anyformer 0.4.8 → 0.4.10

package/CHANGELOG.md

@@ -1,5 +1,35 @@
 # Changelog
 
+## 0.4.10 — 2026-10-24
+
+### 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",
+  until its multi-turn chat check passes (Chirag's conditions for LocalMind, 2026-10-24). `anyformer_models` returns
+  them.
+
+### Verified
+- npm test 90/90. No browser check: catalog fields only.
+
 ## 0.4.8 — 2026-10-24
 
 Skips 0.4.7 on npm: this release carries its Nemotron-Labs-Diffusion-3B entry too.

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@0.4.8/+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": "0.4.8",
+  "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/backends/kohra.js

@@ -65,6 +65,9 @@ export const kohraBackend = {
     const special = SPECIAL[model.architecture];
     const lm = await DiffusionLM.from_pretrained({
       model: `${base}/${graph}`, tokenizer: model.repo, ...(graph === Q4 && { ortVersion: Q4_ORT }), ...special?.opts,
+      // kohra v0.3.1+: transformers.js-style events ({ status: 'initiate' | 'progress' | 'done', file, loaded, total,
+      // progress }) while the graph and its data download into Cache Storage 'kohra-models'. Older kohra ignores it.
+      ...(onProgress && { progress_callback: (p) => onProgress({ backend: 'kohra', ...p }) }),
     });
     signal?.throwIfAborted();
     const blockCausal = special ? special.blockCausal : model.tags.includes('block-diffusion');

package/src/models.js

@@ -1,6 +1,8 @@
 // Models that pass a browser test through anyformer, grouped by what they do. Pass an entry to load() in place of a
 // repo id; it carries the task and, where the back end needs one, the budget. DEFAULT is the smallest download that
 // passed. `test` names the page under test/browser/ that proves the entry; test/models.test.js checks it exists.
+// `diffusion: true` marks a text-diffusion model (the reply denoises in blocks); `experimental: true` marks an entry its
+// app shows as opt-in until that app's own checks pass.
 
 const M = (repo, backend, task, test, extra = {}) => ({ repo, backend, task, test, ...extra });
 
@@ -15,8 +17,8 @@ const QWEN3_5_4B = M('onnx-community/Qwen3.5-4B-ONNX-OPT', 'transformers', 'text
 const GEMMA4_E2B_ONNX = M('onnx-community/gemma-4-E2B-it-ONNX', 'transformers', 'text-generation', 'vision', { budget: 3.5e9, downloadBytes: 3.38e9 });
 const GEMMA4_E4B_ONNX = M('onnx-community/gemma-4-E4B-it-ONNX', 'transformers', 'text-generation', 'transformers', { budget: 5.3e9, downloadBytes: 5.18e9 });
 const MINICPM5_2B = M('openbmb/MiniCPM5-2B-GGUF', 'wllama', 'text-generation', 'chat', { downloadBytes: 1.56e9 });
-const QWEN3_0_6B_MDLM = M('naklitechie/Qwen3-0.6B-diffusion-mdlm-ONNX', 'kohra', 'text-generation', 'kohra', { downloadBytes: 1.54e9 });
-const NEMOTRON_DIFFUSION_3B = M('naklitechie/Nemotron-Labs-Diffusion-3B-ONNX', 'kohra', 'text-generation', 'kohra', { downloadBytes: 2.77e9 });
+const QWEN3_0_6B_MDLM = M('naklitechie/Qwen3-0.6B-diffusion-mdlm-ONNX', 'kohra', 'text-generation', 'kohra', { downloadBytes: 1.54e9, diffusion: true });
+const NEMOTRON_DIFFUSION_3B = M('naklitechie/Nemotron-Labs-Diffusion-3B-ONNX', 'kohra', 'text-generation', 'kohra', { downloadBytes: 2.77e9, diffusion: true, experimental: true });
 const GEMMA4_26B_A4B = M('google/gemma-4-26B-A4B-it-qat-q4_0-gguf', 'diskformer', 'text-generation', 'diskformer-chat', { budget: 2.5e9, downloadBytes: 14.44e9 });
 const NEMOTRON_3_5_BOLT_E4B = M('danyalmalik/NVIDIA-Nemotron-3.5-Bolt-E4B-ONNX-WebGPU', 'transformers', 'text-generation', 'transformers', { budget: 5e9, downloadBytes: 4.94e9 });
 const MINILM_L6 = M('Xenova/all-MiniLM-L6-v2', 'transformers', 'feature-extraction', 'embed', { downloadBytes: 90e6 });

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

package/src/store.js

@@ -3,8 +3,8 @@
 // inventoryModelCaches() (index.html), which covers the same engines' stores.
 //   Cache Storage   'transformers-cache' (transformers.js; kohra's tokenizer too); 'gguf-v1', 'gguf-v1-headers' and
 //                   'bonsai-pipeline-v1' (LocalMind's engines; 'gguf-v1' holds the LFM2
-//                   engine): one entry per file URL (…/<repo>/resolve/<rev>/<file>). kohra's ONNX graph sits in the
-//                   browser's HTTP cache, which a page cannot list.
+//                   engine), 'kohra-models' (kohra v0.3.1+: its ONNX graph and data files): one entry per file URL
+//                   (…/<repo>/resolve/<rev>/<file>). Older kohra left its graph in the HTTP cache, which a page cannot list.
 //   IndexedDB       'gguf-cache-v1' (Bonsai 2) and 'safetensors-cache-v1' (Gemma 4 QAT-mobile): a store keyed by URL
 //                   with { size } and a chunk store keyed [url, start, end]; 'webgpu-prefix-snapshots' (Bonsai 2's
 //                   system-prompt snapshot).
@@ -18,7 +18,7 @@ import { DISKFORMER_MODELS } from './backends/diskformer.js';
 import { SPLIT_ROOT } from './gguf-split.js';
 import { readLlamaIndex, LLAMA_INDEX } from './backends/diskformer-llama.js';
 
-const CACHE_BACKEND = { 'transformers-cache': 'transformers', 'gguf-v1': 'localmind', 'gguf-v1-headers': 'localmind', 'bonsai-pipeline-v1': 'localmind' };
+const CACHE_BACKEND = { 'transformers-cache': 'transformers', 'gguf-v1': 'localmind', 'gguf-v1-headers': 'localmind', 'bonsai-pipeline-v1': 'localmind', 'kohra-models': 'kohra' };
 const IDB_STORES = ['gguf-cache-v1', 'safetensors-cache-v1'];
 const BONSAI2 = 'prism-ml/Ternary-Bonsai-2-27B-gguf';
 

package/src/tools.js

@@ -43,7 +43,7 @@ export const TOOLS = [
   },
   {
     name: 'anyformer_models', consequence: 'read',
-    description: 'Models that pass a browser test through anyformer, by family (chat, embedding, objectDetection): repo, back end, task, budget, download size. Pass a repo to anyformer_plan or anyformer_load.',
+    description: 'Models that pass a browser test through anyformer, by family (chat, embedding, objectDetection): repo, back end, task, budget, download size, and the flags diffusion and experimental. Pass a repo to anyformer_plan or anyformer_load.',
     inputSchema: { type: 'object', properties: {} },
     handler: () => MODELS,
   },