
- Introduced CONTRIBUTING.md and CONTRIBUTING.zh-CN.md to provide clear instructions for contributors.
- Outlined contribution types, local setup instructions, and merging criteria for skills and design systems.
- Enhanced README files to reference the new contributing guidelines.
* Update README and documentation for deck framework directives
- Clarified DECK_FRAMEWORK_DIRECTIVE description in both English and Chinese README files to specify conditions for deck kind without a skill seed.
- Added detailed workflow instructions in deck-framework.ts to emphasize the importance of copying the framework before adding content.
- Enhanced discovery.ts to reinforce the framework-first approach for deck projects.
- Updated system.ts to ensure proper handling of deck projects with and without bound skills, preventing re-authorship of scaling and navigation logic.
* Update README and documentation for deck framework directives
- Clarified DECK_FRAMEWORK_DIRECTIVE description in both English and Chinese README files to specify conditions for deck kind without a skill seed.
- Added detailed workflow instructions in deck-framework.ts to emphasize the importance of copying the framework before adding content.
- Enhanced discovery.ts to reinforce the framework-first approach for deck projects.
- Updated system.ts to ensure proper handling of deck projects with and without bound skills, preventing re-authorship of scaling and navigation logic.
* Enhance README and add star promotion assets
- Added a "Star us" section in both English and Chinese README files to encourage users to star the project on GitHub.
- Included a new image asset for the star promotion.
- Introduced a new HTML file for a dedicated star promotion page.
- Updated .gitignore to exclude new cursor-related files.
* feat(dev): auto-switch ports on dev:all when defaults are busy
Adds a small launcher (scripts/dev-all.mjs) that probes free ports
for the daemon (OD_PORT, default 7456) and Vite (VITE_PORT, default
5173) before invoking concurrently, so a stray process holding
either port no longer breaks the boot. The resolved ports are
exported into the child env; vite.config.ts now reads VITE_PORT to
keep its dev server and /api proxy aligned with the daemon's actual
port.
Made-with: Cursor
- Created .gitignore to exclude build artifacts and dependencies.
- Added index.html as the main entry point for the application.
- Included LICENSE file with Apache 2.0 terms.
- Initialized package.json and package-lock.json for project dependencies.
- Added pnpm-lock.yaml for package management.
- Created QUICKSTART.md for setup instructions.
- Added README.md and README.zh-CN.md for project documentation in English and Chinese.
