Prefer WASM on firefox cause WebGPU is incredibly slow there.

src/worker/protocol.ts

@@ -106,7 +106,18 @@ export type LoadProgressMessage =
       progress: number;
     }
   | { type: "load-progress"; status: "done"; file: string }
-  | { type: "load-progress"; status: "ready"; device: InferenceDevice };
+  | {
+      type: "load-progress";
+      status: "ready";
+      device: InferenceDevice;
+      /**
+       * WASM thread count onnxruntime actually ended up with (D-025) — ort
+       * clamps to 1 when cross-origin isolation is missing, so this is field
+       * observability for "is multithreading really on?". Accelerator devices
+       * report 1 (their WASM side must be single-threaded, D-023).
+       */
+      threads?: number;
+    };
 
 /** Incremental transcript fragment — append to the text streamed so far. */
 export interface PartialMessage {
@@ -155,12 +166,32 @@ export interface ErrorMessage {
   requestId?: string;
 }
 
+/**
+ * The worker cannot finish this load usefully in-place and asks the UI to
+ * respawn it (D-025). Posted when an accelerator attempt already initialized
+ * onnxruntime's WASM runtime — whose thread pool is fixed at first init —
+ * single-threaded, so the WASM fallback in *this* worker would run on one
+ * thread for the worker's whole life. The UI terminates the worker, spawns a
+ * fresh one, and re-issues the load with the explicit `device`, remembering
+ * `modelId`+`preference` so later loads skip the doomed attempt entirely.
+ */
+export interface LoadRestartMessage {
+  type: "load-restart";
+  /** Echo of the aborted load's model id. */
+  modelId: string;
+  /** Echo of the aborted load's device preference. */
+  preference: DevicePreference;
+  /** Explicit device the fresh worker should load with. */
+  device: InferenceDevice;
+}
+
 export type WorkerToUiMessage =
   | LoadProgressMessage
   | PartialMessage
   | TranscribeProgressMessage
   | ResultMessage
-  | ErrorMessage;
+  | ErrorMessage
+  | LoadRestartMessage;
 
 // ---------------------------------------------------------------------------
 // Device selection policy (D-004, D-017) — pure so it is unit-testable; the
@@ -173,6 +204,23 @@ export interface DeviceCapabilities {
   webnn: boolean;
   /** `navigator.gpu.requestAdapter()` returned an adapter (WebGPU). */
   webgpu: boolean;
+  /**
+   * The WebGPU adapter supports the "shader-f16" feature. Firefox ships
+   * WebGPU without it, so fp16 weights cannot run there (D-025); the worker
+   * skips the WebGPU attempt when the resolved dtype needs fp16 and this is
+   * false. Optional so `deviceAttempts` callers that don't probe it (tests)
+   * stay valid.
+   */
+  webgpuF16?: boolean;
+}
+
+/**
+ * Whether a dtype spec involves fp16 weights anywhere — such a model cannot
+ * run on a WebGPU adapter without the "shader-f16" feature (D-025).
+ */
+export function dtypeRequiresF16(dtype: DtypeSpec): boolean {
+  if (typeof dtype === "string") return dtype === "fp16";
+  return dtype.encoder_model === "fp16" || dtype.decoder_model_merged === "fp16";
 }
 
 /**
@@ -284,7 +332,10 @@ export function isWorkerToUiMessage(value: unknown): value is WorkerToUiMessage
             typeof value.progress === "number"
           );
         case "ready":
-          return isInferenceDevice(value.device);
+          return (
+            isInferenceDevice(value.device) &&
+            (value.threads === undefined || typeof value.threads === "number")
+          );
         default:
           return false;
       }
@@ -308,6 +359,12 @@ export function isWorkerToUiMessage(value: unknown): value is WorkerToUiMessage
         (value.stage === "load" || value.stage === "transcribe") &&
         isOptionalString(value.requestId)
       );
+    case "load-restart":
+      return (
+        typeof value.modelId === "string" &&
+        isDevicePreference(value.preference) &&
+        isInferenceDevice(value.device)
+      );
     default:
       return false;
   }