Open-source platform for 3D AI agents. Turn text or a photo into a rigged, animated GLB avatar, give it an LLM brain, memory and a wallet, and embed it anywhere with one web component. Remote MCP server, x402 payments, Three.js, browser-native.
JavaScript 3d-generationai-agentsanimationavatardigital-humangenerative-aiglbgltfimage-to-3dllmmcpmcp-servermodel-context-protocolsolanatext-to-3dthreejsweb-componentswebglwebxrx402
fix(i18n): default the Groq translate lane to qwen/qwen3.8-27b, a model Groq still serves
nirholasd0f17962bb22
diff --git a/docs/i18n.md b/docs/i18n.mdindex ad1fa0aa8..d611a6563 100644--- a/docs/i18n.md+++ b/docs/i18n.md@@ -94,7 +94,7 @@ automatically - an exported variable still wins, so a one-off| ------------------ | ------- | -------------------------------------- | ----------------------------------------------------------- || `vertex` (default) | credits | `GOOGLE_CLOUD_PROJECT` + GCP auth | billed to the platform's GCP credits; no free-tier quota wall || `gemini` | ✅ free | `GEMINI_API_KEY` / `GOOGLE_API_KEY` | <https://aistudio.google.com/apikey> - free tier, best CJK |-| `groq` | ✅ free | `GROQ_API_KEY` | <https://console.groq.com/keys> - Llama 3.3 70B, fast |+| `groq` | ✅ free | `GROQ_API_KEY` | <https://console.groq.com/keys> - fast; the script defaults to `qwen/qwen3.8-27b` (the model `/chat` uses on this lane since Groq retired `llama-3.3-70b-versatile` in August 2026); pass `--model=` to override || `openrouter` | ✅ free | `OPENROUTER_API_KEY` | <https://openrouter.ai/keys> - use a `:free` model || `nvidia` | ✅ free | `NVIDIA_API_KEY` | <https://build.nvidia.com> - free NIM credits || `openai` | paid | `OPENAI_API_KEY` (+ `OPENAI_BASE_URL`) | any OpenAI-compatible endpoint |@@ -147,15 +147,17 @@ billing account. `402` is the balance. `401` really is the credential.`i18n:backfill` (below) exists to clean up catalogs damaged by this before theguard existed.-> **Quality note:** Llama 3.3 70B (Groq) is solid for Latin-script languages. For+> **Quality note:** the Groq lane is fast and solid for Latin-script languages. For> CJK/Arabic/Hindi, Gemini (free tier or Vertex) is noticeably better - switch per> run with no code change. Whatever you pick, `npm run i18n:lint` catches any model> that drops a placeholder, a glossary term, or a tag.### Glossary lock (the important part)-Terms in `doNotTranslate` — `$THREE`, the contract address, `x402`, `USDC`,-`Solana`, `IBM watsonx.ai`, etc. - plus every `{{placeholder}}`, HTML tag, and+Terms in `doNotTranslate` (`$THREE`, the contract address, `x402`, `USDC`,+`Solana`, `IBM watsonx.ai`, the official handles and channels such as+`@trythreews`, `t.me/three_ws`, `[email protected]`, and so on) plus every+`{{placeholder}}`, HTML tag, andHTML entity are **masked to opaque sentinels before the text reaches the modeland restored after**. The model literally never sees them, so they come backbyte-for-byte and can never be translated, reordered, or hallucinated around.@@ -296,6 +298,13 @@ default), fetches `/locales/<code>.json` once, rewrites the annotated DOM, setsfall back to English, so partial locales degrade gracefully. `window.threewsI18n`exposes `{ t, setLocale, getLocale, initI18n }`.+An annotated element whose content becomes live data (a balance, a status, a+count) sets `data-i18n-owned="1"` the moment its script writes a real value into+it. The annotation still ships so the pre-render placeholder is translated, but+from then on the catalog pass skips the element: without that, the pass (which+lands after the async catalog fetch) reverted a freshly rendered value back to+its translated "Loading" placeholder.+The `<lang-switcher>` reads `public/locales/manifest.json`, which lists onlylocales whose catalog is **complete**, so it never offers a language that wouldfall back to English. Presence of the file is not enough: `writeManifest()` counts@@ -309,6 +318,15 @@ that still has them, reporting what it skipped:So a locale that is mid-translation is simply absent from the switcher until therun finishes, instead of shipping as a half-translated page.+The switcher shrinks where space is tight. Below the 640px breakpoint, or on any+page that sets a `compact` attribute on `<lang-switcher>` (a narrow HUD rail),+the control shows the locale code (`shortLocaleLabel()`: `EN`, `PT`, `ZH`) in+place of the full language name, which otherwise makes a ~170px control. The+native `<select>` still owns the interaction and keeps the full names in its+options, so the picker, keyboard and screen readers behave exactly as before; the+host also accepts a `max-width` and follows it instead of pushing its siblings+off screen.+## Adding a languageAdd the code (and display name) to `outputLocales` / `localeNames` indiff --git a/scripts/i18n-translate.mjs b/scripts/i18n-translate.mjsindex 07ad12cb3..cb9c3f6e7 100644--- a/scripts/i18n-translate.mjs+++ b/scripts/i18n-translate.mjs@@ -200,7 +200,7 @@ function chunkKeys(keys, budgetChars) {const PROVIDER_DEFAULT_MODEL = {gemini: 'gemini-2.5-flash',vertex: 'google/gemini-2.5-flash',- groq: 'llama-3.3-70b-versatile',+ groq: 'qwen/qwen3.8-27b',openrouter: 'openai/gpt-oss-20b:free',nvidia: 'meta/llama-3.3-70b-instruct',mistral: 'mistral-small-latest',