Skip to content

Open-source AI browser agent for Chrome and Firefox (monorepo) 🧠

docs(i18n): Compass-only WebGPU docs across locales; OOM error hints at lower context

Emre Sokullu6634eb37ecef
diff --git a/docs/fr/providers-and-models.md b/docs/fr/providers-and-models.md
index bc362a2aa..3075d4408 100644
--- a/docs/fr/providers-and-models.md
+++ b/docs/fr/providers-and-models.md
@@ -46,7 +46,7 @@ class BaseLLMProvider {
| `localai` | `openai` | local | (modèle chargé) | Métadonnées auto / surcharge |
| `gpt4all` | `openai` | local | (modèle chargé) | Oui (activé par défaut) |
| `local_openai_proxy` | `openai` | local | (requis) | Désactivée / bascule manuelle |
-| `webgpu` (Chromium) | `webgpu` | local | LFM2.5 2.6B (valeur par défaut) ou Bonsai 27B en option ; dépôt HF ONNX personnalisé expérimental | Non |
+| `webgpu` (Chromium) | `webgpu` | local | Compass Tiny v2.1 (préréglage unique) ; dépôt HF ONNX personnalisé expérimental | Non |
| `azure_openai` | `azure_openai` | cloud | (déploiement) | Bascule manuelle |
| `aws_bedrock` | `aws_bedrock` | cloud | (ID de modèle) | Non |
| `openai` | `openai` | cloud | `gpt-5.6-terra` | Regex nom de modèle |
@@ -118,13 +118,12 @@ Entrées volontairement exclues : `github-models` (retrait de GitHub Models le
### Fournisseurs Locaux
Sur Chromium, **WebGPU (dans le navigateur)** est un fournisseur local sans
-point de terminaison. Le sélecteur Apocalypse propose deux préréglages
-embarqués : **LFM2.5 2.6B** (`q4f16`, environ 1,55 Go) via Transformers.js /
-ONNX, toujours le défaut et téléchargé à l’activation d’Apocalypse ; et
-**Bonsai 27B** (`Q1_0`, environ 3,8 Go) via un worker bitgpu optionnel, jamais
-téléchargé automatiquement. Bonsai exige un GPU haut de gamme (16 Go+ de
-RAM/VRAM recommandés). LFM et Bonsai ne sont jamais résidents GPU en même
-temps. Firefox n’expose pas cette carte.
+point de terminaison. Le sélecteur Apocalypse propose un préréglage embarqué
+unique : **Compass Tiny v2.1** (`q4f16`, environ 1,87 Go) via Transformers.js /
+ONNX, téléchargé à l’activation d’Apocalypse. Une fois en cache, Compass
+fonctionne sans qu’Apocalypse soit activé. Le fournisseur est texte seul, avec
+une fenêtre de contexte de 32k par défaut ; sur les GPU limités, réduisez-la
+dans Settings → Providers si nécessaire. Firefox n’expose pas cette carte.
Neuf fournisseurs à terminaison locale sont activés par défaut. Les moteurs de
modèles n'exigent pas de clé sauf si le serveur utilise l'authentification ; la
diff --git a/docs/fr/remote-downloads.md b/docs/fr/remote-downloads.md
index 948301c8d..b1651d8d2 100644
--- a/docs/fr/remote-downloads.md
+++ b/docs/fr/remote-downloads.md
@@ -22,7 +22,7 @@ WebBrain est conçu pour minimiser les dépendances réseau distantes. Tous les
| Composant | Serveur distant / Origine | Description de l'origine | Taille typique | Protocole / Méthode | Somme de contrôle & Intégrité | Destination de stockage local |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
-| **Modèle de texte WebGPU** | `huggingface.co` / CDN Hugging Face | Dépôt officiel Hugging Face hébergeant les poids ONNX / SafeTensors (ex. SmolLM2, Llama-3.2) | ~1,5 – 2,5 Go | HTTPS GET (pipeline Transformers.js) | Hash SHA-256 Git LFS Hugging Face | Cache API du navigateur & IndexedDB (`transformers-cache`) |
+| **Modèle de texte WebGPU** | `huggingface.co` / CDN Hugging Face | Poids ONNX `webbrain-one/webbrain-compass-tiny-v2.1`, l'unique préréglage texte embarqué | ~1,87 Go | HTTPS GET (pipeline Transformers.js) | Hash SHA-256 Git LFS Hugging Face | Cache API du navigateur & IndexedDB (`transformers-cache`) |
| **Modèle de vision locale** | `huggingface.co` / CDN Hugging Face | Poids ONNX pour la description locale de captures d'écran (LFM2.5-VL / SmolVLM) | ~770 Mo | HTTPS GET (pipeline Transformers.js) | Hash SHA-256 Git LFS Hugging Face | Cache API du navigateur & IndexedDB (`transformers-cache`) |
| **Pack de texte d'urgence & Index SQLite** | `github.com/webbrain-one/emergency-box-corpus` (GitHub Releases) | Fichiers de référence du domaine public, base SQLite FTS5 préconstruite et vecteurs E5 | ~245 Mo (ZIP compressé) | Flux de téléchargement continu avec reprise `Range: bytes={offset}-` | Comparaison stricte du hash **SHA-256** avec le descripteur de version avant activation | OPFS (`webbrain-offline-rag/emergency-box-text/`) & IndexedDB (`webbrain_offline_rag`) |
| **Modèle sémantique multilingue** | `huggingface.co` / CDN Hugging Face (`Xenova/multilingual-e5-small`) | Poids ONNX pour le plongement de requêtes et la recherche vectorielle / réordonnancement | ~134 Mo | HTTPS GET (ONNX Runtime Web / Transformers.js) | Vérification SHA-256 via manifeste Transformers.js | Cache API du navigateur & IndexedDB (`transformers-cache`) |
@@ -40,7 +40,7 @@ Lors de l'activation du **Mode Apocalypse** (ou à l'ouverture de `apocalypse-mo
```mermaid
flowchart TD
A["L'utilisateur active le Mode Apocalypse"] --> B["1. Téléchargements parallèles"]
- B --> C["Modèle de texte WebGPU (~1,5-2,5 Go)<br/><b>CDN Hugging Face</b>"]
+ B --> C["Modèle de texte Compass Tiny v2.1 (~1,87 Go)<br/><b>CDN Hugging Face</b>"]
B --> D["Modèle de vision locale (~770 Mo)<br/><b>CDN Hugging Face</b>"]
B --> E["Pack de texte d'urgence (~245-502 Mo)<br/><b>CDN GitHub Releases</b>"]
B --> F["Modèle sémantique E5 (~134 Mo)<br/><b>CDN Hugging Face</b>"]
@@ -55,7 +55,7 @@ flowchart TD
1. **Vérifications préalables** : Détection des capacités WebGPU et estimation de l'espace disque disponible.
2. **Téléchargements parallèles en arrière-plan** :
- - Modèle de texte WebGPU (~1,5-2,5 Go depuis Hugging Face)
+ - Modèle de texte Compass Tiny v2.1 (~1,87 Go depuis Hugging Face)
- Modèle de vision locale (~770 Mo depuis Hugging Face)
- Pack de texte d'urgence (~245 Mo depuis GitHub Releases $\rightarrow$ vérification SHA-256 $\rightarrow$ extraction $\rightarrow$ enregistrement SQLite FTS5 dans OPFS)
- Modèle sémantique multilingue E5 (~134 Mo depuis Hugging Face)
diff --git a/docs/providers-and-models.md b/docs/providers-and-models.md
index ca8bd8879..19c303ed7 100644
--- a/docs/providers-and-models.md
+++ b/docs/providers-and-models.md
@@ -47,7 +47,7 @@ class BaseLLMProvider {
| `gpt4all` | `openai` | local | (loaded model) | Yes (default on) |
| `local_openai_proxy` | `openai` | local | (required) | Off / manual toggle |
| `unsloth` | `openai` | local | (required) | Off / manual toggle |
-| `webgpu` (Chromium) | `webgpu` | local | Nine shipped LFM2.5/Nanbeige/MiniCPM5/Compass/Bonsai presets; experimental custom HF ONNX repos | LFM2.5-VL presets |
+| `webgpu` (Chromium) | `webgpu` | local | Compass Tiny v2.1 (only preset); experimental custom HF ONNX repos | No |
| `azure_openai` | `azure_openai` | cloud | (deployment) | Manual toggle |
| `aws_bedrock` | `aws_bedrock` | cloud | (model id) | No |
| `openai` | `openai` | cloud | `gpt-5.6-terra` | Model-name regex |
@@ -150,87 +150,33 @@ duplicate request.
### Local Providers
On Chromium, **WebGPU (In-browser)** is an endpoint-free local provider. Its
-Apocalypse text picker offers nine shipped presets:
-
-- [`LiquidAI/LFM2.5-2.6B-ONNX`](https://huggingface.co/LiquidAI/LFM2.5-2.6B-ONNX/)
- (`q4f16`, about 1.55 GB) through the packaged Transformers.js 4.2 / ONNX
- Runtime Web GPU worker. This remains the default. Enabling Apocalypse Mode
- starts this download automatically.
-- [`LiquidAI/LFM2.5-1.2B-Instruct-ONNX`](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Instruct-ONNX)
- and [`LiquidAI/LFM2.5-1.2B-Thinking-ONNX`](https://huggingface.co/LiquidAI/LFM2.5-1.2B-Thinking-ONNX)
- (`q4f16`, about 760 MB each). The Thinking preset preserves reasoning as
- hidden reasoning content while Instruct uses the normal visible-answer path.
-- [`LiquidAI/LFM2.5-VL-1.6B-ONNX`](https://huggingface.co/LiquidAI/LFM2.5-VL-1.6B-ONNX)
- (FP16 vision/text embeddings plus Q4 decoder, about 2.3 GB) and
- [`LiquidAI/LFM2.5-VL-3B-ONNX`](https://huggingface.co/LiquidAI/LFM2.5-VL-3B-ONNX)
- (the corresponding Transformers.js layout, about 4.0 GB). These two presets
- advertise `supportsVision`, accept image blocks in normal provider chat, and
- are marked **Multimodal** in the picker. The 1.6B export uses older ONNX
- component filenames; WebBrain maps those filenames into the packaged
- Transformers.js image-text runtime before loading it. LiquidAI's current VL
- exports also nest their image metadata in `processor_config.json` and ship
- `chat_template.jinja` separately; the local runtime loads that layout
- explicitly instead of probing for the older `preprocessor_config.json`.
-- [`Michionlion/Nanbeige4.2-3B-ONNX-WebGPU`](https://huggingface.co/Michionlion/Nanbeige4.2-3B-ONNX-WebGPU)
- (`q4f16`, about 3.1 GB), a browser export of
- [`Nanbeige/Nanbeige4.2-3B`](https://huggingface.co/Nanbeige/Nanbeige4.2-3B)
- that runs the same 22 physical layers twice and therefore keeps 44 KV-cache
- slots. It publishes one WebGPU-fused graph under a non-default file name, so
- the worker loads it with `model_file_name: 'model_webgpu_mlp'`; the external
- data shards come from the repository's own `use_external_data_format`. The
- graph needs the `com.microsoft::MatMulNBitsMlp` WebGPU kernel from the
- vendored ONNX Runtime build and an adapter with `shader-f16`. Its practical
- context is set to 4k rather than 16k because those 44 slots cost roughly
- 176 KB per token in FP16, on top of 3.1 GB of weights. The reference
- implementation is the [Nanbeige Browser Lab](https://huggingface.co/spaces/borkiss/nanbeige4-2-3b-browser-lab)
- Space, which drives the same export through a hand-written ONNX Runtime Web
- loop rather than Transformers.js.
-- [`RASMUS/MiniCPM5-2B-ONNX`](https://huggingface.co/RASMUS/MiniCPM5-2B-ONNX)
- (`q4f16`, about 1.83 GB), a browser-ready ONNX export of
- [`openbmb/MiniCPM5-2B`](https://huggingface.co/openbmb/MiniCPM5-2B) built with
- `onnxruntime-genai -e webgpu` (`MatMulNBits` + `GroupQueryAttention`, default
- `onnx/model_q4f16.onnx` layout). It needs an adapter with `shader-f16` and
- emits XML-style tool calls
- (`<function name="..."><param name="...">...</param></function>`, CDATA-wrapped
- when values contain `<`, `&`, or newlines), which the local fallback parser
- accepts. Its practical context is 16k.
+Apocalypse text picker offers a single shipped preset:
+
- [`webbrain-one/webbrain-compass-tiny-v2.1`](https://huggingface.co/webbrain-one/webbrain-compass-tiny-v2.1)
(`q4f16`, about 1.87 GB across two external-data shards), WebBrain's Compass
- Tiny v2.1 fine-tune of MiniCPM5-2B for Compact tool routing (v2.1 export
- revision with the WebGPU numerical-parity fix). Same default
- `onnx/model_q4f16.onnx` layout and MiniCPM5 XML tool calls as the base export.
- It runs greedy with thinking disabled (the worker default for non-reasoning
- presets) at a practical 16k context. Experimental integration-testing release
- under a noncommercial research license; see the repository README and
- `PROVENANCE.json` before treating it as production.
-- [`prism-ml/Bonsai-27B-gguf`](https://huggingface.co/prism-ml/Bonsai-27B-gguf)
- (`Q1_0`, about 3.8 GB) through a dedicated vendored [bitgpu](https://github.com/stfurkan/bitgpu)
- worker. Bonsai is opt-in: WebBrain never auto-downloads the 27B weights.
- It needs a high-end GPU (16 GB+ RAM/VRAM recommended). Mutually exclusive
- WebGPU text runtimes are released when the selected preset changes; disk
- caches may coexist.
+ Tiny v2.1 fine-tune of MiniCPM5-2B for Compact tool routing. It runs greedy
+ with thinking disabled through the packaged Transformers.js 4.2 / ONNX
+ Runtime Web GPU worker, and emits MiniCPM5 XML-style tool calls
+ (`<function name="..."><param name="...">...</param></function>`, CDATA-wrapped
+ when values contain `<`, `&`, or newlines), which the local fallback parser
+ accepts. Enabling Apocalypse Mode starts this download automatically.
Custom Hugging Face repositories have not been tested and are likely not to
work. They must be compatible with Transformers.js text generation, provide a
`q4f16` ONNX variant, and use a chat template that accepts `tools`; WebBrain
validates the template after loading and rejects incompatible repositories.
-Do not point Transformers.js at the Bonsai GGUF — 27B is not an ONNX pipeline.
-
-The provider defaults to the Compact prompt tier with a conservative 16k
-practical context setting (4k for Nanbeige and Bonsai). Text-only presets
-reject image blocks; the two LFM2.5-VL presets route image and text blocks
-through the local image-text runtime. LFM2.5 2.6B, 1.2B Thinking,
-Nanbeige4.2-3B, and MiniCPM5-2B use reasoning paths; WebBrain keeps completed thinking out of
-the visible answer and reports an error when a template that opens `<think>`
-in the generation prompt exhausts its output budget before closing it. Those
-four presets decode with their publisher's recommended sampling settings; the
-remaining ONNX presets stay greedy. Bonsai uses bitgpu
-`think: true` with a 128-token think budget and the same post-think visible-
-answer UX. Each repository is cached separately in Chrome.
-After downloading a preset in Apocalypse Mode, the WebGPU card in
+
+The provider is text-only and defaults to the Compact prompt tier with a
+32k context window. Budget roughly 4 GB of GPU headroom (about 1.87 GB of
+weights plus KV cache that grows with context length); on constrained GPUs,
+lower the context window on the WebGPU card in Settings → Providers (16384 is
+a safe fallback) and retry with a short prompt. Each repository is cached
+separately in Chrome.
+After downloading Compass in Apocalypse Mode, the WebGPU card in
**Settings -> Providers** can be configured, tested, and selected as the normal
chat provider. The nuclear standalone-chat control remains available as a
-per-run override that does not change the global selection.
+per-run override that does not change the global selection. Once its files are
+cached, Compass works without Apocalypse Mode enabled.
**Test Connection** checks only the packaged runtime and hardware WebGPU
adapter, so it does not trigger a model download. There is no API key, base
URL, localhost server, or OpenAI-compatible endpoint. Firefox does not expose
diff --git a/docs/remote-downloads.md b/docs/remote-downloads.md
index 42f77c9ba..c6e8f5da1 100644
--- a/docs/remote-downloads.md
+++ b/docs/remote-downloads.md
@@ -22,7 +22,7 @@ WebBrain is designed to minimize remote network dependencies. All downloads fall
| Component | Remote Server / Origin | Origin Description | Typical Size | Protocol / Method | Checksum & Integrity | Local Storage Destination |
| :--- | :--- | :--- | :--- | :--- | :--- | :--- |
-| **WebGPU Text / Multimodal Models** | `huggingface.co` / Hugging Face CDN | Nine shipped presets: LiquidAI LFM2.5 2.6B, 1.2B Instruct, 1.2B Thinking, VL 1.6B, VL 3B, Michionlion Nanbeige4.2-3B, RASMUS MiniCPM5-2B, webbrain-one Compass Tiny v2.1, and prism-ml Bonsai 27B | ~0.76 – 4.0 GB per selected preset | HTTPS GET (Transformers.js/ONNX or bitgpu) | Hugging Face Git LFS SHA-256 hash | Browser Cache API & IndexedDB (`transformers-cache`) |
+| **WebGPU Text Model** | `huggingface.co` / Hugging Face CDN | `webbrain-one/webbrain-compass-tiny-v2.1` ONNX weights, the only shipped text preset | ~1.87 GB | HTTPS GET (Transformers.js/ONNX) | Hugging Face Git LFS SHA-256 hash | Browser Cache API & IndexedDB (`transformers-cache`) |
| **Local Vision Model** | `huggingface.co` / Hugging Face CDN | `webbrain-one/webbrain-vl-2-450M-onnx` weights for local screenshot description and UI analysis | ~810 MB | HTTPS GET (Transformers.js pipeline) | Hugging Face Git LFS SHA-256 hash | Browser Cache API & IndexedDB (`transformers-cache`) |
| **Emergency Text Pack & SQLite Index** | `github.com/webbrain-one/emergency-box-corpus` (GitHub Releases CDN) | Release assets for curated public-domain field references, prebuilt SQLite FTS5 database, and precomputed E5 embeddings | ~245 MB (compressed ZIP) | Resumable HTTP `Range: bytes={offset}-` streaming fetch | Strict **SHA-256** hash comparison against hardcoded release descriptor before activation | OPFS (`webbrain-offline-rag/emergency-box-text/`) & IndexedDB (`webbrain_offline_rag`) |
| **Multilingual Semantic Model** | `huggingface.co` / Hugging Face CDN (`Xenova/multilingual-e5-small`) | ONNX weights for multilingual query embedding and vector search / candidate reranking | ~134 MB | HTTPS GET (ONNX Runtime Web / Transformers.js) | SHA-256 verification via Transformers.js manifest | Browser Cache API & IndexedDB (`transformers-cache`) |
@@ -40,7 +40,7 @@ When a user turns on **Apocalypse Mode** (or opens `apocalypse-mode.html` with A
```mermaid
flowchart TD
A["User enables Apocalypse Mode"] --> B["1. Parallel Auto-Downloads Start"]
- B --> C["Default WebGPU Text Model (~1.55 GB)<br/><b>Hugging Face CDN</b>"]
+ B --> C["Compass Tiny v2.1 Text Model (~1.87 GB)<br/><b>Hugging Face CDN</b>"]
B --> E["Emergency Text Pack (~245-502 MB)<br/><b>GitHub Releases CDN</b>"]
B --> F["Multilingual E5 Semantic Model (~134 MB)<br/><b>Hugging Face CDN</b>"]
B --> G["Simple English Wikipedia ZIM (~50-100 MB)<br/><b>Kiwix / Wikimedia Mirrors</b>"]
@@ -60,7 +60,7 @@ flowchart TD
│ - Estimate OPFS and storage quota availability
│
├─► 2. Parallel Background Downloads (Active Tab + Service Worker / Offscreen):
- │ ├── [Default WebGPU Text Model] (Offscreen document, ~1.55 GB from Hugging Face)
+ │ ├── [Compass Tiny v2.1 Text Model] (Offscreen document, ~1.87 GB from Hugging Face)
│ ├── [Emergency Text Pack] (Tab stream, ~245 MB from GitHub Releases)
│ │ └── Verify SHA-256 ──► Extract ZIP ──► Register SQLite FTS5 in OPFS SAH-pool
│ ├── [Multilingual E5 Semantic Model] (Tab stream, ~134 MB from Hugging Face)
@@ -89,11 +89,9 @@ flowchart TD
- Triggered when the user clicks the microphone button for the first time with local voice input configured.
- Downloads the quantized Whisper model from Hugging Face into the browser's Cache API.
-4. **Optional WebGPU text and multimodal presets (`apocalypse-mode.html`)**:
- - Selecting and starting a non-default preset downloads only that chosen
- repository. The 1.2B variants are about 760 MB; VL 1.6B is about 2.3 GB;
- Nanbeige4.2-3B is about 3.1 GB; VL 3B is about 4.0 GB; and Bonsai is about
- 3.8 GB.
+4. **WebGPU text model (`apocalypse-mode.html`)**:
+ - The picker offers only Compass Tiny v2.1 (about 1.87 GB); starting its
+ download caches that repository.
- The separate 810 MB local vision fallback is downloaded only after the
user enables it in **Settings -> Multimodal -> Vision**.
diff --git a/docs/zh-CN/providers-and-models.md b/docs/zh-CN/providers-and-models.md
index 06ef29525..6a3eec29d 100644
--- a/docs/zh-CN/providers-and-models.md
+++ b/docs/zh-CN/providers-and-models.md
@@ -46,7 +46,7 @@ class BaseLLMProvider {
| `localai` | `openai` | 本地 | (已加载模型) | 自动元数据 / 覆盖 |
| `gpt4all` | `openai` | 本地 | (已加载模型) | 是(默认开启) |
| `local_openai_proxy` | `openai` | 本地 | (必填) | 默认关闭 / 手动开关 |
-| `webgpu`(Chromium) | `webgpu` | 本地 | LFM2.5 2.6B(默认)或可选 Bonsai 27B;实验性自定义 HF ONNX 仓库 | 否 |
+| `webgpu`(Chromium) | `webgpu` | 本地 | Compass Tiny v2.1(唯一预设);实验性自定义 HF ONNX 仓库 | 否 |
| `azure_openai` | `azure_openai` | 云端 | (部署) | 手动开关 |
| `aws_bedrock` | `aws_bedrock` | 云端 | (模型 ID) | 否 |
| `openai` | `openai` | 云端 | `gpt-5.6-terra` | 模型名正则 |
@@ -111,7 +111,7 @@ WebBrain 会直接记录;若服务省略用量,则记录基于字符数的
### 本地提供商
-在 Chromium 上,**WebGPU(浏览器内)** 是无端点的本地提供商。末日模式文本选择器提供两个内置预设:**LFM2.5 2.6B**(`q4f16`,约 1.55 GB)走 Transformers.js / ONNX,仍是默认项,启用末日模式时会自动开始下载;**Bonsai 27B**(`Q1_0`,约 3.8 GB)走可选的 bitgpu worker,绝不会自动下载。Bonsai 需要高端 GPU(建议 16 GB 以上内存/显存)。LFM 与 Bonsai 不会同时驻留 GPU。Firefox 不提供该卡片。
+在 Chromium 上,**WebGPU(浏览器内)** 是无端点的本地提供商。末日模式文本选择器仅提供一个内置预设:**Compass Tiny v2.1**(`q4f16`,约 1.87 GB),走 Transformers.js / ONNX,启用末日模式时会自动开始下载。缓存完成后,即使未启用末日模式,Compass 也可正常使用。该提供商仅支持文本,默认上下文窗口为 32k;在显存受限的 GPU 上,可在 Settings → Providers 中将其调低。Firefox 不提供该卡片。
九个本地端点提供商默认启用。模型运行时无需 API 密钥(除非服务器启用了认证);
通用代理卡片必须填写客户端密钥:
diff --git a/src/chrome/src/offscreen/inference-worker.js b/src/chrome/src/offscreen/inference-worker.js
index f8994724d..421dfa723 100644
--- a/src/chrome/src/offscreen/inference-worker.js
+++ b/src/chrome/src/offscreen/inference-worker.js
@@ -385,7 +385,7 @@ async function enrichWebGpuExecutionError(error) {
const suffix = [
details.length ? `GPU detail: ${details.join(' ')}` : '',
adapter ? `Adapter: ${adapter}.` : '',
- 'Close other GPU-heavy tabs/apps and retry with a short prompt; a retry restarts the on-device worker and re-creates the session from the cached download, it does not re-download. If it persists, this GPU/driver cannot execute this model with the current WebGPU runtime.',
+ 'Close other GPU-heavy tabs/apps and retry with a short prompt; a retry restarts the on-device worker and re-creates the session from the cached download, it does not re-download. On repeated out-of-memory failures, lower the context window on the WebGPU card in Settings > Providers (16384 is a safe fallback for Compass Tiny v2.1). If it persists, this GPU/driver cannot execute this model with the current WebGPU runtime.',
].filter(Boolean).join(' ');
return new Error(`${error?.message || String(error)} ${suffix}`);
}
diff --git a/src/chrome/src/ui/locales/ar.js b/src/chrome/src/ui/locales/ar.js
index 473c7beb7..d32bf6310 100644
--- a/src/chrome/src/ui/locales/ar.js
+++ b/src/chrome/src/ui/locales/ar.js
@@ -1114,8 +1114,8 @@ export default {
"st.sync.confirm.reset": "هل تريد استبدال النسخة السحابية المشفرة بإعداد WebBrain الحالي لهذا الجهاز؟",
"st.sync.consent.legacy": "هل تريد تفعيل المزامنة المشفرة؟ سيرسل WebBrain نسخة مشفرة من طرف إلى طرف من ذكرياتك، والملء التلقائي لملفك الشخصي، وإعدادات موفر مفتاح واجهة برمجة التطبيقات (API) إلى WebBrain Compass. لا تتم مزامنة سجل الدردشة وتسجيلات الدخول عبر OAuth.",
"st.sync.consent.denied": "لم يتم منح إذن المزامنة المشفرة.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/bn.js b/src/chrome/src/ui/locales/bn.js
index b3fa4bc94..6cdd34e74 100644
--- a/src/chrome/src/ui/locales/bn.js
+++ b/src/chrome/src/ui/locales/bn.js
@@ -1112,8 +1112,8 @@ export default {
"st.sync.confirm.reset": "এই ডিভাইসের বর্তমান WebBrain সেটআপ দিয়ে এনক্রিপ্ট করা ক্লাউড কপি প্রতিস্থাপন করবেন?",
"st.sync.consent.legacy": "এনক্রিপ্ট করা সিঙ্ক চালু করবেন? WebBrain আপনার স্মৃতি, প্রোফাইল অটোফিল এবং API-কী প্রদানকারী সেটিংসের একটি এন্ড-টু-এন্ড এনক্রিপ্টেড কপি WebBrain Compass-এ প্রেরণ করবে। চ্যাট ইতিহাস এবং OAuth সাইন-ইন সিঙ্ক করা হয় না।",
"st.sync.consent.denied": "এনক্রিপ্ট করা সিঙ্ক অনুমতি দেওয়া হয়নি।",
- 'st.providers.webgpu_note.body': '{modelLink} কোনো API এন্ডপয়েন্ট ছাড়াই সম্পূর্ণভাবে Chrome-এ চলে। প্রথম জেনারেশনে প্রায় 4.85 GB ডাউনলোড হয় এবং ব্রাউজারে ক্যাশ করা হয়। সংযোগ পরীক্ষা মডেল ডাউনলোড না করেই প্যাকেজ করা রানটাইম ও হার্ডওয়্যার অ্যাডাপ্টার যাচাই করে।',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} কোনো API এন্ডপয়েন্ট ছাড়াই সম্পূর্ণভাবে Chrome-এ চলে। এটি Settings > Providers > WebGPU বা Apocalypse Mode থেকে ডাউনলোড করুন, তারপর standalone chat-এ nuclear control ব্যবহার করুন।',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/de.js b/src/chrome/src/ui/locales/de.js
index 83c4255cd..dfd5831f9 100644
--- a/src/chrome/src/ui/locales/de.js
+++ b/src/chrome/src/ui/locales/de.js
@@ -1085,8 +1085,8 @@ export default {
"st.sync.confirm.reset": "Die verschlüsselte Cloud-Kopie durch das aktuelle WebBrain-Setup dieses Geräts ersetzen?",
"st.sync.consent.legacy": "Verschlüsselte Synchronisierung aktivieren? WebBrain überträgt eine Ende-zu-Ende-verschlüsselte Kopie Ihrer Erinnerungen, des automatischen Ausfüllens Ihres Profils und der Einstellungen des API-Schlüsselanbieters an die WebBrain Compass. Chatverlauf und OAuth-Anmeldungen werden nicht synchronisiert.",
"st.sync.consent.denied": "Die Berechtigung zur verschlüsselten Synchronisierung wurde nicht erteilt.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/es.js b/src/chrome/src/ui/locales/es.js
index 4624af64b..5a2829871 100644
--- a/src/chrome/src/ui/locales/es.js
+++ b/src/chrome/src/ui/locales/es.js
@@ -1114,8 +1114,8 @@ export default {
"st.sync.confirm.reset": "¿Reemplazar la copia cifrada en la nube con la configuración actual de WebBrain de este dispositivo?",
"st.sync.consent.legacy": "¿Activar sincronización cifrada? WebBrain transmitirá una copia cifrada de extremo a extremo de sus recuerdos, el autocompletado de perfiles y la configuración del proveedor de claves API a WebBrain Compass. El historial de chat y los inicios de sesión de OAuth no están sincronizados.",
"st.sync.consent.denied": "No se concedió el permiso de sincronización cifrada.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/fa.js b/src/chrome/src/ui/locales/fa.js
index 5c72adbae..f2cb26a09 100644
--- a/src/chrome/src/ui/locales/fa.js
+++ b/src/chrome/src/ui/locales/fa.js
@@ -1112,8 +1112,8 @@ export default {
"st.sync.confirm.reset": "کپی ابری رمزگذاری شده با راه‌اندازی فعلی WebBrain این دستگاه جایگزین شود؟",
"st.sync.consent.legacy": "همگام سازی رمزگذاری شده روشن شود؟ WebBrain یک نسخه رمزگذاری شده سرتاسر از خاطرات، تکمیل خودکار نمایه و تنظیمات ارائه دهنده کلید API شما را به WebBrain Compass منتقل می کند. سابقه گپ و ورود به سیستم OAuth همگام سازی نمی شوند.",
"st.sync.consent.denied": "مجوز همگام‌سازی رمزگذاری شده داده نشد.",
- 'st.providers.webgpu_note.body': '{modelLink} بدون هیچ نقطهٔ پایانی API کاملاً در Chrome اجرا می‌شود. نخستین تولید حدود 4.85 GB دانلود می‌کند و آن را در مرورگر ذخیره می‌کند. آزمایش اتصال، محیط اجرایی بسته‌بندی‌شده و آداپتور سخت‌افزاری را بدون دانلود مدل بررسی می‌کند.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} بدون هیچ نقطهٔ پایانی API کاملاً در Chrome اجرا می‌شود. آن را در Settings > Providers > WebGPU یا حالت Apocalypse دانلود کنید، سپس از کنترل nuclear در standalone chat استفاده کنید.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/fr.js b/src/chrome/src/ui/locales/fr.js
index b1ef815ce..1a19cb3f5 100644
--- a/src/chrome/src/ui/locales/fr.js
+++ b/src/chrome/src/ui/locales/fr.js
@@ -1114,8 +1114,8 @@ export default {
"st.sync.confirm.reset": "Remplacer la copie cloud cryptée par la configuration WebBrain actuelle de cet appareil ?",
"st.sync.consent.legacy": "Activer la synchronisation chiffrée ? WebBrain transmettra une copie cryptée de bout en bout de vos souvenirs, du remplissage automatique de votre profil et des paramètres du fournisseur de clé API à WebBrain Compass. L'historique des discussions et les connexions OAuth ne sont pas synchronisés.",
"st.sync.consent.denied": "L'autorisation de synchronisation chiffrée n'a pas été accordée.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/he.js b/src/chrome/src/ui/locales/he.js
index 9641b00fb..ea90dcb53 100644
--- a/src/chrome/src/ui/locales/he.js
+++ b/src/chrome/src/ui/locales/he.js
@@ -1073,8 +1073,8 @@ export default {
'st.vision.local.disable': 'השבתת החלופה המקומית',
'st.vision.local.saved': 'חלופת הראייה המקומית הופעלה.',
"st.vision.local.testing": "הראייה המקומית נטענת ונבדקת…",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/hi.js b/src/chrome/src/ui/locales/hi.js
index 6b3975f10..815e2f5b8 100644
--- a/src/chrome/src/ui/locales/hi.js
+++ b/src/chrome/src/ui/locales/hi.js
@@ -1112,8 +1112,8 @@ export default {
"st.sync.confirm.reset": "क्या एन्क्रिप्टेड क्लाउड कॉपी को इस डिवाइस के मौजूदा WebBrain सेटअप से बदलना है?",
"st.sync.consent.legacy": "एन्क्रिप्टेड सिंक चालू करें? WebBrain आपकी यादों, प्रोफ़ाइल ऑटोफ़िल और API-कुंजी प्रदाता सेटिंग्स की एंड-टू-एंड एन्क्रिप्टेड कॉपी WebBrain Compass को भेजेगा। चैट इतिहास और OAuth साइन-इन सिंक नहीं किए जाते।",
"st.sync.consent.denied": "एन्क्रिप्टेड सिंक अनुमति नहीं दी गई थी.",
- 'st.providers.webgpu_note.body': '{modelLink} बिना किसी API एंडपॉइंट के पूरी तरह Chrome में चलता है। पहली जनरेशन लगभग 4.85 GB डाउनलोड करती है और इसे ब्राउज़र में कैश करती है। कनेक्शन जाँच मॉडल डाउनलोड किए बिना पैकेज किए गए रनटाइम और हार्डवेयर अडैप्टर की जाँच करती है।',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} बिना किसी API एंडपॉइंट के पूरी तरह Chrome में चलता है। इसे Settings > Providers > WebGPU या Apocalypse Mode में डाउनलोड करें, फिर standalone chat में nuclear control का उपयोग करें।',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/id.js b/src/chrome/src/ui/locales/id.js
index 9b435e6c7..f94194f8b 100644
--- a/src/chrome/src/ui/locales/id.js
+++ b/src/chrome/src/ui/locales/id.js
@@ -1114,8 +1114,8 @@ export default {
"st.sync.confirm.reset": "Ganti salinan cloud terenkripsi dengan pengaturan WebBrain perangkat ini saat ini?",
"st.sync.consent.legacy": "Aktifkan sinkronisasi terenkripsi? WebBrain akan mengirimkan salinan memori Anda yang terenkripsi ujung ke ujung, pengisian otomatis profil, dan pengaturan penyedia kunci API ke WebBrain Compass. Riwayat obrolan dan proses masuk OAuth tidak disinkronkan.",
"st.sync.consent.denied": "Izin sinkronisasi terenkripsi tidak diberikan.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/ja.js b/src/chrome/src/ui/locales/ja.js
index 783c6eb22..b10046c16 100644
--- a/src/chrome/src/ui/locales/ja.js
+++ b/src/chrome/src/ui/locales/ja.js
@@ -1114,8 +1114,8 @@ export default {
"st.sync.confirm.reset": "暗号化されたクラウド コピーをこのデバイスの現在の WebBrain セットアップに置き換えますか?",
"st.sync.consent.legacy": "暗号化された同期をオンにしますか? WebBrain は、エンドツーエンドで暗号化された思い出、プロファイルの自動入力、API キー プロバイダー設定のコピーを WebBrain Compass に送信します。チャット履歴と OAuth サインインは同期されません。",
"st.sync.consent.denied": "暗号化された同期権限が付与されませんでした。",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/ko.js b/src/chrome/src/ui/locales/ko.js
index 24ecab22e..8edab285d 100644
--- a/src/chrome/src/ui/locales/ko.js
+++ b/src/chrome/src/ui/locales/ko.js
@@ -1114,8 +1114,8 @@ export default {
"st.sync.confirm.reset": "암호화된 클라우드 사본을 이 기기의 현재 WebBrain 설정으로 바꾸시겠습니까?",
"st.sync.consent.legacy": "암호화된 동기화를 사용하시겠습니까? WebBrain은 추억, 프로필 자동 완성 및 API 키 제공자 설정의 엔드 투 엔드 암호화 사본을 WebBrain Compass로 전송합니다. 채팅 기록과 OAuth 로그인은 동기화되지 않습니다.",
"st.sync.consent.denied": "암호화된 동기화 권한이 부여되지 않았습니다.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/ms.js b/src/chrome/src/ui/locales/ms.js
index d480ab8c8..a53897673 100644
--- a/src/chrome/src/ui/locales/ms.js
+++ b/src/chrome/src/ui/locales/ms.js
@@ -1114,8 +1114,8 @@ export default {
"st.sync.confirm.reset": "Gantikan salinan awan yang disulitkan dengan persediaan WebBrain semasa peranti ini?",
"st.sync.consent.legacy": "Hidupkan penyegerakan yang disulitkan? WebBrain akan menghantar salinan memori anda yang disulitkan hujung ke hujung, autolengkap profil dan tetapan pembekal kunci API ke WebBrain Compass. Sejarah sembang dan log masuk OAuth tidak disegerakkan.",
"st.sync.consent.denied": "Kebenaran penyegerakan yang disulitkan tidak diberikan.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/nl.js b/src/chrome/src/ui/locales/nl.js
index ab64f5421..519b48340 100644
--- a/src/chrome/src/ui/locales/nl.js
+++ b/src/chrome/src/ui/locales/nl.js
@@ -1065,8 +1065,8 @@ export default {
"st.sync.confirm.reset": "De gecodeerde cloudkopie vervangen door de huidige WebBrain-installatie van dit apparaat?",
"st.sync.consent.legacy": "Versleutelde synchronisatie inschakelen? WebBrain verzendt een end-to-end gecodeerde kopie van uw herinneringen, automatisch aanvullen van profielen en API-sleutelproviderinstellingen naar WebBrain Compass. Chatgeschiedenis en OAuth-aanmeldingen worden niet gesynchroniseerd.",
"st.sync.consent.denied": "Er is geen versleutelde synchronisatietoestemming verleend.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/pl.js b/src/chrome/src/ui/locales/pl.js
index a880ee370..a0491622c 100644
--- a/src/chrome/src/ui/locales/pl.js
+++ b/src/chrome/src/ui/locales/pl.js
@@ -1074,8 +1074,8 @@ export default {
"st.sync.confirm.reset": "Zastąpić zaszyfrowaną kopię w chmurze bieżącą konfiguracją WebBrain tego urządzenia?",
"st.sync.consent.legacy": "Włączyć szyfrowaną synchronizację? WebBrain prześle kompleksowo zaszyfrowaną kopię Twoich wspomnień, autouzupełniania profilu i ustawień dostawcy klucza API do WebBrain Compass. Historia czatów i logowania OAuth nie są synchronizowane.",
"st.sync.consent.denied": "Nie przyznano zezwolenia na szyfrowaną synchronizację.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/pt.js b/src/chrome/src/ui/locales/pt.js
index 20d85947d..7ea0c5923 100644
--- a/src/chrome/src/ui/locales/pt.js
+++ b/src/chrome/src/ui/locales/pt.js
@@ -1112,8 +1112,8 @@ export default {
"st.sync.confirm.reset": "Substituir a cópia criptografada na nuvem pela configuração atual do WebBrain deste dispositivo?",
"st.sync.consent.legacy": "Ativar a sincronização criptografada? O WebBrain transmitirá uma cópia criptografada de ponta a ponta de suas memórias, preenchimento automático de perfil e configurações do provedor de chave API para o WebBrain Compass. O histórico de bate-papo e os logins do OAuth não são sincronizados.",
"st.sync.consent.denied": "A permissão de sincronização criptografada não foi concedida.",
- 'st.providers.webgpu_note.body': '{modelLink} é executado inteiramente no Chrome, sem endpoint de API. A primeira geração baixa cerca de 4,85 GB e armazena o modelo no cache do navegador. Testar conexão verifica o runtime incluído e o adaptador de hardware sem baixar o modelo.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} é executado inteiramente no Chrome, sem endpoint de API. Baixe-o em Settings > Providers > WebGPU ou no Modo Apocalipse e use o controle nuclear no standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/ru.js b/src/chrome/src/ui/locales/ru.js
index 285b7b2db..f5b606231 100644
--- a/src/chrome/src/ui/locales/ru.js
+++ b/src/chrome/src/ui/locales/ru.js
@@ -1114,8 +1114,8 @@ export default {
"st.sync.confirm.reset": "Заменить зашифрованную облачную копию текущей настройкой WebBrain этого устройства?",
"st.sync.consent.legacy": "Включить шифрованную синхронизацию? WebBrain передаст сквозную зашифрованную копию ваших воспоминаний, автозаполнение профиля и настройки поставщика ключей API в WebBrain Compass. История чата и входы по OAuth не синхронизируются.",
"st.sync.consent.denied": "Разрешение на зашифрованную синхронизацию не предоставлено.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/th.js b/src/chrome/src/ui/locales/th.js
index e6e4830a8..826470521 100644
--- a/src/chrome/src/ui/locales/th.js
+++ b/src/chrome/src/ui/locales/th.js
@@ -1114,8 +1114,8 @@ export default {
"st.sync.confirm.reset": "แทนที่สำเนาบนคลาวด์ที่เข้ารหัสด้วยการตั้งค่า WebBrain ปัจจุบันของอุปกรณ์นี้หรือไม่",
"st.sync.consent.legacy": "เปิดการซิงค์ที่เข้ารหัสไหม WebBrain จะส่งสำเนาความทรงจำของคุณ การกรอกโปรไฟล์อัตโนมัติ และการตั้งค่าผู้ให้บริการคีย์ API ที่เข้ารหัสจากต้นทางถึงปลายทางไปยัง WebBrain Compass ประวัติการแชทและการลงชื่อเข้าใช้ OAuth จะไม่ซิงค์กัน",
"st.sync.consent.denied": "ไม่ได้รับสิทธิ์การซิงค์ที่เข้ารหัส",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/tl.js b/src/chrome/src/ui/locales/tl.js
index 0a9aa1ba4..6d3672c0a 100644
--- a/src/chrome/src/ui/locales/tl.js
+++ b/src/chrome/src/ui/locales/tl.js
@@ -1114,8 +1114,8 @@ export default {
"st.sync.confirm.reset": "Palitan ang naka-encrypt na cloud copy ng kasalukuyang setup ng WebBrain ng device na ito?",
"st.sync.consent.legacy": "I-on ang naka-encrypt na pag-sync? Magpapadala ang WebBrain ng end-to-end na naka-encrypt na kopya ng iyong mga alaala, profile autofill, at API-key na mga setting ng provider sa WebBrain Compass. Hindi naka-sync ang history ng chat at OAuth sign-in.",
"st.sync.consent.denied": "Hindi ibinigay ang naka-encrypt na pahintulot sa pag-sync.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/tr.js b/src/chrome/src/ui/locales/tr.js
index 90dc4ffe0..db3a0e2ca 100644
--- a/src/chrome/src/ui/locales/tr.js
+++ b/src/chrome/src/ui/locales/tr.js
@@ -1113,8 +1113,8 @@ export default {
"st.sync.confirm.reset": "Şifrelenmiş bulut kopyası bu cihazın mevcut WebBrain kurulumuyla değiştirilsin mi?",
"st.sync.consent.legacy": "Şifreli senkronizasyon açılsın mı? WebBrain, anılarınızın, profil otomatik doldurmanızın ve API anahtarı sağlayıcı ayarlarınızın uçtan uca şifrelenmiş bir kopyasını WebBrain Compass'a iletecektir. Sohbet geçmişi ve OAuth oturum açma işlemleri senkronize edilmez.",
"st.sync.consent.denied": "Şifrelenmiş senkronizasyon izni verilmedi.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/uk.js b/src/chrome/src/ui/locales/uk.js
index f0b7ac2db..aa2821daf 100644
--- a/src/chrome/src/ui/locales/uk.js
+++ b/src/chrome/src/ui/locales/uk.js
@@ -1114,8 +1114,8 @@ export default {
"st.sync.confirm.reset": "Замінити зашифровану хмарну копію на поточні налаштування WebBrain цього пристрою?",
"st.sync.consent.legacy": "Увімкнути зашифровану синхронізацію? WebBrain передасть наскрізну зашифровану копію ваших спогадів, автозаповнення профілю та налаштувань постачальника ключа API до WebBrain Compass. Історія чату та вхід OAuth не синхронізуються.",
"st.sync.consent.denied": "Дозвіл на зашифровану синхронізацію не надано.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/vi.js b/src/chrome/src/ui/locales/vi.js
index 2dcbe53d8..b871f2e32 100644
--- a/src/chrome/src/ui/locales/vi.js
+++ b/src/chrome/src/ui/locales/vi.js
@@ -1112,8 +1112,8 @@ export default {
"st.sync.confirm.reset": "Thay thế bản sao đám mây được mã hóa bằng thiết lập WebBrain hiện tại của thiết bị này?",
"st.sync.consent.legacy": "Bật đồng bộ hóa được mã hóa? WebBrain sẽ truyền bản sao được mã hóa nối đầu các ký ức của bạn, tự động điền hồ sơ và cài đặt nhà cung cấp khóa API tới WebBrain Compass. Lịch sử trò chuyện và thông tin đăng nhập OAuth không được đồng bộ hóa.",
"st.sync.consent.denied": "Quyền đồng bộ hóa được mã hóa không được cấp.",
- 'st.providers.webgpu_note.body': '{modelLink} chạy hoàn toàn trong Chrome mà không cần điểm cuối API. Lần tạo đầu tiên tải xuống khoảng 4,85 GB và lưu vào bộ nhớ đệm của trình duyệt. Kiểm tra kết nối xác minh runtime đóng gói và bộ điều hợp phần cứng mà không tải mô hình.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} chạy hoàn toàn trong Chrome mà không cần điểm cuối API. Tải mô hình trong Settings > Providers > WebGPU hoặc Chế độ Apocalypse, rồi dùng nút nuclear trong standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/chrome/src/ui/locales/zh.js b/src/chrome/src/ui/locales/zh.js
index 22d593ab2..fbd4f59f3 100644
--- a/src/chrome/src/ui/locales/zh.js
+++ b/src/chrome/src/ui/locales/zh.js
@@ -1114,8 +1114,8 @@ export default {
"st.sync.confirm.reset": "使用该设备当前的 WebBrain 设置替换加密的云副本?",
"st.sync.consent.legacy": "开启加密同步? WebBrain 会将您的记忆、个人资料自动填充和 API 密钥提供商设置的端到端加密副本传输到 WebBrain Compass。聊天历史记录和 OAuth 登录不同步。",
"st.sync.consent.denied": "未授予加密同步权限。",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
-'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. LFM2.5 2.6B is the only tested model. Other models entered through Custom are untested and likely will not work. Custom repositories must support Transformers.js text generation, include a q4f16 ONNX graph, and provide a chat template that accepts tools. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
+'st.providers.webgpu_note.managed_body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat. It does not replace your selected provider.',
'st.providers.webgpu_download.title': 'WebGPU model files',
'st.providers.webgpu_download.progress_label': 'WebGPU model download progress',
'st.providers.webgpu_download.checking': 'Checking local model files…',
diff --git a/src/firefox/src/ui/locales/ar.js b/src/firefox/src/ui/locales/ar.js
index f616b5211..ab5b63561 100644
--- a/src/firefox/src/ui/locales/ar.js
+++ b/src/firefox/src/ui/locales/ar.js
@@ -1071,5 +1071,5 @@ export default {
"st.sync.confirm.reset": "هل تريد استبدال النسخة السحابية المشفرة بإعداد WebBrain الحالي لهذا الجهاز؟",
"st.sync.consent.legacy": "هل تريد تفعيل المزامنة المشفرة؟ سيرسل WebBrain نسخة مشفرة من طرف إلى طرف من ذكرياتك، والملء التلقائي لملفك الشخصي، وإعدادات موفر مفتاح واجهة برمجة التطبيقات (API) إلى WebBrain Compass. لا تتم مزامنة سجل الدردشة وتسجيلات الدخول عبر OAuth.",
"st.sync.consent.denied": "لم يتم منح إذن المزامنة المشفرة.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/bn.js b/src/firefox/src/ui/locales/bn.js
index 5e4e8bd89..9324bfe21 100644
--- a/src/firefox/src/ui/locales/bn.js
+++ b/src/firefox/src/ui/locales/bn.js
@@ -1091,5 +1091,5 @@ export default {
"st.sync.confirm.reset": "এই ডিভাইসের বর্তমান WebBrain সেটআপ দিয়ে এনক্রিপ্ট করা ক্লাউড কপি প্রতিস্থাপন করবেন?",
"st.sync.consent.legacy": "এনক্রিপ্ট করা সিঙ্ক চালু করবেন? WebBrain আপনার স্মৃতি, প্রোফাইল অটোফিল এবং API-কী প্রদানকারী সেটিংসের একটি এন্ড-টু-এন্ড এনক্রিপ্টেড কপি WebBrain Compass-এ প্রেরণ করবে। চ্যাট ইতিহাস এবং OAuth সাইন-ইন সিঙ্ক করা হয় না।",
"st.sync.consent.denied": "এনক্রিপ্ট করা সিঙ্ক অনুমতি দেওয়া হয়নি।",
- 'st.providers.webgpu_note.body': '{modelLink} কোনো API এন্ডপয়েন্ট ছাড়াই সম্পূর্ণভাবে Chrome-এ চলে। প্রথম জেনারেশনে প্রায় 4.85 GB ডাউনলোড হয় এবং ব্রাউজারে ক্যাশ করা হয়। সংযোগ পরীক্ষা মডেল ডাউনলোড না করেই প্যাকেজ করা রানটাইম ও হার্ডওয়্যার অ্যাডাপ্টার যাচাই করে।',
+ 'st.providers.webgpu_note.body': '{modelLink} কোনো API এন্ডপয়েন্ট ছাড়াই সম্পূর্ণভাবে Chrome-এ চলে। এটি Settings > Providers > WebGPU বা Apocalypse Mode থেকে ডাউনলোড করুন, তারপর standalone chat-এ nuclear control ব্যবহার করুন।',
};
diff --git a/src/firefox/src/ui/locales/de.js b/src/firefox/src/ui/locales/de.js
index 93de36a6a..f9786dc03 100644
--- a/src/firefox/src/ui/locales/de.js
+++ b/src/firefox/src/ui/locales/de.js
@@ -1064,5 +1064,5 @@ export default {
"st.sync.confirm.reset": "Die verschlüsselte Cloud-Kopie durch das aktuelle WebBrain-Setup dieses Geräts ersetzen?",
"st.sync.consent.legacy": "Verschlüsselte Synchronisierung aktivieren? WebBrain überträgt eine Ende-zu-Ende-verschlüsselte Kopie Ihrer Erinnerungen, des automatischen Ausfüllens Ihres Profils und der Einstellungen des API-Schlüsselanbieters an die WebBrain Compass. Chatverlauf und OAuth-Anmeldungen werden nicht synchronisiert.",
"st.sync.consent.denied": "Die Berechtigung zur verschlüsselten Synchronisierung wurde nicht erteilt.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/en.js b/src/firefox/src/ui/locales/en.js
index d22fa235e..a6284ed95 100644
--- a/src/firefox/src/ui/locales/en.js
+++ b/src/firefox/src/ui/locales/en.js
@@ -1093,5 +1093,5 @@ export default {
'st.sync.confirm.reset': 'Replace the encrypted cloud copy with this device’s current WebBrain setup?',
'st.sync.consent.legacy': 'Turn on encrypted sync? WebBrain will transmit an end-to-end encrypted copy of your memories, profile autofill, and API-key provider settings to WebBrain Compass. Chat history and OAuth sign-ins are not synced.',
'st.sync.consent.denied': 'Encrypted sync permission was not granted.',
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/es.js b/src/firefox/src/ui/locales/es.js
index c54fa70a7..b50604c01 100644
--- a/src/firefox/src/ui/locales/es.js
+++ b/src/firefox/src/ui/locales/es.js
@@ -1071,5 +1071,5 @@ export default {
"st.sync.confirm.reset": "¿Reemplazar la copia cifrada en la nube con la configuración actual de WebBrain de este dispositivo?",
"st.sync.consent.legacy": "¿Activar sincronización cifrada? WebBrain transmitirá una copia cifrada de extremo a extremo de sus recuerdos, el autocompletado de perfiles y la configuración del proveedor de claves API a WebBrain Compass. El historial de chat y los inicios de sesión de OAuth no están sincronizados.",
"st.sync.consent.denied": "No se concedió el permiso de sincronización cifrada.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/fa.js b/src/firefox/src/ui/locales/fa.js
index d5fedea9b..c99dce296 100644
--- a/src/firefox/src/ui/locales/fa.js
+++ b/src/firefox/src/ui/locales/fa.js
@@ -1091,5 +1091,5 @@ export default {
"st.sync.confirm.reset": "کپی ابری رمزگذاری شده با راه‌اندازی فعلی WebBrain این دستگاه جایگزین شود؟",
"st.sync.consent.legacy": "همگام سازی رمزگذاری شده روشن شود؟ WebBrain یک نسخه رمزگذاری شده سرتاسر از خاطرات، تکمیل خودکار نمایه و تنظیمات ارائه دهنده کلید API شما را به WebBrain Compass منتقل می کند. سابقه گپ و ورود به سیستم OAuth همگام سازی نمی شوند.",
"st.sync.consent.denied": "مجوز همگام‌سازی رمزگذاری شده داده نشد.",
- 'st.providers.webgpu_note.body': '{modelLink} بدون هیچ نقطهٔ پایانی API کاملاً در Chrome اجرا می‌شود. نخستین تولید حدود 4.85 GB دانلود می‌کند و آن را در مرورگر ذخیره می‌کند. آزمایش اتصال، محیط اجرایی بسته‌بندی‌شده و آداپتور سخت‌افزاری را بدون دانلود مدل بررسی می‌کند.',
+ 'st.providers.webgpu_note.body': '{modelLink} بدون هیچ نقطهٔ پایانی API کاملاً در Chrome اجرا می‌شود. آن را در Settings > Providers > WebGPU یا حالت Apocalypse دانلود کنید، سپس از کنترل nuclear در standalone chat استفاده کنید.',
};
diff --git a/src/firefox/src/ui/locales/fr.js b/src/firefox/src/ui/locales/fr.js
index 1e1d1a984..35d7d847f 100644
--- a/src/firefox/src/ui/locales/fr.js
+++ b/src/firefox/src/ui/locales/fr.js
@@ -1071,5 +1071,5 @@ export default {
"st.sync.confirm.reset": "Remplacer la copie cloud cryptée par la configuration WebBrain actuelle de cet appareil ?",
"st.sync.consent.legacy": "Activer la synchronisation chiffrée ? WebBrain transmettra une copie cryptée de bout en bout de vos souvenirs, du remplissage automatique de votre profil et des paramètres du fournisseur de clé API à WebBrain Compass. L'historique des discussions et les connexions OAuth ne sont pas synchronisés.",
"st.sync.consent.denied": "L'autorisation de synchronisation chiffrée n'a pas été accordée.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/he.js b/src/firefox/src/ui/locales/he.js
index 59128312c..031cb0afa 100644
--- a/src/firefox/src/ui/locales/he.js
+++ b/src/firefox/src/ui/locales/he.js
@@ -1024,5 +1024,5 @@ export default {
"st.sync.confirm.reset": "האם להחליף את עותק הענן המוצפן בהגדרות WebBrain הנוכחיות של המכשיר הזה?",
"st.sync.consent.legacy": "להפעיל סנכרון מוצפן? WebBrain ישדר עותק מוצפן מקצה לקצה של הזיכרונות, המילוי האוטומטי של הפרופיל והגדרות ספק מפתח ה-API שלך ל-WebBrain Compass. היסטוריית הצ'אט וכניסות OAuth אינן מסונכרנות.",
"st.sync.consent.denied": "הרשאת סנכרון מוצפן לא ניתנה.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/hi.js b/src/firefox/src/ui/locales/hi.js
index 1352131d4..3c713de93 100644
--- a/src/firefox/src/ui/locales/hi.js
+++ b/src/firefox/src/ui/locales/hi.js
@@ -1091,5 +1091,5 @@ export default {
"st.sync.confirm.reset": "क्या एन्क्रिप्टेड क्लाउड कॉपी को इस डिवाइस के मौजूदा WebBrain सेटअप से बदलना है?",
"st.sync.consent.legacy": "एन्क्रिप्टेड सिंक चालू करें? WebBrain आपकी यादों, प्रोफ़ाइल ऑटोफ़िल और API-कुंजी प्रदाता सेटिंग्स की एंड-टू-एंड एन्क्रिप्टेड कॉपी WebBrain Compass को भेजेगा। चैट इतिहास और OAuth साइन-इन सिंक नहीं किए जाते।",
"st.sync.consent.denied": "एन्क्रिप्टेड सिंक अनुमति नहीं दी गई थी.",
- 'st.providers.webgpu_note.body': '{modelLink} बिना किसी API एंडपॉइंट के पूरी तरह Chrome में चलता है। पहली जनरेशन लगभग 4.85 GB डाउनलोड करती है और इसे ब्राउज़र में कैश करती है। कनेक्शन जाँच मॉडल डाउनलोड किए बिना पैकेज किए गए रनटाइम और हार्डवेयर अडैप्टर की जाँच करती है।',
+ 'st.providers.webgpu_note.body': '{modelLink} बिना किसी API एंडपॉइंट के पूरी तरह Chrome में चलता है। इसे Settings > Providers > WebGPU या Apocalypse Mode में डाउनलोड करें, फिर standalone chat में nuclear control का उपयोग करें।',
};
diff --git a/src/firefox/src/ui/locales/id.js b/src/firefox/src/ui/locales/id.js
index 003ea936b..dc94fdaf4 100644
--- a/src/firefox/src/ui/locales/id.js
+++ b/src/firefox/src/ui/locales/id.js
@@ -1071,5 +1071,5 @@ export default {
"st.sync.confirm.reset": "Ganti salinan cloud terenkripsi dengan pengaturan WebBrain perangkat ini saat ini?",
"st.sync.consent.legacy": "Aktifkan sinkronisasi terenkripsi? WebBrain akan mengirimkan salinan memori Anda yang terenkripsi ujung ke ujung, pengisian otomatis profil, dan pengaturan penyedia kunci API ke WebBrain Compass. Riwayat obrolan dan proses masuk OAuth tidak disinkronkan.",
"st.sync.consent.denied": "Izin sinkronisasi terenkripsi tidak diberikan.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/ja.js b/src/firefox/src/ui/locales/ja.js
index 2c36ee8fa..5f05edf35 100644
--- a/src/firefox/src/ui/locales/ja.js
+++ b/src/firefox/src/ui/locales/ja.js
@@ -1071,5 +1071,5 @@ export default {
"st.sync.confirm.reset": "暗号化されたクラウド コピーをこのデバイスの現在の WebBrain セットアップに置き換えますか?",
"st.sync.consent.legacy": "暗号化された同期をオンにしますか? WebBrain は、エンドツーエンドで暗号化された思い出、プロファイルの自動入力、API キー プロバイダー設定のコピーを WebBrain Compass に送信します。チャット履歴と OAuth サインインは同期されません。",
"st.sync.consent.denied": "暗号化された同期権限が付与されませんでした。",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/ko.js b/src/firefox/src/ui/locales/ko.js
index 46dfa6ac8..d351182f9 100644
--- a/src/firefox/src/ui/locales/ko.js
+++ b/src/firefox/src/ui/locales/ko.js
@@ -1071,5 +1071,5 @@ export default {
"st.sync.confirm.reset": "암호화된 클라우드 사본을 이 기기의 현재 WebBrain 설정으로 바꾸시겠습니까?",
"st.sync.consent.legacy": "암호화된 동기화를 사용하시겠습니까? WebBrain은 추억, 프로필 자동 완성 및 API 키 제공자 설정의 엔드 투 엔드 암호화 사본을 WebBrain Compass로 전송합니다. 채팅 기록과 OAuth 로그인은 동기화되지 않습니다.",
"st.sync.consent.denied": "암호화된 동기화 권한이 부여되지 않았습니다.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/ms.js b/src/firefox/src/ui/locales/ms.js
index bd38b2457..3380bc22e 100644
--- a/src/firefox/src/ui/locales/ms.js
+++ b/src/firefox/src/ui/locales/ms.js
@@ -1071,5 +1071,5 @@ export default {
"st.sync.confirm.reset": "Gantikan salinan awan yang disulitkan dengan persediaan WebBrain semasa peranti ini?",
"st.sync.consent.legacy": "Hidupkan penyegerakan yang disulitkan? WebBrain akan menghantar salinan memori anda yang disulitkan hujung ke hujung, autolengkap profil dan tetapan pembekal kunci API ke WebBrain Compass. Sejarah sembang dan log masuk OAuth tidak disegerakkan.",
"st.sync.consent.denied": "Kebenaran penyegerakan yang disulitkan tidak diberikan.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/nl.js b/src/firefox/src/ui/locales/nl.js
index eed02760c..d0ae26982 100644
--- a/src/firefox/src/ui/locales/nl.js
+++ b/src/firefox/src/ui/locales/nl.js
@@ -1044,5 +1044,5 @@ export default {
"st.sync.confirm.reset": "De gecodeerde cloudkopie vervangen door de huidige WebBrain-installatie van dit apparaat?",
"st.sync.consent.legacy": "Versleutelde synchronisatie inschakelen? WebBrain verzendt een end-to-end gecodeerde kopie van uw herinneringen, automatisch aanvullen van profielen en API-sleutelproviderinstellingen naar WebBrain Compass. Chatgeschiedenis en OAuth-aanmeldingen worden niet gesynchroniseerd.",
"st.sync.consent.denied": "Er is geen versleutelde synchronisatietoestemming verleend.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/pl.js b/src/firefox/src/ui/locales/pl.js
index 0ee3eb594..aae1a5980 100644
--- a/src/firefox/src/ui/locales/pl.js
+++ b/src/firefox/src/ui/locales/pl.js
@@ -1031,5 +1031,5 @@ export default {
"st.sync.confirm.reset": "Zastąpić zaszyfrowaną kopię w chmurze bieżącą konfiguracją WebBrain tego urządzenia?",
"st.sync.consent.legacy": "Włączyć szyfrowaną synchronizację? WebBrain prześle kompleksowo zaszyfrowaną kopię Twoich wspomnień, autouzupełniania profilu i ustawień dostawcy klucza API do WebBrain Compass. Historia czatów i logowania OAuth nie są synchronizowane.",
"st.sync.consent.denied": "Nie przyznano zezwolenia na szyfrowaną synchronizację.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/pt.js b/src/firefox/src/ui/locales/pt.js
index b12e85c47..d5d148c21 100644
--- a/src/firefox/src/ui/locales/pt.js
+++ b/src/firefox/src/ui/locales/pt.js
@@ -1091,5 +1091,5 @@ export default {
"st.sync.confirm.reset": "Substituir a cópia criptografada na nuvem pela configuração atual do WebBrain deste dispositivo?",
"st.sync.consent.legacy": "Ativar a sincronização criptografada? O WebBrain transmitirá uma cópia criptografada de ponta a ponta de suas memórias, preenchimento automático de perfil e configurações do provedor de chave API para o WebBrain Compass. O histórico de bate-papo e os logins do OAuth não são sincronizados.",
"st.sync.consent.denied": "A permissão de sincronização criptografada não foi concedida.",
- 'st.providers.webgpu_note.body': '{modelLink} é executado inteiramente no Chrome, sem endpoint de API. A primeira geração baixa cerca de 4,85 GB e armazena o modelo no cache do navegador. Testar conexão verifica o runtime incluído e o adaptador de hardware sem baixar o modelo.',
+ 'st.providers.webgpu_note.body': '{modelLink} é executado inteiramente no Chrome, sem endpoint de API. Baixe-o em Settings > Providers > WebGPU ou no Modo Apocalipse e use o controle nuclear no standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/ru.js b/src/firefox/src/ui/locales/ru.js
index 8cf882342..034d55862 100644
--- a/src/firefox/src/ui/locales/ru.js
+++ b/src/firefox/src/ui/locales/ru.js
@@ -1071,5 +1071,5 @@ export default {
"st.sync.confirm.reset": "Заменить зашифрованную облачную копию текущей настройкой WebBrain этого устройства?",
"st.sync.consent.legacy": "Включить шифрованную синхронизацию? WebBrain передаст сквозную зашифрованную копию ваших воспоминаний, автозаполнение профиля и настройки поставщика ключей API в WebBrain Compass. История чата и входы по OAuth не синхронизируются.",
"st.sync.consent.denied": "Разрешение на зашифрованную синхронизацию не предоставлено.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/th.js b/src/firefox/src/ui/locales/th.js
index 3411a54c7..306c97ca6 100644
--- a/src/firefox/src/ui/locales/th.js
+++ b/src/firefox/src/ui/locales/th.js
@@ -1071,5 +1071,5 @@ export default {
"st.sync.confirm.reset": "แทนที่สำเนาบนคลาวด์ที่เข้ารหัสด้วยการตั้งค่า WebBrain ปัจจุบันของอุปกรณ์นี้หรือไม่",
"st.sync.consent.legacy": "เปิดการซิงค์ที่เข้ารหัสไหม WebBrain จะส่งสำเนาความทรงจำของคุณ การกรอกโปรไฟล์อัตโนมัติ และการตั้งค่าผู้ให้บริการคีย์ API ที่เข้ารหัสจากต้นทางถึงปลายทางไปยัง WebBrain Compass ประวัติการแชทและการลงชื่อเข้าใช้ OAuth จะไม่ซิงค์กัน",
"st.sync.consent.denied": "ไม่ได้รับสิทธิ์การซิงค์ที่เข้ารหัส",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/tl.js b/src/firefox/src/ui/locales/tl.js
index 928724d20..5f07c2b71 100644
--- a/src/firefox/src/ui/locales/tl.js
+++ b/src/firefox/src/ui/locales/tl.js
@@ -1071,5 +1071,5 @@ export default {
"st.sync.confirm.reset": "Palitan ang naka-encrypt na cloud copy ng kasalukuyang setup ng WebBrain ng device na ito?",
"st.sync.consent.legacy": "I-on ang naka-encrypt na pag-sync? Magpapadala ang WebBrain ng end-to-end na naka-encrypt na kopya ng iyong mga alaala, profile autofill, at API-key na mga setting ng provider sa WebBrain Compass. Hindi naka-sync ang history ng chat at OAuth sign-in.",
"st.sync.consent.denied": "Hindi ibinigay ang naka-encrypt na pahintulot sa pag-sync.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/tr.js b/src/firefox/src/ui/locales/tr.js
index 65dbac6ca..2085d5597 100644
--- a/src/firefox/src/ui/locales/tr.js
+++ b/src/firefox/src/ui/locales/tr.js
@@ -1070,5 +1070,5 @@ export default {
"st.sync.confirm.reset": "Şifrelenmiş bulut kopyası bu cihazın mevcut WebBrain kurulumuyla değiştirilsin mi?",
"st.sync.consent.legacy": "Şifreli senkronizasyon açılsın mı? WebBrain, anılarınızın, profil otomatik doldurmanızın ve API anahtarı sağlayıcı ayarlarınızın uçtan uca şifrelenmiş bir kopyasını WebBrain Compass'a iletecektir. Sohbet geçmişi ve OAuth oturum açma işlemleri senkronize edilmez.",
"st.sync.consent.denied": "Şifrelenmiş senkronizasyon izni verilmedi.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/uk.js b/src/firefox/src/ui/locales/uk.js
index 9c20855c5..c9e1f3bd8 100644
--- a/src/firefox/src/ui/locales/uk.js
+++ b/src/firefox/src/ui/locales/uk.js
@@ -1071,5 +1071,5 @@ export default {
"st.sync.confirm.reset": "Замінити зашифровану хмарну копію на поточні налаштування WebBrain цього пристрою?",
"st.sync.consent.legacy": "Увімкнути зашифровану синхронізацію? WebBrain передасть наскрізну зашифровану копію ваших спогадів, автозаповнення профілю та налаштувань постачальника ключа API до WebBrain Compass. Історія чату та вхід OAuth не синхронізуються.",
"st.sync.consent.denied": "Дозвіл на зашифровану синхронізацію не надано.",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/vi.js b/src/firefox/src/ui/locales/vi.js
index 934053098..d1f198e6c 100644
--- a/src/firefox/src/ui/locales/vi.js
+++ b/src/firefox/src/ui/locales/vi.js
@@ -1091,5 +1091,5 @@ export default {
"st.sync.confirm.reset": "Thay thế bản sao đám mây được mã hóa bằng thiết lập WebBrain hiện tại của thiết bị này?",
"st.sync.consent.legacy": "Bật đồng bộ hóa được mã hóa? WebBrain sẽ truyền bản sao được mã hóa nối đầu các ký ức của bạn, tự động điền hồ sơ và cài đặt nhà cung cấp khóa API tới WebBrain Compass. Lịch sử trò chuyện và thông tin đăng nhập OAuth không được đồng bộ hóa.",
"st.sync.consent.denied": "Quyền đồng bộ hóa được mã hóa không được cấp.",
- 'st.providers.webgpu_note.body': '{modelLink} chạy hoàn toàn trong Chrome mà không cần điểm cuối API. Lần tạo đầu tiên tải xuống khoảng 4,85 GB và lưu vào bộ nhớ đệm của trình duyệt. Kiểm tra kết nối xác minh runtime đóng gói và bộ điều hợp phần cứng mà không tải mô hình.',
+ 'st.providers.webgpu_note.body': '{modelLink} chạy hoàn toàn trong Chrome mà không cần điểm cuối API. Tải mô hình trong Settings > Providers > WebGPU hoặc Chế độ Apocalypse, rồi dùng nút nuclear trong standalone chat.',
};
diff --git a/src/firefox/src/ui/locales/zh.js b/src/firefox/src/ui/locales/zh.js
index 041f60143..25a7af6a1 100644
--- a/src/firefox/src/ui/locales/zh.js
+++ b/src/firefox/src/ui/locales/zh.js
@@ -1071,5 +1071,5 @@ export default {
"st.sync.confirm.reset": "使用该设备当前的 WebBrain 设置替换加密的云副本?",
"st.sync.consent.legacy": "开启加密同步? WebBrain 会将您的记忆、个人资料自动填充和 API 密钥提供商设置的端到端加密副本传输到 WebBrain Compass。聊天历史记录和 OAuth 登录不同步。",
"st.sync.consent.denied": "未授予加密同步权限。",
- 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. The first generation downloads about 4.85 GB and caches it in the browser. Test Connection checks the packaged runtime and hardware adapter without downloading the model.',
+ 'st.providers.webgpu_note.body': '{modelLink} runs entirely in Chrome with no API endpoint. Download it in Settings > Providers > WebGPU or Apocalypse Mode, then use the nuclear control in standalone chat.',
};