ai 7.0.158 → 7.0.160

package/dist/internal/index.js

@@ -110,7 +110,7 @@ function asAsyncIterableStream(stream) {
 }
 //#endregion
 //#region src/version.ts
-const VERSION = "7.0.158";
+const VERSION = "7.0.160";
 //#endregion
 //#region src/util/download/download.ts
 /**

package/docs/02-foundations/02-providers-and-models.mdx

@@ -122,6 +122,14 @@ Here are the capabilities of popular models:
 | [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-4.7`                                  | <Check />   | <Check />         | <Check />  | <Check />      |
 | [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-4.6`                                  | <Check />   | <Check />         | <Check />  | <Check />      |
 | [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-4.5`                                  | <Check />   | <Check />         | <Check />  | <Check />      |
+| [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-4.20-reasoning`                       | <Check />   | <Check />         | <Check />  | <Check />      |
+| [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-4.20-non-reasoning`                   | <Check />   | <Check />         | <Check />  | <Check />      |
+| [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-4-1-fast-reasoning`                   | <Check />   | <Check />         | <Check />  | <Check />      |
+| [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-4-1-fast-non-reasoning`               | <Check />   | <Check />         | <Check />  | <Check />      |
+| [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-4-1`                                  | <Cross />   | <Check />         | <Check />  | <Check />      |
+| [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-4-fast-reasoning`                     | <Check />   | <Check />         | <Check />  | <Check />      |
+| [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-4-fast-non-reasoning`                 | <Check />   | <Check />         | <Check />  | <Check />      |
+| [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-code-fast-1`                          | <Cross />   | <Check />         | <Check />  | <Check />      |
 | [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-4`                                    | <Cross />   | <Check />         | <Check />  | <Check />      |
 | [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-3`                                    | <Cross />   | <Check />         | <Check />  | <Check />      |
 | [xAI Grok](/providers/ai-sdk-providers/xai)        | `grok-3-mini`                               | <Cross />   | <Check />         | <Check />  | <Check />      |
@@ -193,14 +201,16 @@ Here are the capabilities of popular models:
 | [Google](/providers/ai-sdk-providers/google)       | `gemini-2.5-flash-lite`                     | <Check />   | <Check />         | <Check />  | <Check />      |
 | [Google](/providers/ai-sdk-providers/google)       | `gemini-2.5-flash-lite-preview-06-17`       | <Check />   | <Check />         | <Check />  | <Check />      |
 | [Google](/providers/ai-sdk-providers/google)       | `gemini-2.0-flash`                          | <Check />   | <Check />         | <Check />  | <Check />      |
-| [Mistral](/providers/ai-sdk-providers/mistral)     | `pixtral-large-latest`                      | <Check />   | <Check />         | <Check />  | <Check />      |
-| [Mistral](/providers/ai-sdk-providers/mistral)     | `mistral-large-latest`                      | <Cross />   | <Check />         | <Check />  | <Check />      |
-| [Mistral](/providers/ai-sdk-providers/mistral)     | `mistral-medium-latest`                     | <Cross />   | <Check />         | <Check />  | <Check />      |
-| [Mistral](/providers/ai-sdk-providers/mistral)     | `mistral-medium-3`                          | <Cross />   | <Check />         | <Check />  | <Check />      |
-| [Mistral](/providers/ai-sdk-providers/mistral)     | `mistral-medium-2505`                       | <Cross />   | <Check />         | <Check />  | <Check />      |
-| [Mistral](/providers/ai-sdk-providers/mistral)     | `mistral-medium-3.5`                        | <Cross />   | <Check />         | <Check />  | <Check />      |
-| [Mistral](/providers/ai-sdk-providers/mistral)     | `mistral-small-latest`                      | <Cross />   | <Check />         | <Check />  | <Check />      |
-| [Mistral](/providers/ai-sdk-providers/mistral)     | `pixtral-12b-2409`                          | <Check />   | <Check />         | <Check />  | <Check />      |
+| [Mistral](/providers/ai-sdk-providers/mistral)     | `labs-leanstral-1-5`                        | <Check />   | <Check />         | <Check />  | <Check />      |
+| [Mistral](/providers/ai-sdk-providers/mistral)     | `magistral-medium-latest`                   | <Check />   | <Check />         | <Check />  | <Check />      |
+| [Mistral](/providers/ai-sdk-providers/mistral)     | `magistral-small-latest`                    | <Check />   | <Check />         | <Check />  | <Check />      |
+| [Mistral](/providers/ai-sdk-providers/mistral)     | `ministral-14b-latest`                      | <Check />   | <Check />         | <Check />  | <Check />      |
+| [Mistral](/providers/ai-sdk-providers/mistral)     | `ministral-8b-latest`                       | <Check />   | <Check />         | <Check />  | <Check />      |
+| [Mistral](/providers/ai-sdk-providers/mistral)     | `mistral-large-latest`                      | <Check />   | <Check />         | <Check />  | <Check />      |
+| [Mistral](/providers/ai-sdk-providers/mistral)     | `mistral-medium-latest`                     | <Check />   | <Check />         | <Check />  | <Check />      |
+| [Mistral](/providers/ai-sdk-providers/mistral)     | `mistral-small-latest`                      | <Check />   | <Check />         | <Check />  | <Check />      |
+| [Mistral](/providers/ai-sdk-providers/mistral)     | `voxtral-small-latest`                      | <Cross />   | <Check />         | <Check />  | <Check />      |
+| [Mistral](/providers/ai-sdk-providers/mistral)     | `zai-glm-5-2`                               | <Cross />   | <Check />         | <Check />  | <Check />      |
 | [DeepSeek](/providers/ai-sdk-providers/deepseek)   | `deepseek-v4-flash`                         | <Cross />   | <Check />         | <Check />  | <Check />      |
 | [DeepSeek](/providers/ai-sdk-providers/deepseek)   | `deepseek-v4-pro`                           | <Cross />   | <Check />         | <Check />  | <Check />      |
 | [Cerebras](/providers/ai-sdk-providers/cerebras)   | `gpt-oss-120b`                              | <Cross />   | <Check />         | <Check />  | <Check />      |

package/docs/03-agents/04-loop-control.mdx

@@ -12,7 +12,7 @@ You can control both the execution flow and the settings at each step of the age
 - A tool call needs approval, or
 - A stop condition is met
 
-A [steering message](#steering) that is waiting when the model finishes its answer keeps the loop going for another step.
+A [steering message](#steering) that is waiting when the model finishes its answer keeps the loop going for another step. So does a [queued message](#queueing-messages), unless the answer was cut off.
 
 The AI SDK provides built-in loop control through two parameters: `stopWhen` for defining stopping conditions and `prepareStep` for modifying settings (model, tools, messages, and more) between steps.
 
@@ -477,6 +477,34 @@ prepareStep: ({ initialMessages, steps, experimental_steeringMessages }) => ({
 }),
 ```
 
+### Queueing Messages
+
+`steer()` changes what the agent is doing right now. Use `queue()` for a follow-up that should wait until the agent has finished its current task:
+
+```ts
+const steering = experimental_createSteering();
+
+const resultPromise = agent.generate({
+  prompt: 'Refactor the auth module.',
+  experimental_steering: steering,
+});
+
+// while the agent is working:
+steering.queue('Then add tests for it.');
+steering.queue('Then update the readme.');
+
+const result = await resultPromise;
+```
+
+A queued message is added once the model finishes its current task, i.e. when it gives a final answer without tool calls. The loop then continues with the message, so the agent works through the queue one task at a time:
+
+- Queued messages are added one per task, in the order they are queued.
+- Waiting steering messages are added first. A queued message waits for the next task that finishes.
+- Messages that are queued before the loop starts wait until the model has answered the prompt.
+- A response that is cut off (finish reason `length` or `content-filter`) does not finish the task, so the loop ends and the queued message is reported as not delivered.
+- Stop conditions still apply, and a queued message that the loop does not reach is reported as not delivered, so you can send it as a new message instead.
+- Queued messages are saved in `experimental_steeringMessages` like steering messages, and `queue()` resolves with the same outcome as `steer()`.
+
 ### Handling the Outcome
 
 `steer()` resolves with the outcome of the message and never rejects:

package/docs/03-ai-sdk-core/60-telemetry.mdx

@@ -16,7 +16,7 @@ to see providers that offer monitoring and tracing for AI SDK applications.
 
 ### Step 1: Register the OpenTelemetry integration
 
-OpenTelemetry span collection requires the `@ai-sdk/otel` package. Install it and register the integration once at application startup:
+OpenTelemetry collection requires the `@ai-sdk/otel` package. Install it and register the integration once at application startup:
 
 ```bash
 pnpm install @ai-sdk/otel
@@ -513,6 +513,37 @@ The `LegacyOpenTelemetry` integration emits legacy AI SDK-specific spans.
 The `OpenTelemetry` emits spans that follow the [OpenTelemetry Semantic Conventions for GenAI](https://opentelemetry.io/docs/specs/semconv/gen-ai/).
 By default, attributes use the `gen_ai.*` prefix. Provider names are mapped to well-known values (e.g. `openai`, `anthropic`, `gcp.vertex_ai`).
 
+#### Inference duration metric
+
+For `generateText` and `streamText`, `OpenTelemetry` also records the
+[`gen_ai.client.inference.duration`](https://github.com/open-telemetry/semantic-conventions-genai/blob/3fe84604a581b3d50dd5b4bd29383b462d2a5018/docs/gen-ai/client-inference.md#metric-gen_aiclientinferenceduration)
+histogram in seconds, following the development GenAI semantic conventions.
+Configure a global OpenTelemetry `MeterProvider` with a metric reader and exporter
+to collect it. A `TracerProvider` alone does not export metrics.
+
+Each language model call contributes one observation, including calls that fail or
+are cancelled. Streaming calls record the full response duration. In a workflow
+with multiple model calls, each call is recorded separately; local tool execution
+time is excluded. Each attempt of a retried model stream contributes its own
+observation, including failed attempts that close without a finish chunk.
+
+The histogram includes these attributes:
+
+- `gen_ai.operation.name`: `"chat"`
+- `gen_ai.provider.name`: the normalized provider name
+- `gen_ai.request.model`: the requested model ID
+- `gen_ai.response.model`: the response model ID, when available
+- `error.type`: the error name for thrown errors, `"AbortError"` for cancellation,
+  or `"_OTHER"` when a call ends with an error finish reason or an unknown error
+
+The default bucket boundary advice is `[0.01, 0.02, 0.04, 0.08, 0.16, 0.32, 0.64,
+1.28, 2.56, 5.12, 10.24, 20.48, 40.96, 81.92]` seconds. Your OpenTelemetry SDK
+configuration can override aggregation and bucket boundaries.
+
+Setting `telemetry.isEnabled` to `false` disables these metrics for a call.
+Setting `recordInputs` or `recordOutputs` to `false` does not disable duration
+metrics. The `LegacyOpenTelemetry` integration does not emit this histogram.
+
 #### generateText / streamText
 
 For `generateText` and `streamText`, the integration records 3 types of spans:

package/docs/07-reference/01-ai-sdk-core/01-generate-text.mdx

@@ -857,7 +857,7 @@ To see `generateText` in action, check out [these examples](#examples).
       type: 'Experimental_Steering',
       isOptional: true,
       description:
-        "Experimental steering object created with `experimental_createSteering()`. Messages sent with `steering.steer()` are added as user messages at the next step boundary, after the current step and its tool calls are done. A waiting message keeps the loop going for another step unless a stop condition is met. `steer()` resolves with `{ type: 'delivered', id, message, stepNumber }` or `{ type: 'not-delivered', id, message, reason }`. See [Steering](/docs/agents/loop-control#steering).",
+        "Experimental steering object created with `experimental_createSteering()`. Messages sent with `steering.steer()` are added as user messages at the next step boundary, after the current step and its tool calls are done. Messages sent with `steering.queue()` wait until the model finishes its current task and are added one per task. A waiting message keeps the loop going for another step unless a stop condition is met. `steer()` and `queue()` resolve with `{ type: 'delivered', id, message, stepNumber }` or `{ type: 'not-delivered', id, message, reason }`. See [Steering](/docs/agents/loop-control#steering).",
     },
     {
       name: 'experimental_download',

package/docs/07-reference/01-ai-sdk-core/02-stream-text.mdx

@@ -914,7 +914,7 @@ retain the content their contracts require.
       type: 'Experimental_Steering',
       isOptional: true,
       description:
-        "Experimental steering object created with `experimental_createSteering()`. Messages sent with `steering.steer()` are added as user messages at the next step boundary, after the current step and its tool calls are done. A waiting message keeps the loop going for another step unless a stop condition is met. `steer()` resolves with `{ type: 'delivered', id, message, stepNumber }` or `{ type: 'not-delivered', id, message, reason }`. See [Steering](/docs/agents/loop-control#steering).",
+        "Experimental steering object created with `experimental_createSteering()`. Messages sent with `steering.steer()` are added as user messages at the next step boundary, after the current step and its tool calls are done. Messages sent with `steering.queue()` wait until the model finishes its current task and are added one per task. A waiting message keeps the loop going for another step unless a stop condition is met. `steer()` and `queue()` resolve with `{ type: 'delivered', id, message, stepNumber }` or `{ type: 'not-delivered', id, message, reason }`. See [Steering](/docs/agents/loop-control#steering).",
     },
     {
       name: 'experimental_download',

package/docs/07-reference/01-ai-sdk-core/16-tool-loop-agent.mdx

@@ -768,7 +768,7 @@ const result = await agent.generate({
       type: 'Experimental_Steering',
       isOptional: true,
       description:
-        "Experimental steering object created with `experimental_createSteering()`. Messages sent with `steering.steer()` are added as user messages at the next step boundary, after the current step and its tool calls are done. A waiting message keeps the loop going for another step unless a stop condition is met. `steer()` resolves with `{ type: 'delivered', id, message, stepNumber }` or `{ type: 'not-delivered', id, message, reason }`. See [Steering](/docs/agents/loop-control#steering).",
+        "Experimental steering object created with `experimental_createSteering()`. Messages sent with `steering.steer()` are added as user messages at the next step boundary, after the current step and its tool calls are done. Messages sent with `steering.queue()` wait until the model finishes its current task and are added one per task. A waiting message keeps the loop going for another step unless a stop condition is met. `steer()` and `queue()` resolve with `{ type: 'delivered', id, message, stepNumber }` or `{ type: 'not-delivered', id, message, reason }`. See [Steering](/docs/agents/loop-control#steering).",
     },
     {
       name: 'options',
@@ -891,7 +891,7 @@ for await (const chunk of stream.textStream) {
       type: 'Experimental_Steering',
       isOptional: true,
       description:
-        "Experimental steering object created with `experimental_createSteering()`. Messages sent with `steering.steer()` are added as user messages at the next step boundary, after the current step and its tool calls are done. A waiting message keeps the loop going for another step unless a stop condition is met. `steer()` resolves with `{ type: 'delivered', id, message, stepNumber }` or `{ type: 'not-delivered', id, message, reason }`. See [Steering](/docs/agents/loop-control#steering).",
+        "Experimental steering object created with `experimental_createSteering()`. Messages sent with `steering.steer()` are added as user messages at the next step boundary, after the current step and its tool calls are done. Messages sent with `steering.queue()` wait until the model finishes its current task and are added one per task. A waiting message keeps the loop going for another step unless a stop condition is met. `steer()` and `queue()` resolve with `{ type: 'delivered', id, message, stepNumber }` or `{ type: 'not-delivered', id, message, reason }`. See [Steering](/docs/agents/loop-control#steering).",
     },
     {
       name: 'options',

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai",
-  "version": "7.0.158",
+  "version": "7.0.160",
   "type": "module",
   "description": "AI SDK by Vercel - build apps like ChatGPT, Claude, Gemini, and more with a single interface for any model using the Vercel AI Gateway or go direct to OpenAI, Anthropic, Google, or any other model provider.",
   "license": "Apache-2.0",
@@ -42,12 +42,12 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/gateway": "4.0.131",
+    "@ai-sdk/gateway": "4.0.133",
     "@ai-sdk/provider": "4.0.35",
     "@ai-sdk/provider-utils": "5.0.72"
   },
   "devDependencies": {
-    "@ai-sdk/amazon-bedrock": "5.0.129",
+    "@ai-sdk/amazon-bedrock": "5.0.130",
     "@ai-sdk/deepseek": "3.0.77",
     "@ai-sdk/google": "4.0.109",
     "@ai-sdk/groq": "4.0.74",
@@ -55,7 +55,7 @@
     "@ai-sdk/moonshotai": "3.0.82",
     "@ai-sdk/openai": "4.0.106",
     "@ai-sdk/test-server": "2.0.4",
-    "@ai-sdk/xai": "5.0.34",
+    "@ai-sdk/xai": "5.0.36",
     "@edge-runtime/vm": "^5.0.0",
     "@smithy/eventstream-codec": "^4.3.3",
     "@smithy/util-utf8": "^4.3.3",

package/src/generate-text/generate-text.ts

@@ -981,7 +981,15 @@ async function generateTextInternal<
           clientToolCalls.length === 0 &&
           pendingDeferredToolCalls.size === 0
         ) {
-          if (!steeringRun?.hasPendingMessages()) {
+          // queued messages wait for a task that was not cut off:
+          const isTruncated =
+            steps[steps.length - 1].finishReason === 'length' ||
+            steps[steps.length - 1].finishReason === 'content-filter';
+
+          if (
+            !steeringRun?.hasPendingMessages() &&
+            (isTruncated || !steeringRun?.promoteQueuedMessage())
+          ) {
             return false;
           }
 

package/src/generate-text/smooth-stream.ts

@@ -79,7 +79,7 @@ export function smoothStream<TOOLS extends ToolSet>({
 
       if (!buffer.startsWith(match)) {
         throw new Error(
-          `Chunking function must return a match that is a prefix of the buffer. Received: "${match}" expected to start with "${buffer}"`,
+          `Chunking function must return a match that is a prefix of the buffer. Received: "${match}" which is not a prefix of buffer "${buffer}"`,
         );
       }
 

package/src/generate-text/steering.ts

@@ -81,6 +81,24 @@ export interface Steering {
     message: string | UserModelMessage,
     options?: { id?: string },
   ): Promise<SteeringOutcome>;
+
+  /**
+   * Adds a user message to the run once the model has finished its current
+   * task, i.e. when it gives a final answer without tool calls. The run then
+   * continues with the message unless a stop condition is met. Queued
+   * messages are delivered one per task, in order, after any waiting steering
+   * messages.
+   *
+   * @param message - The user message, or its text.
+   * @param options.id - The id of the message. Sending a message again with
+   * the same id returns the outcome of the first message.
+   *
+   * @returns The outcome of the message. It never rejects.
+   */
+  queue(
+    message: string | UserModelMessage,
+    options?: { id?: string },
+  ): Promise<SteeringOutcome>;
 }
 
 /**
@@ -89,6 +107,12 @@ export interface Steering {
 export type SteeringRun = {
   hasPendingMessages(): boolean;
 
+  /**
+   * Moves the oldest queued message to the waiting messages for the next
+   * step. Returns `false` when no message is queued.
+   */
+  promoteQueuedMessage(): boolean;
+
   /**
    * Takes the waiting messages for the next step. They are resolved by
    * `resolveTakenMessages` once the prompt of the step is known.
@@ -116,6 +140,7 @@ type PendingSteer = {
 class DefaultSteering implements Steering {
   private state: 'idle' | 'running' | 'ended' = 'idle';
   private pending: Array<PendingSteer> = [];
+  private queued: Array<PendingSteer> = [];
   private taken: Array<PendingSteer> = [];
   private outcomes = new Map<string, Promise<SteeringOutcome>>();
 
@@ -123,8 +148,25 @@ class DefaultSteering implements Steering {
     message: string | UserModelMessage,
     options?: { id?: string },
   ): Promise<SteeringOutcome> {
-    const id = options?.id ?? generateSteeringId();
+    return this.add({ message, id: options?.id, target: this.pending });
+  }
+
+  queue(
+    message: string | UserModelMessage,
+    options?: { id?: string },
+  ): Promise<SteeringOutcome> {
+    return this.add({ message, id: options?.id, target: this.queued });
+  }
 
+  private add({
+    message,
+    id = generateSteeringId(),
+    target,
+  }: {
+    message: string | UserModelMessage;
+    id?: string;
+    target: Array<PendingSteer>;
+  }): Promise<SteeringOutcome> {
     const existingOutcome = this.outcomes.get(id);
     if (existingOutcome != null) {
       return existingOutcome;
@@ -144,7 +186,7 @@ class DefaultSteering implements Steering {
             reason: 'finished',
           })
         : new Promise<SteeringOutcome>(resolve => {
-            this.pending.push({ id, message: userMessage, resolve });
+            target.push({ id, message: userMessage, resolve });
           });
 
     this.outcomes.set(id, outcome);
@@ -168,6 +210,16 @@ class DefaultSteering implements Steering {
       hasPendingMessages: () =>
         this.state === 'running' && this.pending.length > 0,
 
+      promoteQueuedMessage: () => {
+        const next = this.state === 'running' ? this.queued.shift() : undefined;
+        if (next == null) {
+          return false;
+        }
+
+        this.pending.push(next);
+        return true;
+      },
+
       takeMessages: () => {
         if (this.state !== 'running') {
           return [];
@@ -207,9 +259,10 @@ class DefaultSteering implements Steering {
           return;
         }
 
-        const notDelivered = [...this.taken, ...this.pending];
+        const notDelivered = [...this.taken, ...this.pending, ...this.queued];
         this.taken = [];
         this.pending = [];
+        this.queued = [];
         this.state = 'ended';
 
         for (const { id, message, resolve } of notDelivered) {

package/src/generate-text/stream-text.ts

@@ -3389,7 +3389,15 @@ class DefaultStreamTextResult<
                       clientToolCalls.length === 0 &&
                       pendingDeferredToolCalls.size === 0
                     ) {
-                      if (!steeringRun?.hasPendingMessages()) {
+                      // queued messages wait for a task that was not cut off:
+                      const isTruncated =
+                        stepFinishReason === 'length' ||
+                        stepFinishReason === 'content-filter';
+
+                      if (
+                        !steeringRun?.hasPendingMessages() &&
+                        (isTruncated || !steeringRun?.promoteQueuedMessage())
+                      ) {
                         return false;
                       }
 

package/src/ui/process-ui-message-stream.ts

@@ -1056,7 +1056,9 @@ export function processUIMessageStream<UI_MESSAGE extends UIMessage>({
             default: {
               if (isDataUIMessageChunk(chunk)) {
                 // validate data chunk if dataPartSchemas is provided
-                if (dataPartSchemas?.[chunk.type] != null) {
+                // (schemas are keyed by the part name without the 'data-' prefix)
+                const dataPartSchema = dataPartSchemas?.[chunk.type.slice(5)];
+                if (dataPartSchema != null) {
                   const partIdx = state.message.parts.findIndex(
                     p =>
                       'id' in p &&
@@ -1069,7 +1071,7 @@ export function processUIMessageStream<UI_MESSAGE extends UIMessage>({
 
                   await validateTypes({
                     value: chunk.data,
-                    schema: dataPartSchemas[chunk.type],
+                    schema: dataPartSchema,
                     context: {
                       field: `message.parts[${actualPartIdx}].data`,
                       entityName: chunk.type,