@ai-sdk/openai 4.0.13 → 4.0.15

package/CHANGELOG.md

@@ -1,5 +1,18 @@
 # @ai-sdk/openai
 
+## 4.0.15
+
+### Patch Changes
+
+- 0063c2d: Add the client-executed OpenAI Responses API computer tool with batched actions and screenshot outputs.
+
+## 4.0.14
+
+### Patch Changes
+
+- Updated dependencies [31c7be8]
+  - @ai-sdk/provider-utils@5.0.10
+
 ## 4.0.13
 
 ### Patch Changes

package/dist/index.d.ts

@@ -2,6 +2,7 @@ import * as _ai_sdk_provider from '@ai-sdk/provider';
 import { JSONValue, ProviderV4, LanguageModelV4, EmbeddingModelV4, ImageModelV4, TranscriptionModelV4, SpeechModelV4, Experimental_RealtimeFactoryV4, FilesV4, SkillsV4, Experimental_RealtimeModelV4, Experimental_RealtimeModelV4ClientSecretOptions, Experimental_RealtimeModelV4ClientSecretResult, Experimental_RealtimeModelV4ServerEvent, Experimental_RealtimeModelV4ClientEvent, Experimental_RealtimeModelV4SessionConfig } from '@ai-sdk/provider';
 import * as _ai_sdk_provider_utils from '@ai-sdk/provider-utils';
 import { InferSchema, FetchFunction, WebSocketConstructor } from '@ai-sdk/provider-utils';
+import { z } from 'zod/v4';
 
 type OpenAIChatModelId = 'o1' | 'o1-2024-12-17' | 'o3-mini' | 'o3-mini-2025-01-31' | 'o3' | 'o3-2025-04-16' | 'o4-mini' | 'o4-mini-2025-04-16' | 'gpt-4.1' | 'gpt-4.1-2025-04-14' | 'gpt-4.1-mini' | 'gpt-4.1-mini-2025-04-14' | 'gpt-4.1-nano' | 'gpt-4.1-nano-2025-04-14' | 'gpt-4o' | 'gpt-4o-2024-05-13' | 'gpt-4o-2024-08-06' | 'gpt-4o-2024-11-20' | 'gpt-4o-audio-preview' | 'gpt-4o-audio-preview-2024-12-17' | 'gpt-4o-audio-preview-2025-06-03' | 'gpt-4o-mini' | 'gpt-4o-mini-2024-07-18' | 'gpt-4o-mini-audio-preview' | 'gpt-4o-mini-audio-preview-2024-12-17' | 'gpt-4o-search-preview' | 'gpt-4o-search-preview-2025-03-11' | 'gpt-4o-mini-search-preview' | 'gpt-4o-mini-search-preview-2025-03-11' | 'gpt-3.5-turbo-0125' | 'gpt-3.5-turbo' | 'gpt-3.5-turbo-1106' | 'gpt-3.5-turbo-16k' | 'gpt-5' | 'gpt-5-2025-08-07' | 'gpt-5-mini' | 'gpt-5-mini-2025-08-07' | 'gpt-5-nano' | 'gpt-5-nano-2025-08-07' | 'gpt-5-chat-latest' | 'gpt-5.1' | 'gpt-5.1-2025-11-13' | 'gpt-5.1-chat-latest' | 'gpt-5.2' | 'gpt-5.2-2025-12-11' | 'gpt-5.2-chat-latest' | 'gpt-5.2-pro' | 'gpt-5.2-pro-2025-12-11' | 'gpt-5.3-chat-latest' | 'gpt-5.4' | 'gpt-5.4-2026-03-05' | 'gpt-5.4-mini' | 'gpt-5.4-mini-2026-03-17' | 'gpt-5.4-nano' | 'gpt-5.4-nano-2026-03-17' | 'gpt-5.4-pro' | 'gpt-5.4-pro-2026-03-05' | 'gpt-5.5' | 'gpt-5.5-2026-04-23' | 'gpt-5.6' | 'gpt-5.6-luna' | 'gpt-5.6-sol' | 'gpt-5.6-terra' | (string & {});
 declare const openaiLanguageModelChatOptions: _ai_sdk_provider_utils.LazySchema<{
@@ -307,6 +308,98 @@ declare const openaiResponsesChunkSchema: _ai_sdk_provider_utils.LazySchema<{
     type: "response.output_item.added";
     output_index: number;
     item: {
+        type: "computer_call";
+        id: string;
+        status: "completed" | "in_progress" | "incomplete";
+        call_id?: string | null | undefined;
+        action?: {
+            type: "click";
+            button: "left" | "right" | "wheel" | "back" | "forward";
+            x: number;
+            y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "double_click";
+            x: number;
+            y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "drag";
+            path: {
+                x: number;
+                y: number;
+            }[];
+            keys?: string[] | null | undefined;
+        } | {
+            type: "keypress";
+            keys: string[];
+        } | {
+            type: "move";
+            x: number;
+            y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "screenshot";
+        } | {
+            type: "scroll";
+            x: number;
+            y: number;
+            scroll_x: number;
+            scroll_y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "type";
+            text: string;
+        } | {
+            type: "wait";
+        } | null | undefined;
+        actions?: ({
+            type: "click";
+            button: "left" | "right" | "wheel" | "back" | "forward";
+            x: number;
+            y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "double_click";
+            x: number;
+            y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "drag";
+            path: {
+                x: number;
+                y: number;
+            }[];
+            keys?: string[] | null | undefined;
+        } | {
+            type: "keypress";
+            keys: string[];
+        } | {
+            type: "move";
+            x: number;
+            y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "screenshot";
+        } | {
+            type: "scroll";
+            x: number;
+            y: number;
+            scroll_x: number;
+            scroll_y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "type";
+            text: string;
+        } | {
+            type: "wait";
+        })[] | null | undefined;
+        pending_safety_checks?: {
+            id: string;
+            code?: string | null | undefined;
+            message?: string | null | undefined;
+        }[] | null | undefined;
+    } | {
         type: "message";
         id: string;
         phase?: "commentary" | "final_answer" | null | undefined;
@@ -325,10 +418,6 @@ declare const openaiResponsesChunkSchema: _ai_sdk_provider_utils.LazySchema<{
         type: "web_search_call";
         id: string;
         status: string;
-    } | {
-        type: "computer_call";
-        id: string;
-        status: string;
     } | {
         type: "file_search_call";
         id: string;
@@ -428,6 +517,98 @@ declare const openaiResponsesChunkSchema: _ai_sdk_provider_utils.LazySchema<{
     type: "response.output_item.done";
     output_index: number;
     item: {
+        type: "computer_call";
+        id: string;
+        status: "completed" | "in_progress" | "incomplete";
+        call_id?: string | null | undefined;
+        action?: {
+            type: "click";
+            button: "left" | "right" | "wheel" | "back" | "forward";
+            x: number;
+            y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "double_click";
+            x: number;
+            y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "drag";
+            path: {
+                x: number;
+                y: number;
+            }[];
+            keys?: string[] | null | undefined;
+        } | {
+            type: "keypress";
+            keys: string[];
+        } | {
+            type: "move";
+            x: number;
+            y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "screenshot";
+        } | {
+            type: "scroll";
+            x: number;
+            y: number;
+            scroll_x: number;
+            scroll_y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "type";
+            text: string;
+        } | {
+            type: "wait";
+        } | null | undefined;
+        actions?: ({
+            type: "click";
+            button: "left" | "right" | "wheel" | "back" | "forward";
+            x: number;
+            y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "double_click";
+            x: number;
+            y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "drag";
+            path: {
+                x: number;
+                y: number;
+            }[];
+            keys?: string[] | null | undefined;
+        } | {
+            type: "keypress";
+            keys: string[];
+        } | {
+            type: "move";
+            x: number;
+            y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "screenshot";
+        } | {
+            type: "scroll";
+            x: number;
+            y: number;
+            scroll_x: number;
+            scroll_y: number;
+            keys?: string[] | null | undefined;
+        } | {
+            type: "type";
+            text: string;
+        } | {
+            type: "wait";
+        })[] | null | undefined;
+        pending_safety_checks?: {
+            id: string;
+            code?: string | null | undefined;
+            message?: string | null | undefined;
+        }[] | null | undefined;
+    } | {
         type: "message";
         id: string;
         phase?: "commentary" | "final_answer" | null | undefined;
@@ -512,10 +693,6 @@ declare const openaiResponsesChunkSchema: _ai_sdk_provider_utils.LazySchema<{
             working_directory?: string | undefined;
             env?: Record<string, string> | undefined;
         };
-    } | {
-        type: "computer_call";
-        id: string;
-        status: "completed";
     } | {
         type: "mcp_call";
         id: string;
@@ -789,6 +966,49 @@ declare const openaiTools: {
             url: string;
         }> | null;
     }, {}>;
+    /**
+     * The computer tool allows models to operate a browser or desktop through
+     * batched UI actions. Your application executes the actions and returns an
+     * updated screenshot.
+     *
+     * WARNING: Run computer use in an isolated environment, treat on-screen
+     * content as untrusted, and require confirmation for consequential actions.
+     */
+    computer: (options?: Parameters<_ai_sdk_provider_utils.ProviderDefinedToolFactoryWithOutputSchema<{
+        actions: OpenAIComputerAction[];
+        pendingSafetyChecks: OpenAIComputerSafetyCheck[];
+        status: "in_progress" | "completed" | "incomplete";
+    }, {
+        output: {
+            type: "computer_screenshot";
+            imageUrl: string;
+            fileId?: string;
+            detail?: "auto" | "low" | "high" | "original";
+        } | {
+            type: "computer_screenshot";
+            fileId: string;
+            imageUrl?: string;
+            detail?: "auto" | "low" | "high" | "original";
+        };
+        acknowledgedSafetyChecks?: OpenAIComputerSafetyCheck[];
+    }, {}, {}>>[0]) => _ai_sdk_provider_utils.ProviderDefinedTool<{
+        actions: OpenAIComputerAction[];
+        pendingSafetyChecks: OpenAIComputerSafetyCheck[];
+        status: "in_progress" | "completed" | "incomplete";
+    }, {
+        output: {
+            type: "computer_screenshot";
+            imageUrl: string;
+            fileId?: string;
+            detail?: "auto" | "low" | "high" | "original";
+        } | {
+            type: "computer_screenshot";
+            fileId: string;
+            imageUrl?: string;
+            detail?: "auto" | "low" | "high" | "original";
+        };
+        acknowledgedSafetyChecks?: OpenAIComputerSafetyCheck[];
+    }, {}>;
     /**
      * File search is a tool available in the Responses API. It enables models to
      * retrieve information in a knowledge base of previously uploaded files through
@@ -931,21 +1151,7 @@ declare const openaiTools: {
             containerId: string;
         } | {
             type?: "local";
-            skills
-            /**
-             * Web search allows models to access up-to-date information from the internet
-             * and provide answers with sourced citations.
-             *
-             * @param searchContextSize - The search context size to use for the web search.
-             * @param userLocation - The user location to use for the web search.
-             */
-            ? /**
-             * Web search allows models to access up-to-date information from the internet
-             * and provide answers with sourced citations.
-             *
-             * @param searchContextSize - The search context size to use for the web search.
-             * @param userLocation - The user location to use for the web search.
-             */: Array<{
+            skills?: Array<{
                 name: string;
                 description: string;
                 path: string;
@@ -1279,6 +1485,61 @@ declare const openaiFilesOptionsSchema: _ai_sdk_provider_utils.LazySchema<{
 }>;
 type OpenAIFilesOptions = InferSchema<typeof openaiFilesOptionsSchema>;
 
+declare const safetyCheckSchema: z.ZodObject<{
+    id: z.ZodString;
+    code: z.ZodOptional<z.ZodString>;
+    message: z.ZodOptional<z.ZodString>;
+}, z.core.$strip>;
+declare const computerActionSchema: z.ZodDiscriminatedUnion<[z.ZodObject<{
+    type: z.ZodLiteral<"click">;
+    button: z.ZodEnum<{
+        left: "left";
+        right: "right";
+        wheel: "wheel";
+        back: "back";
+        forward: "forward";
+    }>;
+    x: z.ZodNumber;
+    y: z.ZodNumber;
+    keys: z.ZodOptional<z.ZodArray<z.ZodString>>;
+}, z.core.$strip>, z.ZodObject<{
+    type: z.ZodLiteral<"double_click">;
+    x: z.ZodNumber;
+    y: z.ZodNumber;
+    keys: z.ZodOptional<z.ZodArray<z.ZodString>>;
+}, z.core.$strip>, z.ZodObject<{
+    type: z.ZodLiteral<"drag">;
+    path: z.ZodArray<z.ZodObject<{
+        x: z.ZodNumber;
+        y: z.ZodNumber;
+    }, z.core.$strip>>;
+    keys: z.ZodOptional<z.ZodArray<z.ZodString>>;
+}, z.core.$strip>, z.ZodObject<{
+    type: z.ZodLiteral<"keypress">;
+    keys: z.ZodArray<z.ZodString>;
+}, z.core.$strip>, z.ZodObject<{
+    type: z.ZodLiteral<"move">;
+    x: z.ZodNumber;
+    y: z.ZodNumber;
+    keys: z.ZodOptional<z.ZodArray<z.ZodString>>;
+}, z.core.$strip>, z.ZodObject<{
+    type: z.ZodLiteral<"screenshot">;
+}, z.core.$strip>, z.ZodObject<{
+    type: z.ZodLiteral<"scroll">;
+    x: z.ZodNumber;
+    y: z.ZodNumber;
+    scrollX: z.ZodNumber;
+    scrollY: z.ZodNumber;
+    keys: z.ZodOptional<z.ZodArray<z.ZodString>>;
+}, z.core.$strip>, z.ZodObject<{
+    type: z.ZodLiteral<"type">;
+    text: z.ZodString;
+}, z.core.$strip>, z.ZodObject<{
+    type: z.ZodLiteral<"wait">;
+}, z.core.$strip>]>;
+type OpenAIComputerAction = z.infer<typeof computerActionSchema>;
+type OpenAIComputerSafetyCheck = z.infer<typeof safetyCheckSchema>;
+
 type OpenaiResponsesChunk = InferSchema<typeof openaiResponsesChunkSchema>;
 type ResponsesOutputTextAnnotationProviderMetadata = Extract<OpenaiResponsesChunk, {
     type: 'response.output_text.annotation.added';
@@ -1334,4 +1595,4 @@ type OpenaiResponsesSourceDocumentProviderMetadata = {
 
 declare const VERSION: string;
 
-export { OpenAIRealtimeModel as Experimental_OpenAIRealtimeModel, type OpenAIRealtimeModelConfig as Experimental_OpenAIRealtimeModelConfig, type OpenAILanguageModelChatOptions as OpenAIChatLanguageModelOptions, type OpenAIEmbeddingModelOptions, type OpenAIFilesOptions, type OpenAIImageModelEditOptions, type OpenAIImageModelGenerationOptions, type OpenAIImageModelOptions, type OpenAILanguageModelChatOptions, type OpenAILanguageModelCompletionOptions, type OpenAILanguageModelResponsesOptions, type OpenAIProvider, type OpenAIProviderSettings, type OpenAILanguageModelResponsesOptions as OpenAIResponsesProviderOptions, type OpenAISpeechModelOptions, type OpenAITranscriptionModelOptions, type OpenaiResponsesCompactionProviderMetadata, type OpenaiResponsesProviderMetadata, type OpenaiResponsesReasoningProviderMetadata, type OpenaiResponsesSourceDocumentProviderMetadata, type OpenaiResponsesTextProviderMetadata, VERSION, createOpenAI, openai };
+export { OpenAIRealtimeModel as Experimental_OpenAIRealtimeModel, type OpenAIRealtimeModelConfig as Experimental_OpenAIRealtimeModelConfig, type OpenAILanguageModelChatOptions as OpenAIChatLanguageModelOptions, type OpenAIComputerAction, type OpenAIComputerSafetyCheck, type OpenAIEmbeddingModelOptions, type OpenAIFilesOptions, type OpenAIImageModelEditOptions, type OpenAIImageModelGenerationOptions, type OpenAIImageModelOptions, type OpenAILanguageModelChatOptions, type OpenAILanguageModelCompletionOptions, type OpenAILanguageModelResponsesOptions, type OpenAIProvider, type OpenAIProviderSettings, type OpenAILanguageModelResponsesOptions as OpenAIResponsesProviderOptions, type OpenAISpeechModelOptions, type OpenAITranscriptionModelOptions, type OpenaiResponsesCompactionProviderMetadata, type OpenaiResponsesProviderMetadata, type OpenaiResponsesReasoningProviderMetadata, type OpenaiResponsesSourceDocumentProviderMetadata, type OpenaiResponsesTextProviderMetadata, VERSION, createOpenAI, openai };