ai 6.0.40 → 6.0.42

package/docs/02-getting-started/06-nodejs.mdx

@@ -5,7 +5,7 @@ description: Learn how to build your first agent with the AI SDK and Node.js.
 
 # Node.js Quickstart
 
-The AI SDK is a powerful Typescript library designed to help developers build AI-powered applications.
+The AI SDK is a powerful TypeScript library designed to help developers build AI-powered applications.
 
 In this quickstart tutorial, you'll build a simple agent with a streaming chat user interface. Along the way, you'll learn key concepts and techniques that are fundamental to using the SDK in your own projects.
 
@@ -47,7 +47,7 @@ pnpm add ai zod dotenv
 pnpm add -D @types/node tsx typescript
 ```
 
-The `ai` package contains the AI SDK. You will use `zod` to define type-safe schemas that you will pass to the large language model (LLM). You will use `dotenv` to access environment variables (your Vercel AI Gateway key) within your application. There are also three development dependencies, installed with the `-D` flag, that are necessary to run your Typescript code.
+The `ai` package contains the AI SDK. You will use `zod` to define type-safe schemas that you will pass to the large language model (LLM). You will use `dotenv` to access environment variables (your Vercel AI Gateway key) within your application. There are also three development dependencies, installed with the `-D` flag, that are necessary to run your TypeScript code.
 
 ### Configure Vercel AI Gateway API key
 

package/docs/02-getting-started/07-expo.mdx

@@ -105,7 +105,7 @@ export async function POST(req: Request) {
 Let's take a look at what is happening in this code:
 
 1. Define an asynchronous `POST` request handler and extract `messages` from the body of the request. The `messages` variable contains a history of the conversation between you and the chatbot and provides the chatbot with the necessary context to make the next generation.
-2. Call [`streamText`](/docs/reference/ai-sdk-core/stream-text), which is imported from the `ai` package. This function accepts a configuration object that contains a `model` provider (imported from `ai`) and `messages` (defined in step 1). You can pass additional [settings](/docs/ai-sdk-core/settings) to further customise the model's behaviour.
+2. Call [`streamText`](/docs/reference/ai-sdk-core/stream-text), which is imported from the `ai` package. This function accepts a configuration object that contains a `model` provider (imported from `ai`) and `messages` (defined in step 1). You can pass additional [settings](/docs/ai-sdk-core/settings) to further customize the model's behavior.
 3. The `streamText` function returns a [`StreamTextResult`](/docs/reference/ai-sdk-core/stream-text#result-object). This result object contains the [ `toUIMessageStreamResponse` ](/docs/reference/ai-sdk-core/stream-text#to-ui-message-stream-response) function which converts the result to a streamed response object.
 4. Finally, return the result to the client to stream the response.
 

package/docs/02-getting-started/08-tanstack-start.mdx

@@ -5,7 +5,7 @@ description: Learn how to build your first agent with the AI SDK and TanStack St
 
 # TanStack Start Quickstart
 
-The AI SDK is a powerful Typescript library designed to help developers build AI-powered applications.
+The AI SDK is a powerful TypeScript library designed to help developers build AI-powered applications.
 
 In this quickstart tutorial, you'll build a simple agent with a streaming chat user interface. Along the way, you'll learn key concepts and techniques that are fundamental to using the AI SDK in your own projects.
 
@@ -109,7 +109,7 @@ export const Route = createFileRoute('/api/chat')({
 Let's take a look at what is happening in this code:
 
 1. Define an asynchronous `POST` request handler using TanStack Start's server routes and extract `messages` from the body of the request. The `messages` variable contains a history of the conversation between you and the chatbot and provides the chatbot with the necessary context to make the next generation. The `messages` are of UIMessage type, which are designed for use in application UI - they contain the entire message history and associated metadata like timestamps.
-2. Call [`streamText`](/docs/reference/ai-sdk-core/stream-text), which is imported from the `ai` package. This function accepts a configuration object that contains a `model` provider and `messages` (defined in step 1). You can pass additional [settings](/docs/ai-sdk-core/settings) to further customise the model's behaviour. The `messages` key expects a `ModelMessage[]` array. This type is different from `UIMessage` in that it does not include metadata, such as timestamps or sender information. To convert between these types, we use the `convertToModelMessages` function, which strips the UI-specific metadata and transforms the `UIMessage[]` array into the `ModelMessage[]` format that the model expects.
+2. Call [`streamText`](/docs/reference/ai-sdk-core/stream-text), which is imported from the `ai` package. This function accepts a configuration object that contains a `model` provider and `messages` (defined in step 1). You can pass additional [settings](/docs/ai-sdk-core/settings) to further customize the model's behavior. The `messages` key expects a `ModelMessage[]` array. This type is different from `UIMessage` in that it does not include metadata, such as timestamps or sender information. To convert between these types, we use the `convertToModelMessages` function, which strips the UI-specific metadata and transforms the `UIMessage[]` array into the `ModelMessage[]` format that the model expects.
 3. The `streamText` function returns a [`StreamTextResult`](/docs/reference/ai-sdk-core/stream-text#result-object). This result object contains the [ `toUIMessageStreamResponse` ](/docs/reference/ai-sdk-core/stream-text#to-data-stream-response) function which converts the result to a streamed response object.
 4. Finally, return the result to the client to stream the response.
 

package/docs/05-ai-sdk-rsc/03-generative-ui-state.mdx

@@ -44,7 +44,7 @@ For a chat app, the AI State is the conversation history (messages) between the
 
 ### UI State
 
-UI State refers to the state of your application that is rendered on the client. It is a fully client-side state (similar to `useState`) that can store anything from Javascript values to React elements. UI state is a list of actual UI elements that are rendered on the client.
+UI State refers to the state of your application that is rendered on the client. It is a fully client-side state (similar to `useState`) that can store anything from JavaScript values to React elements. UI state is a list of actual UI elements that are rendered on the client.
 
 <Note>**Note**: UI State can only be accessed client-side.</Note>
 

package/docs/05-ai-sdk-rsc/05-streaming-values.mdx

@@ -32,7 +32,7 @@ There are two functions provided by the RSC API that allow you to create streama
 
 ## `createStreamableValue`
 
-The RSC API allows you to stream serializable Javascript values from the server to the client using [`createStreamableValue`](/docs/reference/ai-sdk-rsc/create-streamable-value), such as strings, numbers, objects, and arrays.
+The RSC API allows you to stream serializable JavaScript values from the server to the client using [`createStreamableValue`](/docs/reference/ai-sdk-rsc/create-streamable-value), such as strings, numbers, objects, and arrays.
 
 This is useful when you want to stream:
 

package/docs/06-advanced/02-stopping-streams.mdx

@@ -5,10 +5,10 @@ description: Learn how to cancel streams with the AI SDK
 
 # Stopping Streams
 
-Cancelling ongoing streams is often needed.
+Canceling ongoing streams is often needed.
 For example, users might want to stop a stream when they realize that the response is not what they want.
 
-The different parts of the AI SDK support cancelling streams in different ways.
+The different parts of the AI SDK support canceling streams in different ways.
 
 ## AI SDK Core
 

package/docs/07-reference/02-ai-sdk-ui/01-use-chat.mdx

@@ -282,13 +282,6 @@ Allows you to easily create a conversational user interface for your chatbot app
               description:
                 'The reason why the model finished generating the response. Undefined if the finish reason was not provided by the model.',
             },
-            {
-              name: 'usage',
-              type: 'LanguageModelUsage',
-              isOptional: true,
-              description:
-                'Token usage information for the response, including inputTokens, outputTokens, and totalTokens.',
-            },
           ],
         },
       ],

package/docs/07-reference/02-ai-sdk-ui/02-use-completion.mdx

@@ -50,7 +50,7 @@ Allows you to create text completion based capabilities for your application. It
       name: 'id',
       type: 'string',
       description:
-        'An unique identifier for the completion. If not provided, a random one will be generated. When provided, the `useCompletion` hook with the same `id` will have shared states across components. This is useful when you have multiple components showing the same chat stream',
+        'A unique identifier for the completion. If not provided, a random one will be generated. When provided, the `useCompletion` hook with the same `id` will have shared states across components. This is useful when you have multiple components showing the same chat stream',
     },
     {
       name: 'initialInput',

package/docs/08-migration-guides/26-migration-guide-5-0.mdx

@@ -3104,7 +3104,7 @@ const result = await generateObject({
   }),
   providerOptions: {
     openai: {
-      strictSchemas: true, // default behaviour in AI SDK 4
+      strictSchemas: true, // default behavior in AI SDK 4
     } satisfies OpenAIResponsesProviderOptions,
   },
 });
@@ -3122,7 +3122,7 @@ const result = await generateObject({
   }),
   providerOptions: {
     openai: {
-      strictJsonSchema: true, // defaults to false, opt back in to the AI SDK 4 strict behaviour
+      strictJsonSchema: true, // defaults to false, opt back in to the AI SDK 4 strict behavior
     } satisfies OpenAIResponsesProviderOptions,
   },
 });

package/docs/09-troubleshooting/15-abort-breaks-resumable-streams.mdx

@@ -45,7 +45,7 @@ If you need to allow users to stop streams manually:
 ```tsx
 const { messages, sendMessage, stop } = useChat({
   id: chatId,
-  resume: false, // Disable stream resumption (default behaviour)
+  resume: false, // Disable stream resumption (default behavior)
 });
 ```
 

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai",
-  "version": "6.0.40",
+  "version": "6.0.42",
   "description": "AI SDK by Vercel - The AI Toolkit for TypeScript and JavaScript",
   "license": "Apache-2.0",
   "sideEffects": false,
@@ -42,7 +42,7 @@
   },
   "dependencies": {
     "@opentelemetry/api": "1.9.0",
-    "@ai-sdk/gateway": "3.0.16",
+    "@ai-sdk/gateway": "3.0.17",
     "@ai-sdk/provider": "3.0.4",
     "@ai-sdk/provider-utils": "4.0.8"
   },

package/src/agent/create-agent-ui-stream-response.test.ts

@@ -245,7 +245,7 @@ describe('createAgentUIStreamResponse', () => {
           "data: {"type":"finish-step"}
 
         ",
-          "data: {"type":"finish","finishReason":"stop","usage":{"inputTokens":10,"inputTokenDetails":{"noCacheTokens":10},"outputTokens":10,"outputTokenDetails":{"textTokens":10},"totalTokens":20}}
+          "data: {"type":"finish","finishReason":"stop"}
 
         ",
           "data: [DONE]

package/src/generate-text/__snapshots__/stream-text.test.ts.snap

@@ -655,7 +655,7 @@ exports[`streamText > result.pipeUIMessageStreamToResponse > should mask error m
   "data: {"type":"finish-step"}
 
 ",
-  "data: {"type":"finish","finishReason":"error","usage":{"inputTokenDetails":{},"outputTokenDetails":{}}}
+  "data: {"type":"finish","finishReason":"error"}
 
 ",
   "data: [DONE]
@@ -678,7 +678,7 @@ exports[`streamText > result.pipeUIMessageStreamToResponse > should support cust
   "data: {"type":"finish-step"}
 
 ",
-  "data: {"type":"finish","finishReason":"error","usage":{"inputTokenDetails":{},"outputTokenDetails":{}}}
+  "data: {"type":"finish","finishReason":"error"}
 
 ",
   "data: [DONE]
@@ -803,22 +803,6 @@ exports[`streamText > result.toUIMessageStream > should mask error messages by d
   {
     "finishReason": "error",
     "type": "finish",
-    "usage": {
-      "cachedInputTokens": undefined,
-      "inputTokenDetails": {
-        "cacheReadTokens": undefined,
-        "cacheWriteTokens": undefined,
-        "noCacheTokens": undefined,
-      },
-      "inputTokens": undefined,
-      "outputTokenDetails": {
-        "reasoningTokens": undefined,
-        "textTokens": undefined,
-      },
-      "outputTokens": undefined,
-      "reasoningTokens": undefined,
-      "totalTokens": undefined,
-    },
   },
 ]
 `;
@@ -865,22 +849,6 @@ exports[`streamText > result.toUIMessageStream > should send tool call, tool cal
   {
     "finishReason": "stop",
     "type": "finish",
-    "usage": {
-      "cachedInputTokens": undefined,
-      "inputTokenDetails": {
-        "cacheReadTokens": undefined,
-        "cacheWriteTokens": undefined,
-        "noCacheTokens": 3,
-      },
-      "inputTokens": 3,
-      "outputTokenDetails": {
-        "reasoningTokens": undefined,
-        "textTokens": 10,
-      },
-      "outputTokens": 10,
-      "reasoningTokens": undefined,
-      "totalTokens": 13,
-    },
   },
 ]
 `;
@@ -903,22 +871,6 @@ exports[`streamText > result.toUIMessageStream > should support custom error mes
   {
     "finishReason": "error",
     "type": "finish",
-    "usage": {
-      "cachedInputTokens": undefined,
-      "inputTokenDetails": {
-        "cacheReadTokens": undefined,
-        "cacheWriteTokens": undefined,
-        "noCacheTokens": undefined,
-      },
-      "inputTokens": undefined,
-      "outputTokenDetails": {
-        "reasoningTokens": undefined,
-        "textTokens": undefined,
-      },
-      "outputTokens": undefined,
-      "reasoningTokens": undefined,
-      "totalTokens": undefined,
-    },
   },
 ]
 `;
@@ -937,7 +889,7 @@ exports[`streamText > result.toUIMessageStreamResponse > should mask error messa
   "data: {"type":"finish-step"}
 
 ",
-  "data: {"type":"finish","finishReason":"error","usage":{"inputTokenDetails":{},"outputTokenDetails":{}}}
+  "data: {"type":"finish","finishReason":"error"}
 
 ",
   "data: [DONE]
@@ -960,7 +912,7 @@ exports[`streamText > result.toUIMessageStreamResponse > should support custom e
   "data: {"type":"finish-step"}
 
 ",
-  "data: {"type":"finish","finishReason":"error","usage":{"inputTokenDetails":{},"outputTokenDetails":{}}}
+  "data: {"type":"finish","finishReason":"error"}
 
 ",
   "data: [DONE]