ai 7.0.116 → 7.0.117

package/CHANGELOG.md

@@ -1,5 +1,12 @@
 # ai
 
+## 7.0.117
+
+### Patch Changes
+
+- Updated dependencies [b67b1b7]
+  - @ai-sdk/gateway@4.0.95
+
 ## 7.0.116
 
 ### Patch Changes

package/dist/index.js

@@ -1328,7 +1328,7 @@ import {
 } from "@ai-sdk/provider-utils";
 
 // src/version.ts
-var VERSION = true ? "7.0.116" : "0.0.0-test";
+var VERSION = true ? "7.0.117" : "0.0.0-test";
 
 // src/util/download/download.ts
 var download = async ({

package/dist/internal/index.js

@@ -90,7 +90,7 @@ import {
 } from "@ai-sdk/provider-utils";
 
 // src/version.ts
-var VERSION = true ? "7.0.116" : "0.0.0-test";
+var VERSION = true ? "7.0.117" : "0.0.0-test";
 
 // src/util/download/download.ts
 var download = async ({

package/docs/03-agents/02-building-agents.mdx

@@ -140,8 +140,8 @@ Context](/docs/ai-sdk-core/runtime-and-tool-context).
 ### Tools That Use Experimental Sandboxes
 
 Pass `experimental_sandbox` when an agent tool needs a command or code execution
-environment. The experimental sandbox is a per-call value, so provide it to `generate()`,
-`stream()`, or the agent UI stream helper that invokes the agent.
+environment. The experimental sandbox is a per-call value, so provide it to
+`generate()`, `stream()`, or the agent UI stream helper that invokes the agent.
 
 ```ts highlight="13,19-23,31"
 const agent = new ToolLoopAgent({

package/docs/03-ai-sdk-core/17-mcp-apps.mdx

@@ -242,7 +242,7 @@ export default function Chat() {
 }
 ```
 
-`experimental_MCPAppRenderer` renders nothing for ordinary tools. For app-backed tools, it loads the resource, creates the sandbox bridge, sends tool input and result notifications to the iframe, and forwards supported app requests through your handlers.
+For ordinary tools, `experimental_MCPAppRenderer` renders the provided `fallback` (or nothing when no fallback is provided). For app-backed tools, it loads the resource, creates the sandbox bridge, sends tool input and result notifications to the iframe, and forwards supported app requests through your handlers.
 
 ## Best Practices
 

package/docs/03-ai-sdk-core/26-reasoning.mdx

@@ -77,9 +77,9 @@ This design lets you use the portable `reasoning` parameter by default and fall
 
 ## Provider Support
 
-The `reasoning` parameter is supported by the following providers: OpenAI, Anthropic, Google, xAI, Groq, DeepSeek, Fireworks, and Amazon Bedrock. Each provider translates the value to its native reasoning API. Some providers support all six levels natively, while others coerce to fewer levels (a warning is emitted when coercion occurs). Some providers use a numeric token budget instead of an enum for reasoning control; in those cases the top-level `reasoning` value is mapped to a budget calculated as a percentage of the model's maximum output tokens.
+The `reasoning` parameter is supported by the following providers: OpenAI, Anthropic, Google, xAI, Groq, DeepSeek, Fireworks, Amazon Bedrock, and Perplexity. Each provider translates the value to its native reasoning API. Some providers support all six levels natively, while others coerce to fewer levels (a warning is emitted when coercion occurs). Some providers use a numeric token budget instead of an enum for reasoning control; in those cases the top-level `reasoning` value is mapped to a budget calculated as a percentage of the model's maximum output tokens.
 
-Providers that do not support reasoning (e.g. Mistral, Perplexity, Cohere) emit an `unsupported` warning and ignore the parameter.
+Providers that do not support reasoning (e.g. Mistral and Cohere) emit an `unsupported` warning and ignore the parameter.
 
 ## Migrating from `providerOptions`
 

package/docs/03-ai-sdk-core/32-evaluation.mdx

@@ -132,7 +132,7 @@ with `AI_GATEWAY_API_KEY` or Vercel OIDC, then pass a Gateway model ID:
 import { experimental_evaluate } from 'ai';
 
 const result = await experimental_evaluate({
-  model: 'typesafe-ai/jev-latest',
+  model: 'typesafe-ai/jev',
   state: 'I was charged twice. Please refund the extra charge.',
   questions: {
     refund: {
@@ -246,8 +246,8 @@ if (result.answers.requestsRefund.probability >= 0.8) {
 The model's `supportedQuestionTypes` are checked before calling the provider.
 Any unsupported question fails the entire call with
 `Experimental_EvaluationUnsupportedQuestionTypeError`. Successful calls return
-an answer for every question; there is no partial success or automatic model
-substitution.
+an answer for every question; there is no partial success, and Core does not
+substitute models automatically.
 
 Invalid inputs throw `InvalidArgumentError`. Missing answers, mismatched answer
 types, invalid options, scores, or probabilities throw `InvalidResponseDataError`.
@@ -266,7 +266,10 @@ For tests, use `Experimental_EvaluationMockModelV4` from `ai/test`.
 Evaluation currently returns one complete result for one shared state. It does
 not stream answers, perform multilabel classification, or batch unrelated
 states. Run separate calls for separate states. Provider support and judgment
-quality depend on the chosen model; the SDK does not choose a model automatically.
+quality depend on the chosen model. Core does not choose another model, but a
+provider can implement routing through its provider options. For example, AI
+Gateway supports conditional evaluation fallbacks under
+`providerOptions.gateway.models`.
 
 Runnable examples are in
 [`examples/ai-functions/src/evaluate`](https://github.com/vercel/ai/tree/main/examples/ai-functions/src/evaluate),

package/docs/03-ai-sdk-core/65-lifecycle-callbacks.mdx

@@ -301,8 +301,10 @@ This distinction matters when the step includes local tool execution: the step d
 
 ## Runtime and Tool Context
 
-Lifecycle callbacks receive the full `runtimeContext` and `toolsContext` values that flow through the call.
-This makes callbacks useful for attaching application context without changing prompts or tool inputs.
+Generation and step lifecycle callbacks receive the full `runtimeContext` and
+`toolsContext` values that flow through the call. Tool-execution callbacks receive
+the scoped `toolContext` for the tool being executed. This makes callbacks useful
+for attaching application context without changing prompts or tool inputs.
 
 ```tsx highlight="8-24,26-39"
 import { generateText, tool } from 'ai';
@@ -349,8 +351,9 @@ const result = await generateText({
 
 <Note>
   Telemetry integrations can filter `runtimeContext` and `toolsContext` before
-  exporting them. Lifecycle callbacks receive the full context objects. Be
-  careful not to log secrets or sensitive user data from callbacks.
+  exporting them. Generation and step callbacks receive the full context
+  objects; tool-execution callbacks receive scoped tool context. Be careful not
+  to log secrets or sensitive user data from callbacks.
 </Note>
 
 ## Available Callbacks

package/docs/03-ai-sdk-harnesses/01-overview.mdx

@@ -9,8 +9,9 @@ The AI SDK harness abstraction lets you run established agent harnesses through
 single AI SDK surface. A harness is a complete agent runtime, such as Claude
 Code, Codex, or Pi. It owns capabilities that are larger than a model call:
 workspace access, built-in coding tools, native session state, compaction,
-permission flows, and runtime-specific configuration. Additionally, all AI SDK
-agent harnesses operate in a sandbox, keeping the host environment safe.
+permission flows, and runtime-specific configuration. Harness adapters can run
+the runtime in a sandbox, but their execution environments differ by adapter;
+review the adapter's runtime location and security guidance before use.
 
 The AI SDK harness abstraction is separate from the provider/model abstraction.
 Providers expose models to AI SDK Core functions such as `generateText` and

package/docs/03-ai-sdk-harnesses/05-harness-adapters.mdx

@@ -38,10 +38,10 @@ The AI SDK includes the following harness adapters:
 | [Claude Code](/providers/ai-sdk-harnesses/claude-code)       | Sandbox bridge   | <Check />    | <Check />     | <Check />         | <Check />              | <Check />                    |
 | [Cline](/providers/ai-sdk-harnesses/cline)                   | Host process     | <Check />    | <Check />     | <Check />         | <Check />              | <Check />                    |
 | [Codex](/providers/ai-sdk-harnesses/codex)                   | Sandbox bridge   | <Check />    | <Check />     | <Check />         | <Cross />              | <Cross />                    |
-| [Cursor](/providers/ai-sdk-harnesses/cursor)                 | Sandbox via ACP  | <Check />    | <Check />     | <Cross />         | <Check />              | <Cross />                    |
+| [Cursor](/providers/ai-sdk-harnesses/cursor)                 | Sandbox via ACP  | <Check />    | <Check />     | <Cross />         | <Cross />              | <Cross />                    |
 | [Deep Agents](/providers/ai-sdk-harnesses/deepagents)        | Sandbox bridge   | <Check />    | <Check />     | <Check />         | <Check />              | <Check /> via auto-rejection |
 | [fx](/providers/ai-sdk-harnesses/fx)                         | Sandbox via ACP  | <Check />    | <Check />     | <Cross />         | <Check />              | <Cross />                    |
-| [GitHub Copilot](/providers/ai-sdk-harnesses/github-copilot) | Sandbox via ACP  | <Check />    | <Check />     | <Cross />         | <Check />              | <Cross />                    |
-| [Grok Build](/providers/ai-sdk-harnesses/grok-build)         | Sandbox via ACP  | <Check />    | <Check />     | <Check />         | <Check />              | <Cross />                    |
+| [GitHub Copilot](/providers/ai-sdk-harnesses/github-copilot) | Sandbox via ACP  | <Check />    | <Check />     | <Cross />         | <Cross />              | <Cross />                    |
+| [Grok Build](/providers/ai-sdk-harnesses/grok-build)         | Sandbox via ACP  | <Check />    | <Check />     | <Check />         | <Cross />              | <Cross />                    |
 | [OpenCode](/providers/ai-sdk-harnesses/opencode)             | Sandbox bridge   | <Check />    | <Check />     | <Check />         | <Check />              | <Check /> via auto-rejection |
 | [Pi](/providers/ai-sdk-harnesses/pi)                         | Host process     | <Check />    | <Check />     | <Cross />         | <Check />              | <Check />                    |

package/docs/04-ai-sdk-ui/01-overview.mdx

@@ -9,7 +9,7 @@ AI SDK UI is designed to help you build interactive chat, completion, and assist
 
 AI SDK UI provides robust abstractions that simplify the complex tasks of managing chat streams and UI updates on the frontend, enabling you to develop dynamic AI-driven interfaces more efficiently. With three main hooks — **`useChat`**, **`useCompletion`**, and **`useObject`** — you can incorporate real-time chat capabilities, text completions, streamed JSON, and interactive assistant features into your app.
 
-- **[`useChat`](/docs/ai-sdk-ui/chatbot)** offers real-time streaming of chat messages, abstracting state management for inputs, messages, loading, and errors, allowing for seamless integration into any UI design.
+- **[`useChat`](/docs/ai-sdk-ui/chatbot)** offers real-time streaming of chat messages and manages message, loading, and error state. Manage input state in your component for seamless integration into any UI design.
 - **[`useCompletion`](/docs/ai-sdk-ui/completion)** enables you to handle text completions in your applications, managing the prompt input and automatically updating the UI as new completions are streamed.
 - **[`useObject`](/docs/ai-sdk-ui/object-generation)** is a hook that allows you to consume streamed JSON objects, providing a simple way to handle and display structured data in your application.
 

package/docs/04-ai-sdk-ui/02-chatbot.mdx

@@ -1009,10 +1009,12 @@ These are available as `reasoning-file` parts (`ReasoningFileUIPart`) with
 Some providers such as [Perplexity](/providers/ai-sdk-providers/perplexity#sources) and
 [Google](/providers/ai-sdk-providers/google#sources) include sources in the response.
 
-Currently sources are limited to web pages that ground the response.
-You can forward them to the client with the `sendSources` option:
+You can forward sources to the client with the `sendSources` option. This example uses the Perplexity Agent API's `fast` preset to search the web. Install `@ai-sdk/perplexity` and set `PERPLEXITY_API_KEY` in your environment:
 
-```ts filename="app/api/chat/route.ts" highlight="20"
+<InstallPackages packages="@ai-sdk/perplexity" />
+
+```ts filename="app/api/chat/route.ts" highlight="21"
+import { perplexity } from '@ai-sdk/perplexity';
 import {
   convertToModelMessages,
   createUIMessageStreamResponse,
@@ -1025,7 +1027,7 @@ export async function POST(req: Request) {
   const { messages }: { messages: UIMessage[] } = await req.json();
 
   const result = streamText({
-    model: 'perplexity/sonar-pro',
+    model: perplexity('fast'),
     messages: await convertToModelMessages(messages),
   });
 
@@ -1051,7 +1053,7 @@ messages.map(message => (
     {message.parts
       .filter(part => part.type === 'source-url')
       .map(part => (
-        <span key={`source-${part.id}`}>
+        <span key={`source-${part.sourceId}`}>
           [
           <a href={part.url} target="_blank">
             {part.title ?? new URL(part.url).hostname}
@@ -1064,8 +1066,8 @@ messages.map(message => (
     {message.parts
       .filter(part => part.type === 'source-document')
       .map(part => (
-        <span key={`source-${part.id}`}>
-          [<span>{part.title ?? `Document ${part.id}`}</span>]
+        <span key={`source-${part.sourceId}`}>
+          [<span>{part.title ?? `Document ${part.sourceId}`}</span>]
         </span>
       ))}
   </div>

package/docs/04-ai-sdk-ui/08-object-generation.mdx

@@ -5,7 +5,10 @@ description: Learn how to use the useObject hook.
 
 # Object Generation
 
-<Note>`useObject` is only available in React, Svelte, and Vue.</Note>
+<Note>
+  `useObject` is available in React, Svelte, Vue, and the SolidJS community
+  integration. Angular provides the equivalent `StructuredObject` service.
+</Note>
 
 The [`useObject`](/docs/reference/ai-sdk-ui/use-object) hook allows you to create interfaces that represent a structured JSON object that is being streamed.
 

package/docs/06-advanced/04-caching.mdx

@@ -30,6 +30,7 @@ const redis = new Redis({
 });
 
 export const cacheMiddleware: LanguageModelV4Middleware = {
+  specificationVersion: 'v4',
   wrapGenerate: async ({ doGenerate, params }) => {
     const cacheKey = JSON.stringify(params);
 
@@ -117,7 +118,7 @@ export const cacheMiddleware: LanguageModelV4Middleware = {
   replayed from the cache on later requests.
 </Note>
 
-`LanguageModelV4Middleware` has two methods: `wrapGenerate` and `wrapStream`. `wrapGenerate` is called when using [`generateText`](/docs/reference/ai-sdk-core/generate-text), while `wrapStream` is called when using [`streamText`](/docs/reference/ai-sdk-core/stream-text).
+`LanguageModelV4Middleware` has the `wrapGenerate` and `wrapStream` wrapping methods, plus the optional `transformParams` method. `wrapGenerate` is called when using [`generateText`](/docs/reference/ai-sdk-core/generate-text), while `wrapStream` is called when using [`streamText`](/docs/reference/ai-sdk-core/stream-text).
 
 For `wrapGenerate`, you can cache the response directly. Instead, for `wrapStream`, you cache an array of the stream parts, which can then be used with [`simulateReadableStream`](/docs/ai-sdk-core/testing#simulate-ui-message-stream-responses) function to create a simulated `ReadableStream` that returns the cached response. In this way, the cached response is returned chunk-by-chunk as if it were being generated by the model. You can control the initial delay and delay between chunks by adjusting the `initialDelayInMs` and `chunkDelayInMs` parameters of `simulateReadableStream`.
 

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

@@ -1071,7 +1071,7 @@ To see `generateText` in action, check out [these examples](#examples).
               name: 'Output.json()',
               type: 'Output',
               description:
-                'Output specification for unstructured JSON generation. When the model generates a text response, it will return a JSON object.',
+                'Output specification for unstructured JSON generation. When the model generates a text response, it will return any valid JSON value.',
               properties: [
                 {
                   type: 'Options',

package/docs/07-reference/02-ai-sdk-ui/03-use-object.mdx

@@ -5,7 +5,10 @@ description: API reference for the useObject hook.
 
 # `useObject()`
 
-<Note>`useObject` is only available in React, Svelte, and Vue.</Note>
+<Note>
+  `useObject` is available in React, Svelte, Vue, and the SolidJS community
+  integration. Angular provides the equivalent `StructuredObject` service.
+</Note>
 
 Allows you to consume text streams that represent a JSON object and parse them into a complete object based on a schema.
 You can use it together with [`streamText`](/docs/reference/ai-sdk-core/stream-text) and [`Output.object()`](/docs/reference/ai-sdk-core/output#output-object) in the backend.

package/docs/07-reference/03-ai-sdk-rsc/01-stream-ui.mdx

@@ -36,6 +36,7 @@ To see `streamUI` in action, check out [these examples](#examples).
     },
     {
       name: 'instructions',
+      isOptional: true,
       type: 'Instructions',
       description:
         'Instructions to use that specify the behavior of the model.'

package/docs/07-reference/03-ai-sdk-rsc/02-create-ai.mdx

@@ -40,7 +40,7 @@ Creates a client-server context provider that can be used to wrap parts of your
     },
     {
       name: 'onGetUIState',
-      type: '() => UIState',
+      type: '() => Promise<UIState | undefined>',
       description: 'is called during SSR to compare and update UI state.',
     },
     {

package/docs/07-reference/03-ai-sdk-rsc/03-create-streamable-ui.mdx

@@ -72,7 +72,7 @@ Create a stream that sends UI from the server to the client. On the client side,
     },
     {
       name: 'error',
-      type: '(Error) => void',
+      type: '(any) => StreamableUIWrapper',
       description:
         'Signals that there is an error in the UI stream. It will be thrown on the client side and caught by the nearest error boundary component.',
     },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai",
-  "version": "7.0.116",
+  "version": "7.0.117",
   "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",
@@ -42,18 +42,18 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/gateway": "4.0.94",
+    "@ai-sdk/gateway": "4.0.95",
     "@ai-sdk/provider": "4.0.18",
     "@ai-sdk/provider-utils": "5.0.49"
   },
   "devDependencies": {
-    "@ai-sdk/amazon-bedrock": "5.0.96",
+    "@ai-sdk/amazon-bedrock": "5.0.97",
     "@ai-sdk/deepseek": "3.0.54",
     "@ai-sdk/google": "4.0.82",
     "@ai-sdk/groq": "4.0.50",
     "@ai-sdk/huggingface": "2.0.57",
     "@ai-sdk/moonshotai": "3.0.58",
-    "@ai-sdk/openai": "4.0.77",
+    "@ai-sdk/openai": "4.0.78",
     "@ai-sdk/test-server": "2.0.2",
     "@ai-sdk/xai": "5.0.10",
     "@edge-runtime/vm": "^5.0.0",