@ai-sdk/anthropic 0.0.50 → 0.0.53

package/CHANGELOG.md

@@ -1,5 +1,38 @@
 # @ai-sdk/anthropic
 
+## 0.0.53
+
+### Patch Changes
+
+- 3b1b69a: feat (provider/anthropic): add computer use tools
+- 3b1b69a: feat: provider-defined tools
+- 8c222cd: feat (provider/anthropic): update model ids
+- 811a317: feat (ai/core): multi-part tool results (incl. images)
+- Updated dependencies [aa98cdb]
+- Updated dependencies [1486128]
+- Updated dependencies [7b937c5]
+- Updated dependencies [3b1b69a]
+- Updated dependencies [811a317]
+  - @ai-sdk/provider-utils@1.0.22
+  - @ai-sdk/provider@0.0.26
+
+## 0.0.52
+
+### Patch Changes
+
+- b9b0d7b: feat (ai): access raw request body
+- Updated dependencies [b9b0d7b]
+  - @ai-sdk/provider@0.0.25
+  - @ai-sdk/provider-utils@1.0.21
+
+## 0.0.51
+
+### Patch Changes
+
+- Updated dependencies [d595d0d]
+  - @ai-sdk/provider@0.0.24
+  - @ai-sdk/provider-utils@1.0.20
+
 ## 0.0.50
 
 ### Patch Changes

package/README.md

@@ -1,6 +1,6 @@
-# Vercel AI SDK - Anthropic Provider
+# AI SDK - Anthropic Provider
 
-The **[Anthropic provider](https://sdk.vercel.ai/providers/ai-sdk-providers/anthropic)** for the [Vercel AI SDK](https://sdk.vercel.ai/docs) contains language model support for the [Anthropic Messages API](https://docs.anthropic.com/claude/reference/messages_post).
+The **[Anthropic provider](https://sdk.vercel.ai/providers/ai-sdk-providers/anthropic)** for the [AI SDK](https://sdk.vercel.ai/docs) contains language model support for the [Anthropic Messages API](https://docs.anthropic.com/claude/reference/messages_post).
 
 ## Setup
 

package/dist/index.d.mts

@@ -1,7 +1,8 @@
 import { LanguageModelV1, ProviderV1 } from '@ai-sdk/provider';
 import { FetchFunction } from '@ai-sdk/provider-utils';
+import { z } from 'zod';
 
-type AnthropicMessagesModelId = 'claude-3-5-sonnet-20240620' | 'claude-3-opus-20240229' | 'claude-3-sonnet-20240229' | 'claude-3-haiku-20240307' | (string & {});
+type AnthropicMessagesModelId = 'claude-3-5-sonnet-latest' | 'claude-3-5-sonnet-20241022' | 'claude-3-5-sonnet-20240620' | 'claude-3-opus-latest' | 'claude-3-opus-20240229' | 'claude-3-sonnet-20240229' | 'claude-3-haiku-20240307' | (string & {});
 interface AnthropicMessagesSettings {
     /**
   Only sample from the top K options for each subsequent token.
@@ -40,6 +41,194 @@ declare class AnthropicMessagesLanguageModel implements LanguageModelV1 {
     doStream(options: Parameters<LanguageModelV1['doStream']>[0]): Promise<Awaited<ReturnType<LanguageModelV1['doStream']>>>;
 }
 
+type ExecuteFunction<PARAMETERS, RESULT> = undefined | ((args: PARAMETERS, options: {
+    abortSignal?: AbortSignal;
+}) => Promise<RESULT>);
+type ToolResultContent = Array<{
+    type: 'text';
+    text: string;
+} | {
+    type: 'image';
+    data: string;
+    mimeType?: string;
+}>;
+declare const Bash20241022Parameters: z.ZodObject<{
+    command: z.ZodString;
+    restart: z.ZodOptional<z.ZodBoolean>;
+}, "strip", z.ZodTypeAny, {
+    command: string;
+    restart?: boolean | undefined;
+}, {
+    command: string;
+    restart?: boolean | undefined;
+}>;
+/**
+ * Creates a tool for running a bash command. Must have name "bash".
+ *
+ * Image results are supported.
+ *
+ * @param execute - The function to execute the tool. Optional.
+ */
+declare function bashTool_20241022<RESULT>(options?: {
+    execute?: ExecuteFunction<{
+        /**
+         * The bash command to run. Required unless the tool is being restarted.
+         */
+        command: string;
+        /**
+         * Specifying true will restart this tool. Otherwise, leave this unspecified.
+         */
+        restart?: boolean;
+    }, RESULT>;
+    experimental_toToolResultContent?: (result: RESULT) => ToolResultContent;
+}): {
+    type: 'provider-defined';
+    id: 'anthropic.bash_20241022';
+    args: {};
+    parameters: typeof Bash20241022Parameters;
+    execute: ExecuteFunction<z.infer<typeof Bash20241022Parameters>, RESULT>;
+    experimental_toToolResultContent?: (result: RESULT) => ToolResultContent;
+};
+declare const TextEditor20241022Parameters: z.ZodObject<{
+    command: z.ZodEnum<["view", "create", "str_replace", "insert", "undo_edit"]>;
+    path: z.ZodString;
+    file_text: z.ZodOptional<z.ZodString>;
+    insert_line: z.ZodOptional<z.ZodNumber>;
+    new_str: z.ZodOptional<z.ZodString>;
+    old_str: z.ZodOptional<z.ZodString>;
+    view_range: z.ZodOptional<z.ZodArray<z.ZodNumber, "many">>;
+}, "strip", z.ZodTypeAny, {
+    path: string;
+    command: "view" | "create" | "str_replace" | "insert" | "undo_edit";
+    file_text?: string | undefined;
+    insert_line?: number | undefined;
+    new_str?: string | undefined;
+    old_str?: string | undefined;
+    view_range?: number[] | undefined;
+}, {
+    path: string;
+    command: "view" | "create" | "str_replace" | "insert" | "undo_edit";
+    file_text?: string | undefined;
+    insert_line?: number | undefined;
+    new_str?: string | undefined;
+    old_str?: string | undefined;
+    view_range?: number[] | undefined;
+}>;
+/**
+ * Creates a tool for editing text. Must have name "str_replace_editor".
+ *
+ * Image results are supported.
+ *
+ * @param execute - The function to execute the tool. Optional.
+ */
+declare function textEditorTool_20241022<RESULT>(options?: {
+    execute?: ExecuteFunction<{
+        /**
+         * The commands to run. Allowed options are: `view`, `create`, `str_replace`, `insert`, `undo_edit`.
+         */
+        command: 'view' | 'create' | 'str_replace' | 'insert' | 'undo_edit';
+        /**
+         * Absolute path to file or directory, e.g. `/repo/file.py` or `/repo`.
+         */
+        path: string;
+        /**
+         * Required parameter of `create` command, with the content of the file to be created.
+         */
+        file_text?: string;
+        /**
+         * Required parameter of `insert` command. The `new_str` will be inserted AFTER the line `insert_line` of `path`.
+         */
+        insert_line?: number;
+        /**
+         * Optional parameter of `str_replace` command containing the new string (if not given, no string will be added). Required parameter of `insert` command containing the string to insert.
+         */
+        new_str?: string;
+        /**
+         * Required parameter of `str_replace` command containing the string in `path` to replace.
+         */
+        old_str?: string;
+        /**
+         * Optional parameter of `view` command when `path` points to a file. If none is given, the full file is shown. If provided, the file will be shown in the indicated line number range, e.g. [11, 12] will show lines 11 and 12. Indexing at 1 to start. Setting `[start_line, -1]` shows all lines from `start_line` to the end of the file.
+         */
+        view_range?: number[];
+    }, RESULT>;
+    experimental_toToolResultContent?: (result: RESULT) => ToolResultContent;
+}): {
+    type: 'provider-defined';
+    id: 'anthropic.text_editor_20241022';
+    args: {};
+    parameters: typeof TextEditor20241022Parameters;
+    execute: ExecuteFunction<z.infer<typeof TextEditor20241022Parameters>, RESULT>;
+    experimental_toToolResultContent?: (result: RESULT) => ToolResultContent;
+};
+declare const Computer20241022Parameters: z.ZodObject<{
+    action: z.ZodEnum<["key", "type", "mouse_move", "left_click", "left_click_drag", "right_click", "middle_click", "double_click", "screenshot", "cursor_position"]>;
+    coordinate: z.ZodOptional<z.ZodArray<z.ZodNumber, "many">>;
+    text: z.ZodOptional<z.ZodString>;
+}, "strip", z.ZodTypeAny, {
+    action: "type" | "key" | "mouse_move" | "left_click" | "left_click_drag" | "right_click" | "middle_click" | "double_click" | "screenshot" | "cursor_position";
+    text?: string | undefined;
+    coordinate?: number[] | undefined;
+}, {
+    action: "type" | "key" | "mouse_move" | "left_click" | "left_click_drag" | "right_click" | "middle_click" | "double_click" | "screenshot" | "cursor_position";
+    text?: string | undefined;
+    coordinate?: number[] | undefined;
+}>;
+/**
+ * Creates a tool for executing actions on a computer. Must have name "computer".
+ *
+ * Image results are supported.
+ *
+ * @param displayWidthPx - The width of the display being controlled by the model in pixels.
+ * @param displayHeightPx - The height of the display being controlled by the model in pixels.
+ * @param displayNumber - The display number to control (only relevant for X11 environments). If specified, the tool will be provided a display number in the tool definition.
+ * @param execute - The function to execute the tool. Optional.
+ */
+declare function computerTool_20241022<RESULT>(options: {
+    displayWidthPx: number;
+    displayHeightPx: number;
+    displayNumber?: number;
+    execute?: ExecuteFunction<{
+        /**
+         * The action to perform. The available actions are:
+         * - `key`: Press a key or key-combination on the keyboard.
+         *   - This supports xdotool's `key` syntax.
+         *   - Examples: "a", "Return", "alt+Tab", "ctrl+s", "Up", "KP_0" (for the numpad 0 key).
+         * - `type`: Type a string of text on the keyboard.
+         * - `cursor_position`: Get the current (x, y) pixel coordinate of the cursor on the screen.
+         * - `mouse_move`: Move the cursor to a specified (x, y) pixel coordinate on the screen.
+         * - `left_click`: Click the left mouse button.
+         * - `left_click_drag`: Click and drag the cursor to a specified (x, y) pixel coordinate on the screen.
+         * - `right_click`: Click the right mouse button.
+         * - `middle_click`: Click the middle mouse button.
+         * - `double_click`: Double-click the left mouse button.
+         * - `screenshot`: Take a screenshot of the screen.
+         */
+        action: 'key' | 'type' | 'mouse_move' | 'left_click' | 'left_click_drag' | 'right_click' | 'middle_click' | 'double_click' | 'screenshot' | 'cursor_position';
+        /**
+         * (x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by `action=mouse_move` and `action=left_click_drag`.
+         */
+        coordinate?: number[];
+        /**
+         * Required only by `action=type` and `action=key`.
+         */
+        text?: string;
+    }, RESULT>;
+    experimental_toToolResultContent?: (result: RESULT) => ToolResultContent;
+}): {
+    type: 'provider-defined';
+    id: 'anthropic.computer_20241022';
+    args: {};
+    parameters: typeof Computer20241022Parameters;
+    execute: ExecuteFunction<z.infer<typeof Computer20241022Parameters>, RESULT>;
+    experimental_toToolResultContent?: (result: RESULT) => ToolResultContent;
+};
+declare const anthropicTools: {
+    bash_20241022: typeof bashTool_20241022;
+    textEditor_20241022: typeof textEditorTool_20241022;
+    computer_20241022: typeof computerTool_20241022;
+};
+
 interface AnthropicProvider extends ProviderV1 {
     /**
   Creates a model for text generation.
@@ -57,6 +246,10 @@ interface AnthropicProvider extends ProviderV1 {
   @deprecated Use `.languageModel()` instead.
      */
     messages(modelId: AnthropicMessagesModelId, settings?: AnthropicMessagesSettings): LanguageModelV1;
+    /**
+  Anthropic-specific computer use tool.
+     */
+    tools: typeof anthropicTools;
 }
 interface AnthropicProviderSettings {
     /**

package/dist/index.d.ts

@@ -1,7 +1,8 @@
 import { LanguageModelV1, ProviderV1 } from '@ai-sdk/provider';
 import { FetchFunction } from '@ai-sdk/provider-utils';
+import { z } from 'zod';
 
-type AnthropicMessagesModelId = 'claude-3-5-sonnet-20240620' | 'claude-3-opus-20240229' | 'claude-3-sonnet-20240229' | 'claude-3-haiku-20240307' | (string & {});
+type AnthropicMessagesModelId = 'claude-3-5-sonnet-latest' | 'claude-3-5-sonnet-20241022' | 'claude-3-5-sonnet-20240620' | 'claude-3-opus-latest' | 'claude-3-opus-20240229' | 'claude-3-sonnet-20240229' | 'claude-3-haiku-20240307' | (string & {});
 interface AnthropicMessagesSettings {
     /**
   Only sample from the top K options for each subsequent token.
@@ -40,6 +41,194 @@ declare class AnthropicMessagesLanguageModel implements LanguageModelV1 {
     doStream(options: Parameters<LanguageModelV1['doStream']>[0]): Promise<Awaited<ReturnType<LanguageModelV1['doStream']>>>;
 }
 
+type ExecuteFunction<PARAMETERS, RESULT> = undefined | ((args: PARAMETERS, options: {
+    abortSignal?: AbortSignal;
+}) => Promise<RESULT>);
+type ToolResultContent = Array<{
+    type: 'text';
+    text: string;
+} | {
+    type: 'image';
+    data: string;
+    mimeType?: string;
+}>;
+declare const Bash20241022Parameters: z.ZodObject<{
+    command: z.ZodString;
+    restart: z.ZodOptional<z.ZodBoolean>;
+}, "strip", z.ZodTypeAny, {
+    command: string;
+    restart?: boolean | undefined;
+}, {
+    command: string;
+    restart?: boolean | undefined;
+}>;
+/**
+ * Creates a tool for running a bash command. Must have name "bash".
+ *
+ * Image results are supported.
+ *
+ * @param execute - The function to execute the tool. Optional.
+ */
+declare function bashTool_20241022<RESULT>(options?: {
+    execute?: ExecuteFunction<{
+        /**
+         * The bash command to run. Required unless the tool is being restarted.
+         */
+        command: string;
+        /**
+         * Specifying true will restart this tool. Otherwise, leave this unspecified.
+         */
+        restart?: boolean;
+    }, RESULT>;
+    experimental_toToolResultContent?: (result: RESULT) => ToolResultContent;
+}): {
+    type: 'provider-defined';
+    id: 'anthropic.bash_20241022';
+    args: {};
+    parameters: typeof Bash20241022Parameters;
+    execute: ExecuteFunction<z.infer<typeof Bash20241022Parameters>, RESULT>;
+    experimental_toToolResultContent?: (result: RESULT) => ToolResultContent;
+};
+declare const TextEditor20241022Parameters: z.ZodObject<{
+    command: z.ZodEnum<["view", "create", "str_replace", "insert", "undo_edit"]>;
+    path: z.ZodString;
+    file_text: z.ZodOptional<z.ZodString>;
+    insert_line: z.ZodOptional<z.ZodNumber>;
+    new_str: z.ZodOptional<z.ZodString>;
+    old_str: z.ZodOptional<z.ZodString>;
+    view_range: z.ZodOptional<z.ZodArray<z.ZodNumber, "many">>;
+}, "strip", z.ZodTypeAny, {
+    path: string;
+    command: "view" | "create" | "str_replace" | "insert" | "undo_edit";
+    file_text?: string | undefined;
+    insert_line?: number | undefined;
+    new_str?: string | undefined;
+    old_str?: string | undefined;
+    view_range?: number[] | undefined;
+}, {
+    path: string;
+    command: "view" | "create" | "str_replace" | "insert" | "undo_edit";
+    file_text?: string | undefined;
+    insert_line?: number | undefined;
+    new_str?: string | undefined;
+    old_str?: string | undefined;
+    view_range?: number[] | undefined;
+}>;
+/**
+ * Creates a tool for editing text. Must have name "str_replace_editor".
+ *
+ * Image results are supported.
+ *
+ * @param execute - The function to execute the tool. Optional.
+ */
+declare function textEditorTool_20241022<RESULT>(options?: {
+    execute?: ExecuteFunction<{
+        /**
+         * The commands to run. Allowed options are: `view`, `create`, `str_replace`, `insert`, `undo_edit`.
+         */
+        command: 'view' | 'create' | 'str_replace' | 'insert' | 'undo_edit';
+        /**
+         * Absolute path to file or directory, e.g. `/repo/file.py` or `/repo`.
+         */
+        path: string;
+        /**
+         * Required parameter of `create` command, with the content of the file to be created.
+         */
+        file_text?: string;
+        /**
+         * Required parameter of `insert` command. The `new_str` will be inserted AFTER the line `insert_line` of `path`.
+         */
+        insert_line?: number;
+        /**
+         * Optional parameter of `str_replace` command containing the new string (if not given, no string will be added). Required parameter of `insert` command containing the string to insert.
+         */
+        new_str?: string;
+        /**
+         * Required parameter of `str_replace` command containing the string in `path` to replace.
+         */
+        old_str?: string;
+        /**
+         * Optional parameter of `view` command when `path` points to a file. If none is given, the full file is shown. If provided, the file will be shown in the indicated line number range, e.g. [11, 12] will show lines 11 and 12. Indexing at 1 to start. Setting `[start_line, -1]` shows all lines from `start_line` to the end of the file.
+         */
+        view_range?: number[];
+    }, RESULT>;
+    experimental_toToolResultContent?: (result: RESULT) => ToolResultContent;
+}): {
+    type: 'provider-defined';
+    id: 'anthropic.text_editor_20241022';
+    args: {};
+    parameters: typeof TextEditor20241022Parameters;
+    execute: ExecuteFunction<z.infer<typeof TextEditor20241022Parameters>, RESULT>;
+    experimental_toToolResultContent?: (result: RESULT) => ToolResultContent;
+};
+declare const Computer20241022Parameters: z.ZodObject<{
+    action: z.ZodEnum<["key", "type", "mouse_move", "left_click", "left_click_drag", "right_click", "middle_click", "double_click", "screenshot", "cursor_position"]>;
+    coordinate: z.ZodOptional<z.ZodArray<z.ZodNumber, "many">>;
+    text: z.ZodOptional<z.ZodString>;
+}, "strip", z.ZodTypeAny, {
+    action: "type" | "key" | "mouse_move" | "left_click" | "left_click_drag" | "right_click" | "middle_click" | "double_click" | "screenshot" | "cursor_position";
+    text?: string | undefined;
+    coordinate?: number[] | undefined;
+}, {
+    action: "type" | "key" | "mouse_move" | "left_click" | "left_click_drag" | "right_click" | "middle_click" | "double_click" | "screenshot" | "cursor_position";
+    text?: string | undefined;
+    coordinate?: number[] | undefined;
+}>;
+/**
+ * Creates a tool for executing actions on a computer. Must have name "computer".
+ *
+ * Image results are supported.
+ *
+ * @param displayWidthPx - The width of the display being controlled by the model in pixels.
+ * @param displayHeightPx - The height of the display being controlled by the model in pixels.
+ * @param displayNumber - The display number to control (only relevant for X11 environments). If specified, the tool will be provided a display number in the tool definition.
+ * @param execute - The function to execute the tool. Optional.
+ */
+declare function computerTool_20241022<RESULT>(options: {
+    displayWidthPx: number;
+    displayHeightPx: number;
+    displayNumber?: number;
+    execute?: ExecuteFunction<{
+        /**
+         * The action to perform. The available actions are:
+         * - `key`: Press a key or key-combination on the keyboard.
+         *   - This supports xdotool's `key` syntax.
+         *   - Examples: "a", "Return", "alt+Tab", "ctrl+s", "Up", "KP_0" (for the numpad 0 key).
+         * - `type`: Type a string of text on the keyboard.
+         * - `cursor_position`: Get the current (x, y) pixel coordinate of the cursor on the screen.
+         * - `mouse_move`: Move the cursor to a specified (x, y) pixel coordinate on the screen.
+         * - `left_click`: Click the left mouse button.
+         * - `left_click_drag`: Click and drag the cursor to a specified (x, y) pixel coordinate on the screen.
+         * - `right_click`: Click the right mouse button.
+         * - `middle_click`: Click the middle mouse button.
+         * - `double_click`: Double-click the left mouse button.
+         * - `screenshot`: Take a screenshot of the screen.
+         */
+        action: 'key' | 'type' | 'mouse_move' | 'left_click' | 'left_click_drag' | 'right_click' | 'middle_click' | 'double_click' | 'screenshot' | 'cursor_position';
+        /**
+         * (x, y): The x (pixels from the left edge) and y (pixels from the top edge) coordinates to move the mouse to. Required only by `action=mouse_move` and `action=left_click_drag`.
+         */
+        coordinate?: number[];
+        /**
+         * Required only by `action=type` and `action=key`.
+         */
+        text?: string;
+    }, RESULT>;
+    experimental_toToolResultContent?: (result: RESULT) => ToolResultContent;
+}): {
+    type: 'provider-defined';
+    id: 'anthropic.computer_20241022';
+    args: {};
+    parameters: typeof Computer20241022Parameters;
+    execute: ExecuteFunction<z.infer<typeof Computer20241022Parameters>, RESULT>;
+    experimental_toToolResultContent?: (result: RESULT) => ToolResultContent;
+};
+declare const anthropicTools: {
+    bash_20241022: typeof bashTool_20241022;
+    textEditor_20241022: typeof textEditorTool_20241022;
+    computer_20241022: typeof computerTool_20241022;
+};
+
 interface AnthropicProvider extends ProviderV1 {
     /**
   Creates a model for text generation.
@@ -57,6 +246,10 @@ interface AnthropicProvider extends ProviderV1 {
   @deprecated Use `.languageModel()` instead.
      */
     messages(modelId: AnthropicMessagesModelId, settings?: AnthropicMessagesSettings): LanguageModelV1;
+    /**
+  Anthropic-specific computer use tool.
+     */
+    tools: typeof anthropicTools;
 }
 interface AnthropicProviderSettings {
     /**