ai 7.0.155 → 7.0.157

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

@@ -24,7 +24,7 @@ The `reasoning` parameter accepts the following values:
 | Value                | Behavior                                                             |
 | -------------------- | -------------------------------------------------------------------- |
 | `'provider-default'` | Use the provider's default reasoning behavior (default when omitted) |
-| `'none'`             | Disable reasoning                                                    |
+| `'none'`             | Disable reasoning (lowest reasoning level if it cannot be disabled)  |
 | `'minimal'`          | Bare-minimum reasoning                                               |
 | `'low'`              | Fast, concise reasoning                                              |
 | `'medium'`           | Balanced reasoning                                                   |
@@ -80,9 +80,15 @@ This design lets you use the portable `reasoning` parameter by default and fall
 
 The `reasoning` parameter is supported by providers including OpenAI, Anthropic, Google, xAI, Groq, DeepSeek, Moonshot AI, Fireworks, Amazon Bedrock, Mistral, Cohere, Alibaba, Open Responses, OpenAI Compatible, and Perplexity. Each provider translates the value to its native reasoning API.
 
-Providers with a distinct native maximum tier, such as supported OpenAI, Anthropic, DeepSeek, and Moonshot AI models, receive `'max'` directly. Amazon Bedrock preserves `'max'` for its Anthropic and OpenAI effort mappings, while Amazon Nova 2 maps `'xhigh'` and `'max'` to `'high'` with a compatibility warning. Providers whose highest native tier is lower coerce `'max'` to their closest supported tier and emit a compatibility warning when their adapter supports warning propagation. OpenAI-compatible and Open Responses endpoints receive `'max'` directly so compatible servers can interpret it.
+### How values are mapped
 
-Some providers use a numeric token budget instead of an enum for reasoning control. In those cases, `'max'` maps to 95% of the model's maximum output tokens by default, subject to the provider's minimum and maximum reasoning budget limits.
+When a model does not support the requested value, the provider uses the closest supported value, rounding down. The values are ordered `none` < `minimal` < `low` < `medium` < `high` < `xhigh` < `max`, so `'xhigh'` becomes `'high'` on a model without an `xhigh` level. If there is no lower value, the next higher one is used.
+
+Rounding never turns reasoning off: other values never map to `'none'`, and `'none'` on a model that cannot disable reasoning maps to the model's lowest level. Providers emit a `compatibility` warning whenever the value they send differs from the requested value. Values set in `providerOptions` are sent unchanged (see [Precedence Rules](#precedence-rules)).
+
+Providers only round values for models and model families they recognize by model ID, so newer versions of a known family use that family's levels. Unrecognized model IDs, such as fine-tuned or custom models, and OpenAI-compatible and Open Responses endpoints receive the value directly and the API decides whether it is supported.
+
+For providers that use a token budget, the value maps to a percentage of the model's maximum output tokens (`'max'` maps to 95% by default), within the provider's budget limits.
 
 Maximum reasoning can substantially increase token usage, latency, cost, and the chance of reaching request or output limits. Use it when the model's additional reasoning depth is worth those tradeoffs.
 

package/docs/03-ai-sdk-harnesses/03-tools.mdx

@@ -272,12 +272,42 @@ const agent = new HarnessAgent({
 `toolApproval` accepts the same status values as AI SDK tool approval status
 objects: `not-applicable`, `approved`, `user-approval`, and `denied`.
 
+When a host tool call is denied, the model and response messages receive an
+`execution-denied` tool result with the denial reason, if provided. The tool's
+`execute` and `toModelOutput` functions are not called for the denial.
+
 When approval is required, the stream pauses after a `tool-approval-request`.
 Continue the same session by sending a tool approval response message. In UI
 flows, `useChat` sends those messages for you when you add the approval result.
 In direct agent code, pass the approval response as `messages` on the next
 `stream()` or `generate()` call.
 
+### Native Tool Names
+
+Built-in tool calls use the harness tool name, such as `bash`, `write`, or
+`edit`, while their input follows the underlying runtime's schema. When an
+adapter supplies a different native name, `HarnessAgent` exposes it as
+`providerMetadata[harnessId].nativeToolName` on the streamed `tool-call` and
+on the `toolCall` inside a `tool-approval-request`.
+
+For example, a Claude Code approval request for `bash` includes
+`toolCall.providerMetadata['claude-code'].nativeToolName: 'Bash'`. An approval
+gate that works with Claude Code's native tool names can read it without
+changing the harness-facing `toolName` or interpreting the input shape:
+
+```ts
+for await (const part of result.fullStream) {
+  if (part.type === 'tool-approval-request') {
+    const nativeToolName =
+      part.toolCall.providerMetadata?.['claude-code']?.nativeToolName;
+    console.log(nativeToolName ?? part.toolCall.toolName, part.toolCall.input);
+  }
+}
+```
+
+The metadata field is omitted when the adapter does not supply a native name
+or when it matches `toolName`. Existing provider metadata is preserved.
+
 ## Built-in Approval Support
 
 Most adapters can pause built-in tool calls for approval. Adapters that do not

package/docs/07-reference/01-ai-sdk-core/29-filter-active-tools.mdx

@@ -5,8 +5,6 @@ description: Filter a tool set to the currently active tools (API Reference)
 
 # `filterActiveTools()`
 
-<Note type="warning">`filterActiveTools` is an experimental feature.</Note>
-
 `filterActiveTools` filters a tool set to only the string tool names listed in `activeTools`.
 If `activeTools` is `undefined`, it returns the original tool set.
 If `tools` is `undefined`, it returns `undefined`.
@@ -14,7 +12,7 @@ If `tools` is `undefined`, it returns `undefined`.
 `filterActiveTools` is useful for limiting which tools are sent to a model in a particular step.
 
 ```ts
-import { experimental_filterActiveTools as filterActiveTools, tool } from 'ai';
+import { filterActiveTools, tool } from 'ai';
 import { z } from 'zod';
 
 const tools = {
@@ -38,10 +36,7 @@ const filteredTools = filterActiveTools({
 
 ## Import
 
-<Snippet
-  text={`import { experimental_filterActiveTools as filterActiveTools } from "ai"`}
-  prompt={false}
-/>
+<Snippet text={`import { filterActiveTools } from "ai"`} prompt={false} />
 
 ## API Signature
 

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

@@ -143,7 +143,7 @@ It also contains the following helper functions:
       href: '/docs/reference/ai-sdk-core/sandbox',
     },
     {
-      title: 'experimental_filterActiveTools()',
+      title: 'filterActiveTools()',
       description: 'Filters a tool set to only the currently active tools.',
       href: '/docs/reference/ai-sdk-core/filter-active-tools',
     },

package/package.json

@@ -1,6 +1,6 @@
 {
   "name": "ai",
-  "version": "7.0.155",
+  "version": "7.0.157",
   "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",
@@ -42,20 +42,20 @@
     }
   },
   "dependencies": {
-    "@ai-sdk/gateway": "4.0.128",
+    "@ai-sdk/gateway": "4.0.130",
     "@ai-sdk/provider": "4.0.34",
-    "@ai-sdk/provider-utils": "5.0.70"
+    "@ai-sdk/provider-utils": "5.0.71"
   },
   "devDependencies": {
-    "@ai-sdk/amazon-bedrock": "5.0.126",
-    "@ai-sdk/deepseek": "3.0.75",
-    "@ai-sdk/google": "4.0.107",
-    "@ai-sdk/groq": "4.0.72",
-    "@ai-sdk/huggingface": "2.0.80",
-    "@ai-sdk/moonshotai": "3.0.80",
-    "@ai-sdk/openai": "4.0.104",
+    "@ai-sdk/amazon-bedrock": "5.0.128",
+    "@ai-sdk/deepseek": "3.0.76",
+    "@ai-sdk/google": "4.0.108",
+    "@ai-sdk/groq": "4.0.73",
+    "@ai-sdk/huggingface": "2.0.81",
+    "@ai-sdk/moonshotai": "3.0.81",
+    "@ai-sdk/openai": "4.0.105",
     "@ai-sdk/test-server": "2.0.4",
-    "@ai-sdk/xai": "5.0.32",
+    "@ai-sdk/xai": "5.0.33",
     "@edge-runtime/vm": "^5.0.0",
     "@smithy/eventstream-codec": "^4.3.3",
     "@smithy/util-utf8": "^4.3.3",

package/src/generate-text/index.ts

@@ -1,6 +1,13 @@
 export type { ActiveTools } from './active-tools';
 export type { ContentPart } from './content-part';
-export { filterActiveTools as experimental_filterActiveTools } from './filter-active-tools';
+export {
+  filterActiveTools,
+
+  /**
+   * @deprecated Use `filterActiveTools` instead.
+   */
+  filterActiveTools as experimental_filterActiveTools,
+} from './filter-active-tools';
 export { generateText, type GenerateTextInclude } from './generate-text';
 export type {
   GenerateTextAbortEvent,
@@ -69,6 +76,11 @@ export {
 } from './stop-condition';
 export {
   streamLanguageModelCall as experimental_streamLanguageModelCall,
+  type LanguageModelStreamPart,
+
+  /**
+   * @deprecated Use `LanguageModelStreamPart` instead. This alias will be removed in v8.
+   */
   type LanguageModelStreamPart as Experimental_LanguageModelStreamPart,
 } from './stream-language-model-call';
 export {

package/src/util/is-node-runtime.ts

@@ -1,3 +1,5 @@
 export function isNodeRuntime(): boolean {
-  return typeof process !== 'undefined' && process.release?.name === 'node';
+  // Access the optional global directly so Edge bundlers do not treat this
+  // runtime check as an unsupported use of the Node.js process API.
+  return globalThis.process?.release?.name === 'node';
 }