@anthropic-ai/sdk 0.70.1 → 0.71.0

package/src/resources/beta/messages/batches.ts

@@ -10,6 +10,7 @@ import { RequestOptions } from '../../../internal/request-options';
 import { JSONLDecoder } from '../../../internal/decoders/jsonl';
 import { AnthropicError } from '../../../error';
 import { path } from '../../../internal/utils/path';
+import * as MessagesApi from '../../messages/messages';
 
 export class Batches extends APIResource {
   /**
@@ -438,10 +439,313 @@ export namespace BatchCreateParams {
     /**
      * Messages API creation parameters for the individual request.
      *
-     * See the [Messages API reference](/en/api/messages) for full documentation on
-     * available parameters.
+     * See the [Messages API reference](https://docs.claude.com/en/api/messages) for
+     * full documentation on available parameters.
      */
-    params: Omit<BetaMessagesAPI.MessageCreateParamsNonStreaming, 'betas'>;
+    params: Request.Params;
+  }
+
+  export namespace Request {
+    /**
+     * Messages API creation parameters for the individual request.
+     *
+     * See the [Messages API reference](https://docs.claude.com/en/api/messages) for
+     * full documentation on available parameters.
+     */
+    export interface Params {
+      /**
+       * The maximum number of tokens to generate before stopping.
+       *
+       * Note that our models may stop _before_ reaching this maximum. This parameter
+       * only specifies the absolute maximum number of tokens to generate.
+       *
+       * Different models have different maximum values for this parameter. See
+       * [models](https://docs.claude.com/en/docs/models-overview) for details.
+       */
+      max_tokens: number;
+
+      /**
+       * Input messages.
+       *
+       * Our models are trained to operate on alternating `user` and `assistant`
+       * conversational turns. When creating a new `Message`, you specify the prior
+       * conversational turns with the `messages` parameter, and the model then generates
+       * the next `Message` in the conversation. Consecutive `user` or `assistant` turns
+       * in your request will be combined into a single turn.
+       *
+       * Each input message must be an object with a `role` and `content`. You can
+       * specify a single `user`-role message, or you can include multiple `user` and
+       * `assistant` messages.
+       *
+       * If the final message uses the `assistant` role, the response content will
+       * continue immediately from the content in that message. This can be used to
+       * constrain part of the model's response.
+       *
+       * Example with a single `user` message:
+       *
+       * ```json
+       * [{ "role": "user", "content": "Hello, Claude" }]
+       * ```
+       *
+       * Example with multiple conversational turns:
+       *
+       * ```json
+       * [
+       *   { "role": "user", "content": "Hello there." },
+       *   { "role": "assistant", "content": "Hi, I'm Claude. How can I help you?" },
+       *   { "role": "user", "content": "Can you explain LLMs in plain English?" }
+       * ]
+       * ```
+       *
+       * Example with a partially-filled response from Claude:
+       *
+       * ```json
+       * [
+       *   {
+       *     "role": "user",
+       *     "content": "What's the Greek name for Sun? (A) Sol (B) Helios (C) Sun"
+       *   },
+       *   { "role": "assistant", "content": "The best answer is (" }
+       * ]
+       * ```
+       *
+       * Each input message `content` may be either a single `string` or an array of
+       * content blocks, where each block has a specific `type`. Using a `string` for
+       * `content` is shorthand for an array of one content block of type `"text"`. The
+       * following input messages are equivalent:
+       *
+       * ```json
+       * { "role": "user", "content": "Hello, Claude" }
+       * ```
+       *
+       * ```json
+       * { "role": "user", "content": [{ "type": "text", "text": "Hello, Claude" }] }
+       * ```
+       *
+       * See [input examples](https://docs.claude.com/en/api/messages-examples).
+       *
+       * Note that if you want to include a
+       * [system prompt](https://docs.claude.com/en/docs/system-prompts), you can use the
+       * top-level `system` parameter — there is no `"system"` role for input messages in
+       * the Messages API.
+       *
+       * There is a limit of 100,000 messages in a single request.
+       */
+      messages: Array<BetaMessagesAPI.BetaMessageParam>;
+
+      /**
+       * The model that will complete your prompt.\n\nSee
+       * [models](https://docs.anthropic.com/en/docs/models-overview) for additional
+       * details and options.
+       */
+      model: MessagesApi.Model;
+
+      /**
+       * Container identifier for reuse across requests.
+       */
+      container?: BetaMessagesAPI.BetaContainerParams | string | null;
+
+      /**
+       * Context management configuration.
+       *
+       * This allows you to control how Claude manages context across multiple requests,
+       * such as whether to clear function results or not.
+       */
+      context_management?: BetaMessagesAPI.BetaContextManagementConfig | null;
+
+      /**
+       * MCP servers to be utilized in this request
+       */
+      mcp_servers?: Array<BetaMessagesAPI.BetaRequestMCPServerURLDefinition>;
+
+      /**
+       * An object describing metadata about the request.
+       */
+      metadata?: BetaMessagesAPI.BetaMetadata;
+
+      /**
+       * Configuration options for the model's output. Controls aspects like how much
+       * effort the model puts into its response.
+       */
+      output_config?: BetaMessagesAPI.BetaOutputConfig;
+
+      /**
+       * A schema to specify Claude's output format in responses.
+       */
+      output_format?: BetaMessagesAPI.BetaJSONOutputFormat | null;
+
+      /**
+       * Determines whether to use priority capacity (if available) or standard capacity
+       * for this request.
+       *
+       * Anthropic offers different levels of service for your API requests. See
+       * [service-tiers](https://docs.claude.com/en/api/service-tiers) for details.
+       */
+      service_tier?: 'auto' | 'standard_only';
+
+      /**
+       * Custom text sequences that will cause the model to stop generating.
+       *
+       * Our models will normally stop when they have naturally completed their turn,
+       * which will result in a response `stop_reason` of `"end_turn"`.
+       *
+       * If you want the model to stop generating when it encounters custom strings of
+       * text, you can use the `stop_sequences` parameter. If the model encounters one of
+       * the custom sequences, the response `stop_reason` value will be `"stop_sequence"`
+       * and the response `stop_sequence` value will contain the matched stop sequence.
+       */
+      stop_sequences?: Array<string>;
+
+      /**
+       * Whether to incrementally stream the response using server-sent events.
+       *
+       * See [streaming](https://docs.claude.com/en/api/messages-streaming) for details.
+       */
+      stream?: boolean;
+
+      /**
+       * System prompt.
+       *
+       * A system prompt is a way of providing context and instructions to Claude, such
+       * as specifying a particular goal or role. See our
+       * [guide to system prompts](https://docs.claude.com/en/docs/system-prompts).
+       */
+      system?: string | Array<BetaMessagesAPI.BetaTextBlockParam>;
+
+      /**
+       * Amount of randomness injected into the response.
+       *
+       * Defaults to `1.0`. Ranges from `0.0` to `1.0`. Use `temperature` closer to `0.0`
+       * for analytical / multiple choice, and closer to `1.0` for creative and
+       * generative tasks.
+       *
+       * Note that even with `temperature` of `0.0`, the results will not be fully
+       * deterministic.
+       */
+      temperature?: number;
+
+      /**
+       * Configuration for enabling Claude's extended thinking.
+       *
+       * When enabled, responses include `thinking` content blocks showing Claude's
+       * thinking process before the final answer. Requires a minimum budget of 1,024
+       * tokens and counts towards your `max_tokens` limit.
+       *
+       * See
+       * [extended thinking](https://docs.claude.com/en/docs/build-with-claude/extended-thinking)
+       * for details.
+       */
+      thinking?: BetaMessagesAPI.BetaThinkingConfigParam;
+
+      /**
+       * How the model should use the provided tools. The model can use a specific tool,
+       * any available tool, decide by itself, or not use tools at all.
+       */
+      tool_choice?: BetaMessagesAPI.BetaToolChoice;
+
+      /**
+       * Definitions of tools that the model may use.
+       *
+       * If you include `tools` in your API request, the model may return `tool_use`
+       * content blocks that represent the model's use of those tools. You can then run
+       * those tools using the tool input generated by the model and then optionally
+       * return results back to the model using `tool_result` content blocks.
+       *
+       * There are two types of tools: **client tools** and **server tools**. The
+       * behavior described below applies to client tools. For
+       * [server tools](https://docs.claude.com/en/docs/agents-and-tools/tool-use/overview#server-tools),
+       * see their individual documentation as each has its own behavior (e.g., the
+       * [web search tool](https://docs.claude.com/en/docs/agents-and-tools/tool-use/web-search-tool)).
+       *
+       * Each tool definition includes:
+       *
+       * - `name`: Name of the tool.
+       * - `description`: Optional, but strongly-recommended description of the tool.
+       * - `input_schema`: [JSON schema](https://json-schema.org/draft/2020-12) for the
+       *   tool `input` shape that the model will produce in `tool_use` output content
+       *   blocks.
+       *
+       * For example, if you defined `tools` as:
+       *
+       * ```json
+       * [
+       *   {
+       *     "name": "get_stock_price",
+       *     "description": "Get the current stock price for a given ticker symbol.",
+       *     "input_schema": {
+       *       "type": "object",
+       *       "properties": {
+       *         "ticker": {
+       *           "type": "string",
+       *           "description": "The stock ticker symbol, e.g. AAPL for Apple Inc."
+       *         }
+       *       },
+       *       "required": ["ticker"]
+       *     }
+       *   }
+       * ]
+       * ```
+       *
+       * And then asked the model "What's the S&P 500 at today?", the model might produce
+       * `tool_use` content blocks in the response like this:
+       *
+       * ```json
+       * [
+       *   {
+       *     "type": "tool_use",
+       *     "id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
+       *     "name": "get_stock_price",
+       *     "input": { "ticker": "^GSPC" }
+       *   }
+       * ]
+       * ```
+       *
+       * You might then run your `get_stock_price` tool with `{"ticker": "^GSPC"}` as an
+       * input, and return the following back to the model in a subsequent `user`
+       * message:
+       *
+       * ```json
+       * [
+       *   {
+       *     "type": "tool_result",
+       *     "tool_use_id": "toolu_01D7FLrfh4GYq7yT1ULFeyMV",
+       *     "content": "259.75 USD"
+       *   }
+       * ]
+       * ```
+       *
+       * Tools can be used for workflows that include running client-side tools and
+       * functions, or more generally whenever you want the model to produce a particular
+       * JSON structure of output.
+       *
+       * See our [guide](https://docs.claude.com/en/docs/tool-use) for more details.
+       */
+      tools?: Array<BetaMessagesAPI.BetaToolUnion>;
+
+      /**
+       * Only sample from the top K options for each subsequent token.
+       *
+       * Used to remove "long tail" low probability responses.
+       * [Learn more technical details here](https://towardsdatascience.com/how-to-sample-from-language-models-682bceb97277).
+       *
+       * Recommended for advanced use cases only. You usually only need to use
+       * `temperature`.
+       */
+      top_k?: number;
+
+      /**
+       * Use nucleus sampling.
+       *
+       * In nucleus sampling, we compute the cumulative distribution over all the options
+       * for each subsequent token in decreasing probability order and cut it off once it
+       * reaches a particular probability specified by `top_p`. You should either alter
+       * `temperature` or `top_p`, but not both.
+       *
+       * Recommended for advanced use cases only. You usually only need to use
+       * `temperature`.
+       */
+      top_p?: number;
+    }
   }
 }
 

package/src/resources/beta/messages/index.ts

@@ -75,6 +75,7 @@ export {
   type BetaContextManagementConfig,
   type BetaContextManagementResponse,
   type BetaCountTokensContextManagementResponse,
+  type BetaDirectCaller,
   type BetaDocumentBlock,
   type BetaFileDocumentSource,
   type BetaFileImageSource,
@@ -86,6 +87,7 @@ export {
   type BetaMCPToolResultBlock,
   type BetaMCPToolUseBlock,
   type BetaMCPToolUseBlockParam,
+  type BetaMCPToolset,
   type BetaMemoryTool20250818,
   type BetaMemoryTool20250818Command,
   type BetaMemoryTool20250818CreateCommand,
@@ -99,6 +101,7 @@ export {
   type BetaMessageParam,
   type BetaMessageTokensCount,
   type BetaMetadata,
+  type BetaOutputConfig,
   type BetaPlainTextSource,
   type BetaRawContentBlockDelta,
   type BetaRawContentBlockDeltaEvent,
@@ -115,6 +118,7 @@ export {
   type BetaRequestMCPServerURLDefinition,
   type BetaRequestMCPToolResultBlockParam,
   type BetaSearchResultBlockParam,
+  type BetaServerToolCaller,
   type BetaServerToolUsage,
   type BetaServerToolUseBlock,
   type BetaServerToolUseBlockParam,
@@ -154,8 +158,10 @@ export {
   type BetaToolChoiceTool,
   type BetaToolComputerUse20241022,
   type BetaToolComputerUse20250124,
+  type BetaToolComputerUse20251124,
+  type BetaToolReferenceBlock,
+  type BetaToolReferenceBlockParam,
   type BetaToolResultBlockParam,
-  type BetaToolResultContentBlockParam,
   type BetaToolTextEditor20241022,
   type BetaToolTextEditor20250124,
   type BetaToolTextEditor20250429,
@@ -192,5 +198,16 @@ export {
   type MessageCreateParamsStreaming,
   type MessageCountTokensParams,
   type BetaMessageStreamParams,
+  type BetaToolSearchToolBm25_20251119,
+  type BetaToolSearchToolRegex20251119,
+  type BetaToolSearchToolResultBlock,
+  type BetaToolSearchToolResultBlockParam,
+  type BetaToolSearchToolResultError,
+  type BetaToolSearchToolResultErrorParam,
+  type BetaToolSearchToolSearchResultBlock,
+  type BetaToolSearchToolSearchResultBlockParam,
+  type BetaMCPToolConfig,
+  type BetaMCPToolDefaultConfig,
+  type BetaToolResultContentBlockParam,
 } from './messages';
 export { BetaToolRunner, type BetaToolRunnerParams } from './messages';