Release 0.1.55 [auto-version-bump]

.gitea/workflows/publish.yaml

@@ -29,22 +29,14 @@ jobs:
           python3 scripts/bump-version.py --check
           scripts/check-frontend.sh
 
-      - name: Build Piper WebAssembly assets
+      - name: Bundle Piper worker client code
         shell: bash
         run: |
           set -euo pipefail
           npm install --no-audit --no-fund
           npm run build:piper
-          test -s public/tts/piper-wasm-v1/piper/piper_phonemize.wasm
-          test -s public/tts/piper-wasm-v1/piper/piper_phonemize.data
           test -s public/tts/piper-wasm-v1/piper-worker.js
           test -s public/piper-runtime.js
-          test -s public/tts/piper-wasm-v1/voices/sv/sv_SE/alma/medium/sv_SE-alma-medium.onnx
-          test -s public/tts/piper-wasm-v1/voices/sv/sv_SE/alma/medium/sv_SE-alma-medium.onnx.json
-          test -s public/tts/piper-wasm-v1/voices/sv/sv_SE/lisa/medium/sv_SE-lisa-medium.onnx
-          test -s public/tts/piper-wasm-v1/voices/sv/sv_SE/lisa/medium/sv_SE-lisa-medium.onnx.json
-          test -s public/tts/piper-wasm-v1/voices/sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx
-          test -s public/tts/piper-wasm-v1/voices/sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx.json
 
       - name: Ensure Helm is available
         shell: bash

AGENTS.md

@@ -3,9 +3,10 @@
 - This repository owns only the static, accessible web client and its container/chart packaging.
 - Rust remains the sole authority for game state. The frontend calls the backend through same-origin `/api/...` and `/version` paths.
 - Keep frontend and backend behind `ai-spel.k3s.k0.nu` so session cookies remain same-origin.
+- The public footer displays frontend, static-service, and API versions; load static-service version from uncached `/static/version.json`.
 - `VERSION` is the only release-version source in this repository. Use `scripts/bump-version.py`; do not manually edit chart versions.
 - Changes are written locally and built, checked, published, and exercised by Gitea Actions on the existing `large` runner and Kubernetes. Never run apps, tests, containers, images, or binaries locally. Do not create or register runners.
 - Never commit secrets, generated credentials, kubeconfigs, or environment files.
 - Helm charts are published to `harbor.k3s.k0.nu/ai-spel`; Argo CD uses the existing `ai-spel` project and namespace.
-- Player-facing speech uses the local Piper WebAssembly adapter when the player has activated audio. All supported Swedish Piper voice models are packaged into the frontend image and served from this origin; model downloads are redirected to same-origin paths and cached by the browser when supported. Game text is synthesized on-device and must never be sent to a TTS provider.
+- Player-facing speech uses the local Piper WebAssembly adapter when the player has activated audio. The separate `ai-spel-static` Nginx service serves pinned Swedish Piper models and ONNX/Piper runtime files from same-origin `/static/piper-wasm-v1/` URLs with immutable caching. Game text is synthesized on-device and must never be sent to a TTS provider.
-- Build Piper/ONNX WebAssembly files and fetch/checksum pinned Swedish model files in the `large` runner; serve them from the frontend image under `/tts/piper-wasm-v1/`. Never build or run these assets locally.
+- This pipeline bundles only the Piper worker/client glue. Model/runtime downloads, image builds, and deployment belong to `ai-spel/ai-spel-static` and the existing `large` runner. Never build or run these assets locally.

PIPER_VOICE_NOTICES.txt

@@ -1,25 +0,0 @@
-Swedish Piper voice models
-==========================
-
-This frontend distributes the Swedish medium Piper models Alma, Lisa, and NST
-from the rhasspy/piper-voices repository, pinned to revision
-c10ece1aade47bb51c153c893d14e5bf8e5b7117. Model weights are delivered by this
-site from /tts/piper-wasm-v1/voices/ after integrity verification in CI.
-
-Alma (sv_SE-alma-medium)
-Source: https://huggingface.co/rhasspy/piper-voices/tree/c10ece1aade47bb51c153c893d14e5bf8e5b7117/sv/sv_SE/alma/medium
-The model card states CC BY 4.0 and identifies the upstream voice project at
-https://huggingface.co/yeagersthlm/piper-voice-sv-alma.
-
-Lisa (sv_SE-lisa-medium)
-Source: https://huggingface.co/rhasspy/piper-voices/tree/c10ece1aade47bb51c153c893d14e5bf8e5b7117/sv/sv_SE/lisa/medium
-The upstream model card describes this as fine-tuned from the Norwegian
-talesyntese medium voice.
-
-NST (sv_SE-nst-medium)
-Source: https://huggingface.co/rhasspy/piper-voices/tree/c10ece1aade47bb51c153c893d14e5bf8e5b7117/sv/sv_SE/nst/medium
-The upstream model card identifies the NST Swedish TTS dataset as CC0 and
-credits KBLab at the National Library of Sweden for training the voice.
-
-The upstream model files and their model cards remain the source of truth for
-license terms. The complete source revision is pinned in scripts/build-piper.mjs.

README.md

@@ -14,7 +14,7 @@ The game is text- and dialogue-based and uses no images. Place descriptions incl
 
 Player-facing speech uses Piper TTS in WebAssembly in the browser after audio is activated by a user gesture. It reads game dialogue, onboarding, account responses, character and world creation, gameplay replies, in-game errors, and microphone disclosures; the `/admin` route is excluded. The audio is decoded and played through the Web Audio API, independently of `speechSynthesis`. The first unauthenticated visit keeps the introduction visible and it can be started with `Läs introduktionen`. New game replies are read automatically and the transcript remains available to screen readers and as text. Returning players hear the latest saved game reply when they reopen the game. The player can change speaking rate; narrator pitch is neutral and character pitch is varied consistently by voice identity. These preferences are stored in browser `localStorage`. If WebAssembly, model loading, or audio playback fails, the same content remains available as text and the dialogue offers a retry.
 
-The Piper engine, WebAssembly runtime, and all three Swedish medium voice models (Alma, Lisa, and NST) are served from this frontend's same-origin `/tts/piper-wasm-v1/` path. The Gitea pipeline downloads the pinned model files, verifies their sizes and cryptographic hashes, and packages them into the versioned frontend image. The browser's Piper adapter redirects the library's built-in model URLs to this same-origin server; it does not request voice files from Hugging Face. A voice model is fetched on first use and cached in browser storage when supported. The game currently uses the NST model. Dialogue text is synthesized on the device and is not sent to a TTS provider. Voice model attribution and license references are available in the voice settings and at `/tts/piper-wasm-v1/voices/ATTRIBUTION.txt`.
+The Piper engine, ONNX WebAssembly runtime, and all three Swedish medium voice models (Alma, Lisa, and NST) are served by the separate `ai-spel-static` Nginx service from same-origin `/static/piper-wasm-v1/`. Its own Gitea pipeline downloads pinned models, verifies sizes and hashes, and publishes a versioned image and Helm chart independently from frontend changes. The frontend's Piper adapter redirects the library's built-in model URLs to this static service; it does not request voice files from Hugging Face. Voice models are fetched on first use and cached in browser storage when supported. Dialogue text is synthesized on the device and is not sent to a TTS provider. Attribution is available at `/static/piper-wasm-v1/voices/ATTRIBUTION.txt`.
 
 The microphone button beside the text field uses Web Speech API when available and sends only its final Swedish transcript through the same submission path as typed text. Before its first use, the client explains that the browser may process audio through a provider-selected service; the game itself does not receive or store recordings, while the final transcript is saved as ordinary dialogue. Writing `röstinställningar` or saying `röstkommando alternativ` opens temporary voice controls in the dialogue. The player can adjust speaking rate and enable or disable short audio cues. Voice preferences are stored in browser `localStorage`.
 
@@ -26,6 +26,8 @@ On iPhone and iPad, Safari requires a user gesture to unlock Web Audio. The fron
 
 The browser and API stay on the same public origin, `https://ai-spel.k3s.k0.nu`. The ingress routes `/` to this frontend service and routes `/api`, `/version`, and `/health` to the Rust service. That keeps the current server-side session cookie same-origin and avoids browser CORS configuration.
 
+The public footer displays the frontend, static-service, and API versions. It fetches `/static/version.json` without caching; the static service creates that file from its sole `VERSION` source during the same image build used for the matching Helm chart and release tag.
+
 ## Release flow
 
 `VERSION` is the only version source for this repository. Gitea Actions on the existing `large` runner runs the static checks, Helm lint/template, publishes a commit image, bumps the patch version through `scripts/bump-version.py`, creates the matching release commit and Git tag, and publishes the release image, Helm chart, and rendered frontend manifest to Harbor. Argo CD tracks the newest published frontend chart. The image and chart releases use the same version as the commit and tag.

VERSION

@@ -1 +1 @@
-0.1.47
+0.1.55

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: 0.1.47
+version: 0.1.55
-appVersion: "0.1.47"
+appVersion: "0.1.55"

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>
@@ -71,7 +78,7 @@
       <div id="admin-content" aria-live="polite" aria-busy="false"></div>
     </section>
   </main>
-  <footer id="version-footer">Frontend <span id="frontend-version">__FRONTEND_VERSION__</span> · API <span id="api-version">hämtar version…</span></footer>
+  <footer id="version-footer">Frontend <span id="frontend-version">__FRONTEND_VERSION__</span> · Statik <span id="static-version">hämtar version…</span> · API <span id="api-version">hämtar version…</span></footer>
   <script src="/piper-runtime.js?v=__FRONTEND_VERSION__"></script>
   <script src="/voice.js?v=__FRONTEND_VERSION__"></script>
   <script>
@@ -157,6 +164,40 @@
       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 starting = message.startsWith('Startar svensk röstmotor och förbereder modellen.');
+      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) {
+        container.hidden = true;
+        progress.removeAttribute('value');
+        value.textContent = 'Väntar på nedladdning';
+        return false;
+      }
+      container.hidden = false;
+      label.textContent = starting
+        ? 'Startar och läser in den svenska röstmodellen'
+        : '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 = starting ? 'Startar röstmotorn…' : 'Förbereder…';
+      return true;
+    }
     function clearSpeechRecovery() {
       speechRecoveryElement?.remove();
       speechRecoveryElement = null;
@@ -218,8 +259,15 @@
         microphone.setAttribute('aria-pressed', String(listening));
         microphone.textContent = listening ? 'Avsluta mikrofon' : 'Starta mikrofon';
         refreshMicrophone();
-        if (message) setVoiceStatus(message);
+        if (message) {
-        else if (state === 'IDLE') setVoiceStatus('');
+          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);
       },
@@ -260,7 +308,7 @@
       voiceSettings.voiceName = piperVoice.value;
       voiceLabel.append(voice); fieldset.append(voiceLabel);
       const modelCredits = document.createElement('a');
-      modelCredits.href = '/tts/piper-wasm-v1/voices/ATTRIBUTION.txt';
+      modelCredits.href = '/static/piper-wasm-v1/voices/ATTRIBUTION.txt';
       modelCredits.textContent = 'Svenska rösters upphov och licenser';
       fieldset.append(modelCredits);
       const signalLabel = document.createElement('label'); const signals = document.createElement('input');
@@ -863,6 +911,11 @@
     }).catch(() => {
       document.querySelector('#api-version').textContent = 'otillgänglig';
     });
+    request('/static/version.json', {cache: 'no-store'}).then(({version}) => {
+      document.querySelector('#static-version').textContent = version;
+    }).catch(() => {
+      document.querySelector('#static-version').textContent = 'otillgänglig';
+    });
     request('/api/me').then(() => location.pathname === '/admin' ? openAdmin() : openGame()).catch(showAuth);
   </script>
 </body>

nginx/default.conf

@@ -12,9 +12,10 @@ server {
     location ^~ /tts/piper-wasm-v1/ {
         types {
             application/wasm wasm;
-            application/javascript js;
+            application/javascript js mjs;
             application/json json;
             application/octet-stream onnx;
+            text/plain txt;
         }
         add_header Cache-Control "public, max-age=31536000, immutable" always;
         add_header Cross-Origin-Opener-Policy "same-origin" always;

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-model-routing.mjs

@@ -1,5 +1,5 @@
 const PIPER_MODEL_ORIGIN = 'https://huggingface.co/diffusionstudio/piper-voices/resolve/main/';
-const localPathPrefix = '/tts/piper-wasm-v1/voices/';
+const localPathPrefix = '/static/piper-wasm-v1/voices/';
 
 export function localPiperModelUrl(requestedUrl, origin) {
   if (!requestedUrl.startsWith(PIPER_MODEL_ORIGIN)) return null;

piper-onnx-config.mjs

@@ -0,0 +1,7 @@
+const assetRoot = '/static/piper-wasm-v1/onnx/';
+
+export function createOnnxWasmPaths(origin) {
+  const absoluteAssetRoot = new URL(assetRoot, origin).href;
+  return absoluteAssetRoot;
+}
+

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

@@ -1,30 +1,37 @@
 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';
 
 const VOICE_ID = 'sv_SE-nst-medium';
-const ASSET_ROOT = '/tts/piper-wasm-v1';
+const ASSET_ROOT = '/static/piper-wasm-v1';
 const localFetch = self.fetch.bind(self);
 
-// The pinned TTS library uses a fixed Hugging Face URL. Keep its OPFS cache logic,
+// Keep the TTS library's OPFS cache logic, but serve models/config from the
-// but serve every model/config request from this frontend origin instead.
+// 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);
   const redirected = resource instanceof Request ? new Request(localModelUrl, resource) : localModelUrl;
-  return localFetch(redirected, options);
+  const response = await localFetch(redirected, options);
+  if (!activeRequestId || !localModelUrl.endsWith('.onnx')) return response;
+  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: `${ASSET_ROOT}/onnx/`,
+        onnxWasm: createOnnxWasmPaths(self.location.origin),
         piperData: `${ASSET_ROOT}/piper/piper_phonemize.data`,
         piperWasm: `${ASSET_ROOT}/piper/piper_phonemize.wasm`,
       },
@@ -39,13 +46,17 @@ async function getSession(onProgress) {
 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'}});
   try {
-    const session = await getSession(progress => self.postMessage({id, type: 'progress', progress}));
+    const session = await getSession();
     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

@@ -1,80 +1,13 @@
 import {build} from 'esbuild';
-import {createHash} from 'node:crypto';
+import {mkdir, rm, readFile} from 'node:fs/promises';
-import {createWriteStream} from 'node:fs';
-import {cp, mkdir, readdir, rm, stat, rename, unlink} from 'node:fs/promises';
 import {join, resolve} from 'node:path';
-import {Readable, Transform} from 'node:stream';
-import {pipeline} from 'node:stream/promises';
 
 const root = process.cwd();
 const publicRoot = join(root, 'public');
-const assetRoot = join(publicRoot, 'tts', 'piper-wasm-v1');
+const workerRoot = join(publicRoot, 'tts', 'piper-wasm-v1');
-const onnxSource = join(root, 'node_modules', 'onnxruntime-web', 'dist');
-const piperSource = join(root, 'node_modules', '@diffusionstudio', 'piper-wasm', 'build');
-const piperWasm = join(piperSource, 'piper_phonemize.wasm');
-const piperData = join(piperSource, 'piper_phonemize.data');
 
-const voiceRevision = 'c10ece1aade47bb51c153c893d14e5bf8e5b7117';
+await rm(workerRoot, {recursive: true, force: true});
-const voiceRepository = 'https://huggingface.co/rhasspy/piper-voices/resolve';
+await mkdir(workerRoot, {recursive: true});
-const voiceFiles = [
-  {path: 'sv/sv_SE/alma/medium/sv_SE-alma-medium.onnx', size: 63434611, sha256: 'f75455eb6afeb1db9e2905d5bd7e4115afcd3710e0d399b6a40981766d32fedc'},
-  {path: 'sv/sv_SE/alma/medium/sv_SE-alma-medium.onnx.json', size: 6059, gitBlobSha1: '7eaf3ef20af4a74e9cee9d29b98de3d9fcec0bdc'},
-  {path: 'sv/sv_SE/lisa/medium/sv_SE-lisa-medium.onnx', size: 63511038, sha256: '94cae912b31d6e9140d3f5160f1815951588600c7a9e43d539ba1e81a110d131'},
-  {path: 'sv/sv_SE/lisa/medium/sv_SE-lisa-medium.onnx.json', size: 7239, gitBlobSha1: 'b2b5fb0f8af2aae4ddfb81eaa7709c6b8faa412b'},
-  {path: 'sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx', size: 63104526, sha256: 'df011f56825a59dd1efc080c38a65a1ef70407e60f63050e9246f43a3d7e471e'},
-  {path: 'sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx.json', size: 4157, gitBlobSha1: '9766b9769436046a610a505fda925032e12a66b3'},
-];
-
-async function downloadVoiceFile(file) {
-  const destination = join(assetRoot, 'voices', file.path);
-  const temporary = `${destination}.part`;
-  await mkdir(join(destination, '..'), {recursive: true});
-  const response = await fetch(`${voiceRepository}/${voiceRevision}/${file.path}`);
-  if (!response.ok || !response.body) {
-    throw new Error(`Unable to download Piper voice asset ${file.path}: HTTP ${response.status}`);
-  }
-  const sha256 = createHash('sha256');
-  const sha1 = createHash('sha1').update(Buffer.from(`blob ${file.size}\0`));
-  let size = 0;
-  const verifyAndPassThrough = new Transform({
-    transform(chunk, _encoding, callback) {
-      size += chunk.length;
-      sha256.update(chunk);
-      sha1.update(chunk);
-      callback(null, chunk);
-    },
-  });
-  try {
-    await pipeline(Readable.fromWeb(response.body), verifyAndPassThrough, createWriteStream(temporary));
-    const actualSha1 = sha1.digest('hex');
-    if (size !== file.size || (file.sha256 && sha256.digest('hex') !== file.sha256) ||
-        (file.gitBlobSha1 && actualSha1 !== file.gitBlobSha1)) {
-      throw new Error(`Piper voice asset integrity check failed for ${file.path} (${size} bytes)`);
-    }
-    await rename(temporary, destination);
-  } catch (error) {
-    await unlink(temporary).catch(() => {});
-    throw error;
-  }
-}
-
-await rm(assetRoot, {recursive: true, force: true});
-await mkdir(join(assetRoot, 'onnx'), {recursive: true});
-await mkdir(join(assetRoot, 'piper'), {recursive: true});
-for (const file of voiceFiles) await downloadVoiceFile(file);
-await cp(join(root, 'PIPER_VOICE_NOTICES.txt'), join(assetRoot, 'voices', 'ATTRIBUTION.txt'));
-
-const wasmFiles = (await readdir(onnxSource))
-  .filter(name => name.endsWith('.wasm'));
-if (wasmFiles.length === 0) throw new Error('ONNX Runtime WebAssembly files are missing');
-for (const file of wasmFiles) {
-  await cp(join(onnxSource, file), join(assetRoot, 'onnx', file));
-}
-for (const file of [piperWasm, piperData]) {
-  const fileStat = await stat(file).catch(() => null);
-  if (!fileStat?.isFile() || fileStat.size === 0) throw new Error(`Missing Piper WebAssembly asset: ${file}`);
-  await cp(file, join(assetRoot, 'piper', file.split('/').at(-1)));
-}
 
 await build({
   entryPoints: [resolve(root, 'piper-runtime.js')],
@@ -90,9 +23,9 @@ await build({
 
 await build({
   entryPoints: [resolve(root, 'piper-worker.js')],
-  outfile: join(assetRoot, 'piper-worker.js'),
+  outfile: join(workerRoot, 'piper-worker.js'),
   bundle: true,
-  format: 'iife',
+  format: 'esm',
   platform: 'browser',
   target: ['es2022'],
   external: ['fs', 'path'],
@@ -100,14 +33,14 @@ await build({
   legalComments: 'none',
 });
 
-for (const file of voiceFiles) {
+const workerBundle = await readFile(join(workerRoot, 'piper-worker.js'), 'utf8');
-  const downloaded = join(assetRoot, 'voices', file.path);
+for (const route of [
-  if ((await stat(downloaded)).size !== file.size) throw new Error(`Missing Piper voice asset: ${downloaded}`);
+  'https://huggingface.co/diffusionstudio/piper-voices/resolve/main/',
-}
+  '/static/piper-wasm-v1',
-const workerBundle = await (await import('node:fs/promises')).readFile(join(assetRoot, 'piper-worker.js'), 'utf8');
+  '/static/piper-wasm-v1/voices/',
-if (!workerBundle.includes('https://huggingface.co/diffusionstudio/piper-voices/resolve/main/') ||
+  '/static/piper-wasm-v1/onnx/',
-    !workerBundle.includes('/tts/piper-wasm-v1/voices/')) {
+]) {
-  throw new Error('The Piper worker is missing its same-origin model download route.');
+  if (!workerBundle.includes(route)) throw new Error(`The Piper worker is missing static route ${route}`);
 }
 
-console.log(`Piper browser assets prepared at ${assetRoot}`);
+console.log(`Piper worker bundle prepared at ${workerRoot}`);

scripts/check-frontend.sh

@@ -10,8 +10,10 @@ grep -q 'no-store, no-cache, must-revalidate, proxy-revalidate, max-age=0' nginx
 grep -q 'Cross-Origin-Embedder-Policy "require-corp"' nginx/default.conf
 grep -q 'add_header Cross-Origin-Embedder-Policy "require-corp" always;' nginx/default.conf
 grep -q 'add_header Cross-Origin-Resource-Policy "same-origin" always;' nginx/default.conf
-grep -q 'application/javascript js;' nginx/default.conf
+grep -q 'application/javascript js mjs;' nginx/default.conf
 grep -q "request('/version')" index.html
+grep -q 'id="static-version">hämtar version…' index.html
+grep -q "request('/static/version.json', {cache: 'no-store'})" index.html
 grep -Fq "credentials: 'same-origin'" index.html
 grep -q 'id="dialogue" aria-label="Dialoghistorik" role="log" aria-live="polite"' index.html
 grep -q 'id="message" name="message"' index.html
@@ -27,6 +29,9 @@ 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 "window.GameVoice.createVoiceController" index.html
 grep -q "addVoiceButton(item, 'Testa ljudet'" index.html
 grep -q 'Jag förstår – starta mikrofonen' index.html
@@ -43,13 +48,17 @@ 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
-grep -q '/tts/piper-wasm-v1/voices/' piper-model-routing.mjs
+grep -q '/static/piper-wasm-v1/voices/' piper-model-routing.mjs
-grep -q 'same-origin.*voice' README.md
+grep -q 'ai-spel-static' README.md
 grep -q 'ATTRIBUTION.txt' index.html
 grep -q "SpeechRecognition || win.webkitSpeechRecognition" voice.js
 grep -q "submitMessage(text, 'voice')" index.html

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-model-routing.test.cjs

@@ -6,11 +6,11 @@ test('Piper model and config requests use the same-origin voice mirror', async (
   const origin = 'https://ai-spel.k3s.k0.nu';
   assert.equal(
     localPiperModelUrl('https://huggingface.co/diffusionstudio/piper-voices/resolve/main/sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx', origin),
-    'https://ai-spel.k3s.k0.nu/tts/piper-wasm-v1/voices/sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx',
+    'https://ai-spel.k3s.k0.nu/static/piper-wasm-v1/voices/sv/sv_SE/nst/medium/sv_SE-nst-medium.onnx',
   );
   assert.equal(
     localPiperModelUrl('https://huggingface.co/diffusionstudio/piper-voices/resolve/main/sv/sv_SE/lisa/medium/sv_SE-lisa-medium.onnx.json', origin),
-    'https://ai-spel.k3s.k0.nu/tts/piper-wasm-v1/voices/sv/sv_SE/lisa/medium/sv_SE-lisa-medium.onnx.json',
+    'https://ai-spel.k3s.k0.nu/static/piper-wasm-v1/voices/sv/sv_SE/lisa/medium/sv_SE-lisa-medium.onnx.json',
   );
 });
 

tests/piper-onnx-config.test.cjs

@@ -0,0 +1,15 @@
+const test = require('node:test');
+const assert = require('node:assert/strict');
+
+test('ONNX Runtime receives an absolute same-origin base URL', async () => {
+  const {createOnnxWasmPaths} = await import('../piper-onnx-config.mjs');
+  const wasmPaths = createOnnxWasmPaths('https://ai-spel.k3s.k0.nu');
+  assert.equal(wasmPaths, 'https://ai-spel.k3s.k0.nu/static/piper-wasm-v1/onnx/');
+  assert.equal(new URL('ort-wasm-simd-threaded.mjs', wasmPaths).href,
+    'https://ai-spel.k3s.k0.nu/static/piper-wasm-v1/onnx/ort-wasm-simd-threaded.mjs');
+});
+
+test('ONNX Runtime base URL rejects an invalid worker origin', async () => {
+  const {createOnnxWasmPaths} = await import('../piper-onnx-config.mjs');
+  assert.throws(() => createOnnxWasmPaths('undefined'), TypeError);
+});

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 +254,20 @@ 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]({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 +250,26 @@
         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;
+        if (token !== generation) return;
-        const percent = Math.min(100, Math.floor((event.loaded / event.total) * 100));
+        if (event?.stage === 'starting') {
-        if (percent === lastProgress) return;
+          setState('PROCESSING', 'Startar svensk röstmotor och förbereder modellen.');
-        lastProgress = percent;
+          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()