Better tests and more user feedback while doing transcription; WIP.

src/worker/protocol.ts

@@ -10,8 +10,10 @@
 export type InferenceDevice = "webgpu" | "wasm" | "webnn";
 
 /**
- * What the UI may request. "auto" (the default) lets the worker probe
- * `navigator.gpu` and pick WebGPU with automatic WASM fallback (D-004).
+ * What the UI may request. "auto" (the default) lets the worker probe the
+ * available backends and pick in priority order WebNN → WebGPU → WASM
+ * (D-004/D-017), with automatic fallback down the same chain if pipeline
+ * creation fails on the picked device.
  */
 export type DevicePreference = InferenceDevice | "auto";
 
@@ -79,7 +81,7 @@ export type UiToWorkerMessage = LoadMessage | TranscribeMessage;
  * Model download / initialization progress. Mirrors the Transformers.js
  * `progress_callback` events we care about; `status: "ready"` marks the end
  * of a successful load and reports the backend that actually got selected
- * (after WebGPU detection / fallback, D-004).
+ * (after device detection / fallback, D-004, D-017).
  */
 export type LoadProgressMessage =
   | { type: "load-progress"; status: "initiate"; file: string }
@@ -135,6 +137,53 @@ export type WorkerToUiMessage =
   | ResultMessage
   | ErrorMessage;
 
+// ---------------------------------------------------------------------------
+// Device selection policy (D-004, D-017) — pure so it is unit-testable; the
+// worker probes the browser capabilities and this decides the attempt order.
+// ---------------------------------------------------------------------------
+
+/** What the worker's capability probe found (see inference.worker.ts). */
+export interface DeviceCapabilities {
+  /** `navigator.ml` exists (WebNN). */
+  webnn: boolean;
+  /** `navigator.gpu.requestAdapter()` returned an adapter (WebGPU). */
+  webgpu: boolean;
+}
+
+/**
+ * Resolve a device preference against probed capabilities into the ordered
+ * list of devices to attempt pipeline creation on. The first entry is the
+ * selected device; later entries are automatic fallbacks for when creation
+ * throws (driver quirks, unsupported ops, out-of-memory). Never empty — WASM
+ * is always the last resort.
+ *
+ * - "auto": WebNN → WebGPU → WASM (D-017), skipping backends the probe ruled
+ *   out, so an auto-detected WebNN that fails still tries WebGPU before WASM.
+ * - Explicit "webnn"/"webgpu": that device (if available) → WASM. An explicit
+ *   choice deliberately does not detour through the other accelerator.
+ * - "wasm": WASM only.
+ */
+export function deviceAttempts(
+  preference: DevicePreference,
+  capabilities: DeviceCapabilities,
+): InferenceDevice[] {
+  switch (preference) {
+    case "wasm":
+      return ["wasm"];
+    case "webgpu":
+      return capabilities.webgpu ? ["webgpu", "wasm"] : ["wasm"];
+    case "webnn":
+      return capabilities.webnn ? ["webnn", "wasm"] : ["wasm"];
+    case "auto": {
+      const attempts: InferenceDevice[] = [];
+      if (capabilities.webnn) attempts.push("webnn");
+      if (capabilities.webgpu) attempts.push("webgpu");
+      attempts.push("wasm");
+      return attempts;
+    }
+  }
+}
+
 // ---------------------------------------------------------------------------
 // Runtime guards (postMessage data arrives untyped)
 // ---------------------------------------------------------------------------