Release 0.1.59 [auto-version-bump]

VERSION

@@ -1 +1 @@
-0.1.55
+0.1.59

deploy/helm/ai-spel-frontend/Chart.yaml

@@ -2,5 +2,5 @@ apiVersion: v2
 name: ai-spel-frontend
 description: Static web frontend for the Swedish life simulator
 type: application
-version: 0.1.55
+version: 0.1.59
-appVersion: "0.1.55"
+appVersion: "0.1.59"

docs/adr/0002-single-thread-onnx-for-mobile-tts.md

@@ -0,0 +1,13 @@
+# ADR 0002: Run ONNX with one thread inside the Piper worker
+
+## Decision
+
+Configure ONNX Runtime Web to use one thread and stop backend initialization after 60 seconds. Piper already runs in a dedicated worker, so ONNX does not need to create another worker pool.
+
+## Context
+
+On iPad, the threaded ONNX WASM file downloaded fully, but the runtime did not report that initialization had completed. Nested worker startup and shared-memory setup are a likely compatibility boundary on mobile Safari. The available production assets currently include the threaded ONNX build.
+
+## Consequences
+
+This removes ONNX's additional worker pool and bounds initialization failures with a visible error. It may reduce inference throughput on desktop devices. CI and Kubernetes release verification must confirm that Piper still initializes and speaks on supported browsers; iPad acceptance remains a manual device check.

index.html

@@ -170,19 +170,41 @@
       const value = document.querySelector('#speech-progress-value');
       const label = container.querySelector('label');
       const preparing = message.startsWith('Förbereder svensk uppläsning.');
-      const starting = message.startsWith('Startar svensk röstmotor och förbereder modellen.');
+      const phase = [
+        'Laddar WebAssembly-motorn för svensk uppläsning.',
+        'Startar WebAssembly-motorn efter nedladdning av',
+        'Hämtar information om den svenska röstmodellen.',
+        'Ansluter till servern för att hämta den svenska röstmodellen.',
+        'Läser in den svenska röstmodellen.',
+        'Röstmodellen är inläst. Skapar uppläsningen.',
+      ].find(text => message.startsWith(text));
       const match = message.match(/^Hämtar svensk röstmodell till enheten: (\d+) procent\.$/);
       const bytesMatch = message.match(/^Hämtar svensk röstmodell till enheten: ([\d.,]+) MB hämtade\.$/);
-      if (!preparing && !starting && !match && !bytesMatch) {
+      const runtimeFile = message.match(/^(?:Hämtar|Läser in) WebAssembly-filen ([\w.-]+)\.?$/);
+      const runtimePercent = message.match(/^Hämtar WebAssembly-filen ([\w.-]+): (\d+) procent\.$/);
+      const runtimeBytes = message.match(/^Hämtar WebAssembly-filen ([\w.-]+): ([\d.,]+) MB hämtade\.$/);
+      if (!preparing && !phase && !match && !bytesMatch && !runtimeFile && !runtimePercent && !runtimeBytes) {
         container.hidden = true;
         progress.removeAttribute('value');
         value.textContent = 'Väntar på nedladdning';
         return false;
       }
       container.hidden = false;
-      label.textContent = starting
+      label.textContent = runtimePercent || runtimeBytes
-        ? 'Startar och läser in den svenska röstmodellen'
+        ? `Hämtar WebAssembly-filen ${runtimePercent?.[1] || runtimeBytes?.[1]}`
-        : 'Hämtar svensk röstmodell till enheten';
+        : runtimeFile
+          ? runtimeFile[0].replace(/\.$/, '')
+          : phase || 'Hämtar svensk röstmodell till enheten';
+      if (runtimePercent) {
+        progress.value = Math.max(0, Math.min(100, Number(runtimePercent[2])));
+        value.textContent = `${runtimePercent[2]}%`;
+        return true;
+      }
+      if (runtimeBytes) {
+        progress.removeAttribute('value');
+        value.textContent = `${runtimeBytes[2]} MB hämtade`;
+        return true;
+      }
       if (match) {
         const percent = Math.max(0, Math.min(100, Number(match[1])));
         progress.value = percent;
@@ -195,7 +217,7 @@
         return true;
       }
       progress.removeAttribute('value');
-      value.textContent = starting ? 'Startar röstmotorn…' : 'Förbereder…';
+      value.textContent = phase ? 'Pågår…' : 'Förbereder…';
       return true;
     }
     function clearSpeechRecovery() {
@@ -576,8 +598,7 @@
           body: JSON.stringify({input: message, current_draft: worldDraft}),
         });
         worldDraft = proposal.draft;
-        const senses = worldDraft.location_senses;
+        appendLine('assistant', `${proposal.message}\n\nVärld: ${worldDraft.name}\nStartplats: ${worldDraft.location_name}. ${worldDraft.location_description}\nStartbelopp: ${worldDraft.starting_balance_sek} kronor. ${worldDraft.offer_name} kostar ${worldDraft.offer_price_sek} kronor.\n\nSkriv ändringar eller “godkänn”.`);
-        appendLine('assistant', `${proposal.message}\n\nVärld: ${worldDraft.name}\nStartplats: ${worldDraft.location_name}. ${worldDraft.location_description}\nLjud: ${senses.sound}\nDoft: ${senses.smell}\nLuft och temperatur: ${senses.air_and_temperature}\nBeröring och ytor: ${senses.touch_and_surfaces}\nOrientering: ${senses.spatial_orientation}\nStartbelopp: ${worldDraft.starting_balance_sek} kronor. ${worldDraft.offer_name} kostar ${worldDraft.offer_price_sek} kronor.\n\nSkriv ändringar eller “godkänn”.`);
       } catch (error) {
         appendLine('assistant', `Förslaget kunde inte tas fram: ${error.message}. Skriv “försök igen” när du vill försöka på nytt.`);
       }
@@ -615,8 +636,7 @@
         voiceController?.speak(latestAssistantText, {role: 'narrator', voiceIdentity: 'neutral'});
       } else if (lines.length === 0 && gameState?.world) {
         const place = gameState.world.location;
-        const senses = place.senses || {};
+        appendLine('assistant', `Du börjar på ${place.name}. ${place.description}`);
-        appendLine('assistant', `Du börjar på ${place.name}. ${place.description} Ljud: ${senses.sound || 'Inget särskilt ljud beskrivet.'} Doft: ${senses.smell || 'Ingen särskild doft beskriven.'} Luft och temperatur: ${senses.air_and_temperature || 'Inte beskrivet.'} Beröring och ytor: ${senses.touch_and_surfaces || 'Inte beskrivet.'} Orientering: ${senses.spatial_orientation || 'Inte beskrivet.'}`);
       }
     }
     async function openGame() {

piper-download-progress.mjs

@@ -1,4 +1,4 @@
-export function trackModelDownload(response, {id, postMessage}) {
+export function trackDownloadProgress(response, {id, postMessage, asset = 'model', file}) {
   const reader = response.body?.getReader?.();
   if (!reader || typeof ReadableStream !== 'function' || typeof Response !== 'function') return response;
 
@@ -9,11 +9,16 @@ export function trackModelDownload(response, {id, postMessage}) {
       try {
         const {done, value} = await reader.read();
         if (done) {
+          if (asset === 'runtime') {
+            postMessage({id, type: 'progress', progress: {stage: 'initializing-runtime', file}});
+          }
           controller.close();
           return;
         }
         loaded += value.byteLength;
-        postMessage({id, type: 'progress', progress: {loaded, total}});
+        const progress = {asset, loaded, total};
+        if (file) progress.file = file;
+        postMessage({id, type: 'progress', progress});
         controller.enqueue(value);
       } catch (error) {
         controller.error(error);

piper-onnx-config.mjs

@@ -5,3 +5,10 @@ export function createOnnxWasmPaths(origin) {
   return absoluteAssetRoot;
 }
 
+export function configureOnnxRuntime(onnxRuntime) {
+  if (!onnxRuntime?.env?.wasm) throw new TypeError('ONNX Runtime WebAssembly settings are unavailable.');
+  // Piper already runs in a worker. Avoid a second worker pool on mobile Safari.
+  onnxRuntime.env.wasm.numThreads = 1;
+  onnxRuntime.env.wasm.initTimeout = 60000;
+}
+

piper-worker.js

@@ -1,22 +1,45 @@
 import {TtsSession} from '@mintplex-labs/piper-tts-web';
-import {trackModelDownload} from './piper-download-progress.mjs';
+import * as onnxRuntime from 'onnxruntime-web';
+import {trackDownloadProgress} from './piper-download-progress.mjs';
 import {localPiperModelUrl} from './piper-model-routing.mjs';
-import {createOnnxWasmPaths} from './piper-onnx-config.mjs';
+import {configureOnnxRuntime, createOnnxWasmPaths} from './piper-onnx-config.mjs';
 
 const VOICE_ID = 'sv_SE-nst-medium';
 const ASSET_ROOT = '/static/piper-wasm-v1';
 const localFetch = self.fetch.bind(self);
 
+function reportStage(id, stage, details = {}) {
+  if (Number.isSafeInteger(id)) self.postMessage({id, type: 'progress', progress: {stage, ...details}});
+}
+
 // Keep the TTS library's OPFS cache logic, but serve models/config from the
 // same-origin static asset service instead of its built-in external model URL.
 self.fetch = async (resource, options) => {
   const requestedUrl = resource instanceof Request ? resource.url : String(resource);
   const localModelUrl = localPiperModelUrl(requestedUrl, self.location.origin);
-  if (!localModelUrl) return localFetch(resource, options);
+  if (!localModelUrl) {
+    const runtimeAsset = requestedUrl.includes('/static/piper-wasm-v1/onnx/');
+    const runtimeFile = runtimeAsset ? new URL(requestedUrl, self.location.origin).pathname.split('/').pop() : undefined;
+    if (activeRequestId && runtimeAsset) {
+      reportStage(activeRequestId, 'loading-runtime-assets', {file: runtimeFile});
+    }
+    const response = await localFetch(resource, options);
+    if (!activeRequestId || !runtimeAsset) return response;
+    reportStage(activeRequestId, 'reading-runtime-assets', {file: runtimeFile});
+    return trackDownloadProgress(response, {
+      id: activeRequestId,
+      asset: 'runtime',
+      file: runtimeFile,
+      postMessage: message => self.postMessage(message),
+    });
+  }
+  const isModel = localModelUrl.endsWith('.onnx');
+  if (activeRequestId) reportStage(activeRequestId, isModel ? 'loading-model' : 'loading-model-info');
   const redirected = resource instanceof Request ? new Request(localModelUrl, resource) : localModelUrl;
   const response = await localFetch(redirected, options);
-  if (!activeRequestId || !localModelUrl.endsWith('.onnx')) return response;
+  if (!activeRequestId || !isModel) return response;
-  return trackModelDownload(response, {
+  reportStage(activeRequestId, 'reading-model');
+  return trackDownloadProgress(response, {
     id: activeRequestId,
     postMessage: message => self.postMessage(message),
   });
@@ -28,6 +51,7 @@ let activeRequestId = null;
 
 async function getSession() {
   if (!sessionPromise) {
+    configureOnnxRuntime(onnxRuntime);
     sessionPromise = TtsSession.create({
       voiceId: VOICE_ID,
       wasmPaths: {
@@ -47,9 +71,10 @@ async function synthesizeMessage(event) {
   const {id, text} = event.data || {};
   if (!Number.isSafeInteger(id) || typeof text !== 'string') return;
   activeRequestId = id;
-  self.postMessage({id, type: 'progress', progress: {stage: 'starting'}});
+  reportStage(id, 'loading-runtime');
   try {
     const session = await getSession();
+    reportStage(id, 'model-ready');
     const blob = await session.predict(text);
     const audio = await blob.arrayBuffer();
     self.postMessage({id, type: 'audio', audio}, [audio]);

scripts/check-frontend.sh

@@ -32,6 +32,8 @@ grep -q 'id="voice-status" role="status" aria-live="polite"' index.html
 grep -q 'id="speech-progress" aria-label="Nedladdning av svensk röstmodell"' index.html
 grep -q 'id="speech-progress-value"' index.html
 grep -q 'MB hämtade' index.html
+grep -q 'loading-runtime-assets' piper-worker.js
+grep -q 'Röstmodellen är inläst' voice.js
 grep -q "window.GameVoice.createVoiceController" index.html
 grep -q "addVoiceButton(item, 'Testa ljudet'" index.html
 grep -q 'Jag förstår – starta mikrofonen' index.html
@@ -52,9 +54,11 @@ grep -q "new Worker(workerUrl, {type: 'module'})" piper-runtime.js
 grep -q 'worker.js?v=' piper-runtime.js
 grep -q 'worker.onmessageerror' piper-runtime.js
 grep -q 'localPiperModelUrl' piper-worker.js
-grep -q 'trackModelDownload' piper-worker.js
+grep -q 'trackDownloadProgress' piper-worker.js
 grep -q 'new ReadableStream' piper-download-progress.mjs
 grep -q 'createOnnxWasmPaths(self.location.origin)' piper-worker.js
+grep -q 'configureOnnxRuntime(onnxRuntime)' piper-worker.js
+grep -q 'numThreads = 1' piper-onnx-config.mjs
 grep -q '/static/piper-wasm-v1/onnx/' piper-onnx-config.mjs
 grep -q 'PIPER_MODEL_ORIGIN' piper-model-routing.mjs
 grep -q '/static/piper-wasm-v1/voices/' piper-model-routing.mjs

tests/piper-download-progress.test.cjs

@@ -2,7 +2,7 @@ const assert = require('node:assert/strict');
 const test = require('node:test');
 
 test('model response progress forwards each downloaded chunk and preserves the response', async () => {
-  const {trackModelDownload} = await import('../piper-download-progress.mjs');
+  const {trackDownloadProgress} = await import('../piper-download-progress.mjs');
   const source = new ReadableStream({
     start(controller) {
       controller.enqueue(new Uint8Array([1, 2]));
@@ -12,22 +12,48 @@ test('model response progress forwards each downloaded chunk and preserves the r
   });
   const response = new Response(source, {headers: {'content-length': '5'}});
   const messages = [];
-  const tracked = trackModelDownload(response, {id: 7, postMessage: message => messages.push(message)});
+  const tracked = trackDownloadProgress(response, {id: 7, postMessage: message => messages.push(message)});
 
   assert.deepEqual([...new Uint8Array(await tracked.arrayBuffer())], [1, 2, 3, 4, 5]);
   assert.deepEqual(messages.map(message => message.progress), [
-    {loaded: 2, total: 5},
+    {asset: 'model', loaded: 2, total: 5},
-    {loaded: 5, total: 5},
+    {asset: 'model', loaded: 5, total: 5},
   ]);
   assert.ok(messages.every(message => message.id === 7 && message.type === 'progress'));
 });
 
 test('model response progress works when content length is absent', async () => {
-  const {trackModelDownload} = await import('../piper-download-progress.mjs');
+  const {trackDownloadProgress} = await import('../piper-download-progress.mjs');
   const source = new Response(new Uint8Array([1, 2, 3]));
   const messages = [];
-  const tracked = trackModelDownload(source, {id: 9, postMessage: message => messages.push(message)});
+  const tracked = trackDownloadProgress(source, {
+    id: 9,
+    asset: 'runtime',
+    file: 'runtime.wasm',
+    postMessage: message => messages.push(message),
+  });
 
   assert.equal((await tracked.arrayBuffer()).byteLength, 3);
-  assert.deepEqual(messages.map(message => message.progress), [{loaded: 3, total: 0}]);
+  assert.deepEqual(messages
+    .map(message => message.progress)
+    .filter(progress => Number.isFinite(progress.loaded)),
+  [{asset: 'runtime', file: 'runtime.wasm', loaded: 3, total: 0}]);
+});
+
+test('runtime asset completion reports that initialization follows the download', async () => {
+  const {trackDownloadProgress} = await import('../piper-download-progress.mjs');
+  const response = new Response(new Uint8Array([1, 2]), {headers: {'content-length': '2'}});
+  const messages = [];
+  const tracked = trackDownloadProgress(response, {
+    id: 10,
+    asset: 'runtime',
+    file: 'ort-wasm-simd-threaded.wasm',
+    postMessage: message => messages.push(message),
+  });
+
+  await tracked.arrayBuffer();
+  assert.deepEqual(messages.at(-1).progress, {
+    stage: 'initializing-runtime',
+    file: 'ort-wasm-simd-threaded.wasm',
+  });
 });

tests/piper-onnx-config.test.cjs

@@ -13,3 +13,11 @@ test('ONNX Runtime base URL rejects an invalid worker origin', async () => {
   const {createOnnxWasmPaths} = await import('../piper-onnx-config.mjs');
   assert.throws(() => createOnnxWasmPaths('undefined'), TypeError);
 });
+
+test('ONNX Runtime uses one thread and a bounded startup timeout', async () => {
+  const {configureOnnxRuntime} = await import('../piper-onnx-config.mjs');
+  const runtime = {env: {wasm: {numThreads: 0, initTimeout: 0}}};
+  configureOnnxRuntime(runtime);
+  assert.equal(runtime.env.wasm.numThreads, 1);
+  assert.equal(runtime.env.wasm.initTimeout, 60000);
+});

tests/voice.test.cjs

@@ -259,6 +259,10 @@ test('Piper model download progress is reported as a bounded percentage', async
   h.controller.activateFromUserGesture();
   h.controller.speak('Ett svar från Piper.');
   await new Promise(resolve => setImmediate(resolve));
+  h.piperProgressCallbacks[0]({stage: 'loading-model'});
+  assert.match(h.states.at(-1).message, /Ansluter till servern/);
+  h.piperProgressCallbacks[0]({asset: 'runtime', file: 'ort-wasm-simd-threaded.wasm', loaded: 5 * 1024 * 1024, total: 10 * 1024 * 1024});
+  assert.match(h.states.at(-1).message, /ort-wasm-simd-threaded\.wasm: 50 procent/);
   h.piperProgressCallbacks[0]({loaded: 31_500_000, total: 63_000_000});
   assert.equal(h.states.at(-1).state, 'PROCESSING');
   assert.match(h.states.at(-1).message, /50 procent/);

voice.js

@@ -252,10 +252,42 @@
 
       let lastProgressPercent = -1;
       let lastProgressMegabytes = -1;
+      let lastProgressResource = '';
       const progress = event => {
         if (token !== generation) return;
-        if (event?.stage === 'starting') {
+        const resource = `${event?.asset || 'model'}:${event?.file || ''}`;
-          setState('PROCESSING', 'Startar svensk röstmotor och förbereder modellen.');
+        if (resource !== lastProgressResource) {
+          lastProgressResource = resource;
+          lastProgressPercent = -1;
+          lastProgressMegabytes = -1;
+        }
+        if (event?.asset === 'runtime' && Number.isFinite(event.loaded) && event.loaded >= 0) {
+          const file = /^[\w.-]+$/.test(event.file || '') ? event.file : 'WebAssembly-fil';
+          if (Number.isFinite(event.total) && event.total > 0) {
+            const percent = Math.max(0, Math.min(100, Math.floor((event.loaded / event.total) * 100)));
+            if (percent === lastProgressPercent) return;
+            lastProgressPercent = percent;
+            setState('PROCESSING', `Hämtar WebAssembly-filen ${file}: ${percent} procent.`);
+          } else {
+            const megabytes = Math.floor((event.loaded / (1024 * 1024)) * 10) / 10;
+            if (megabytes === lastProgressMegabytes) return;
+            lastProgressMegabytes = megabytes;
+            setState('PROCESSING', `Hämtar WebAssembly-filen ${file}: ${megabytes.toLocaleString('sv-SE')} MB hämtade.`);
+          }
+          return;
+        }
+        const stages = {
+          'loading-runtime': 'Laddar WebAssembly-motorn för svensk uppläsning.',
+          'loading-runtime-assets': `Hämtar WebAssembly-filen ${event?.file || 'från servern'}.`,
+          'reading-runtime-assets': `Läser in WebAssembly-filen ${event?.file || ''}.`,
+          'initializing-runtime': `Startar WebAssembly-motorn efter nedladdning av ${event?.file || 'filen'}.`,
+          'loading-model-info': 'Hämtar information om den svenska röstmodellen.',
+          'loading-model': 'Ansluter till servern för att hämta den svenska röstmodellen.',
+          'reading-model': 'Läser in den svenska röstmodellen.',
+          'model-ready': 'Röstmodellen är inläst. Skapar uppläsningen.',
+        };
+        if (stages[event?.stage]) {
+          setState('PROCESSING', stages[event.stage]);
           return;
         }
         if (!Number.isFinite(event?.loaded) || event.loaded < 0) return;