Release 0.1.57 [auto-version-bump]

VERSION

@@ -1 +1 @@
-0.1.53
+0.1.57

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: 0.1.53
+version: 0.1.57
-appVersion: "0.1.53"
+appVersion: "0.1.57"

index.html

@@ -168,23 +168,55 @@
       const container = document.querySelector('#speech-progress-container');
       const progress = document.querySelector('#speech-progress');
       const value = document.querySelector('#speech-progress-value');
+      const label = container.querySelector('label');
       const preparing = message.startsWith('Förbereder svensk uppläsning.');
+      const phase = [
+        'Laddar WebAssembly-motorn för svensk uppläsning.',
+        '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\.$/);
-      if (!preparing && !match) {
+      const bytesMatch = message.match(/^Hämtar svensk röstmodell till enheten: ([\d.,]+) MB hämtade\.$/);
+      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 = runtimePercent || runtimeBytes
+        ? `Hämtar WebAssembly-filen ${runtimePercent?.[1] || runtimeBytes?.[1]}`
+        : runtimeFile
+          ? runtimeFile[0].replace(/\.$/, '')
+          : 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;
         value.textContent = `${percent}%`;
         return true;
       }
+      if (bytesMatch) {
+        progress.removeAttribute('value');
+        value.textContent = `${bytesMatch[1]} MB hämtade`;
+        return true;
+      }
       progress.removeAttribute('value');
-      value.textContent = 'Förbereder…';
+      value.textContent = phase ? 'Pågår…' : 'Förbereder…';
       return true;
     }
     function clearSpeechRecovery() {

piper-download-progress.mjs

@@ -0,0 +1,34 @@
+export function trackDownloadProgress(response, {id, postMessage, asset = 'model', file}) {
+  const reader = response.body?.getReader?.();
+  if (!reader || typeof ReadableStream !== 'function' || typeof Response !== 'function') return response;
+
+  const total = Number(response.headers.get('content-length')) || 0;
+  let loaded = 0;
+  const body = new ReadableStream({
+    async pull(controller) {
+      try {
+        const {done, value} = await reader.read();
+        if (done) {
+          controller.close();
+          return;
+        }
+        loaded += value.byteLength;
+        const progress = {asset, loaded, total};
+        if (file) progress.file = file;
+        postMessage({id, type: 'progress', progress});
+        controller.enqueue(value);
+      } catch (error) {
+        controller.error(error);
+      }
+    },
+    cancel(reason) {
+      return reader.cancel(reason);
+    },
+  });
+
+  return new Response(body, {
+    status: response.status,
+    statusText: response.statusText,
+    headers: response.headers,
+  });
+}

piper-worker.js

@@ -1,4 +1,5 @@
 import {TtsSession} from '@mintplex-labs/piper-tts-web';
+import {trackDownloadProgress} from './piper-download-progress.mjs';
 import {localPiperModelUrl} from './piper-model-routing.mjs';
 import {createOnnxWasmPaths} from './piper-onnx-config.mjs';
 
@@ -6,24 +7,51 @@ 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 = (resource, options) => {
+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;
-  return localFetch(redirected, options);
+  const response = await localFetch(redirected, options);
+  if (!activeRequestId || !isModel) return response;
+  reportStage(activeRequestId, 'reading-model');
+  return trackDownloadProgress(response, {
+    id: activeRequestId,
+    postMessage: message => self.postMessage(message),
+  });
 };
 
 let sessionPromise;
 let inferenceQueue = Promise.resolve();
+let activeRequestId = null;
 
-async function getSession(onProgress) {
+async function getSession() {
   if (!sessionPromise) {
     sessionPromise = TtsSession.create({
       voiceId: VOICE_ID,
-      progress: onProgress,
       wasmPaths: {
         onnxWasm: createOnnxWasmPaths(self.location.origin),
         piperData: `${ASSET_ROOT}/piper/piper_phonemize.data`,
@@ -40,13 +68,18 @@ async function getSession(onProgress) {
 async function synthesizeMessage(event) {
   const {id, text} = event.data || {};
   if (!Number.isSafeInteger(id) || typeof text !== 'string') return;
+  activeRequestId = id;
+  reportStage(id, 'loading-runtime');
   try {
-    const session = await getSession(progress => self.postMessage({id, type: 'progress', progress}));
+    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]);
   } catch (error) {
     self.postMessage({id, type: 'error', error: String(error?.message || error)});
+  } finally {
+    activeRequestId = null;
   }
 }
 

scripts/check-frontend.sh

@@ -31,6 +31,9 @@ grep -q 'id="microphone" aria-pressed="false"' index.html
 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
@@ -51,6 +54,8 @@ 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 'trackDownloadProgress' piper-worker.js
+grep -q 'new ReadableStream' piper-download-progress.mjs
 grep -q 'createOnnxWasmPaths(self.location.origin)' piper-worker.js
 grep -q '/static/piper-wasm-v1/onnx/' piper-onnx-config.mjs
 grep -q 'PIPER_MODEL_ORIGIN' piper-model-routing.mjs

tests/piper-download-progress.test.cjs

@@ -0,0 +1,38 @@
+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 {trackDownloadProgress} = await import('../piper-download-progress.mjs');
+  const source = new ReadableStream({
+    start(controller) {
+      controller.enqueue(new Uint8Array([1, 2]));
+      controller.enqueue(new Uint8Array([3, 4, 5]));
+      controller.close();
+    },
+  });
+  const response = new Response(source, {headers: {'content-length': '5'}});
+  const messages = [];
+  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), [
+    {asset: 'model', loaded: 2, 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 {trackDownloadProgress} = await import('../piper-download-progress.mjs');
+  const source = new Response(new Uint8Array([1, 2, 3]));
+  const messages = [];
+  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), [{asset: 'runtime', file: 'runtime.wasm', loaded: 3, total: 0}]);
+});

tests/voice.test.cjs

@@ -259,11 +259,17 @@ 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/);
   h.piperProgressCallbacks[0]({loaded: 90_000_000, total: 63_000_000});
   assert.match(h.states.at(-1).message, /100 procent/);
+  h.piperProgressCallbacks[0]({loaded: 10 * 1024 * 1024, total: 0});
+  assert.match(h.states.at(-1).message, /10 MB hämtade/);
 });
 
 test('Piper output keeps per-character pitch and rate stable', async () => {

voice.js

@@ -250,13 +250,57 @@
         setState('IDLE', 'Piper tog för lång tid på sig. Dialogen finns kvar som text. Tryck på Läs senaste repliken för att försöka igen.');
       }, 180000);
 
-      let lastProgress = -1;
+      let lastProgressPercent = -1;
+      let lastProgressMegabytes = -1;
+      let lastProgressResource = '';
       const progress = event => {
-        if (token !== generation || !Number.isFinite(event?.loaded) || !Number.isFinite(event?.total) || event.total <= 0) return;
+        if (token !== generation) return;
-        const percent = Math.max(0, Math.min(100, Math.floor((event.loaded / event.total) * 100)));
+        const resource = `${event?.asset || 'model'}:${event?.file || ''}`;
-        if (percent === lastProgress) return;
+        if (resource !== lastProgressResource) {
-        lastProgress = percent;
+          lastProgressResource = resource;
-        setState('PROCESSING', `Hämtar svensk röstmodell till enheten: ${percent} procent.`);
+          lastProgressPercent = -1;
+          lastProgressMegabytes = -1;
+        }
+        if (event?.asset === 'runtime' && Number.isFinite(event.loaded) && event.loaded >= 0) {
+          const file = /^[\w.-]+$/.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 || ''}.`,
+          '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;
+        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 svensk röstmodell till enheten: ${percent} procent.`);
+          return;
+        }
+        const megabytes = Math.floor((event.loaded / (1024 * 1024)) * 10) / 10;
+        if (megabytes === lastProgressMegabytes) return;
+        lastProgressMegabytes = megabytes;
+        setState('PROCESSING', `Hämtar svensk röstmodell till enheten: ${megabytes.toLocaleString('sv-SE')} MB hämtade.`);
       };
 
       Promise.resolve()