anyformer 0.4.9 → 0.4.10

package/CHANGELOG.md

@@ -1,14 +1,26 @@
 # Changelog
 
-## Unreleased
+## 0.4.10 — 2026-10-24
 
-### Added
-- `kohra`: `onProgress` is forwarded to kohra's `from_pretrained` as `progress_callback` (kohra v0.3.1+), so the
-  2.7 GB Nemotron download reports bytes. `stored()` and `remove()` list kohra's Cache Storage 'kohra-models'.
-  Waits on the kohra v0.3.1 pin.
+### Changed
+- kohra pinned to v0.3.1 (bf95d44): `from_pretrained` reports download progress, which anyformer's `onProgress`
+  receives (forwarded since npm 0.4.9), and caches the graph files in Cache Storage 'kohra-models', which `stored()`
+  lists and `remove()` deletes. A second load of Nemotron-Labs-Diffusion-3B reads them from there.
+
+### Verified
+- npm test 90/90. kohra's own Chrome check on v0.3.1 (kohra session): the first Nemotron load cached all 3 files with
+  their content-length; a reload was ready in 7.4 s with no graph fetches; output unchanged. anyformer's own browser
+  check is owed (the GPU is with Quench), and the npm publish waits for it.
 
 ## 0.4.9 — 2026-10-24
 
+npm 0.4.9 was published from main 69bed78, one commit after tag v0.4.9 (cce1e1a), so it also carries the change
+below. With the kohra v0.3.0 pin that change does nothing yet: v0.3.0 ignores `progress_callback` and caches nothing.
+
+### Added (69bed78)
+- `kohra`: `onProgress` is forwarded to kohra's `from_pretrained` as `progress_callback` (kohra v0.3.1+), so the
+  2.7 GB Nemotron download reports bytes. `stored()` and `remove()` list kohra's Cache Storage 'kohra-models'.
+
 ### Added
 - Catalog flags: `diffusion: true` on the two kohra entries (Qwen3-0.6B MDLM, Nemotron-Labs-Diffusion-3B), and
   `experimental: true` on Nemotron-Labs-Diffusion-3B, so LocalMind can show it as opt-in, "experimental · diffusion",

package/README.md

@@ -14,7 +14,7 @@ browser storage; no account, no server, no telemetry.
 | How | Command |
 |---|---|
 | npm | `npm install anyformer` |
-| CDN | `import { load } from 'https://cdn.jsdelivr.net/npm/anyformer@0.4.9/+esm';` |
+| CDN | `import { load } from 'https://cdn.jsdelivr.net/npm/anyformer@0.4.10/+esm';` |
 | Copy | `index.js` and `src/`; nothing else is needed |
 
 ```js

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "anyformer",
-  "version": "0.4.9",
+  "version": "0.4.10",
   "description": "One call to run a model in a browser tab: anyformer reads the Hub repo, probes the browser, and picks the back end (transformers.js, LocalMind's WebGPU kernels, diskformer, kohra) that fits the model's format, architecture and your GPU budget.",
   "type": "module",
   "main": "./index.js",

package/src/sources.js

@@ -6,8 +6,9 @@
 export const PINS = {
   transformers: '4.3.1',
   wllama: '3.4.1',      // LocalMind's pin; its stream-drain workaround (src/backends/wllama.js) is for this version
-  // v0.3.0: seeded block-KV graphs (Nemotron-Labs-Diffusion-3B), chatFormat, split external data.
-  kohra: '85e01f0193163b0f2e9696d4f6f5e12b68a277e9',
+  // v0.3.1: seeded block-KV graphs (Nemotron-Labs-Diffusion-3B), chatFormat, split external data; download progress
+  // (progress_callback) and the graph files cached in Cache Storage 'kohra-models'.
+  kohra: 'bf95d44c3e3cfc001201baa03fa121c2bf9c7d73',
   // v0.6.8: every engine (the disk-tier MoE engines, Ling 3.0 Flash, and LocalMind's whole-model engines LFM2.5,
   // Gemma 4 E2B/E4B and Ternary Bonsai 2) under engines/, and the llama.cpp path under ggml/, which loads split GGUFs
   // and drafters, and reads past 2 GiB (Nemotron 3.5 Bolt E4B needs v0.6.8 or later). The hand engines' ingest