Compare commits

..
4 Commits
Author SHA1 Message Date
Gitea Actions a111b95cef Release 0.1.62 [auto-version-bump] 2026-10-18 12:56:05 +02:00
Ein Anderssono f4d3e2fc3b Add explicit send button to dialogue input
Build and publish frontend / publish (push) Successful in 52s
2026-10-18 12:55:39 +02:00
Gitea Actions fa11314b23 Release 0.1.61 [auto-version-bump] 2026-10-17 16:38:43 +02:00
Ein Anderssono c9b14e0726 Fix Piper memory pressure on iOS
Build and publish frontend / publish (push) Successful in 49s
2026-10-17 16:38:16 +02:00
10 changed files with 75 additions and 14 deletions
+1 -1
View File
@@ -10,7 +10,7 @@ If the player asks to find or approach someone and no NPC is present, the direct
The separate `/admin` route provides an authenticated operations view for player search/profile/trace, YAML prompt assets, generated Luau rules with validation results, runtime debug logging, and the append-only audit log. All privileged data comes from the Rust `/api/admin/...` API; the browser never connects directly to PostgreSQL. Backend endpoints require `accounts.is_admin=true`. The Driftloggar view lets an administrator switch `debug=true` on or off without restarting pods; the setting is stored in PostgreSQL and propagated to running replicas. Verbose pod logs include request, AI-call, validation, and commit metadata but never raw player text, prompts, model responses, sessions, or secrets. Full protected prompt/provider exchanges remain in the audited player trace. The separate `/admin` route provides an authenticated operations view for player search/profile/trace, YAML prompt assets, generated Luau rules with validation results, runtime debug logging, and the append-only audit log. All privileged data comes from the Rust `/api/admin/...` API; the browser never connects directly to PostgreSQL. Backend endpoints require `accounts.is_admin=true`. The Driftloggar view lets an administrator switch `debug=true` on or off without restarting pods; the setting is stored in PostgreSQL and propagated to running replicas. Verbose pod logs include request, AI-call, validation, and commit metadata but never raw player text, prompts, model responses, sessions, or secrets. Full protected prompt/provider exchanges remain in the audited player trace.
The game is text- and dialogue-based and uses no images. Place descriptions include sound, smell, air/temperature, touch/surface, and spatial-orientation cues. Visible details may also be described in words, but are never required to understand the scene or play. The transcript is screen-reader announced, and Enter submits the input while Shift+Enter inserts a newline; no separate send button is required. The game is text- and dialogue-based and uses no images. Place descriptions include sound, smell, air/temperature, touch/surface, and spatial-orientation cues. Visible details may also be described in words, but are never required to understand the scene or play. The transcript is screen-reader announced. A clearly labeled **Skicka** button beside the microphone submits typed text; Enter also submits while Shift+Enter inserts a newline. Typed text, speech transcriptions, and the send button all use the same submission flow.
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. 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.
+1 -1
View File
@@ -1 +1 @@
0.1.60 0.1.62
+2 -2
View File
@@ -2,5 +2,5 @@ apiVersion: v2
name: ai-spel-frontend name: ai-spel-frontend
description: Static web frontend for the Swedish life simulator description: Static web frontend for the Swedish life simulator
type: application type: application
version: 0.1.60 version: 0.1.62
appVersion: "0.1.60" appVersion: "0.1.62"
@@ -0,0 +1,13 @@
# ADR 0003: Limit Piper WASM to one thread and reset failed workers
## Decision
The Piper worker reports one available processor to Piper and configures ONNX Runtime for one thread. If a synthesis request fails, the browser client terminates that worker; the next player retry creates a fresh worker and ONNX module.
## Context
Piper TTS Web 1.0.3 sets `env.wasm.numThreads` from `navigator.hardwareConcurrency` during `TtsSession.init()`, after the application had configured ONNX Runtime. On iPad this could undo the single-thread setting and request a larger WASM worker pool. The library also retains a singleton session if ONNX initialization fails, so retrying in the same worker can reuse a failed initialization.
## Consequences
The one-thread limit reduces parallel inference but lowers memory pressure on mobile Safari. Failed initialization no longer poisons future attempts in the same worker. This cannot guarantee that every device has enough memory for the 63 MB medium voice model; the CI release and Kubernetes checks validate packaging and deployment, while actual iPad memory behavior still requires device verification.
+4 -2
View File
@@ -70,8 +70,8 @@
<form id="message-form"> <form id="message-form">
<label for="message" id="message-label">Skriv ett meddelande</label> <label for="message" id="message-label">Skriv ett meddelande</label>
<textarea id="message" name="message" maxlength="4000" aria-describedby="message-help" autocomplete="off"></textarea> <textarea id="message" name="message" maxlength="4000" aria-describedby="message-help" autocomplete="off"></textarea>
<div id="message-tools"><button type="button" id="microphone" aria-pressed="false" aria-describedby="voice-status">Starta mikrofon</button></div> <div id="message-tools"><button type="submit" id="send-message">Skicka</button> <button type="button" id="microphone" aria-pressed="false" aria-describedby="voice-status">Starta mikrofon</button></div>
<span id="message-help" class="sr-only">Tryck Enter för att skicka. Tryck Skift och Enter för ny rad.</span> <span id="message-help" class="sr-only">Tryck på Skicka eller Enter för att skicka. Tryck Skift och Enter för ny rad.</span>
</form> </form>
<p id="voice-status" role="status" aria-live="polite"></p> <p id="voice-status" role="status" aria-live="polite"></p>
<div id="speech-progress-container" hidden> <div id="speech-progress-container" hidden>
@@ -280,6 +280,8 @@
function refreshMicrophone() { function refreshMicrophone() {
const button = document.querySelector('#microphone'); const button = document.querySelector('#microphone');
if (button) button.disabled = play.hidden || messageField.disabled || submitBusy; if (button) button.disabled = play.hidden || messageField.disabled || submitBusy;
const sendButton = document.querySelector('#send-message');
if (sendButton) sendButton.disabled = play.hidden || messageField.disabled || submitBusy;
} }
function persistVoiceSettings() { function persistVoiceSettings() {
voiceSettings.mode = 'game-voice'; voiceSettings.mode = 'game-voice';
+17
View File
@@ -7,6 +7,23 @@ export function createOnnxWasmPaths(origin) {
export function configureOnnxRuntime(onnxRuntime) { export function configureOnnxRuntime(onnxRuntime) {
if (!onnxRuntime?.env?.wasm) throw new TypeError('ONNX Runtime WebAssembly settings are unavailable.'); if (!onnxRuntime?.env?.wasm) throw new TypeError('ONNX Runtime WebAssembly settings are unavailable.');
// Piper 1.0.3 overwrites this value in TtsSession.init() with
// navigator.hardwareConcurrency. Override that source as well, otherwise an
// iPad may start a large WASM worker pool despite this setting.
const navigatorObject = globalThis.navigator;
if (navigatorObject && navigatorObject.hardwareConcurrency !== 1) {
try {
Object.defineProperty(navigatorObject, 'hardwareConcurrency', {
configurable: true,
value: 1,
});
} catch (_) {
// The check below converts an unsupported override into a clear error.
}
}
if (navigatorObject && navigatorObject.hardwareConcurrency !== 1) {
throw new Error('Piper could not be restricted to one processor thread.');
}
// Piper already runs in a worker. Avoid a second worker pool on mobile Safari. // Piper already runs in a worker. Avoid a second worker pool on mobile Safari.
onnxRuntime.env.wasm.numThreads = 1; onnxRuntime.env.wasm.numThreads = 1;
onnxRuntime.env.wasm.initTimeout = 60000; onnxRuntime.env.wasm.initTimeout = 60000;
+13 -2
View File
@@ -17,8 +17,19 @@ function getWorker() {
request.onProgress?.(message.progress); request.onProgress?.(message.progress);
} else { } else {
pending.delete(message.id); pending.delete(message.id);
if (message.type === 'audio') request.resolve(new Blob([message.audio], {type: 'audio/x-wav'})); if (message.type === 'audio') {
else request.reject(new Error(message.error || 'Piper-arbetaren misslyckades.')); request.resolve(new Blob([message.audio], {type: 'audio/x-wav'}));
} else {
const error = new Error(message.error || 'Piper-arbetaren misslyckades.');
request.reject(error);
// TtsSession keeps a singleton even when ONNX initialization fails.
// Discard the whole worker so a player retry starts with a clean ONNX
// module and does not reuse a poisoned WASM initialization.
for (const queued of pending.values()) queued.reject(error);
pending.clear();
worker?.terminate();
worker = null;
}
} }
}; };
worker.onerror = event => { worker.onerror = event => {
+5 -2
View File
@@ -28,6 +28,7 @@ grep -q "retry.textContent = 'Läs senaste repliken'" index.html
grep -q "location.pathname !== '/admin'" index.html grep -q "location.pathname !== '/admin'" index.html
grep -q "if (options.speak !== false && 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="microphone" aria-pressed="false"' index.html
grep -q 'type="submit" id="send-message">Skicka</button>' index.html
grep -q 'id="voice-status" role="status" aria-live="polite"' 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" aria-label="Nedladdning av svensk röstmodell"' index.html
grep -q 'id="speech-progress-value"' index.html grep -q 'id="speech-progress-value"' index.html
@@ -59,6 +60,8 @@ grep -q 'new ReadableStream' piper-download-progress.mjs
grep -q 'createOnnxWasmPaths(self.location.origin)' piper-worker.js grep -q 'createOnnxWasmPaths(self.location.origin)' piper-worker.js
grep -q 'configureOnnxRuntime(onnxRuntime)' piper-worker.js grep -q 'configureOnnxRuntime(onnxRuntime)' piper-worker.js
grep -q 'numThreads = 1' piper-onnx-config.mjs grep -q 'numThreads = 1' piper-onnx-config.mjs
grep -q "hardwareConcurrency'" piper-onnx-config.mjs
grep -q 'Piper could not be restricted to one processor thread' piper-onnx-config.mjs
grep -q '/static/piper-wasm-v1/onnx/' 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 'PIPER_MODEL_ORIGIN' piper-model-routing.mjs
grep -q '/static/piper-wasm-v1/voices/' piper-model-routing.mjs grep -q '/static/piper-wasm-v1/voices/' piper-model-routing.mjs
@@ -99,8 +102,8 @@ if grep -Eq 'id="(new-character|world-setup|shop|buy-offer|balance|inventory|pla
echo 'The active player UI must not contain permanent data panels, forms, or action buttons.' >&2 echo 'The active player UI must not contain permanent data panels, forms, or action buttons.' >&2
exit 1 exit 1
fi fi
if sed -n '/<section id="play"/,/^ <\/section>/p' index.html | grep '<button' | grep -v 'id="microphone"' >/dev/null; then if sed -n '/<section id="play"/,/^ <\/section>/p' index.html | grep '<button' | grep -Ev 'id="(microphone|send-message)"' >/dev/null; then
echo 'Only the microphone control may appear beside the game text input.' >&2 echo 'Only the send and microphone controls may appear beside the game text input.' >&2
exit 1 exit 1
fi fi
+13 -4
View File
@@ -14,10 +14,19 @@ test('ONNX Runtime base URL rejects an invalid worker origin', async () => {
assert.throws(() => createOnnxWasmPaths('undefined'), TypeError); assert.throws(() => createOnnxWasmPaths('undefined'), TypeError);
}); });
test('ONNX Runtime uses one thread and a bounded startup timeout', async () => { test('Piper and ONNX Runtime stay on one thread even though Piper overwrites ONNX settings', async () => {
const {configureOnnxRuntime} = await import('../piper-onnx-config.mjs'); const {configureOnnxRuntime} = await import('../piper-onnx-config.mjs');
const navigatorObject = {hardwareConcurrency: 8};
const previousNavigator = globalThis.navigator;
Object.defineProperty(globalThis, 'navigator', {configurable: true, value: navigatorObject});
const runtime = {env: {wasm: {numThreads: 0, initTimeout: 0}}}; const runtime = {env: {wasm: {numThreads: 0, initTimeout: 0}}};
configureOnnxRuntime(runtime); try {
assert.equal(runtime.env.wasm.numThreads, 1); configureOnnxRuntime(runtime);
assert.equal(runtime.env.wasm.initTimeout, 60000); assert.equal(navigatorObject.hardwareConcurrency, 1);
assert.equal(runtime.env.wasm.numThreads, 1);
assert.equal(runtime.env.wasm.initTimeout, 60000);
} finally {
if (previousNavigator === undefined) delete globalThis.navigator;
else Object.defineProperty(globalThis, 'navigator', {configurable: true, value: previousNavigator});
}
}); });
+6
View File
@@ -11,3 +11,9 @@ test('Piper worker is built and started as an ES module', async () => {
assert.match(buildScript, /outfile: join\(workerRoot, 'piper-worker\.js'\),\s*bundle: true,\s*format: 'esm'/); assert.match(buildScript, /outfile: join\(workerRoot, 'piper-worker\.js'\),\s*bundle: true,\s*format: 'esm'/);
assert.match(runtime, /new Worker\(workerUrl, \{type: 'module'\}\)/); assert.match(runtime, /new Worker\(workerUrl, \{type: 'module'\}\)/);
}); });
test('Piper runtime discards a worker after a failed initialization for a clean retry', async () => {
const runtime = await readFile(join(__dirname, '..', 'piper-runtime.js'), 'utf8');
assert.match(runtime, /TtsSession keeps a singleton even when ONNX initialization fails/);
assert.match(runtime, /worker\?\.terminate\(\);\s*worker = null;/);
});