anyformer 0.4.14 → 0.4.16

package/CHANGELOG.md

@@ -1,5 +1,30 @@
 # Changelog
 
+## 0.4.16 — 2026-10-30
+
+### Changed
+- diskformer pin 7ffbea5 → 93193d0 (v0.6.14: LFM3-Omni speech out runs at 1.5–1.8x real time, up from 0.54x, on an
+  M4 Pro; the inverse STFT uses an FFT with the same output; changes only `engines/lfm3_omni.js`).
+- Browser test `omni-speech` on the new pin (Chrome, this Mac, local files, about 22:50 IST): 13.52 s of speech in
+  7.1 s (1.9x real time), first sound after 0.98 s; abort at the first speech chunk; text reply after it equal.
+
+## 0.4.15 — 2026-10-30
+
+### Fixed
+- A caller that stops reading a reply early (a `break` out of `for await`, as after a tool call) without aborting
+  now stops the reply on `diskformer-onnx` and `transformers`: the back end aborts the engine call (a linked
+  AbortController for diskformer-onnx, the stopping criteria's interrupt for transformers.js) and waits for it before
+  the next generate() starts. Before, the engine kept generating, and the next reply ran on the same onnxruntime
+  sessions beside it: "failed to call OrtRun() … Failed to download data from buffer" or a hang of over 10 minutes in
+  Chrome (reported by NakliOS, root-caused by LocalMind). `diskformer-llama` already did this.
+
+### Changed
+- diskformer pin 1fe19f8 → 7ffbea5 (v0.6.13: LFM3-Omni serves one reply at a time; changes only
+  `engines/lfm3_omni.js`).
+- Browser tests `omni` and `omni-speech` break out of a reply (text, and spoken at its first speech chunk) without
+  aborting, then require the next reply to equal the text reference within 10 s. Passed 2026-10-30 (Chrome, this Mac,
+  local files), with `transformers` and the LFM3 1.7B `chat` check.
+
 ## 0.4.14 — 2026-10-30
 
 ### Added

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "anyformer",
-  "version": "0.4.14",
+  "version": "0.4.16",
   "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/diskformer-onnx.js

@@ -87,8 +87,12 @@ export const diskformerOnnxBackend = {
         let wake = () => {}, done = false, failed = null, text = '', tokens = 0;
         const msgs = await media(messages);
         const sampleRate = engine.speech?.sampling_rate ?? 24000;
-        engine.generate(msgs, {
-          max_new_tokens: maxNewTokens, do_sample: false, enable_thinking: thinking === true, signal,
+        // The engine reads this signal, linked to the caller's, so a caller that stops reading can end the reply too.
+        const stop = new AbortController();
+        const abort = () => stop.abort();
+        if (signal?.aborted) abort(); else signal?.addEventListener('abort', abort, { once: true });
+        const job = engine.generate(msgs, {
+          max_new_tokens: maxNewTokens, do_sample: false, enable_thinking: thinking === true, signal: stop.signal,
           ...(tools && { tools }), ...(repetitionPenalty && { repetition_penalty: repetitionPenalty }), ...(seed !== undefined && { seed }),
           ...(speech && {
             output_modalities: ['text', 'audio'],
@@ -100,12 +104,19 @@ export const diskformerOnnxBackend = {
           onToken: () => { tokens++; },
           onText: (delta) => { text += delta; queue.push({ text, tokens }); wake(); },
         }).catch((err) => { failed = err; }).finally(() => { done = true; wake(); });
-        while (true) {
-          if (queue.length) { yield queue.shift(); continue; }
-          if (done) break;
-          await new Promise((r) => { wake = r; });
+        try {
+          while (true) {
+            if (queue.length) { yield queue.shift(); continue; }
+            if (done) break;
+            await new Promise((r) => { wake = r; });
+          }
+          if (failed) throw failed;
+        } finally {
+          signal?.removeEventListener('abort', abort);
+          // The caller stopped reading early (a break after a tool call): stop the reply, so the next call on this
+          // engine's sessions does not run beside it or queue behind it.
+          if (!done) { stop.abort(); await job; }
         }
-        if (failed) throw failed;
       },
       dispose: () => engine.dispose(),
     };

package/src/backends/transformers.js

@@ -177,14 +177,21 @@ async function* stream(lib, tokenizer, signal, run) {
     token_callback_function: () => { tokens++; },
   });
   const stop = new lib.InterruptableStoppingCriteria();
-  signal?.addEventListener('abort', () => stop.interrupt(), { once: true });
-  run(streamer, stop).catch((e) => { failed = e; }).finally(() => { done = true; wake(); });
-  while (true) {
-    if (queue.length) { yield queue.shift(); continue; }
-    if (done) break;
-    await new Promise((r) => { wake = r; });
+  const interrupt = () => stop.interrupt();
+  signal?.addEventListener('abort', interrupt, { once: true });
+  const job = run(streamer, stop).catch((e) => { failed = e; }).finally(() => { done = true; wake(); });
+  try {
+    while (true) {
+      if (queue.length) { yield queue.shift(); continue; }
+      if (done) break;
+      await new Promise((r) => { wake = r; });
+    }
+    if (failed) throw failed;
+  } finally {
+    signal?.removeEventListener('abort', interrupt);
+    // The caller stopped reading early: stop the reply so the next call on this model does not run beside it.
+    if (!done) { stop.interrupt(); await job; }
   }
-  if (failed) throw failed;
 }
 
 // A text-only model in the multimodal layout: the causal-LM class over embed_tokens + decoder_model_merged.

package/src/sources.js

@@ -9,6 +9,9 @@ export const PINS = {
   // 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',
+  // v0.6.14 (93193d0): LFM3-Omni speech out's inverse STFT uses an FFT (same samples), 0.54x → 1.5–1.8x real time on
+  // an M4 Pro. Changes only engines/lfm3_omni.js.
+  // v0.6.13 (7ffbea5): LFM3-Omni serves one reply at a time; overlapping runs broke onnxruntime-web WebGPU.
   // v0.6.12 (1fe19f8): LFM3-Omni speech out (interleaved text and 24 kHz speech; depth and codec decoders). Changes
   // only engines/lfm3_omni.js; its text, image and speech-in gate (3/3) is unchanged.
   // 48f2c2a (main after v0.6.9): engines/lfm3_omni.js, LFM3-Omni-2B on onnxruntime-web 1.30.0 (text, image and speech
@@ -18,7 +21,7 @@ export const PINS = {
   // 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
   // streams the GGUF header with progress and resumes a dropped range.
-  diskformer: '1fe19f8f430f3af2c78e5d2534fdd7938b36b307',
+  diskformer: '93193d0913f5e76059fa45db509dc670e7527430',
 };
 
 const gh = (repo, sha, path) => `https://cdn.jsdelivr.net/gh/NakliTechie/${repo}@${sha}/${path}`;