Skip to content

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

docs: distinguish Compass-only UI from runtime model support in changelog and vendor docs

Emre Sokullua24d95ce0923
diff --git a/CHANGELOG.md b/CHANGELOG.md
index 072e656fc..ff63ad1b6 100644
--- a/CHANGELOG.md
+++ b/CHANGELOG.md
@@ -821,12 +821,12 @@ This changelog was generated from the repository Git history and release tags. V
### Added
- Added OpenRouter routing variant controls, including support for encoding **Exacto** as an OpenRouter model variant
-- Added LFM2.5 1.2B Instruct, 1.2B Thinking, VL 1.6B, and VL 3B to the Chromium WebGPU picker; the VL presets are exposed as multimodal providers
-- Added the Nanbeige4.2-3B ONNX WebGPU export as a Chromium WebGPU text preset, with its non-default graph file name, publisher sampling settings, and a 4k context sized for its 44 KV-cache slots
+- Added WebBrain Compass Tiny v2.1 (`webbrain-one/webbrain-compass-tiny-v2.1`, ~1.87 GB) with a 32k context window as the sole exposed Chromium WebGPU text model
+- Added runtime support for LFM2.5 text/VL and Nanbeige ONNX exports in the underlying WebGPU worker
### Changed
- Restored the **default compact activity history** behavior
-- Restored the Chromium WebGPU text provider in Settings and the normal chat provider picker while keeping model downloads in Apocalypse Mode
+- Restored the Chromium WebGPU text provider in Settings and the normal chat provider picker with direct download controls and standalone operation outside Apocalypse Mode
- Preserved OpenRouter model variants when routing, and synced routing after loaded model selection (Chrome + Firefox)
- Updated provider compatibility handling for DeepSeek support
diff --git a/src/chrome/vendor/transformers/README.md b/src/chrome/vendor/transformers/README.md
index 76ce77c54..77657d097 100644
--- a/src/chrome/vendor/transformers/README.md
+++ b/src/chrome/vendor/transformers/README.md
@@ -3,9 +3,11 @@
This directory packages the JavaScript and WASM runtime used by two local
WebGPU paths in Chrome and by offline RAG's CPU/WASM semantic reranker:
-- **Apocalypse Mode -> local WebGPU chat** downloads the selected LFM2.5 text
- or vision-language preset, or the Nanbeige4.2-3B ONNX export, used by the
- standalone-chat nuclear override. An opt-in Bonsai 27B preset uses a separate
+- **Apocalypse Mode / Settings -> local WebGPU chat** downloads Compass Tiny
+ v2.1 (`webbrain-one/webbrain-compass-tiny-v2.1`, ~1.87 GB), the sole text
+ preset exposed in the UI, used by the standalone-chat nuclear control and
+ selectable as a normal chat provider. The underlying runtime also supports
+ LFM2.5 and Nanbeige exports. An opt-in Bonsai 27B preset uses a separate
vendored bitgpu worker, not this Transformers.js runtime; see
`src/chrome/vendor/bitgpu/README.webbrain.md`.
- **Settings -> Multimodal -> Vision -> LFM2.5-VL local fallback** runs
@@ -14,13 +16,14 @@ WebGPU paths in Chrome and by offline RAG's CPU/WASM semantic reranker:
`Xenova/multilingual-e5-small` q8 model in a separate CPU/WASM worker. Model
weights remain optional and are never bundled or downloaded by a question.
-Model weights are not bundled. Transformers.js downloads each selected WebGPU
-model on first use and stores it in the browser cache. The shipped ONNX chat
-presets are LFM2.5 2.6B, 1.2B Instruct, 1.2B Thinking, VL 1.6B, VL 3B, and
-Nanbeige4.2-3B.
-They are available through the nuclear control in standalone chat and can also
-be selected as the normal provider after download. The reasoning presets keep
-completed thinking out of visible answers. Current LFM2.5-VL layouts use:
+Model weights are not bundled. Transformers.js downloads the WebGPU model on
+first use and stores it in the browser cache. The exposed UI text preset is
+Compass Tiny v2.1 (~1.87 GB), with underlying runtime support for LFM2.5
+(2.6B, 1.2B Instruct, 1.2B Thinking, VL 1.6B, VL 3B) and Nanbeige4.2-3B.
+Compass Tiny v2.1 is available through the nuclear control in standalone chat
+and can also be configured, downloaded, and selected directly in Settings ->
+Providers -> WebGPU. Reasoning presets supported by the runtime keep completed
+thinking out of visible answers. Current LFM2.5-VL layouts use:
- `embed_tokens`: FP16
- `vision_encoder`: FP16
@@ -145,7 +148,7 @@ ProviderManager._createProvider('webgpu') / getVisionProvider()
-> MV3 offscreen document
-> dedicated module Worker
-> text-generation pipeline / AutoProcessor + AutoModelForImageTextToText
- -> selected LFM2.5 or Nanbeige ONNX repo / LFM2.5-VL-450M-ONNX over WebGPU
+ -> selected Compass Tiny v2.1 (or custom ONNX repo) / local vision sidecar over WebGPU
```
Keep inference in the Worker. The MV3 service worker has no WebGPU, while the