@ai-sdk/gateway 4.0.61 → 4.0.63

package/docs/00-ai-gateway.mdx

@@ -765,6 +765,112 @@ token-efficient content controls. Deep synthesis modes and generated summaries
 are intentionally not exposed yet because they have separate pricing from
 standard Search.
 
+#### Tako Search
+
+The Tako Search tool enables models to search the web and Tako's curated knowledge graph in a single call using [Tako's Search API](https://docs.tako.com/documentation/integrating-tako/search/overview). This tool is executed by the AI Gateway and returns token-efficient web excerpts, plus knowledge-graph results that carry structured data, premium source attribution, and an embed-ready visualization.
+
+```ts
+import { gateway, generateText } from 'ai';
+
+const result = await generateText({
+  model: 'openai/gpt-5.4-nano',
+  prompt: 'How has Nvidia quarterly revenue changed over the last two years?',
+  tools: {
+    tako_search: gateway.tools.takoSearch(),
+  },
+});
+
+console.log(result.text);
+console.log('Tool calls:', JSON.stringify(result.toolCalls, null, 2));
+console.log('Tool results:', JSON.stringify(result.toolResults, null, 2));
+```
+
+Configure the search with effort, source selection, and localization defaults. These defaults override values the model includes in a tool call:
+
+```ts
+import { gateway, generateText } from 'ai';
+
+const result = await generateText({
+  model: 'openai/gpt-5.4-nano',
+  prompt: 'AMD vs. Nvidia headcount since 2013',
+  tools: {
+    tako_search: gateway.tools.takoSearch({
+      effort: 'fast',
+      sources: {
+        data: {
+          contentFormat: 'json_compact',
+          includeContents: true,
+          maxRows: 100,
+        },
+        web: {
+          count: 3,
+        },
+      },
+      countryCode: 'US',
+      locale: 'en-US',
+    }),
+  },
+});
+
+console.log(result.text);
+```
+
+The Tako Search tool supports these optional configuration options:
+
+- **effort** _'fast' | 'instant' | 'deep'_ - Search effort. `'fast'` is the balanced default, `'instant'` favors cached low-latency results, and `'deep'` broadens retrieval with reranking at higher cost and latency.
+- **sources** _object_ - Omit to search both curated Tako data and the live web. When set, only source keys present are searched.
+- **sources.web** _object_ - Configure web results:
+  - **count** _number_ - Maximum web results, 1-20.
+  - **category** _'finance' | 'news' | 'sports'_ - Restrict web results to one category.
+  - **includeDomains** / **excludeDomains** _string[]_ - Only return, or drop, results from these bare domains. Up to 20 each.
+  - **publishedAfter** / **publishedBefore** _string_ - Keep results published on or after, or on or before, this `YYYY-MM-DD` date.
+  - **snippetMaxChars** _number_ - Character cap on each result's text excerpt. Defaults to 4,000; maximum 20,000.
+  - **highlights** _boolean_ - Return query-relevant passages as each result's snippet instead of the opening text of the page. The snippet can hold multiple passages joined by `' ... '`, and a page with no highlight returns `snippet: null`. Defaults to `true` in the AI Gateway.
+  - **includeContents** _boolean_ - Inline each page's extracted full text in `content`. **articleContentMaxChars** caps it, defaulting to 30,000 characters (maximum 1,000,000).
+- **sources.data** _object_ - Configure data results:
+  - **count** _number_ - Maximum data results, 1-20. Defaults to 5.
+  - **includeContents** _boolean_ - Inline each card's underlying rows in `content.dataset` as typed, unit-labeled columns.
+  - **contentFormat** _'json_compact' | 'json_records' | 'csv' | 'card_json'_ - Serialization for inlined card data. Defaults to `'json_compact'`.
+  - **maxRows** _number_ - Row cap for inlined card data. Omit to use your account's default inline cap (20 rows on the standard plan); maximum 2,000.
+  - **nodeIds** _string[]_ - Data Graph node IDs to prioritize. Up to 20.
+  - **strict** _boolean_ - Only return cards matching `nodeIds`. Requires at least one `nodeIds` value.
+- **location** _object_ - End-user `{ latitude, longitude }` coordinates for localized results.
+- **countryCode** _string_ - ISO 3166-1 alpha-2 country code, such as `'US'`.
+- **locale** _string_ - BCP-47 locale, such as `'en-US'`.
+- **timezone** _string_ - IANA timezone, such as `'America/New_York'`.
+- **outputSettings** _object_ - Card rendering controls. `forceRefresh` is available only with `'instant'` effort.
+- **includeRelated** _number_ - Number of related search suggestions to include (1-20).
+
+For precise entity matching, quote a phrase in the query and optionally append a label: `"Tesla":PRODUCT price`. Tako treats the quoted phrase as one entity before searching.
+
+The tool works with both `generateText` and `streamText`:
+
+```ts
+import { gateway, streamText } from 'ai';
+
+const result = streamText({
+  model: 'openai/gpt-5.4-nano',
+  prompt: 'What is the latest US inflation rate?',
+  tools: {
+    tako_search: gateway.tools.takoSearch(),
+  },
+});
+
+for await (const part of result.stream) {
+  switch (part.type) {
+    case 'text-delta':
+      process.stdout.write(part.text);
+      break;
+    case 'tool-call':
+      console.log('\nTool call:', JSON.stringify(part, null, 2));
+      break;
+    case 'tool-result':
+      console.log('\nTool result:', JSON.stringify(part, null, 2));
+      break;
+  }
+}
+```
+
 #### Parallel Search
 
 The Parallel Search tool enables models to search the web using [Parallel AI's Search API](https://docs.parallel.ai/api-reference/search-beta/search). This tool is optimized for LLM consumption, returning relevant excerpts from web pages that can replace multiple keyword searches with a single call.

package/package.json

@@ -1,7 +1,7 @@
 {
   "name": "@ai-sdk/gateway",
   "private": false,
-  "version": "4.0.61",
+  "version": "4.0.63",
   "type": "module",
   "license": "Apache-2.0",
   "sideEffects": false,
@@ -32,12 +32,12 @@
   "dependencies": {
     "@vercel/oidc": "3.2.0",
     "@ai-sdk/provider": "4.0.7",
-    "@ai-sdk/provider-utils": "5.0.28"
+    "@ai-sdk/provider-utils": "5.0.29"
   },
   "devDependencies": {
     "@types/node": "22.19.19",
     "tsup": "^8.5.1",
-    "tsx": "4.19.2",
+    "tsx": "4.23.12",
     "typescript": "5.8.3",
     "zod": "3.25.76",
     "@ai-sdk/test-server": "2.0.1",

package/src/gateway-language-model-settings.ts

@@ -133,6 +133,7 @@ export type GatewayModelId =
   | 'nvidia/nemotron-3-super-120b-a12b'
   | 'nvidia/nemotron-3-ultra-550b-a55b'
   | 'nvidia/nemotron-3.5-lightning'
+  | 'nvidia/nemotron-3.5-lightning-free'
   | 'nvidia/nemotron-nano-12b-v2-vl'
   | 'nvidia/nemotron-nano-9b-v2'
   | 'openai/gpt-3.5-turbo'

package/src/gateway-tools.ts

@@ -1,6 +1,7 @@
 import { exaSearch } from './tool/exa-search';
 import { parallelSearch } from './tool/parallel-search';
 import { perplexitySearch } from './tool/perplexity-search';
+import { takoSearch } from './tool/tako-search';
 
 /**
  * Gateway-specific provider-defined tools.
@@ -33,4 +34,14 @@ export const gatewayTools = {
    * domain, language, date range, and recency filters.
    */
   perplexitySearch,
+
+  /**
+   * Search the web and Tako's curated knowledge graph in one call for
+   * token-efficient web excerpts and structured data results grounded in
+   * premium sources, each with an embed-ready visualization.
+   *
+   * Supports effort, per-source web and data controls, localization, and inline
+   * contents for agents that need to reason over underlying data.
+   */
+  takoSearch,
 };

package/src/gateway-video-model-settings.ts

@@ -10,6 +10,7 @@ export type GatewayVideoModelId =
   | 'bfl/flux-3-video'
   | 'bytedance/seedance-2.0'
   | 'bytedance/seedance-2.0-fast'
+  | 'bytedance/seedance-2.0-mini'
   | 'bytedance/seedance-2.5'
   | 'bytedance/seedance-v1.0-pro'
   | 'bytedance/seedance-v1.0-pro-fast'