Release 0.1.56 [auto-version-bump]

VERSION

@@ -1 +1 @@
-0.1.51
+0.1.56

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: 0.1.51
-appVersion: "0.1.51"
+version: 0.1.56
+appVersion: "0.1.56"

docs/adr/0001-piper-es-module-worker.md

@@ -0,0 +1,13 @@
+# ADR 0001: Run Piper in an ES module worker
+
+## Decision
+
+Bundle the Piper worker as an ES module and start it with `new Worker(url, { type: 'module' })`.
+
+## Context
+
+Piper loads ONNX Runtime Web and its WebAssembly loader dynamically. The current IIFE/classic worker bundle reports `TypeError: "undefined" cannot be parsed as a URL` during WASM backend initialization, even though the pinned same-origin ONNX loader and binary are available. This is consistent with module-relative URL metadata being lost in the classic bundle.
+
+## Consequences
+
+The browser must support module workers. Current supported browser targets already require modern WebAssembly and worker support. CI asserts that the worker is built and started in module mode; production acceptance remains the real deployed browser flow.

index.html

@@ -20,6 +20,8 @@
     #message { width: 100%; min-height: 3.5rem; box-sizing: border-box; }
     #message-tools { display: flex; flex-wrap: wrap; align-items: center; gap: .5rem; }
     #voice-status { min-height: 1.5em; }
+    #speech-progress { width: min(100%, 32rem); height: 1.25rem; }
+    #speech-progress-value { margin-inline-start: .5rem; font-variant-numeric: tabular-nums; }
     #dialogue li[data-role="voice-controls"] { border: 1px solid currentColor; border-radius: .35rem; padding: .75rem; }
     #dialogue li[data-role="voice-controls"] fieldset { display: grid; gap: .5rem; margin-block: .5rem; }
     #admin-content { display: grid; gap: 1rem; }
@@ -56,6 +58,11 @@
         <span id="message-help" class="sr-only">Tryck Enter för att skicka. Tryck Skift och Enter för ny rad.</span>
       </form>
       <p id="voice-status" role="status" aria-live="polite"></p>
+      <div id="speech-progress-container" hidden>
+        <label for="speech-progress">Hämtar svensk röstmodell till enheten</label>
+        <progress id="speech-progress" aria-label="Nedladdning av svensk röstmodell"></progress>
+        <output id="speech-progress-value" for="speech-progress">Väntar på nedladdning</output>
+      </div>
     </section>
     <section id="admin-view" aria-labelledby="admin-heading" hidden>
       <h1 id="admin-heading">Administration</h1>
@@ -157,6 +164,45 @@
       const authVoiceStatus = document.querySelector('#auth-voice-status');
       if (authVoiceStatus && !auth.hidden && message) authVoiceStatus.textContent = message;
     }
+    function updateSpeechProgress(message = '') {
+      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.',
+        'Laddar WebAssembly-filer 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\.$/);
+      const bytesMatch = message.match(/^Hämtar svensk röstmodell till enheten: ([\d.,]+) MB hämtade\.$/);
+      if (!preparing && !phase && !match && !bytesMatch) {
+        container.hidden = true;
+        progress.removeAttribute('value');
+        value.textContent = 'Väntar på nedladdning';
+        return false;
+      }
+      container.hidden = false;
+      label.textContent = phase || 'Hämtar svensk röstmodell till enheten';
+      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 = phase ? 'Pågår…' : 'Förbereder…';
+      return true;
+    }
     function clearSpeechRecovery() {
       speechRecoveryElement?.remove();
       speechRecoveryElement = null;
@@ -218,8 +264,15 @@
         microphone.setAttribute('aria-pressed', String(listening));
         microphone.textContent = listening ? 'Avsluta mikrofon' : 'Starta mikrofon';
         refreshMicrophone();
-        if (message) setVoiceStatus(message);
-        else if (state === 'IDLE') setVoiceStatus('');
+        if (message) {
+          const downloading = updateSpeechProgress(message);
+          setVoiceStatus(downloading && message.startsWith('Hämtar svensk röstmodell')
+            ? 'Hämtar svensk röstmodell till enheten.'
+            : message);
+        } else if (state === 'IDLE') {
+          updateSpeechProgress('');
+          setVoiceStatus('');
+        }
         if (/Läs senaste repliken/.test(message)) showSpeechRecovery(message);
         playVoiceSignal(state === 'IDLE' && /Mikrofonen är avstängd/.test(message) ? 'STOPPED' : state);
       },

piper-download-progress.mjs

@@ -0,0 +1,32 @@
+export function trackModelDownload(response, {id, postMessage}) {
+  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;
+        postMessage({id, type: 'progress', progress: {loaded, total}});
+        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-runtime.js

@@ -6,7 +6,9 @@ const pending = new Map();
 
 function getWorker() {
   if (worker) return worker;
-  worker = new Worker(workerUrl);
+  // ONNX Runtime resolves its WASM loader relative to the worker module URL.
+  // Keep the worker as ESM so import.meta.url remains available at runtime.
+  worker = new Worker(workerUrl, {type: 'module'});
   worker.onmessage = event => {
     const message = event.data || {};
     const request = pending.get(message.id);

piper-worker.js

@@ -1,4 +1,5 @@
 import {TtsSession} from '@mintplex-labs/piper-tts-web';
+import {trackModelDownload} from './piper-download-progress.mjs';
 import {localPiperModelUrl} from './piper-model-routing.mjs';
 import {createOnnxWasmPaths} from './piper-onnx-config.mjs';
 
@@ -6,24 +7,41 @@ const VOICE_ID = 'sv_SE-nst-medium';
 const ASSET_ROOT = '/static/piper-wasm-v1';
 const localFetch = self.fetch.bind(self);
 
+function reportStage(id, stage) {
+  if (Number.isSafeInteger(id)) self.postMessage({id, type: 'progress', progress: {stage}});
+}
+
 // 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) {
+    if (activeRequestId && requestedUrl.includes('/static/piper-wasm-v1/onnx/')) {
+      reportStage(activeRequestId, 'loading-runtime-assets');
+    }
+    return localFetch(resource, options);
+  }
+  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 trackModelDownload(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 +58,18 @@ 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/build-piper.mjs

@@ -25,7 +25,7 @@ await build({
   entryPoints: [resolve(root, 'piper-worker.js')],
   outfile: join(workerRoot, 'piper-worker.js'),
   bundle: true,
-  format: 'iife',
+  format: 'esm',
   platform: 'browser',
   target: ['es2022'],
   external: ['fs', 'path'],

scripts/check-frontend.sh

@@ -29,6 +29,11 @@ grep -q "location.pathname !== '/admin'" index.html
 grep -q "if (options.speak !== false && location.pathname !== '/admin')" index.html
 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
@@ -45,10 +50,12 @@ grep -q 'COPY public/tts/piper-wasm-v1/' Dockerfile
 grep -q 'build:piper' .gitea/workflows/publish.yaml
 grep -q 'Piper' piper-runtime.js
 grep -q 'sv_SE-nst-medium' piper-worker.js
-grep -q 'new Worker(workerUrl)' piper-runtime.js
+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 '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 +1,33 @@
+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 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 = trackModelDownload(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},
+    {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 source = new Response(new Uint8Array([1, 2, 3]));
+  const messages = [];
+  const tracked = trackModelDownload(source, {id: 9, postMessage: message => messages.push(message)});
+
+  assert.equal((await tracked.arrayBuffer()).byteLength, 3);
+  assert.deepEqual(messages.map(message => message.progress), [{loaded: 3, total: 0}]);
+});

tests/piper-worker-format.test.cjs

@@ -0,0 +1,13 @@
+const test = require('node:test');
+const assert = require('node:assert/strict');
+const {readFile} = require('node:fs/promises');
+const {join} = require('node:path');
+
+test('Piper worker is built and started as an ES module', async () => {
+  const [buildScript, runtime] = await Promise.all([
+    readFile(join(__dirname, '..', 'scripts', 'build-piper.mjs'), 'utf8'),
+    readFile(join(__dirname, '..', 'piper-runtime.js'), 'utf8'),
+  ]);
+  assert.match(buildScript, /outfile: join\(workerRoot, 'piper-worker\.js'\),\s*bundle: true,\s*format: 'esm'/);
+  assert.match(runtime, /new Worker\(workerUrl, \{type: 'module'\}\)/);
+});

tests/voice.test.cjs

@@ -26,6 +26,7 @@ function makeHarness({supported = true, tts = true, piper = false, onTranscript
     constructor(text) { this.text = text; utterances.push(this); }
   }
   const audioSources = [];
+  const piperProgressCallbacks = [];
   class AudioContext {
     constructor() { this.state = 'running'; this.destination = {}; }
     resume() { this.state = 'running'; return Promise.resolve(); }
@@ -49,7 +50,10 @@ function makeHarness({supported = true, tts = true, piper = false, onTranscript
     SpeechSynthesisUtterance: tts ? Utterance : undefined,
     SpeechRecognition: supported ? Recognition : undefined,
     AudioContext,
-    GamePiper: piper ? {synthesize: () => Promise.resolve({arrayBuffer: () => Promise.resolve(new ArrayBuffer(8))})} : undefined,
+    GamePiper: piper ? {synthesize: (_text, onProgress) => {
+      piperProgressCallbacks.push(onProgress);
+      return Promise.resolve({arrayBuffer: () => Promise.resolve(new ArrayBuffer(8))});
+    }} : undefined,
   };
   vm.runInNewContext(source, {window, globalThis: window, Promise, String, Math, Object});
   const controller = window.GameVoice.createVoiceController({
@@ -58,7 +62,7 @@ function makeHarness({supported = true, tts = true, piper = false, onTranscript
     onTranscript,
   });
   return {
-    controller, recognitions, utterances, synthesis, states, timers, audioSources,
+    controller, recognitions, utterances, synthesis, states, timers, audioSources, piperProgressCallbacks,
     runTimer(delay) {
       const match = [...timerDelays.entries()].find(([, value]) => value === delay);
       if (!match) throw new Error(`No timer found with delay ${delay}`);
@@ -250,6 +254,22 @@ test('Piper WASM output uses the unlocked audio context and starts only after lo
   assert.equal(h.controller.getState(), 'IDLE');
 });
 
+test('Piper model download progress is reported as a bounded percentage', async () => {
+  const h = makeHarness({piper: true});
+  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]({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 () => {
   const h = makeHarness({piper: true});
   h.controller.activateFromUserGesture();

voice.js

@@ -250,13 +250,34 @@
         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;
       const progress = event => {
-        if (token !== generation || !event?.total) return;
-        const percent = Math.min(100, Math.floor((event.loaded / event.total) * 100));
-        if (percent === lastProgress) return;
-        lastProgress = percent;
-        setState('PROCESSING', `Hämtar svensk röstmodell till enheten: ${percent} procent.`);
+        if (token !== generation) return;
+        const stages = {
+          'loading-runtime': 'Laddar WebAssembly-motorn för svensk uppläsning.',
+          'loading-runtime-assets': 'Laddar WebAssembly-filer för svensk uppläsning.',
+          '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()