@ai-sdk/xai - npm Package Compare versions

Comparing version 4.0.10 to 4.0.12

package.json

 {
   "name": "@ai-sdk/xai",
-  "version": "4.0.10",
+  "version": "4.0.12",
   "type": "module",
@@ -32,5 +32,5 @@ "license": "Apache-2.0",
   "dependencies": {
-    "@ai-sdk/openai-compatible": "3.0.7",
+    "@ai-sdk/openai-compatible": "3.0.9",
     "@ai-sdk/provider": "4.0.3",
-    "@ai-sdk/provider-utils": "5.0.7"
+    "@ai-sdk/provider-utils": "5.0.9"
   },
@@ -37,0 +37,0 @@ "devDependencies": {

src/xai-image-model.ts

@@ -204,2 +204,5 @@ import type { ImageModelV4, SharedV4Warning } from '@ai-sdk/provider';
       url,
+      // url is a generated-image URL from the provider response; validate it.
+      validateUrl: true,
+      trustedOrigin: this.config.baseURL,
       abortSignal,
@@ -206,0 +209,0 @@ failedResponseHandler: createStatusCodeErrorResponseHandler(),

src/xai-transcription-model.ts

@@ -11,14 +11,16 @@ import {
   createJsonResponseHandler,
-  getWebSocketConstructor,
+  connectToWebSocket,
   mediaTypeToExtension,
   parseProviderOptions,
   postFormDataToApi,
-  readWebSocketMessageText,
   safeParseJSON,
   serializeModelOptions,
   toWebSocketUrl,
+  waitForWebSocketBufferDrain,
   WORKFLOW_DESERIALIZE,
   WORKFLOW_SERIALIZE,
   type FetchFunction,
+  type WebSocketConnection,
   type WebSocketConstructor,
+  type WebSocketLike,
 } from '@ai-sdk/provider-utils';
@@ -277,5 +279,7 @@ import { z } from 'zod/v4';
     start: controller => {
-      const WebSocketConstructor = getWebSocketConstructor(webSocket);
-      const ws = new WebSocketConstructor(url, undefined, { headers });
       const doneTexts = new Map<number, string>();
+      // per-channel finalized utterances + latest revisable text, used to
+      // reconstruct the finish text (xAI's `transcript.done` has empty text):
+      const finalizedTexts = new Map<number, string[]>();
+      const pendingTexts = new Map<number, string>();
       let doneDuration: number | undefined;
@@ -285,9 +289,13 @@ let audioReader:
         | undefined;
+      let connection: WebSocketConnection | undefined;
 
       cleanup = (closeCode?: number) => {
-        abortSignal?.removeEventListener('abort', abort);
-        void audioReader?.cancel().catch(() => {});
-        try {
-          ws.close(closeCode);
-        } catch {}
+        if (audioReader != null) {
+          void audioReader.cancel().catch(() => {});
+        } else {
+          // pre-open failure or abort: cancel the caller's audio stream so an
+          // upstream producer piping into it does not hang:
+          void audio.cancel().catch(() => {});
+        }
+        connection?.close(closeCode);
       };
@@ -320,12 +328,3 @@
 
-      const abort = () => {
-        finishWithError(abortSignal?.reason ?? new Error('Aborted'));
-      };
-      if (abortSignal?.aborted) {
-        abort();
-        return;
-      }
-      abortSignal?.addEventListener('abort', abort, { once: true });
-
-      const sendAudio = async () => {
+      const sendAudio = async (socket: WebSocketLike) => {
         audioReader = audio.getReader();
@@ -336,3 +335,3 @@ try {
             if (done || finished) break;
-            ws.send(
+            socket.send(
               value instanceof Uint8Array
@@ -342,93 +341,123 @@ ? value
             );
+            // backpressure: pause reads while the socket buffer is full
+            await waitForWebSocketBufferDrain(socket);
           }
         } finally {
           audioReader.releaseLock();
+          // unlocked again: cleanup must cancel `audio`, not the reader
+          audioReader = undefined;
         }
         if (!finished) {
-          ws.send(JSON.stringify({ type: 'audio.done' }));
+          socket.send(JSON.stringify({ type: 'audio.done' }));
         }
       };
 
-      ws.onmessage = event => {
-        void readWebSocketMessageText(event.data)
-          .then(async text => {
-            const parsed = await safeParseJSON({ text });
-            if (!parsed.success) return;
-            const raw = parsed.value as XaiStreamingTranscriptionEvent;
+      connection = connectToWebSocket({
+        url,
+        headers,
+        webSocket,
+        abortSignal,
+        onAbort: finishWithError,
+        onProcessingError: finishWithError,
+        onMessageText: async text => {
+          const parsed = await safeParseJSON({ text });
+          if (!parsed.success) return;
+          const raw = parsed.value as XaiStreamingTranscriptionEvent;
 
-            if (includeRawChunks) {
-              controller.enqueue({ type: 'raw', rawValue: raw });
-            }
+          if (includeRawChunks) {
+            controller.enqueue({ type: 'raw', rawValue: raw });
+          }
 
-            switch (raw.type) {
-              case 'transcript.created': {
-                controller.enqueue({ type: 'stream-start', warnings });
-                void sendAudio().catch(finishWithError);
+          switch (raw.type) {
+            case 'transcript.created': {
+              controller.enqueue({ type: 'stream-start', warnings });
+              const socket = connection?.socket;
+              if (socket == null) {
+                finishWithError(new Error('WebSocket is not connected.'));
                 break;
               }
+              void sendAudio(socket).catch(finishWithError);
+              break;
+            }
 
-              case 'transcript.partial': {
-                const id = channelId(raw.channel_index);
+            case 'transcript.partial': {
+              const id = channelId(raw.channel_index);
+              const channelIndex = raw.channel_index ?? 0;
+              // only `speech_final` completes an utterance; `is_final`
+              // fragments are re-sent/revised later, so they stay partials:
+              if (raw.is_final && raw.speech_final) {
                 const timing = timingFromXaiEvent(raw);
-                if (raw.is_final) {
-                  controller.enqueue({
-                    type: 'transcript-final',
-                    id,
-                    text: raw.text ?? '',
-                    ...timing,
-                    channelIndex: raw.channel_index,
-                  });
-                } else {
-                  controller.enqueue({
-                    type: 'transcript-partial',
-                    id,
-                    text: raw.text ?? '',
-                    startSecond: raw.start,
-                    durationInSeconds: raw.duration,
-                    channelIndex: raw.channel_index,
-                  });
+                if (raw.text) {
+                  finalizedTexts.set(channelIndex, [
+                    ...(finalizedTexts.get(channelIndex) ?? []),
+                    raw.text,
+                  ]);
                 }
-                break;
+                pendingTexts.delete(channelIndex);
+                controller.enqueue({
+                  type: 'transcript-final',
+                  id,
+                  text: raw.text ?? '',
+                  ...timing,
+                  channelIndex: raw.channel_index,
+                });
+              } else {
+                pendingTexts.set(channelIndex, raw.text ?? '');
+                controller.enqueue({
+                  type: 'transcript-partial',
+                  id,
+                  text: raw.text ?? '',
+                  startSecond: raw.start,
+                  durationInSeconds: raw.duration,
+                  channelIndex: raw.channel_index,
+                });
               }
+              break;
+            }
 
-              case 'transcript.done': {
-                const channelIndex = raw.channel_index ?? 0;
-                doneTexts.set(channelIndex, raw.text ?? '');
-                doneDuration = raw.duration ?? doneDuration;
-                maybeFinish();
-                break;
-              }
+            case 'transcript.done': {
+              const channelIndex = raw.channel_index ?? 0;
+              // `transcript.done` text is empty; fall back to the
+              // accumulated utterances plus any trailing unfinalized text:
+              const accumulated = [
+                ...(finalizedTexts.get(channelIndex) ?? []),
+                ...(pendingTexts.get(channelIndex)
+                  ? [pendingTexts.get(channelIndex) as string]
+                  : []),
+              ].join(' ');
+              doneTexts.set(channelIndex, raw.text || accumulated);
+              doneDuration = raw.duration ?? doneDuration;
+              maybeFinish();
+              break;
+            }
 
-              case 'error': {
-                // xAI STT errors are terminal: surface the server message
-                // instead of letting the socket close mask it.
-                finishWithError(new Error(raw.message ?? 'xAI STT error'));
-                break;
-              }
+            case 'error': {
+              // xAI STT errors are terminal: surface the server message
+              // instead of letting the socket close mask it.
+              finishWithError(new Error(raw.message ?? 'xAI STT error'));
+              break;
             }
-          })
-          .catch(finishWithError);
-      };
-
-      ws.onerror = () => {
-        finishWithError(
-          new Error(
-            'xAI streaming transcription error.' +
-              (webSocket == null
-                ? ' Note: the native WebSocket implementation in browsers,' +
-                  ' Node.js, Deno, and Bun cannot send the Authorization' +
-                  ' header required by xAI. Pass a header-capable WebSocket' +
-                  " implementation (e.g. the 'ws' package) via" +
-                  ' createXai({ webSocket }).'
-                : ''),
-          ),
-        );
-      };
-
-      ws.onclose = () => {
-        if (finished) return;
-        finished = true;
-        cleanup();
-        controller.close();
-      };
+          }
+        },
+        onSocketError: () => {
+          finishWithError(
+            new Error(
+              'xAI streaming transcription error.' +
+                (webSocket == null
+                  ? ' Note: the native WebSocket implementation in browsers,' +
+                    ' Node.js, Deno, and Bun cannot send the Authorization' +
+                    ' header required by xAI. Pass a header-capable WebSocket' +
+                    " implementation (e.g. the 'ws' package) via" +
+                    ' createXai({ webSocket }).'
+                  : ''),
+            ),
+          );
+        },
+        onClose: () => {
+          if (finished) return;
+          finished = true;
+          cleanup();
+          controller.close();
+        },
+      });
     },
@@ -435,0 +464,0 @@

src/xai-video-model.ts

@@ -431,2 +431,3 @@ import {
           url: `${baseURL}/videos/${requestId}`,
+          validateUrl: false,
           headers: combineHeaders(this.config.headers(), options.headers),
@@ -433,0 +434,0 @@ successfulResponseHandler: createJsonResponseHandler(

New alerts

URL strings

Supply chain risk

Package contains fragments of external URLs or IP addresses, which the package may be accessing at runtime.

Fixed alerts

URL strings

Supply chain risk

Package contains fragments of external URLs or IP addresses, which the package may be accessing at runtime.

Improved metrics

Total package byte prevSize

795892

1.19%

Lines of code

11358

0.52%

Dependency changes

• + Added

  @ai-sdk/openai-compatible@3.0.9
  (transitive)

• + Added

  @ai-sdk/provider-utils@5.0.9
  (transitive)

• - Removed

  @ai-sdk/openai-compatible@3.0.7
  (transitive)

• - Removed

  @ai-sdk/provider-utils@5.0.7
  (transitive)

• Updated

  @ai-sdk/openai-compatible@3.0.9

• Updated

  @ai-sdk/provider-utils@5.0.9