openai 7.4.0 → 7.6.0

package/src/resources/beta/responses/responses.ts

@@ -1,4 +1,4 @@
-// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+// File generated from our OpenAPI spec by Castiron. See CONTRIBUTING.md for details.
 
 import { APIResource } from '../../../core/resource';
 import * as ResponsesAPI from './responses';
@@ -919,6 +919,8 @@ export interface BetaFunctionTool {
   output_schema?: { [key: string]: unknown } | null;
 }
 
+export type BetaImageDetail = 'low' | 'high' | 'auto' | 'original';
+
 export interface BetaInlineSkill {
   /**
    * The description of the skill.
@@ -990,6 +992,35 @@ export interface BetaLocalSkill {
   path: string;
 }
 
+export type BetaMcpToolCallError =
+  | BetaMcpToolCallError.McpProtocolError
+  | BetaMcpToolCallError.McpToolExecutionError
+  | BetaMcpToolCallError.HTTPError;
+
+export namespace BetaMcpToolCallError {
+  export interface McpProtocolError {
+    code: number;
+
+    message: string;
+
+    type: 'mcp_protocol_error';
+  }
+
+  export interface McpToolExecutionError {
+    content: unknown;
+
+    type: 'mcp_tool_execution_error';
+  }
+
+  export interface HTTPError {
+    code: number;
+
+    message: string;
+
+    type: 'http_error';
+  }
+}
+
 /**
  * Groups function/custom tools under a shared namespace.
  */
@@ -1102,6 +1133,7 @@ export interface BetaResponse {
     | 'gpt-5.6-terra'
     | 'gpt-5.6-luna'
     | 'gpt-5.5'
+    | 'gpt-5.5-2026-04-23'
     | 'gpt-5.4'
     | 'gpt-5.4-mini'
     | 'gpt-5.4-nano'
@@ -1190,10 +1222,15 @@ export interface BetaResponse {
     | 'o4-mini-deep-research-2025-06-26'
     | 'computer-use-preview'
     | 'computer-use-preview-2025-03-11'
+    | 'gpt-5.5-pro'
+    | 'gpt-5.5-pro-2026-04-23'
     | 'gpt-5-codex'
     | 'gpt-5-pro'
     | 'gpt-5-pro-2025-10-06'
     | 'gpt-5.1-codex-max'
+    | 'gpt-daybreak-blue-latest'
+    | 'gpt-daybreak-red-latest'
+    | 'gpt-5.6-cyber'
     | (string & {});
 
   /**
@@ -1393,6 +1430,10 @@ export interface BetaResponse {
    *   Responses or Chat Completions. The response will show `service_tier=priority`
    *   regardless of if you specify `service_tier=fast` or `priority` in your
    *   request.
+   * - If set to 'ultrafast', then the request will be processed with the
+   *   access-controlled Ultrafast Processing service tier. This tier is currently
+   *   available for `gpt-5.6-sol`; a response served through it will show
+   *   `service_tier=ultrafast`.
    * - When not set, the default behavior is 'auto'.
    *
    * When the `service_tier` parameter is set, the response body will include the
@@ -1400,7 +1441,7 @@ export interface BetaResponse {
    * request. This response value may be different from the value set in the
    * parameter.
    */
-  service_tier?: 'auto' | 'default' | 'flex' | 'scale' | 'priority' | 'fast' | null;
+  service_tier?: BetaServiceTier | null;
 
   /**
    * The status of the response generation. One of `completed`, `failed`,
@@ -4397,6 +4438,26 @@ export interface BetaResponseImageGenCallPartialImageEvent {
    * The agent that owns this multi-agent streaming event.
    */
   agent?: BetaResponseImageGenCallPartialImageEvent.Agent | null;
+
+  /**
+   * The background setting that was used.
+   */
+  background?: string;
+
+  /**
+   * The output format that was used.
+   */
+  output_format?: string;
+
+  /**
+   * The image quality that was used.
+   */
+  quality?: string;
+
+  /**
+   * The image size that was used.
+   */
+  size?: string;
 }
 
 export namespace BetaResponseImageGenCallPartialImageEvent {
@@ -4787,7 +4848,7 @@ export interface BetaResponseInputImage {
    * The detail level of the image to be sent to the model. One of `high`, `low`,
    * `auto`, or `original`. Defaults to `auto`.
    */
-  detail: 'low' | 'high' | 'auto' | 'original';
+  detail: BetaImageDetail;
 
   /**
    * The type of the input item. Always `input_image`.
@@ -4841,7 +4902,7 @@ export interface BetaResponseInputImageContent {
    * The detail level of the image to be sent to the model. One of `high`, `low`,
    * `auto`, or `original`. Defaults to `auto`.
    */
-  detail?: 'low' | 'high' | 'auto' | 'original' | null;
+  detail?: BetaImageDetail | null;
 
   /**
    * The ID of the file to be sent to the model.
@@ -6235,7 +6296,7 @@ export namespace BetaResponseInputItem {
     /**
      * The error from the tool call, if any.
      */
-    error?: string | null;
+    error?: ResponsesAPI.BetaMcpToolCallError | null;
 
     /**
      * The output from the tool call.
@@ -6662,7 +6723,7 @@ export namespace BetaResponseItem {
        * The detail level of the screenshot image to be sent to the model. One of `high`,
        * `low`, `auto`, or `original`. Defaults to `auto`.
        */
-      detail: 'low' | 'high' | 'auto' | 'original';
+      detail: ResponsesAPI.BetaImageDetail;
 
       /**
        * The identifier of an uploaded file that contains the screenshot.
@@ -7332,7 +7393,7 @@ export namespace BetaResponseItem {
     /**
      * The error from the tool call, if any.
      */
-    error?: string | null;
+    error?: ResponsesAPI.BetaMcpToolCallError | null;
 
     /**
      * The output from the tool call.
@@ -7866,7 +7927,7 @@ export namespace BetaResponseOutputItem {
        * The detail level of the screenshot image to be sent to the model. One of `high`,
        * `low`, `auto`, or `original`. Defaults to `auto`.
        */
-      detail: 'low' | 'high' | 'auto' | 'original';
+      detail: ResponsesAPI.BetaImageDetail;
 
       /**
        * The identifier of an uploaded file that contains the screenshot.
@@ -8370,7 +8431,7 @@ export namespace BetaResponseOutputItem {
     /**
      * The error from the tool call, if any.
      */
-    error?: string | null;
+    error?: ResponsesAPI.BetaMcpToolCallError | null;
 
     /**
      * The output from the tool call.
@@ -8568,7 +8629,10 @@ export namespace BetaResponseOutputItem {
  */
 export interface BetaResponseOutputItemAddedEvent {
   /**
-   * The output item that was added.
+   * The output item that was added. For reasoning items, `encrypted_content` may be
+   * incomplete while the item is in progress. Use the reasoning item from the
+   * corresponding `response.output_item.done` event when passing it as input to a
+   * subsequent request.
    */
   item: BetaResponseOutputItem;
 
@@ -8888,9 +8952,14 @@ export namespace BetaResponseOutputText {
  */
 export interface BetaResponseOutputTextAnnotationAddedEvent {
   /**
-   * The annotation object being added. (See annotation schema for details.)
+   * An annotation that applies to a span of output text.
    */
-  annotation: unknown;
+  annotation:
+    | BetaResponseOutputTextAnnotationAddedEvent.FileCitation
+    | BetaResponseOutputTextAnnotationAddedEvent.URLCitation
+    | BetaResponseOutputTextAnnotationAddedEvent.ContainerFileCitation
+    | BetaResponseOutputTextAnnotationAddedEvent.FilePath
+    | null;
 
   /**
    * The index of the annotation within the content part.
@@ -8929,6 +8998,116 @@ export interface BetaResponseOutputTextAnnotationAddedEvent {
 }
 
 export namespace BetaResponseOutputTextAnnotationAddedEvent {
+  /**
+   * A citation to a file.
+   */
+  export interface FileCitation {
+    /**
+     * The ID of the file.
+     */
+    file_id: string;
+
+    /**
+     * The filename of the file cited.
+     */
+    filename: string;
+
+    /**
+     * The index of the file in the list of files.
+     */
+    index: number;
+
+    /**
+     * The type of the file citation. Always `file_citation`.
+     */
+    type: 'file_citation';
+  }
+
+  /**
+   * A citation for a web resource used to generate a model response.
+   */
+  export interface URLCitation {
+    /**
+     * The index of the last character of the URL citation in the message.
+     */
+    end_index: number;
+
+    /**
+     * The index of the first character of the URL citation in the message.
+     */
+    start_index: number;
+
+    /**
+     * The title of the web resource.
+     */
+    title: string;
+
+    /**
+     * The type of the URL citation. Always `url_citation`.
+     */
+    type: 'url_citation';
+
+    /**
+     * The URL of the web resource.
+     */
+    url: string;
+  }
+
+  /**
+   * A citation for a container file used to generate a model response.
+   */
+  export interface ContainerFileCitation {
+    /**
+     * The ID of the container file.
+     */
+    container_id: string;
+
+    /**
+     * The index of the last character of the container file citation in the message.
+     */
+    end_index: number;
+
+    /**
+     * The ID of the file.
+     */
+    file_id: string;
+
+    /**
+     * The filename of the container file cited.
+     */
+    filename: string;
+
+    /**
+     * The index of the first character of the container file citation in the message.
+     */
+    start_index: number;
+
+    /**
+     * The type of the container file citation. Always `container_file_citation`.
+     */
+    type: 'container_file_citation';
+  }
+
+  /**
+   * A path to a file.
+   */
+  export interface FilePath {
+    /**
+     * The ID of the file.
+     */
+    file_id: string;
+
+    /**
+     * The index of the file in the list of files.
+     */
+    index: number;
+
+    /**
+     * The type of the file path. Always `file_path`.
+     */
+    type: 'file_path';
+  }
+
   /**
    * The agent that owns this multi-agent streaming event.
    */
@@ -9038,6 +9217,11 @@ export interface BetaResponseReasoningItem {
    * The encrypted content of the reasoning item. This is populated by default for
    * reasoning items returned by `POST /v1/responses` and WebSocket `response.create`
    * requests.
+   *
+   * When streaming, use the completed reasoning item and its `encrypted_content`
+   * from the `response.output_item.done` event in subsequent requests. The
+   * `encrypted_content` in `response.output_item.added` may be incomplete. This is
+   * especially important when `store` is `false` or when using Zero Data Retention.
    */
   encrypted_content?: string | null;
 
@@ -9543,191 +9727,41 @@ export namespace BetaResponseRefusalDoneEvent {
 }
 
 /**
- * The status of the response generation. One of `completed`, `failed`,
- * `in_progress`, `cancelled`, `queued`, or `incomplete`.
- */
-export type BetaResponseStatus =
-  | 'completed'
-  | 'failed'
-  | 'in_progress'
-  | 'cancelled'
-  | 'queued'
-  | 'incomplete';
-
-/**
- * Emitted when there is a partial audio response.
- */
-export type BetaResponseStreamEvent =
-  | BetaResponseAudioDeltaEvent
-  | BetaResponseAudioDoneEvent
-  | BetaResponseAudioTranscriptDeltaEvent
-  | BetaResponseAudioTranscriptDoneEvent
-  | BetaResponseCodeInterpreterCallCodeDeltaEvent
-  | BetaResponseCodeInterpreterCallCodeDoneEvent
-  | BetaResponseCodeInterpreterCallCompletedEvent
-  | BetaResponseCodeInterpreterCallInProgressEvent
-  | BetaResponseCodeInterpreterCallInterpretingEvent
-  | BetaResponseCompletedEvent
-  | BetaResponseContentPartAddedEvent
-  | BetaResponseContentPartDoneEvent
-  | BetaResponseCreatedEvent
-  | BetaResponseErrorEvent
-  | BetaResponseFileSearchCallCompletedEvent
-  | BetaResponseFileSearchCallInProgressEvent
-  | BetaResponseFileSearchCallSearchingEvent
-  | BetaResponseFunctionCallArgumentsDeltaEvent
-  | BetaResponseFunctionCallArgumentsDoneEvent
-  | BetaResponseInProgressEvent
-  | BetaResponseFailedEvent
-  | BetaResponseIncompleteEvent
-  | BetaResponseOutputItemAddedEvent
-  | BetaResponseOutputItemDoneEvent
-  | BetaResponseReasoningSummaryPartAddedEvent
-  | BetaResponseReasoningSummaryPartDoneEvent
-  | BetaResponseReasoningSummaryTextDeltaEvent
-  | BetaResponseReasoningSummaryTextDoneEvent
-  | BetaResponseReasoningTextDeltaEvent
-  | BetaResponseReasoningTextDoneEvent
-  | BetaResponseRefusalDeltaEvent
-  | BetaResponseRefusalDoneEvent
-  | BetaResponseTextDeltaEvent
-  | BetaResponseTextDoneEvent
-  | BetaResponseWebSearchCallCompletedEvent
-  | BetaResponseWebSearchCallInProgressEvent
-  | BetaResponseWebSearchCallSearchingEvent
-  | BetaResponseImageGenCallCompletedEvent
-  | BetaResponseImageGenCallGeneratingEvent
-  | BetaResponseImageGenCallInProgressEvent
-  | BetaResponseImageGenCallPartialImageEvent
-  | BetaResponseMcpCallArgumentsDeltaEvent
-  | BetaResponseMcpCallArgumentsDoneEvent
-  | BetaResponseMcpCallCompletedEvent
-  | BetaResponseMcpCallFailedEvent
-  | BetaResponseMcpCallInProgressEvent
-  | BetaResponseMcpListToolsCompletedEvent
-  | BetaResponseMcpListToolsFailedEvent
-  | BetaResponseMcpListToolsInProgressEvent
-  | BetaResponseOutputTextAnnotationAddedEvent
-  | BetaResponseQueuedEvent
-  | BetaResponseCustomToolCallInputDeltaEvent
-  | BetaResponseCustomToolCallInputDoneEvent;
-
-/**
- * Configuration options for a text response from the model. Can be plain text or
- * structured JSON data. Learn more:
- *
- * - [Text inputs and outputs](https://platform.openai.com/docs/guides/text)
- * - [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs)
+ * A streaming event that indicated a shell command was added to a tool call.
  */
-export interface BetaResponseTextConfig {
+export interface BetaResponseShellCallCommandAddedEvent {
   /**
-   * An object specifying the format that the model must output.
-   *
-   * Configuring `{ "type": "json_schema" }` enables Structured Outputs, which
-   * ensures the model will match your supplied JSON schema. Learn more in the
-   * [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
-   *
-   * The default format is `{ "type": "text" }` with no additional options.
-   *
-   * **Not recommended for gpt-4o and newer models:**
-   *
-   * Setting to `{ "type": "json_object" }` enables the older JSON mode, which
-   * ensures the message the model generates is valid JSON. Using `json_schema` is
-   * preferred for models that support it.
+   * The shell command that was added.
    */
-  format?: BetaResponseFormatTextConfig;
+  command: string;
 
   /**
-   * Constrains the verbosity of the model's response. Lower values will result in
-   * more concise responses, while higher values will result in more verbose
-   * responses. Currently supported values are `low`, `medium`, and `high`. The
-   * default is `medium`.
+   * The index of the shell command that was added.
    */
-  verbosity?: 'low' | 'medium' | 'high' | null;
-}
+  command_index: number;
 
-/**
- * Emitted when there is an additional text delta.
- */
-export interface BetaResponseTextDeltaEvent {
   /**
-   * The index of the content part that the text delta was added to.
+   * The index of the output item that was updated.
    */
-  content_index: number;
+  output_index: number;
 
   /**
-   * The text delta that was added.
+   * The sequence number of the event that was emitted.
    */
-  delta: string;
+  sequence_number: number;
 
   /**
-   * The ID of the output item that the text delta was added to.
+   * The type of the event, always `response.shell_call_command.added`.
    */
-  item_id: string;
+  type: 'response.shell_call_command.added';
 
   /**
-   * The log probabilities of the tokens in the delta.
+   * The agent that owns this multi-agent streaming event.
    */
-  logprobs: Array<BetaResponseTextDeltaEvent.Logprob>;
-
-  /**
-   * The index of the output item that the text delta was added to.
-   */
-  output_index: number;
-
-  /**
-   * The sequence number for this event.
-   */
-  sequence_number: number;
-
-  /**
-   * The type of the event. Always `response.output_text.delta`.
-   */
-  type: 'response.output_text.delta';
-
-  /**
-   * The agent that owns this multi-agent streaming event.
-   */
-  agent?: BetaResponseTextDeltaEvent.Agent | null;
-}
-
-export namespace BetaResponseTextDeltaEvent {
-  /**
-   * A logprob is the logarithmic probability that the model assigns to producing a
-   * particular token at a given position in the sequence. Less-negative (higher)
-   * logprob values indicate greater model confidence in that token choice.
-   */
-  export interface Logprob {
-    /**
-     * A possible text token.
-     */
-    token: string;
-
-    /**
-     * The log probability of this token.
-     */
-    logprob: number;
-
-    /**
-     * The log probabilities of up to 20 of the most likely tokens.
-     */
-    top_logprobs?: Array<Logprob.TopLogprob>;
-  }
-
-  export namespace Logprob {
-    export interface TopLogprob {
-      /**
-       * A possible text token.
-       */
-      token?: string;
-
-      /**
-       * The log probability of this token.
-       */
-      logprob?: number;
-    }
-  }
+  agent?: BetaResponseShellCallCommandAddedEvent.Agent;
+}
 
+export namespace BetaResponseShellCallCommandAddedEvent {
   /**
    * The agent that owns this multi-agent streaming event.
    */
@@ -9740,87 +9774,46 @@ export namespace BetaResponseTextDeltaEvent {
 }
 
 /**
- * Emitted when text content is finalized.
+ * A streaming event that indicated a shell command was incrementally updated.
  */
-export interface BetaResponseTextDoneEvent {
-  /**
-   * The index of the content part that the text content is finalized.
-   */
-  content_index: number;
-
+export interface BetaResponseShellCallCommandDeltaEvent {
   /**
-   * The ID of the output item that the text content is finalized.
+   * The index of the shell command that was updated.
    */
-  item_id: string;
+  command_index: number;
 
   /**
-   * The log probabilities of the tokens in the delta.
+   * The shell command delta that was appended.
    */
-  logprobs: Array<BetaResponseTextDoneEvent.Logprob>;
+  delta: string;
 
   /**
-   * The index of the output item that the text content is finalized.
+   * The index of the output item that was updated.
    */
   output_index: number;
 
   /**
-   * The sequence number for this event.
+   * The sequence number of the event that was emitted.
    */
   sequence_number: number;
 
   /**
-   * The text content that is finalized.
-   */
-  text: string;
-
-  /**
-   * The type of the event. Always `response.output_text.done`.
+   * The type of the event, always `response.shell_call_command.delta`.
    */
-  type: 'response.output_text.done';
+  type: 'response.shell_call_command.delta';
 
   /**
    * The agent that owns this multi-agent streaming event.
    */
-  agent?: BetaResponseTextDoneEvent.Agent | null;
-}
+  agent?: BetaResponseShellCallCommandDeltaEvent.Agent;
 
-export namespace BetaResponseTextDoneEvent {
   /**
-   * A logprob is the logarithmic probability that the model assigns to producing a
-   * particular token at a given position in the sequence. Less-negative (higher)
-   * logprob values indicate greater model confidence in that token choice.
+   * An obfuscation string that was added to pad the event payload.
    */
-  export interface Logprob {
-    /**
-     * A possible text token.
-     */
-    token: string;
-
-    /**
-     * The log probability of this token.
-     */
-    logprob: number;
-
-    /**
-     * The log probabilities of up to 20 of the most likely tokens.
-     */
-    top_logprobs?: Array<Logprob.TopLogprob>;
-  }
-
-  export namespace Logprob {
-    export interface TopLogprob {
-      /**
-       * A possible text token.
-       */
-      token?: string;
-
-      /**
-       * The log probability of this token.
-       */
-      logprob?: number;
-    }
-  }
+  obfuscation?: string;
+}
 
+export namespace BetaResponseShellCallCommandDeltaEvent {
   /**
    * The agent that owns this multi-agent streaming event.
    */
@@ -9832,51 +9825,44 @@ export namespace BetaResponseTextDoneEvent {
   }
 }
 
-export interface BetaResponseToolSearchCall {
-  /**
-   * The unique ID of the tool search call item.
-   */
-  id: string;
-
-  /**
-   * Arguments used for the tool search call.
-   */
-  arguments: unknown;
-
+/**
+ * A streaming event that indicated a shell command was completed.
+ */
+export interface BetaResponseShellCallCommandDoneEvent {
   /**
-   * The unique ID of the tool search call generated by the model.
+   * The final shell command that was emitted.
    */
-  call_id: string | null;
+  command: string;
 
   /**
-   * Whether tool search was executed by the server or by the client.
+   * The index of the shell command that was completed.
    */
-  execution: 'server' | 'client';
+  command_index: number;
 
   /**
-   * The status of the tool search call item that was recorded.
+   * The index of the output item that was updated.
    */
-  status: 'in_progress' | 'completed' | 'incomplete';
+  output_index: number;
 
   /**
-   * The type of the item. Always `tool_search_call`.
+   * The sequence number of the event that was emitted.
    */
-  type: 'tool_search_call';
+  sequence_number: number;
 
   /**
-   * The agent that produced this item.
+   * The type of the event, always `response.shell_call_command.done`.
    */
-  agent?: BetaResponseToolSearchCall.Agent;
+  type: 'response.shell_call_command.done';
 
   /**
-   * The identifier of the actor that created the item.
+   * The agent that owns this multi-agent streaming event.
    */
-  created_by?: string;
+  agent?: BetaResponseShellCallCommandDoneEvent.Agent;
 }
 
-export namespace BetaResponseToolSearchCall {
+export namespace BetaResponseShellCallCommandDoneEvent {
   /**
-   * The agent that produced this item.
+   * The agent that owns this multi-agent streaming event.
    */
   export interface Agent {
     /**
@@ -9886,51 +9872,64 @@ export namespace BetaResponseToolSearchCall {
   }
 }
 
-export interface BetaResponseToolSearchOutputItem {
+/**
+ * A streaming event that indicated shell call output was incrementally added.
+ */
+export interface BetaResponseShellCallOutputContentDeltaEvent {
   /**
-   * The unique ID of the tool search output item.
+   * The index of the shell command that produced output.
    */
-  id: string;
+  command_index: number;
 
   /**
-   * The unique ID of the tool search call generated by the model.
+   * The stdout/stderr delta that was emitted.
    */
-  call_id: string | null;
+  delta: BetaResponseShellCallOutputContentDeltaEvent.Delta;
 
   /**
-   * Whether tool search was executed by the server or by the client.
+   * The ID of the output item that was updated.
    */
-  execution: 'server' | 'client';
+  item_id: string;
 
   /**
-   * The status of the tool search output item that was recorded.
+   * The index of the output item that was updated.
    */
-  status: 'in_progress' | 'completed' | 'incomplete';
+  output_index: number;
 
   /**
-   * The loaded tool definitions returned by tool search.
+   * The sequence number of the event that was emitted.
    */
-  tools: Array<BetaTool>;
+  sequence_number: number;
 
   /**
-   * The type of the item. Always `tool_search_output`.
+   * The type of the event, always `response.shell_call_output_content.delta`.
    */
-  type: 'tool_search_output';
+  type: 'response.shell_call_output_content.delta';
 
   /**
-   * The agent that produced this item.
+   * The agent that owns this multi-agent streaming event.
    */
-  agent?: BetaResponseToolSearchOutputItem.Agent;
+  agent?: BetaResponseShellCallOutputContentDeltaEvent.Agent;
+}
 
+export namespace BetaResponseShellCallOutputContentDeltaEvent {
   /**
-   * The identifier of the actor that created the item.
+   * The stdout/stderr delta that was emitted.
    */
-  created_by?: string;
-}
+  export interface Delta {
+    /**
+     * The stderr delta that was emitted.
+     */
+    stderr?: string;
+
+    /**
+     * The stdout delta that was emitted.
+     */
+    stdout?: string;
+  }
 
-export namespace BetaResponseToolSearchOutputItem {
   /**
-   * The agent that produced this item.
+   * The agent that owns this multi-agent streaming event.
    */
   export interface Agent {
     /**
@@ -9940,187 +9939,302 @@ export namespace BetaResponseToolSearchOutputItem {
   }
 }
 
-export interface BetaResponseToolSearchOutputItemParam {
+/**
+ * A streaming event that indicated shell call output was completed.
+ */
+export interface BetaResponseShellCallOutputContentDoneEvent {
   /**
-   * The loaded tool definitions returned by the tool search output.
+   * The index of the shell command that produced output.
    */
-  tools: Array<BetaTool>;
+  command_index: number;
 
   /**
-   * The item type. Always `tool_search_output`.
+   * The ID of the output item that was updated.
    */
-  type: 'tool_search_output';
+  item_id: string;
 
   /**
-   * The unique ID of this tool search output.
+   * The output contents emitted for the shell command.
    */
-  id?: string | null;
+  output: Array<BetaResponseShellCallOutputContentDoneEvent.Output>;
 
   /**
-   * The agent that produced this item.
+   * The index of the output item that was updated.
    */
-  agent?: BetaResponseToolSearchOutputItemParam.Agent | null;
+  output_index: number;
 
   /**
-   * The unique ID of the tool search call generated by the model.
+   * The sequence number of the event that was emitted.
    */
-  call_id?: string | null;
+  sequence_number: number;
 
   /**
-   * Whether tool search was executed by the server or by the client.
+   * The type of the event, always `response.shell_call_output_content.done`.
    */
-  execution?: 'server' | 'client';
+  type: 'response.shell_call_output_content.done';
 
   /**
-   * The status of the tool search output.
+   * The agent that owns this multi-agent streaming event.
    */
-  status?: 'in_progress' | 'completed' | 'incomplete' | null;
+  agent?: BetaResponseShellCallOutputContentDoneEvent.Agent;
 }
 
-export namespace BetaResponseToolSearchOutputItemParam {
+export namespace BetaResponseShellCallOutputContentDoneEvent {
   /**
-   * The agent that produced this item.
+   * The content of a shell tool call output that was emitted.
    */
-  export interface Agent {
+  export interface Output {
     /**
-     * The canonical name of the agent that produced this item.
+     * Represents either an exit outcome (with an exit code) or a timeout outcome for a
+     * shell call output chunk.
      */
-    agent_name: string;
-  }
-}
-
-/**
- * Represents token usage details including input tokens, output tokens, a
- * breakdown of output tokens, and the total tokens used.
- */
-export interface BetaResponseUsage {
-  /**
-   * The number of input tokens.
-   */
-  input_tokens: number;
-
-  /**
-   * A detailed breakdown of the input tokens.
-   */
-  input_tokens_details: BetaResponseUsage.InputTokensDetails;
-
-  /**
-   * The number of output tokens.
-   */
-  output_tokens: number;
-
-  /**
-   * A detailed breakdown of the output tokens.
-   */
-  output_tokens_details: BetaResponseUsage.OutputTokensDetails;
-
-  /**
-   * The total number of tokens used.
-   */
-  total_tokens: number;
-}
+    outcome: Output.Timeout | Output.Exit;
 
-export namespace BetaResponseUsage {
-  /**
-   * A detailed breakdown of the input tokens.
-   */
-  export interface InputTokensDetails {
     /**
-     * The number of input tokens that were written to the cache.
+     * The standard error output that was captured.
      */
-    cache_write_tokens: number;
+    stderr: string;
 
     /**
-     * The number of tokens that were retrieved from the cache.
-     * [More on prompt caching](https://platform.openai.com/docs/guides/prompt-caching).
+     * The standard output that was captured.
      */
-    cached_tokens: number;
+    stdout: string;
+
+    /**
+     * The identifier of the actor that created the item.
+     */
+    created_by?: string;
+  }
+
+  export namespace Output {
+    /**
+     * Indicates that the shell call exceeded its configured time limit.
+     */
+    export interface Timeout {
+      /**
+       * The outcome type. Always `timeout`.
+       */
+      type: 'timeout';
+    }
+
+    /**
+     * Indicates that the shell commands finished and returned an exit code.
+     */
+    export interface Exit {
+      /**
+       * Exit code from the shell process.
+       */
+      exit_code: number;
+
+      /**
+       * The outcome type. Always `exit`.
+       */
+      type: 'exit';
+    }
   }
 
   /**
-   * A detailed breakdown of the output tokens.
+   * The agent that owns this multi-agent streaming event.
    */
-  export interface OutputTokensDetails {
+  export interface Agent {
     /**
-     * The number of reasoning tokens.
+     * The canonical name of the agent that produced this item.
      */
-    reasoning_tokens: number;
+    agent_name: string;
   }
 }
 
 /**
- * Emitted when a web search call is completed.
+ * The status of the response generation. One of `completed`, `failed`,
+ * `in_progress`, `cancelled`, `queued`, or `incomplete`.
  */
-export interface BetaResponseWebSearchCallCompletedEvent {
-  /**
-   * Unique ID for the output item associated with the web search call.
-   */
-  item_id: string;
+export type BetaResponseStatus =
+  | 'completed'
+  | 'failed'
+  | 'in_progress'
+  | 'cancelled'
+  | 'queued'
+  | 'incomplete';
+
+/**
+ * Event emitted while a response is streamed.
+ */
+export type BetaResponseStreamEvent =
+  | BetaResponseAudioDeltaEvent
+  | BetaResponseAudioDoneEvent
+  | BetaResponseAudioTranscriptDeltaEvent
+  | BetaResponseAudioTranscriptDoneEvent
+  | BetaResponseCodeInterpreterCallCodeDeltaEvent
+  | BetaResponseCodeInterpreterCallCodeDoneEvent
+  | BetaResponseCodeInterpreterCallCompletedEvent
+  | BetaResponseCodeInterpreterCallInProgressEvent
+  | BetaResponseCodeInterpreterCallInterpretingEvent
+  | BetaResponseCompletedEvent
+  | BetaResponseContentPartAddedEvent
+  | BetaResponseContentPartDoneEvent
+  | BetaResponseCreatedEvent
+  | BetaResponseErrorEvent
+  | BetaResponseFileSearchCallCompletedEvent
+  | BetaResponseFileSearchCallInProgressEvent
+  | BetaResponseFileSearchCallSearchingEvent
+  | BetaResponseFunctionCallArgumentsDeltaEvent
+  | BetaResponseFunctionCallArgumentsDoneEvent
+  | BetaResponseShellCallCommandAddedEvent
+  | BetaResponseShellCallCommandDeltaEvent
+  | BetaResponseShellCallCommandDoneEvent
+  | BetaResponseShellCallOutputContentDeltaEvent
+  | BetaResponseShellCallOutputContentDoneEvent
+  | BetaResponseInProgressEvent
+  | BetaResponseFailedEvent
+  | BetaResponseIncompleteEvent
+  | BetaResponseOutputItemAddedEvent
+  | BetaResponseOutputItemDoneEvent
+  | BetaResponseReasoningSummaryPartAddedEvent
+  | BetaResponseReasoningSummaryPartDoneEvent
+  | BetaResponseReasoningSummaryTextDeltaEvent
+  | BetaResponseReasoningSummaryTextDoneEvent
+  | BetaResponseReasoningTextDeltaEvent
+  | BetaResponseReasoningTextDoneEvent
+  | BetaResponseRefusalDeltaEvent
+  | BetaResponseRefusalDoneEvent
+  | BetaResponseTextDeltaEvent
+  | BetaResponseTextDoneEvent
+  | BetaResponseWebSearchCallCompletedEvent
+  | BetaResponseWebSearchCallInProgressEvent
+  | BetaResponseWebSearchCallSearchingEvent
+  | BetaResponseImageGenCallCompletedEvent
+  | BetaResponseImageGenCallGeneratingEvent
+  | BetaResponseImageGenCallInProgressEvent
+  | BetaResponseImageGenCallPartialImageEvent
+  | BetaResponseMcpCallArgumentsDeltaEvent
+  | BetaResponseMcpCallArgumentsDoneEvent
+  | BetaResponseMcpCallCompletedEvent
+  | BetaResponseMcpCallFailedEvent
+  | BetaResponseMcpCallInProgressEvent
+  | BetaResponseMcpListToolsCompletedEvent
+  | BetaResponseMcpListToolsFailedEvent
+  | BetaResponseMcpListToolsInProgressEvent
+  | BetaResponseOutputTextAnnotationAddedEvent
+  | BetaResponseQueuedEvent
+  | BetaResponseCustomToolCallInputDeltaEvent
+  | BetaResponseCustomToolCallInputDoneEvent;
 
+/**
+ * Configuration options for a text response from the model. Can be plain text or
+ * structured JSON data. Learn more:
+ *
+ * - [Text inputs and outputs](https://platform.openai.com/docs/guides/text)
+ * - [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs)
+ */
+export interface BetaResponseTextConfig {
   /**
-   * The index of the output item that the web search call is associated with.
+   * An object specifying the format that the model must output.
+   *
+   * Configuring `{ "type": "json_schema" }` enables Structured Outputs, which
+   * ensures the model will match your supplied JSON schema. Learn more in the
+   * [Structured Outputs guide](https://platform.openai.com/docs/guides/structured-outputs).
+   *
+   * The default format is `{ "type": "text" }` with no additional options.
+   *
+   * **Not recommended for gpt-4o and newer models:**
+   *
+   * Setting to `{ "type": "json_object" }` enables the older JSON mode, which
+   * ensures the message the model generates is valid JSON. Using `json_schema` is
+   * preferred for models that support it.
    */
-  output_index: number;
+  format?: BetaResponseFormatTextConfig;
 
   /**
-   * The sequence number of the web search call being processed.
+   * Constrains the verbosity of the model's response. Lower values will result in
+   * more concise responses, while higher values will result in more verbose
+   * responses. Currently supported values are `low`, `medium`, and `high`. The
+   * default is `medium`.
    */
-  sequence_number: number;
+  verbosity?: 'low' | 'medium' | 'high' | null;
+}
 
+/**
+ * Emitted when there is an additional text delta.
+ */
+export interface BetaResponseTextDeltaEvent {
   /**
-   * The type of the event. Always `response.web_search_call.completed`.
+   * The index of the content part that the text delta was added to.
    */
-  type: 'response.web_search_call.completed';
+  content_index: number;
 
   /**
-   * The agent that owns this multi-agent streaming event.
+   * The text delta that was added.
    */
-  agent?: BetaResponseWebSearchCallCompletedEvent.Agent | null;
-}
+  delta: string;
 
-export namespace BetaResponseWebSearchCallCompletedEvent {
   /**
-   * The agent that owns this multi-agent streaming event.
+   * The ID of the output item that the text delta was added to.
    */
-  export interface Agent {
-    /**
-     * The canonical name of the agent that produced this item.
-     */
-    agent_name: string;
-  }
-}
+  item_id: string;
 
-/**
- * Emitted when a web search call is initiated.
- */
-export interface BetaResponseWebSearchCallInProgressEvent {
   /**
-   * Unique ID for the output item associated with the web search call.
+   * The log probabilities of the tokens in the delta.
    */
-  item_id: string;
+  logprobs: Array<BetaResponseTextDeltaEvent.Logprob>;
 
   /**
-   * The index of the output item that the web search call is associated with.
+   * The index of the output item that the text delta was added to.
    */
   output_index: number;
 
   /**
-   * The sequence number of the web search call being processed.
+   * The sequence number for this event.
    */
   sequence_number: number;
 
   /**
-   * The type of the event. Always `response.web_search_call.in_progress`.
+   * The type of the event. Always `response.output_text.delta`.
    */
-  type: 'response.web_search_call.in_progress';
+  type: 'response.output_text.delta';
 
   /**
    * The agent that owns this multi-agent streaming event.
    */
-  agent?: BetaResponseWebSearchCallInProgressEvent.Agent | null;
+  agent?: BetaResponseTextDeltaEvent.Agent | null;
 }
 
-export namespace BetaResponseWebSearchCallInProgressEvent {
+export namespace BetaResponseTextDeltaEvent {
+  /**
+   * A logprob is the logarithmic probability that the model assigns to producing a
+   * particular token at a given position in the sequence. Less-negative (higher)
+   * logprob values indicate greater model confidence in that token choice.
+   */
+  export interface Logprob {
+    /**
+     * A possible text token.
+     */
+    token: string;
+
+    /**
+     * The log probability of this token.
+     */
+    logprob: number;
+
+    /**
+     * The log probabilities of up to 20 of the most likely tokens.
+     */
+    top_logprobs?: Array<Logprob.TopLogprob>;
+  }
+
+  export namespace Logprob {
+    export interface TopLogprob {
+      /**
+       * A possible text token.
+       */
+      token?: string;
+
+      /**
+       * The log probability of this token.
+       */
+      logprob?: number;
+    }
+  }
+
   /**
    * The agent that owns this multi-agent streaming event.
    */
@@ -10133,737 +10247,1915 @@ export namespace BetaResponseWebSearchCallInProgressEvent {
 }
 
 /**
- * Emitted when a web search call is executing.
+ * Emitted when text content is finalized.
  */
-export interface BetaResponseWebSearchCallSearchingEvent {
+export interface BetaResponseTextDoneEvent {
   /**
-   * Unique ID for the output item associated with the web search call.
+   * The index of the content part that the text content is finalized.
+   */
+  content_index: number;
+
+  /**
+   * The ID of the output item that the text content is finalized.
    */
   item_id: string;
 
   /**
-   * The index of the output item that the web search call is associated with.
+   * The log probabilities of the tokens in the delta.
+   */
+  logprobs: Array<BetaResponseTextDoneEvent.Logprob>;
+
+  /**
+   * The index of the output item that the text content is finalized.
    */
   output_index: number;
 
   /**
-   * The sequence number of the web search call being processed.
+   * The sequence number for this event.
    */
   sequence_number: number;
 
   /**
-   * The type of the event. Always `response.web_search_call.searching`.
+   * The text content that is finalized.
    */
-  type: 'response.web_search_call.searching';
+  text: string;
 
   /**
-   * The agent that owns this multi-agent streaming event.
+   * The type of the event. Always `response.output_text.done`.
    */
-  agent?: BetaResponseWebSearchCallSearchingEvent.Agent | null;
-}
+  type: 'response.output_text.done';
 
-export namespace BetaResponseWebSearchCallSearchingEvent {
   /**
    * The agent that owns this multi-agent streaming event.
    */
+  agent?: BetaResponseTextDoneEvent.Agent | null;
+}
+
+export namespace BetaResponseTextDoneEvent {
+  /**
+   * A logprob is the logarithmic probability that the model assigns to producing a
+   * particular token at a given position in the sequence. Less-negative (higher)
+   * logprob values indicate greater model confidence in that token choice.
+   */
+  export interface Logprob {
+    /**
+     * A possible text token.
+     */
+    token: string;
+
+    /**
+     * The log probability of this token.
+     */
+    logprob: number;
+
+    /**
+     * The log probabilities of up to 20 of the most likely tokens.
+     */
+    top_logprobs?: Array<Logprob.TopLogprob>;
+  }
+
+  export namespace Logprob {
+    export interface TopLogprob {
+      /**
+       * A possible text token.
+       */
+      token?: string;
+
+      /**
+       * The log probability of this token.
+       */
+      logprob?: number;
+    }
+  }
+
+  /**
+   * The agent that owns this multi-agent streaming event.
+   */
+  export interface Agent {
+    /**
+     * The canonical name of the agent that produced this item.
+     */
+    agent_name: string;
+  }
+}
+
+export interface BetaResponseToolSearchCall {
+  /**
+   * The unique ID of the tool search call item.
+   */
+  id: string;
+
+  /**
+   * Arguments used for the tool search call.
+   */
+  arguments: unknown;
+
+  /**
+   * The unique ID of the tool search call generated by the model.
+   */
+  call_id: string | null;
+
+  /**
+   * Whether tool search was executed by the server or by the client.
+   */
+  execution: 'server' | 'client';
+
+  /**
+   * The status of the tool search call item that was recorded.
+   */
+  status: 'in_progress' | 'completed' | 'incomplete';
+
+  /**
+   * The type of the item. Always `tool_search_call`.
+   */
+  type: 'tool_search_call';
+
+  /**
+   * The agent that produced this item.
+   */
+  agent?: BetaResponseToolSearchCall.Agent;
+
+  /**
+   * The identifier of the actor that created the item.
+   */
+  created_by?: string;
+}
+
+export namespace BetaResponseToolSearchCall {
+  /**
+   * The agent that produced this item.
+   */
+  export interface Agent {
+    /**
+     * The canonical name of the agent that produced this item.
+     */
+    agent_name: string;
+  }
+}
+
+export interface BetaResponseToolSearchOutputItem {
+  /**
+   * The unique ID of the tool search output item.
+   */
+  id: string;
+
+  /**
+   * The unique ID of the tool search call generated by the model.
+   */
+  call_id: string | null;
+
+  /**
+   * Whether tool search was executed by the server or by the client.
+   */
+  execution: 'server' | 'client';
+
+  /**
+   * The status of the tool search output item that was recorded.
+   */
+  status: 'in_progress' | 'completed' | 'incomplete';
+
+  /**
+   * The loaded tool definitions returned by tool search.
+   */
+  tools: Array<BetaTool>;
+
+  /**
+   * The type of the item. Always `tool_search_output`.
+   */
+  type: 'tool_search_output';
+
+  /**
+   * The agent that produced this item.
+   */
+  agent?: BetaResponseToolSearchOutputItem.Agent;
+
+  /**
+   * The identifier of the actor that created the item.
+   */
+  created_by?: string;
+}
+
+export namespace BetaResponseToolSearchOutputItem {
+  /**
+   * The agent that produced this item.
+   */
+  export interface Agent {
+    /**
+     * The canonical name of the agent that produced this item.
+     */
+    agent_name: string;
+  }
+}
+
+export interface BetaResponseToolSearchOutputItemParam {
+  /**
+   * The loaded tool definitions returned by the tool search output.
+   */
+  tools: Array<BetaTool>;
+
+  /**
+   * The item type. Always `tool_search_output`.
+   */
+  type: 'tool_search_output';
+
+  /**
+   * The unique ID of this tool search output.
+   */
+  id?: string | null;
+
+  /**
+   * The agent that produced this item.
+   */
+  agent?: BetaResponseToolSearchOutputItemParam.Agent | null;
+
+  /**
+   * The unique ID of the tool search call generated by the model.
+   */
+  call_id?: string | null;
+
+  /**
+   * Whether tool search was executed by the server or by the client.
+   */
+  execution?: 'server' | 'client';
+
+  /**
+   * The status of the tool search output.
+   */
+  status?: 'in_progress' | 'completed' | 'incomplete' | null;
+}
+
+export namespace BetaResponseToolSearchOutputItemParam {
+  /**
+   * The agent that produced this item.
+   */
   export interface Agent {
     /**
-     * The canonical name of the agent that produced this item.
+     * The canonical name of the agent that produced this item.
+     */
+    agent_name: string;
+  }
+}
+
+/**
+ * Represents token usage details including input tokens, output tokens, a
+ * breakdown of output tokens, and the total tokens used.
+ */
+export interface BetaResponseUsage {
+  /**
+   * The number of input tokens.
+   */
+  input_tokens: number;
+
+  /**
+   * A detailed breakdown of the input tokens.
+   */
+  input_tokens_details: BetaResponseUsage.InputTokensDetails;
+
+  /**
+   * The number of output tokens.
+   */
+  output_tokens: number;
+
+  /**
+   * A detailed breakdown of the output tokens.
+   */
+  output_tokens_details: BetaResponseUsage.OutputTokensDetails;
+
+  /**
+   * The total number of tokens used.
+   */
+  total_tokens: number;
+}
+
+export namespace BetaResponseUsage {
+  /**
+   * A detailed breakdown of the input tokens.
+   */
+  export interface InputTokensDetails {
+    /**
+     * The number of input tokens that were written to the cache.
+     */
+    cache_write_tokens: number;
+
+    /**
+     * The number of tokens that were retrieved from the cache.
+     * [More on prompt caching](https://platform.openai.com/docs/guides/prompt-caching).
+     */
+    cached_tokens: number;
+  }
+
+  /**
+   * A detailed breakdown of the output tokens.
+   */
+  export interface OutputTokensDetails {
+    /**
+     * The number of reasoning tokens.
+     */
+    reasoning_tokens: number;
+  }
+}
+
+/**
+ * Emitted when a web search call is completed.
+ */
+export interface BetaResponseWebSearchCallCompletedEvent {
+  /**
+   * Unique ID for the output item associated with the web search call.
+   */
+  item_id: string;
+
+  /**
+   * The index of the output item that the web search call is associated with.
+   */
+  output_index: number;
+
+  /**
+   * The sequence number of the web search call being processed.
+   */
+  sequence_number: number;
+
+  /**
+   * The type of the event. Always `response.web_search_call.completed`.
+   */
+  type: 'response.web_search_call.completed';
+
+  /**
+   * The agent that owns this multi-agent streaming event.
+   */
+  agent?: BetaResponseWebSearchCallCompletedEvent.Agent | null;
+}
+
+export namespace BetaResponseWebSearchCallCompletedEvent {
+  /**
+   * The agent that owns this multi-agent streaming event.
+   */
+  export interface Agent {
+    /**
+     * The canonical name of the agent that produced this item.
+     */
+    agent_name: string;
+  }
+}
+
+/**
+ * Emitted when a web search call is initiated.
+ */
+export interface BetaResponseWebSearchCallInProgressEvent {
+  /**
+   * Unique ID for the output item associated with the web search call.
+   */
+  item_id: string;
+
+  /**
+   * The index of the output item that the web search call is associated with.
+   */
+  output_index: number;
+
+  /**
+   * The sequence number of the web search call being processed.
+   */
+  sequence_number: number;
+
+  /**
+   * The type of the event. Always `response.web_search_call.in_progress`.
+   */
+  type: 'response.web_search_call.in_progress';
+
+  /**
+   * The agent that owns this multi-agent streaming event.
+   */
+  agent?: BetaResponseWebSearchCallInProgressEvent.Agent | null;
+}
+
+export namespace BetaResponseWebSearchCallInProgressEvent {
+  /**
+   * The agent that owns this multi-agent streaming event.
+   */
+  export interface Agent {
+    /**
+     * The canonical name of the agent that produced this item.
+     */
+    agent_name: string;
+  }
+}
+
+/**
+ * Emitted when a web search call is executing.
+ */
+export interface BetaResponseWebSearchCallSearchingEvent {
+  /**
+   * Unique ID for the output item associated with the web search call.
+   */
+  item_id: string;
+
+  /**
+   * The index of the output item that the web search call is associated with.
+   */
+  output_index: number;
+
+  /**
+   * The sequence number of the web search call being processed.
+   */
+  sequence_number: number;
+
+  /**
+   * The type of the event. Always `response.web_search_call.searching`.
+   */
+  type: 'response.web_search_call.searching';
+
+  /**
+   * The agent that owns this multi-agent streaming event.
+   */
+  agent?: BetaResponseWebSearchCallSearchingEvent.Agent | null;
+}
+
+export namespace BetaResponseWebSearchCallSearchingEvent {
+  /**
+   * The agent that owns this multi-agent streaming event.
+   */
+  export interface Agent {
+    /**
+     * The canonical name of the agent that produced this item.
+     */
+    agent_name: string;
+  }
+}
+
+/**
+ * Client events accepted by the Responses WebSocket server.
+ */
+export type BetaResponsesClientEvent = BetaResponsesClientEvent.ResponseCreate | BetaResponseInjectEvent;
+
+export namespace BetaResponsesClientEvent {
+  /**
+   * Client event for creating a response over a persistent WebSocket connection.
+   * This payload uses the same top-level fields as `POST /v1/responses`, plus
+   * WebSocket-only envelope metadata.
+   *
+   * Notes:
+   *
+   * - `stream` is implicit over WebSocket and should not be sent.
+   * - `background` is not supported over WebSocket.
+   * - `stream_id` is WebSocket-only and is not part of `POST /v1/responses`.
+   */
+  export interface ResponseCreate {
+    /**
+     * The type of the client event. Always `response.create`.
+     */
+    type: 'response.create';
+
+    /**
+     * Whether to run the model response in the background.
+     * [Learn more](https://platform.openai.com/docs/guides/background).
+     */
+    background?: boolean | null;
+
+    /**
+     * Context management configuration for this request.
+     */
+    context_management?: Array<ResponseCreate.ContextManagement> | null;
+
+    /**
+     * The conversation that this response belongs to. Items from this conversation are
+     * prepended to `input_items` for this response request. Input items and output
+     * items from this response are automatically added to this conversation after this
+     * response completes.
+     */
+    conversation?: string | ResponsesAPI.BetaResponseConversationParam | null;
+
+    /**
+     * Specify additional output data to include in the model response. Currently
+     * supported values are:
+     *
+     * - `web_search_call.action.sources`: Include the sources of the web search tool
+     *   call.
+     * - `code_interpreter_call.outputs`: Includes the outputs of python code execution
+     *   in code interpreter tool call items.
+     * - `computer_call_output.output.image_url`: Include image urls from the computer
+     *   call output.
+     * - `file_search_call.results`: Include the search results of the file search tool
+     *   call.
+     * - `message.input_image.image_url`: Include image urls from the input message.
+     * - `message.output_text.logprobs`: Include logprobs with assistant messages.
+     * - `reasoning.encrypted_content`: Includes an encrypted version of reasoning
+     *   tokens in reasoning item outputs. This enables reasoning items to be used in
+     *   multi-turn conversations when using the Responses API statelessly (like when
+     *   the `store` parameter is set to `false`, or when an organization is enrolled
+     *   in the zero data retention program).
+     */
+    include?: Array<ResponsesAPI.BetaResponseIncludable> | null;
+
+    /**
+     * Text, image, or file inputs to the model, used to generate a response.
+     *
+     * Learn more:
+     *
+     * - [Text inputs and outputs](https://platform.openai.com/docs/guides/text)
+     * - [Image inputs](https://platform.openai.com/docs/guides/images)
+     * - [File inputs](https://platform.openai.com/docs/guides/pdf-files)
+     * - [Conversation state](https://platform.openai.com/docs/guides/conversation-state)
+     * - [Function calling](https://platform.openai.com/docs/guides/function-calling)
+     */
+    input?: string | ResponsesAPI.BetaResponseInput;
+
+    /**
+     * A system (or developer) message inserted into the model's context.
+     *
+     * When using along with `previous_response_id`, the instructions from a previous
+     * response will not be carried over to the next response. This makes it simple to
+     * swap out system (or developer) messages in new responses.
+     */
+    instructions?: string | null;
+
+    /**
+     * An upper bound for the number of tokens that can be generated for a response,
+     * including visible output tokens and
+     * [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+     */
+    max_output_tokens?: number | null;
+
+    /**
+     * The maximum number of total calls to built-in tools that can be processed in a
+     * response. This maximum number applies across all built-in tool calls, not per
+     * individual tool. Any further attempts to call a tool by the model will be
+     * ignored.
+     */
+    max_tool_calls?: number | null;
+
+    /**
+     * Set of 16 key-value pairs that can be attached to an object. This can be useful
+     * for storing additional information about the object in a structured format, and
+     * querying for objects via API or the dashboard.
+     *
+     * Keys are strings with a maximum length of 64 characters. Values are strings with
+     * a maximum length of 512 characters.
+     */
+    metadata?: { [key: string]: string } | null;
+
+    /**
+     * Model ID used to generate the response, like `gpt-4o` or `o3`. OpenAI offers a
+     * wide range of models with different capabilities, performance characteristics,
+     * and price points. Refer to the
+     * [model guide](https://platform.openai.com/docs/models) to browse and compare
+     * available models.
+     */
+    model?:
+      | 'gpt-5.6-sol'
+      | 'gpt-5.6-terra'
+      | 'gpt-5.6-luna'
+      | 'gpt-5.5'
+      | 'gpt-5.5-2026-04-23'
+      | 'gpt-5.4'
+      | 'gpt-5.4-mini'
+      | 'gpt-5.4-nano'
+      | 'gpt-5.4-mini-2026-03-17'
+      | 'gpt-5.4-nano-2026-03-17'
+      | 'gpt-5.3-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-5.1'
+      | 'gpt-5.1-2025-11-13'
+      | 'gpt-5.1-codex'
+      | 'gpt-5.1-mini'
+      | 'gpt-5.1-chat-latest'
+      | 'gpt-5'
+      | 'gpt-5-mini'
+      | 'gpt-5-nano'
+      | 'gpt-5-2025-08-07'
+      | 'gpt-5-mini-2025-08-07'
+      | 'gpt-5-nano-2025-08-07'
+      | 'gpt-5-chat-latest'
+      | 'gpt-4.1'
+      | 'gpt-4.1-mini'
+      | 'gpt-4.1-nano'
+      | 'gpt-4.1-2025-04-14'
+      | 'gpt-4.1-mini-2025-04-14'
+      | 'gpt-4.1-nano-2025-04-14'
+      | 'o4-mini'
+      | 'o4-mini-2025-04-16'
+      | 'o3'
+      | 'o3-2025-04-16'
+      | 'o3-mini'
+      | 'o3-mini-2025-01-31'
+      | 'o1'
+      | 'o1-2024-12-17'
+      | 'o1-preview'
+      | 'o1-preview-2024-09-12'
+      | 'o1-mini'
+      | 'o1-mini-2024-09-12'
+      | 'gpt-4o'
+      | 'gpt-4o-2024-11-20'
+      | 'gpt-4o-2024-08-06'
+      | 'gpt-4o-2024-05-13'
+      | 'gpt-4o-audio-preview'
+      | 'gpt-4o-audio-preview-2024-10-01'
+      | 'gpt-4o-audio-preview-2024-12-17'
+      | 'gpt-4o-audio-preview-2025-06-03'
+      | 'gpt-4o-mini-audio-preview'
+      | 'gpt-4o-mini-audio-preview-2024-12-17'
+      | 'gpt-4o-search-preview'
+      | 'gpt-4o-mini-search-preview'
+      | 'gpt-4o-search-preview-2025-03-11'
+      | 'gpt-4o-mini-search-preview-2025-03-11'
+      | 'chatgpt-4o-latest'
+      | 'codex-mini-latest'
+      | 'gpt-4o-mini'
+      | 'gpt-4o-mini-2024-07-18'
+      | 'gpt-4-turbo'
+      | 'gpt-4-turbo-2024-04-09'
+      | 'gpt-4-0125-preview'
+      | 'gpt-4-turbo-preview'
+      | 'gpt-4-1106-preview'
+      | 'gpt-4-vision-preview'
+      | 'gpt-4'
+      | 'gpt-4-0314'
+      | 'gpt-4-0613'
+      | 'gpt-4-32k'
+      | 'gpt-4-32k-0314'
+      | 'gpt-4-32k-0613'
+      | 'gpt-3.5-turbo'
+      | 'gpt-3.5-turbo-16k'
+      | 'gpt-3.5-turbo-0301'
+      | 'gpt-3.5-turbo-0613'
+      | 'gpt-3.5-turbo-1106'
+      | 'gpt-3.5-turbo-0125'
+      | 'gpt-3.5-turbo-16k-0613'
+      | 'o1-pro'
+      | 'o1-pro-2025-03-19'
+      | 'o3-pro'
+      | 'o3-pro-2025-06-10'
+      | 'o3-deep-research'
+      | 'o3-deep-research-2025-06-26'
+      | 'o4-mini-deep-research'
+      | 'o4-mini-deep-research-2025-06-26'
+      | 'computer-use-preview'
+      | 'computer-use-preview-2025-03-11'
+      | 'gpt-5.5-pro'
+      | 'gpt-5.5-pro-2026-04-23'
+      | 'gpt-5-codex'
+      | 'gpt-5-pro'
+      | 'gpt-5-pro-2025-10-06'
+      | 'gpt-5.1-codex-max'
+      | 'gpt-daybreak-blue-latest'
+      | 'gpt-daybreak-red-latest'
+      | 'gpt-5.6-cyber'
+      | (string & {});
+
+    /**
+     * Configuration for running moderation on the input and output of this response.
+     */
+    moderation?: ResponseCreate.Moderation | null;
+
+    /**
+     * Configuration for server-hosted multi-agent execution.
+     */
+    multi_agent?: ResponseCreate.MultiAgent | null;
+
+    /**
+     * Whether to allow the model to run tool calls in parallel.
+     */
+    parallel_tool_calls?: boolean | null;
+
+    /**
+     * The unique ID of the previous response to the model. Use this to create
+     * multi-turn conversations. Learn more about
+     * [conversation state](https://platform.openai.com/docs/guides/conversation-state).
+     * Cannot be used in conjunction with `conversation`.
+     */
+    previous_response_id?: string | null;
+
+    /**
+     * Reference to a prompt template and its variables.
+     * [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts).
+     */
+    prompt?: ResponsesAPI.BetaResponsePrompt | null;
+
+    /**
+     * Used by OpenAI to cache responses for similar requests to optimize your cache
+     * hit rates. Replaces the `user` field.
+     * [Learn more](https://platform.openai.com/docs/guides/prompt-caching).
+     */
+    prompt_cache_key?: string | null;
+
+    /**
+     * Options for prompt caching. Supported for `gpt-5.6` and later models. By
+     * default, OpenAI automatically chooses one implicit cache breakpoint. You can add
+     * explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each
+     * request can write up to four breakpoints. For cache matching, OpenAI considers
+     * up to the latest 80 breakpoints in the conversation, without a content-block
+     * lookback limit. Set `mode` to `explicit` to disable the implicit breakpoint. The
+     * `ttl` defaults to `30m`, which is currently the only supported value. See the
+     * [prompt caching guide](https://platform.openai.com/docs/guides/prompt-caching)
+     * for current details.
+     */
+    prompt_cache_options?: ResponseCreate.PromptCacheOptions;
+
+    /**
+     * @deprecated Deprecated. Use `prompt_cache_options.ttl` instead.
+     *
+     * The retention policy for the prompt cache. Set to `24h` to enable extended
+     * prompt caching, which keeps cached prefixes active for longer, up to a maximum
+     * of 24 hours.
+     * [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention).
+     * This field expresses a maximum retention policy, while
+     * `prompt_cache_options.ttl` expresses a minimum cache lifetime. The two fields
+     * are independent and do not interact. For `gpt-5.5`, `gpt-5.5-pro`, and future
+     * models, only `24h` is supported.
+     *
+     * For older models that support both `in_memory` and `24h`, the default depends on
+     * your organization's data retention policy:
+     *
+     * - Organizations without ZDR enabled default to `24h`.
+     * - Organizations with ZDR enabled default to `in_memory` when
+     *   `prompt_cache_retention` is not specified.
+     */
+    prompt_cache_retention?: 'in_memory' | '24h' | null;
+
+    /**
+     * **gpt-5 and o-series models only**
+     *
+     * Configuration options for
+     * [reasoning models](https://platform.openai.com/docs/guides/reasoning).
+     */
+    reasoning?: ResponseCreate.Reasoning | null;
+
+    /**
+     * A stable identifier used to help detect users of your application that may be
+     * violating OpenAI's usage policies. The IDs should be a string that uniquely
+     * identifies each user, with a maximum length of 64 characters. We recommend
+     * hashing their username or email address, in order to avoid sending us any
+     * identifying information.
+     * [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+     */
+    safety_identifier?: string | null;
+
+    /**
+     * Specifies the processing type used for serving the request.
+     *
+     * - If set to 'auto', then the request will be processed with the service tier
+     *   configured in the Project settings. Unless otherwise configured, the Project
+     *   will use 'default'.
+     * - If set to 'default', then the request will be processed with the standard
+     *   pricing and performance for the selected model.
+     * - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+     *   then the request will be processed with the Flex Processing service tier.
+     * - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+     *   include the `service_tier=fast` or `service_tier=priority` parameter for
+     *   Responses or Chat Completions. The response will show `service_tier=priority`
+     *   regardless of if you specify `service_tier=fast` or `priority` in your
+     *   request.
+     * - If set to 'ultrafast', then the request will be processed with the
+     *   access-controlled Ultrafast Processing service tier. This tier is currently
+     *   available for `gpt-5.6-sol`; a response served through it will show
+     *   `service_tier=ultrafast`.
+     * - When not set, the default behavior is 'auto'.
+     *
+     * When the `service_tier` parameter is set, the response body will include the
+     * `service_tier` value based on the processing mode actually used to serve the
+     * request. This response value may be different from the value set in the
+     * parameter.
+     */
+    service_tier?: ResponsesAPI.BetaServiceTier | null;
+
+    /**
+     * Whether to store the generated model response for later retrieval via API.
+     */
+    store?: boolean | null;
+
+    /**
+     * If set to true, the model response data will be streamed to the client as it is
+     * generated using
+     * [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
+     * See the
+     * [Streaming section below](https://platform.openai.com/docs/api-reference/responses-streaming)
+     * for more information.
+     */
+    stream?: boolean | null;
+
+    /**
+     * The WebSocket lane for this response. Requests with the same `stream_id` are
+     * processed FIFO, and events for the response echo the same `stream_id`.
+     *
+     * `stream_id` controls routing; `previous_response_id` controls conversation
+     * lineage, so a new lane can fork from a response created on another lane.
+     */
+    stream_id?: string;
+
+    /**
+     * Options for streaming responses. Only set this when you set `stream: true`.
+     */
+    stream_options?: ResponseCreate.StreamOptions | null;
+
+    /**
+     * What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
+     * make the output more random, while lower values like 0.2 will make it more
+     * focused and deterministic. We generally recommend altering this or `top_p` but
+     * not both.
+     */
+    temperature?: number | null;
+
+    /**
+     * Configuration options for a text response from the model. Can be plain text or
+     * structured JSON data. Learn more:
+     *
+     * - [Text inputs and outputs](https://platform.openai.com/docs/guides/text)
+     * - [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs)
+     */
+    text?: ResponsesAPI.BetaResponseTextConfig;
+
+    /**
+     * How the model should select which tool (or tools) to use when generating a
+     * response. See the `tools` parameter to see how to specify which tools the model
+     * can call.
+     */
+    tool_choice?:
+      | ResponsesAPI.BetaToolChoiceOptions
+      | ResponsesAPI.BetaToolChoiceAllowed
+      | ResponsesAPI.BetaToolChoiceTypes
+      | ResponsesAPI.BetaToolChoiceFunction
+      | ResponsesAPI.BetaToolChoiceMcp
+      | ResponsesAPI.BetaToolChoiceCustom
+      | ResponseCreate.BetaSpecificProgrammaticToolCallingParam
+      | ResponsesAPI.BetaToolChoiceApplyPatch
+      | ResponsesAPI.BetaToolChoiceShell;
+
+    /**
+     * An array of tools the model may call while generating a response. You can
+     * specify which tool to use by setting the `tool_choice` parameter.
+     *
+     * We support the following categories of tools:
+     *
+     * - **Built-in tools**: Tools that are provided by OpenAI that extend the model's
+     *   capabilities, like
+     *   [web search](https://platform.openai.com/docs/guides/tools-web-search) or
+     *   [file search](https://platform.openai.com/docs/guides/tools-file-search).
+     *   Learn more about
+     *   [built-in tools](https://platform.openai.com/docs/guides/tools).
+     * - **MCP Tools**: Integrations with third-party systems via custom MCP servers or
+     *   predefined connectors such as Google Drive and SharePoint. Learn more about
+     *   [MCP Tools](https://platform.openai.com/docs/guides/tools-connectors-mcp).
+     * - **Function calls (custom tools)**: Functions that are defined by you, enabling
+     *   the model to call your own code with strongly typed arguments and outputs.
+     *   Learn more about
+     *   [function calling](https://platform.openai.com/docs/guides/function-calling).
+     *   You can also use custom tools to call your own code.
+     */
+    tools?: Array<ResponsesAPI.BetaTool>;
+
+    /**
+     * An integer between 0 and 20 specifying the maximum number of most likely tokens
+     * to return at each token position, each with an associated log probability. In
+     * some cases, the number of returned tokens may be fewer than requested.
+     */
+    top_logprobs?: number | null;
+
+    /**
+     * An alternative to sampling with temperature, called nucleus sampling, where the
+     * model considers the results of the tokens with top_p probability mass. So 0.1
+     * means only the tokens comprising the top 10% probability mass are considered.
+     *
+     * We generally recommend altering this or `temperature` but not both.
+     */
+    top_p?: number | null;
+
+    /**
+     * @deprecated The truncation strategy to use for the model response.
+     *
+     * - `auto`: If the input to this Response exceeds the model's context window size,
+     *   the model will truncate the response to fit the context window by dropping
+     *   items from the beginning of the conversation.
+     * - `disabled` (default): If the input size will exceed the context window size
+     *   for a model, the request will fail with a 400 error.
+     */
+    truncation?: 'auto' | 'disabled' | null;
+
+    /**
+     * @deprecated This field is being replaced by `safety_identifier` and
+     * `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching
+     * optimizations. A stable identifier for your end-users. Used to boost cache hit
+     * rates by better bucketing similar requests and to help OpenAI detect and prevent
+     * abuse.
+     * [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+     */
+    user?: string;
+  }
+
+  export namespace ResponseCreate {
+    export interface ContextManagement {
+      /**
+       * The context management entry type. Currently only 'compaction' is supported.
+       */
+      type: string;
+
+      /**
+       * Token threshold at which compaction should be triggered for this entry.
+       */
+      compact_threshold?: number | null;
+    }
+
+    /**
+     * Configuration for running moderation on the input and output of this response.
+     */
+    export interface Moderation {
+      /**
+       * The moderation model to use for moderated completions, e.g.
+       * 'omni-moderation-latest'.
+       */
+      model: string;
+
+      /**
+       * The policy to apply to moderated response input and output.
+       */
+      policy?: Moderation.Policy | null;
+    }
+
+    export namespace Moderation {
+      /**
+       * The policy to apply to moderated response input and output.
+       */
+      export interface Policy {
+        /**
+         * The moderation policy for the response input.
+         */
+        input?: Policy.Input | null;
+
+        /**
+         * The moderation policy for the response output.
+         */
+        output?: Policy.Output | null;
+      }
+
+      export namespace Policy {
+        /**
+         * The moderation policy for the response input.
+         */
+        export interface Input {
+          mode: 'score' | 'block';
+        }
+
+        /**
+         * The moderation policy for the response output.
+         */
+        export interface Output {
+          mode: 'score' | 'block';
+        }
+      }
+    }
+
+    /**
+     * Configuration for server-hosted multi-agent execution.
+     */
+    export interface MultiAgent {
+      /**
+       * Whether to enable server-hosted multi-agent execution for this response.
+       */
+      enabled: boolean;
+
+      /**
+       * `max_concurrent_subagents` sets the maximum number of subagents that can be
+       * active simultaneously across the entire agent tree. It includes all
+       * descendants—children, grandchildren, and deeper subagents—but excludes the root
+       * agent. The API does not impose a fixed upper bound on this setting. The default
+       * is `3`, which is recommended for most workloads. Multi-agent runs also have no
+       * fixed limit on tree depth or the total number of subagents created during a run.
+       */
+      max_concurrent_subagents?: number;
+    }
+
+    /**
+     * Options for prompt caching. Supported for `gpt-5.6` and later models. By
+     * default, OpenAI automatically chooses one implicit cache breakpoint. You can add
+     * explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each
+     * request can write up to four breakpoints. For cache matching, OpenAI considers
+     * up to the latest 80 breakpoints in the conversation, without a content-block
+     * lookback limit. Set `mode` to `explicit` to disable the implicit breakpoint. The
+     * `ttl` defaults to `30m`, which is currently the only supported value. See the
+     * [prompt caching guide](https://platform.openai.com/docs/guides/prompt-caching)
+     * for current details.
+     */
+    export interface PromptCacheOptions {
+      /**
+       * Controls whether OpenAI automatically creates an implicit cache breakpoint.
+       * Defaults to `implicit`. With `implicit`, OpenAI creates one implicit breakpoint
+       * and writes up to the latest three explicit breakpoints in the request. With
+       * `explicit`, OpenAI does not create an implicit breakpoint and writes up to the
+       * latest four explicit breakpoints. If there are no explicit breakpoints, the
+       * request does not use prompt caching.
+       */
+      mode?: 'implicit' | 'explicit';
+
+      /**
+       * The minimum lifetime applied to every implicit and explicit cache breakpoint
+       * written by the request. Defaults to `30m`, which is currently the only supported
+       * value. The backend may retain cache entries for longer.
+       */
+      ttl?: '30m';
+    }
+
+    /**
+     * **gpt-5 and o-series models only**
+     *
+     * Configuration options for
+     * [reasoning models](https://platform.openai.com/docs/guides/reasoning).
+     */
+    export interface Reasoning {
+      /**
+       * Controls which reasoning items are rendered back to the model on later turns. If
+       * omitted or set to `auto`, the model determines the context mode. The `gpt-5.6`
+       * model family defaults to `all_turns`; earlier models default to `current_turn`.
+       *
+       * When returned on a response, this is the effective reasoning context mode used
+       * for the response.
+       */
+      context?: 'auto' | 'current_turn' | 'all_turns' | null;
+
+      /**
+       * Constrains effort on reasoning for reasoning models. Currently supported values
+       * are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. Reducing
+       * reasoning effort can result in faster responses and fewer tokens used on
+       * reasoning in a response. Not all reasoning models support every value. See the
+       * [reasoning guide](https://platform.openai.com/docs/guides/reasoning) for
+       * model-specific support.
+       */
+      effort?: 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | 'max' | null;
+
+      /**
+       * @deprecated **Deprecated:** use `summary` instead.
+       *
+       * A summary of the reasoning performed by the model. This can be useful for
+       * debugging and understanding the model's reasoning process. One of `auto`,
+       * `concise`, or `detailed`.
+       */
+      generate_summary?: 'auto' | 'concise' | 'detailed' | null;
+
+      /**
+       * Controls the reasoning execution mode for the request.
+       *
+       * When returned on a response, this is the effective execution mode.
+       */
+      mode?: (string & {}) | 'standard' | 'pro';
+
+      /**
+       * A summary of the reasoning performed by the model. This can be useful for
+       * debugging and understanding the model's reasoning process. One of `auto`,
+       * `concise`, or `detailed`.
+       *
+       * `concise` is supported for `computer-use-preview` models and all reasoning
+       * models after `gpt-5`.
+       */
+      summary?: 'auto' | 'concise' | 'detailed' | null;
+    }
+
+    /**
+     * Options for streaming responses. Only set this when you set `stream: true`.
+     */
+    export interface StreamOptions {
+      /**
+       * When true, stream obfuscation will be enabled. Stream obfuscation adds random
+       * characters to an `obfuscation` field on streaming delta events to normalize
+       * payload sizes as a mitigation to certain side-channel attacks. These obfuscation
+       * fields are included by default, but add a small amount of overhead to the data
+       * stream. You can set `include_obfuscation` to false to optimize for bandwidth if
+       * you trust the network links between your application and the OpenAI API.
+       */
+      include_obfuscation?: boolean;
+    }
+
+    export interface BetaSpecificProgrammaticToolCallingParam {
+      /**
+       * The tool to call. Always `programmatic_tool_calling`.
+       */
+      type: 'programmatic_tool_calling';
+    }
+  }
+}
+
+/**
+ * Server events emitted by the Responses WebSocket server.
+ */
+export type BetaResponsesServerEvent =
+  | BetaResponsesServerEvent.BetaResponseAudioWsDelta
+  | BetaResponsesServerEvent.BetaResponseAudioWsDone
+  | BetaResponsesServerEvent.BetaResponseAudioTranscriptWsDelta
+  | BetaResponsesServerEvent.BetaResponseAudioTranscriptWsDone
+  | BetaResponsesServerEvent.BetaResponseCodeInterpreterCallCodeWsDelta
+  | BetaResponsesServerEvent.BetaResponseCodeInterpreterCallCodeWsDone
+  | BetaResponsesServerEvent.BetaResponseCodeInterpreterCallWsCompleted
+  | BetaResponsesServerEvent.BetaResponseCodeInterpreterCallInWsProgress
+  | BetaResponsesServerEvent.BetaResponseCodeInterpreterCallWsInterpreting
+  | BetaResponsesServerEvent.BetaResponseWsCompleted
+  | BetaResponsesServerEvent.BetaResponseContentPartWsAdded
+  | BetaResponsesServerEvent.BetaResponseContentPartWsDone
+  | BetaResponsesServerEvent.BetaResponseWsCreated
+  | BetaResponsesServerEvent.BetaResponseFileSearchCallWsCompleted
+  | BetaResponsesServerEvent.BetaResponseFileSearchCallInWsProgress
+  | BetaResponsesServerEvent.BetaResponseFileSearchCallWsSearching
+  | BetaResponsesServerEvent.BetaResponseFunctionCallArgumentsWsDelta
+  | BetaResponsesServerEvent.BetaResponseFunctionCallArgumentsWsDone
+  | BetaResponsesServerEvent.BetaResponseShellCallCommandWsAdded
+  | BetaResponsesServerEvent.BetaResponseShellCallCommandWsDelta
+  | BetaResponsesServerEvent.BetaResponseShellCallCommandWsDone
+  | BetaResponsesServerEvent.BetaResponseShellCallOutputContentWsDelta
+  | BetaResponsesServerEvent.BetaResponseShellCallOutputContentWsDone
+  | BetaResponsesServerEvent.BetaResponseInWsProgress
+  | BetaResponsesServerEvent.BetaResponseWsFailed
+  | BetaResponsesServerEvent.BetaResponseWsIncomplete
+  | BetaResponsesServerEvent.BetaResponseOutputItemWsAdded
+  | BetaResponsesServerEvent.BetaResponseOutputItemWsDone
+  | BetaResponsesServerEvent.BetaResponseReasoningSummaryPartWsAdded
+  | BetaResponsesServerEvent.BetaResponseReasoningSummaryPartWsDone
+  | BetaResponsesServerEvent.BetaResponseReasoningSummaryTextWsDelta
+  | BetaResponsesServerEvent.BetaResponseReasoningSummaryTextWsDone
+  | BetaResponsesServerEvent.BetaResponseReasoningTextWsDelta
+  | BetaResponsesServerEvent.BetaResponseReasoningTextWsDone
+  | BetaResponsesServerEvent.BetaResponseRefusalWsDelta
+  | BetaResponsesServerEvent.BetaResponseRefusalWsDone
+  | BetaResponsesServerEvent.BetaResponseTextWsDelta
+  | BetaResponsesServerEvent.BetaResponseTextWsDone
+  | BetaResponsesServerEvent.BetaResponseWebSearchCallWsCompleted
+  | BetaResponsesServerEvent.BetaResponseWebSearchCallInWsProgress
+  | BetaResponsesServerEvent.BetaResponseWebSearchCallWsSearching
+  | BetaResponsesServerEvent.BetaResponseImageGenCallWsCompleted
+  | BetaResponsesServerEvent.BetaResponseImageGenCallWsGenerating
+  | BetaResponsesServerEvent.BetaResponseImageGenCallInWsProgress
+  | BetaResponsesServerEvent.BetaResponseImageGenCallPartialWsImage
+  | BetaResponsesServerEvent.BetaResponseMcpCallArgumentsWsDelta
+  | BetaResponsesServerEvent.BetaResponseMcpCallArgumentsWsDone
+  | BetaResponsesServerEvent.BetaResponseMcpCallWsCompleted
+  | BetaResponsesServerEvent.BetaResponseMcpCallWsFailed
+  | BetaResponsesServerEvent.BetaResponseMcpCallInWsProgress
+  | BetaResponsesServerEvent.BetaResponseMcpListToolsWsCompleted
+  | BetaResponsesServerEvent.BetaResponseMcpListToolsWsFailed
+  | BetaResponsesServerEvent.BetaResponseMcpListToolsInWsProgress
+  | BetaResponsesServerEvent.BetaResponseOutputTextAnnotationWsAdded
+  | BetaResponsesServerEvent.BetaResponseWsQueued
+  | BetaResponsesServerEvent.BetaResponseCustomToolCallInputWsDelta
+  | BetaResponsesServerEvent.BetaResponseCustomToolCallInputWsDone
+  | BetaResponsesServerEvent.BetaResponseWsStreamingError
+  | BetaResponsesServerEvent.BetaResponseWsError
+  | BetaResponseInjectCreatedEvent
+  | BetaResponseInjectFailedEvent;
+
+export namespace BetaResponsesServerEvent {
+  /**
+   * Emitted when there is a partial audio response.
+   */
+  export interface BetaResponseAudioWsDelta extends BetaResponseAudioDeltaEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when the audio response is complete.
+   */
+  export interface BetaResponseAudioWsDone extends BetaResponseAudioDoneEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when there is a partial transcript of audio.
+   */
+  export interface BetaResponseAudioTranscriptWsDelta extends BetaResponseAudioTranscriptDeltaEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when the full audio transcript is completed.
+   */
+  export interface BetaResponseAudioTranscriptWsDone extends BetaResponseAudioTranscriptDoneEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when a partial code snippet is streamed by the code interpreter.
+   */
+  export interface BetaResponseCodeInterpreterCallCodeWsDelta extends BetaResponseCodeInterpreterCallCodeDeltaEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when the code snippet is finalized by the code interpreter.
+   */
+  export interface BetaResponseCodeInterpreterCallCodeWsDone extends BetaResponseCodeInterpreterCallCodeDoneEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when the code interpreter call is completed.
+   */
+  export interface BetaResponseCodeInterpreterCallWsCompleted extends BetaResponseCodeInterpreterCallCompletedEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when a code interpreter call is in progress.
+   */
+  export interface BetaResponseCodeInterpreterCallInWsProgress extends BetaResponseCodeInterpreterCallInProgressEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    agent_name: string;
+    stream_id?: string;
   }
-}
 
-/**
- * Client events accepted by the Responses WebSocket server.
- */
-export type BetaResponsesClientEvent = BetaResponsesClientEvent.ResponseCreate | BetaResponseInjectEvent;
+  /**
+   * Emitted when the code interpreter is actively interpreting the code snippet.
+   */
+  export interface BetaResponseCodeInterpreterCallWsInterpreting extends BetaResponseCodeInterpreterCallInterpretingEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
 
-export namespace BetaResponsesClientEvent {
   /**
-   * Client event for creating a response over a persistent WebSocket connection.
-   * This payload uses the same top-level fields as `POST /v1/responses`.
-   *
-   * Notes:
-   *
-   * - `stream` is implicit over WebSocket and should not be sent.
-   * - `background` is not supported over WebSocket.
+   * Emitted when the model response is complete.
    */
-  export interface ResponseCreate {
+  export interface BetaResponseWsCompleted extends BetaResponseCompletedEvent {
     /**
-     * The type of the client event. Always `response.create`.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    type: 'response.create';
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a new content part is added.
+   */
+  export interface BetaResponseContentPartWsAdded extends BetaResponseContentPartAddedEvent {
     /**
-     * Whether to run the model response in the background.
-     * [Learn more](https://platform.openai.com/docs/guides/background).
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    background?: boolean | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a content part is done.
+   */
+  export interface BetaResponseContentPartWsDone extends BetaResponseContentPartDoneEvent {
     /**
-     * Context management configuration for this request.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    context_management?: Array<ResponseCreate.ContextManagement> | null;
+    stream_id?: string;
+  }
 
+  /**
+   * An event that is emitted when a response is created.
+   */
+  export interface BetaResponseWsCreated extends BetaResponseCreatedEvent {
     /**
-     * The conversation that this response belongs to. Items from this conversation are
-     * prepended to `input_items` for this response request. Input items and output
-     * items from this response are automatically added to this conversation after this
-     * response completes.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    conversation?: string | ResponsesAPI.BetaResponseConversationParam | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a file search call is completed (results found).
+   */
+  export interface BetaResponseFileSearchCallWsCompleted extends BetaResponseFileSearchCallCompletedEvent {
     /**
-     * Specify additional output data to include in the model response. Currently
-     * supported values are:
-     *
-     * - `web_search_call.action.sources`: Include the sources of the web search tool
-     *   call.
-     * - `code_interpreter_call.outputs`: Includes the outputs of python code execution
-     *   in code interpreter tool call items.
-     * - `computer_call_output.output.image_url`: Include image urls from the computer
-     *   call output.
-     * - `file_search_call.results`: Include the search results of the file search tool
-     *   call.
-     * - `message.input_image.image_url`: Include image urls from the input message.
-     * - `message.output_text.logprobs`: Include logprobs with assistant messages.
-     * - `reasoning.encrypted_content`: Includes an encrypted version of reasoning
-     *   tokens in reasoning item outputs. This enables reasoning items to be used in
-     *   multi-turn conversations when using the Responses API statelessly (like when
-     *   the `store` parameter is set to `false`, or when an organization is enrolled
-     *   in the zero data retention program).
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    include?: Array<ResponsesAPI.BetaResponseIncludable> | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a file search call is initiated.
+   */
+  export interface BetaResponseFileSearchCallInWsProgress extends BetaResponseFileSearchCallInProgressEvent {
     /**
-     * Text, image, or file inputs to the model, used to generate a response.
-     *
-     * Learn more:
-     *
-     * - [Text inputs and outputs](https://platform.openai.com/docs/guides/text)
-     * - [Image inputs](https://platform.openai.com/docs/guides/images)
-     * - [File inputs](https://platform.openai.com/docs/guides/pdf-files)
-     * - [Conversation state](https://platform.openai.com/docs/guides/conversation-state)
-     * - [Function calling](https://platform.openai.com/docs/guides/function-calling)
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    input?: string | ResponsesAPI.BetaResponseInput;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a file search is currently searching.
+   */
+  export interface BetaResponseFileSearchCallWsSearching extends BetaResponseFileSearchCallSearchingEvent {
     /**
-     * A system (or developer) message inserted into the model's context.
-     *
-     * When using along with `previous_response_id`, the instructions from a previous
-     * response will not be carried over to the next response. This makes it simple to
-     * swap out system (or developer) messages in new responses.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    instructions?: string | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when there is a partial function-call arguments delta.
+   */
+  export interface BetaResponseFunctionCallArgumentsWsDelta extends BetaResponseFunctionCallArgumentsDeltaEvent {
     /**
-     * An upper bound for the number of tokens that can be generated for a response,
-     * including visible output tokens and
-     * [reasoning tokens](https://platform.openai.com/docs/guides/reasoning).
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    max_output_tokens?: number | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when function-call arguments are finalized.
+   */
+  export interface BetaResponseFunctionCallArgumentsWsDone extends BetaResponseFunctionCallArgumentsDoneEvent {
     /**
-     * The maximum number of total calls to built-in tools that can be processed in a
-     * response. This maximum number applies across all built-in tool calls, not per
-     * individual tool. Any further attempts to call a tool by the model will be
-     * ignored.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    max_tool_calls?: number | null;
+    stream_id?: string;
+  }
 
+  /**
+   * A streaming event that indicated a shell command was added to a tool call.
+   */
+  export interface BetaResponseShellCallCommandWsAdded extends BetaResponseShellCallCommandAddedEvent {
     /**
-     * Set of 16 key-value pairs that can be attached to an object. This can be useful
-     * for storing additional information about the object in a structured format, and
-     * querying for objects via API or the dashboard.
-     *
-     * Keys are strings with a maximum length of 64 characters. Values are strings with
-     * a maximum length of 512 characters.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    metadata?: { [key: string]: string } | null;
+    stream_id?: string;
+  }
 
+  /**
+   * A streaming event that indicated a shell command was incrementally updated.
+   */
+  export interface BetaResponseShellCallCommandWsDelta extends BetaResponseShellCallCommandDeltaEvent {
     /**
-     * Model ID used to generate the response, like `gpt-4o` or `o3`. OpenAI offers a
-     * wide range of models with different capabilities, performance characteristics,
-     * and price points. Refer to the
-     * [model guide](https://platform.openai.com/docs/models) to browse and compare
-     * available models.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    model?:
-      | 'gpt-5.6-sol'
-      | 'gpt-5.6-terra'
-      | 'gpt-5.6-luna'
-      | 'gpt-5.5'
-      | 'gpt-5.4'
-      | 'gpt-5.4-mini'
-      | 'gpt-5.4-nano'
-      | 'gpt-5.4-mini-2026-03-17'
-      | 'gpt-5.4-nano-2026-03-17'
-      | 'gpt-5.3-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-5.1'
-      | 'gpt-5.1-2025-11-13'
-      | 'gpt-5.1-codex'
-      | 'gpt-5.1-mini'
-      | 'gpt-5.1-chat-latest'
-      | 'gpt-5'
-      | 'gpt-5-mini'
-      | 'gpt-5-nano'
-      | 'gpt-5-2025-08-07'
-      | 'gpt-5-mini-2025-08-07'
-      | 'gpt-5-nano-2025-08-07'
-      | 'gpt-5-chat-latest'
-      | 'gpt-4.1'
-      | 'gpt-4.1-mini'
-      | 'gpt-4.1-nano'
-      | 'gpt-4.1-2025-04-14'
-      | 'gpt-4.1-mini-2025-04-14'
-      | 'gpt-4.1-nano-2025-04-14'
-      | 'o4-mini'
-      | 'o4-mini-2025-04-16'
-      | 'o3'
-      | 'o3-2025-04-16'
-      | 'o3-mini'
-      | 'o3-mini-2025-01-31'
-      | 'o1'
-      | 'o1-2024-12-17'
-      | 'o1-preview'
-      | 'o1-preview-2024-09-12'
-      | 'o1-mini'
-      | 'o1-mini-2024-09-12'
-      | 'gpt-4o'
-      | 'gpt-4o-2024-11-20'
-      | 'gpt-4o-2024-08-06'
-      | 'gpt-4o-2024-05-13'
-      | 'gpt-4o-audio-preview'
-      | 'gpt-4o-audio-preview-2024-10-01'
-      | 'gpt-4o-audio-preview-2024-12-17'
-      | 'gpt-4o-audio-preview-2025-06-03'
-      | 'gpt-4o-mini-audio-preview'
-      | 'gpt-4o-mini-audio-preview-2024-12-17'
-      | 'gpt-4o-search-preview'
-      | 'gpt-4o-mini-search-preview'
-      | 'gpt-4o-search-preview-2025-03-11'
-      | 'gpt-4o-mini-search-preview-2025-03-11'
-      | 'chatgpt-4o-latest'
-      | 'codex-mini-latest'
-      | 'gpt-4o-mini'
-      | 'gpt-4o-mini-2024-07-18'
-      | 'gpt-4-turbo'
-      | 'gpt-4-turbo-2024-04-09'
-      | 'gpt-4-0125-preview'
-      | 'gpt-4-turbo-preview'
-      | 'gpt-4-1106-preview'
-      | 'gpt-4-vision-preview'
-      | 'gpt-4'
-      | 'gpt-4-0314'
-      | 'gpt-4-0613'
-      | 'gpt-4-32k'
-      | 'gpt-4-32k-0314'
-      | 'gpt-4-32k-0613'
-      | 'gpt-3.5-turbo'
-      | 'gpt-3.5-turbo-16k'
-      | 'gpt-3.5-turbo-0301'
-      | 'gpt-3.5-turbo-0613'
-      | 'gpt-3.5-turbo-1106'
-      | 'gpt-3.5-turbo-0125'
-      | 'gpt-3.5-turbo-16k-0613'
-      | 'o1-pro'
-      | 'o1-pro-2025-03-19'
-      | 'o3-pro'
-      | 'o3-pro-2025-06-10'
-      | 'o3-deep-research'
-      | 'o3-deep-research-2025-06-26'
-      | 'o4-mini-deep-research'
-      | 'o4-mini-deep-research-2025-06-26'
-      | 'computer-use-preview'
-      | 'computer-use-preview-2025-03-11'
-      | 'gpt-5-codex'
-      | 'gpt-5-pro'
-      | 'gpt-5-pro-2025-10-06'
-      | 'gpt-5.1-codex-max'
-      | (string & {});
+    stream_id?: string;
+  }
+
+  /**
+   * A streaming event that indicated a shell command was completed.
+   */
+  export interface BetaResponseShellCallCommandWsDone extends BetaResponseShellCallCommandDoneEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * A streaming event that indicated shell call output was incrementally added.
+   */
+  export interface BetaResponseShellCallOutputContentWsDelta extends BetaResponseShellCallOutputContentDeltaEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * A streaming event that indicated shell call output was completed.
+   */
+  export interface BetaResponseShellCallOutputContentWsDone extends BetaResponseShellCallOutputContentDoneEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when the response is in progress.
+   */
+  export interface BetaResponseInWsProgress extends BetaResponseInProgressEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * An event that is emitted when a response fails.
+   */
+  export interface BetaResponseWsFailed extends BetaResponseFailedEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * An event that is emitted when a response finishes as incomplete.
+   */
+  export interface BetaResponseWsIncomplete extends BetaResponseIncompleteEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a new output item is added.
+   */
+  export interface BetaResponseOutputItemWsAdded extends BetaResponseOutputItemAddedEvent {
     /**
-     * Configuration for running moderation on the input and output of this response.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    moderation?: ResponseCreate.Moderation | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when an output item is marked done.
+   */
+  export interface BetaResponseOutputItemWsDone extends BetaResponseOutputItemDoneEvent {
     /**
-     * Configuration for server-hosted multi-agent execution.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    multi_agent?: ResponseCreate.MultiAgent | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a new reasoning summary part is added.
+   */
+  export interface BetaResponseReasoningSummaryPartWsAdded extends BetaResponseReasoningSummaryPartAddedEvent {
     /**
-     * Whether to allow the model to run tool calls in parallel.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    parallel_tool_calls?: boolean | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a reasoning summary part is completed.
+   */
+  export interface BetaResponseReasoningSummaryPartWsDone extends BetaResponseReasoningSummaryPartDoneEvent {
     /**
-     * The unique ID of the previous response to the model. Use this to create
-     * multi-turn conversations. Learn more about
-     * [conversation state](https://platform.openai.com/docs/guides/conversation-state).
-     * Cannot be used in conjunction with `conversation`.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    previous_response_id?: string | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a delta is added to a reasoning summary text.
+   */
+  export interface BetaResponseReasoningSummaryTextWsDelta extends BetaResponseReasoningSummaryTextDeltaEvent {
     /**
-     * Reference to a prompt template and its variables.
-     * [Learn more](https://platform.openai.com/docs/guides/text?api-mode=responses#reusable-prompts).
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    prompt?: ResponsesAPI.BetaResponsePrompt | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a reasoning summary text is completed.
+   */
+  export interface BetaResponseReasoningSummaryTextWsDone extends BetaResponseReasoningSummaryTextDoneEvent {
     /**
-     * Used by OpenAI to cache responses for similar requests to optimize your cache
-     * hit rates. Replaces the `user` field.
-     * [Learn more](https://platform.openai.com/docs/guides/prompt-caching).
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    prompt_cache_key?: string | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a delta is added to a reasoning text.
+   */
+  export interface BetaResponseReasoningTextWsDelta extends BetaResponseReasoningTextDeltaEvent {
     /**
-     * Options for prompt caching. Supported for `gpt-5.6` and later models. By
-     * default, OpenAI automatically chooses one implicit cache breakpoint. You can add
-     * explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each
-     * request can write up to four breakpoints. For cache matching, OpenAI considers
-     * up to the latest 80 breakpoints in the conversation, without a content-block
-     * lookback limit. Set `mode` to `explicit` to disable the implicit breakpoint. The
-     * `ttl` defaults to `30m`, which is currently the only supported value. See the
-     * [prompt caching guide](https://platform.openai.com/docs/guides/prompt-caching)
-     * for current details.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    prompt_cache_options?: ResponseCreate.PromptCacheOptions;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a reasoning text is completed.
+   */
+  export interface BetaResponseReasoningTextWsDone extends BetaResponseReasoningTextDoneEvent {
     /**
-     * @deprecated Deprecated. Use `prompt_cache_options.ttl` instead.
-     *
-     * The retention policy for the prompt cache. Set to `24h` to enable extended
-     * prompt caching, which keeps cached prefixes active for longer, up to a maximum
-     * of 24 hours.
-     * [Learn more](https://platform.openai.com/docs/guides/prompt-caching#prompt-cache-retention).
-     * This field expresses a maximum retention policy, while
-     * `prompt_cache_options.ttl` expresses a minimum cache lifetime. The two fields
-     * are independent and do not interact. For `gpt-5.5`, `gpt-5.5-pro`, and future
-     * models, only `24h` is supported.
-     *
-     * For older models that support both `in_memory` and `24h`, the default depends on
-     * your organization's data retention policy:
-     *
-     * - Organizations without ZDR enabled default to `24h`.
-     * - Organizations with ZDR enabled default to `in_memory` when
-     *   `prompt_cache_retention` is not specified.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    prompt_cache_retention?: 'in_memory' | '24h' | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when there is a partial refusal text.
+   */
+  export interface BetaResponseRefusalWsDelta extends BetaResponseRefusalDeltaEvent {
     /**
-     * **gpt-5 and o-series models only**
-     *
-     * Configuration options for
-     * [reasoning models](https://platform.openai.com/docs/guides/reasoning).
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    reasoning?: ResponseCreate.Reasoning | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when refusal text is finalized.
+   */
+  export interface BetaResponseRefusalWsDone extends BetaResponseRefusalDoneEvent {
     /**
-     * A stable identifier used to help detect users of your application that may be
-     * violating OpenAI's usage policies. The IDs should be a string that uniquely
-     * identifies each user, with a maximum length of 64 characters. We recommend
-     * hashing their username or email address, in order to avoid sending us any
-     * identifying information.
-     * [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    safety_identifier?: string | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when there is an additional text delta.
+   */
+  export interface BetaResponseTextWsDelta extends BetaResponseTextDeltaEvent {
     /**
-     * Specifies the processing type used for serving the request.
-     *
-     * - If set to 'auto', then the request will be processed with the service tier
-     *   configured in the Project settings. Unless otherwise configured, the Project
-     *   will use 'default'.
-     * - If set to 'default', then the request will be processed with the standard
-     *   pricing and performance for the selected model.
-     * - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
-     *   then the request will be processed with the Flex Processing service tier.
-     * - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
-     *   include the `service_tier=fast` or `service_tier=priority` parameter for
-     *   Responses or Chat Completions. The response will show `service_tier=priority`
-     *   regardless of if you specify `service_tier=fast` or `priority` in your
-     *   request.
-     * - When not set, the default behavior is 'auto'.
-     *
-     * When the `service_tier` parameter is set, the response body will include the
-     * `service_tier` value based on the processing mode actually used to serve the
-     * request. This response value may be different from the value set in the
-     * parameter.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    service_tier?: 'auto' | 'default' | 'flex' | 'scale' | 'priority' | 'fast' | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when text content is finalized.
+   */
+  export interface BetaResponseTextWsDone extends BetaResponseTextDoneEvent {
     /**
-     * Whether to store the generated model response for later retrieval via API.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    store?: boolean | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a web search call is completed.
+   */
+  export interface BetaResponseWebSearchCallWsCompleted extends BetaResponseWebSearchCallCompletedEvent {
     /**
-     * If set to true, the model response data will be streamed to the client as it is
-     * generated using
-     * [server-sent events](https://developer.mozilla.org/en-US/docs/Web/API/Server-sent_events/Using_server-sent_events#Event_stream_format).
-     * See the
-     * [Streaming section below](https://platform.openai.com/docs/api-reference/responses-streaming)
-     * for more information.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    stream?: boolean | null;
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when a web search call is initiated.
+   */
+  export interface BetaResponseWebSearchCallInWsProgress extends BetaResponseWebSearchCallInProgressEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a web search call is executing.
+   */
+  export interface BetaResponseWebSearchCallWsSearching extends BetaResponseWebSearchCallSearchingEvent {
     /**
-     * Options for streaming responses. Only set this when you set `stream: true`.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    stream_options?: ResponseCreate.StreamOptions | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when an image generation tool call has completed and the final image is
+   * available.
+   */
+  export interface BetaResponseImageGenCallWsCompleted extends BetaResponseImageGenCallCompletedEvent {
     /**
-     * What sampling temperature to use, between 0 and 2. Higher values like 0.8 will
-     * make the output more random, while lower values like 0.2 will make it more
-     * focused and deterministic. We generally recommend altering this or `top_p` but
-     * not both.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    temperature?: number | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when an image generation tool call is actively generating an image
+   * (intermediate state).
+   */
+  export interface BetaResponseImageGenCallWsGenerating extends BetaResponseImageGenCallGeneratingEvent {
     /**
-     * Configuration options for a text response from the model. Can be plain text or
-     * structured JSON data. Learn more:
-     *
-     * - [Text inputs and outputs](https://platform.openai.com/docs/guides/text)
-     * - [Structured Outputs](https://platform.openai.com/docs/guides/structured-outputs)
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    text?: ResponsesAPI.BetaResponseTextConfig;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when an image generation tool call is in progress.
+   */
+  export interface BetaResponseImageGenCallInWsProgress extends BetaResponseImageGenCallInProgressEvent {
     /**
-     * How the model should select which tool (or tools) to use when generating a
-     * response. See the `tools` parameter to see how to specify which tools the model
-     * can call.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    tool_choice?:
-      | ResponsesAPI.BetaToolChoiceOptions
-      | ResponsesAPI.BetaToolChoiceAllowed
-      | ResponsesAPI.BetaToolChoiceTypes
-      | ResponsesAPI.BetaToolChoiceFunction
-      | ResponsesAPI.BetaToolChoiceMcp
-      | ResponsesAPI.BetaToolChoiceCustom
-      | ResponseCreate.BetaSpecificProgrammaticToolCallingParam
-      | ResponsesAPI.BetaToolChoiceApplyPatch
-      | ResponsesAPI.BetaToolChoiceShell;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when a partial image is available during image generation streaming.
+   */
+  export interface BetaResponseImageGenCallPartialWsImage extends BetaResponseImageGenCallPartialImageEvent {
     /**
-     * An array of tools the model may call while generating a response. You can
-     * specify which tool to use by setting the `tool_choice` parameter.
-     *
-     * We support the following categories of tools:
-     *
-     * - **Built-in tools**: Tools that are provided by OpenAI that extend the model's
-     *   capabilities, like
-     *   [web search](https://platform.openai.com/docs/guides/tools-web-search) or
-     *   [file search](https://platform.openai.com/docs/guides/tools-file-search).
-     *   Learn more about
-     *   [built-in tools](https://platform.openai.com/docs/guides/tools).
-     * - **MCP Tools**: Integrations with third-party systems via custom MCP servers or
-     *   predefined connectors such as Google Drive and SharePoint. Learn more about
-     *   [MCP Tools](https://platform.openai.com/docs/guides/tools-connectors-mcp).
-     * - **Function calls (custom tools)**: Functions that are defined by you, enabling
-     *   the model to call your own code with strongly typed arguments and outputs.
-     *   Learn more about
-     *   [function calling](https://platform.openai.com/docs/guides/function-calling).
-     *   You can also use custom tools to call your own code.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    tools?: Array<ResponsesAPI.BetaTool>;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when there is a delta (partial update) to the arguments of an MCP tool
+   * call.
+   */
+  export interface BetaResponseMcpCallArgumentsWsDelta extends BetaResponseMcpCallArgumentsDeltaEvent {
     /**
-     * An integer between 0 and 20 specifying the maximum number of most likely tokens
-     * to return at each token position, each with an associated log probability. In
-     * some cases, the number of returned tokens may be fewer than requested.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    top_logprobs?: number | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Emitted when the arguments for an MCP tool call are finalized.
+   */
+  export interface BetaResponseMcpCallArgumentsWsDone extends BetaResponseMcpCallArgumentsDoneEvent {
     /**
-     * An alternative to sampling with temperature, called nucleus sampling, where the
-     * model considers the results of the tokens with top_p probability mass. So 0.1
-     * means only the tokens comprising the top 10% probability mass are considered.
-     *
-     * We generally recommend altering this or `temperature` but not both.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when an MCP tool call has completed successfully.
+   */
+  export interface BetaResponseMcpCallWsCompleted extends BetaResponseMcpCallCompletedEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when an MCP tool call has failed.
+   */
+  export interface BetaResponseMcpCallWsFailed extends BetaResponseMcpCallFailedEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when an MCP tool call is in progress.
+   */
+  export interface BetaResponseMcpCallInWsProgress extends BetaResponseMcpCallInProgressEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when the list of available MCP tools has been successfully retrieved.
+   */
+  export interface BetaResponseMcpListToolsWsCompleted extends BetaResponseMcpListToolsCompletedEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when the attempt to list available MCP tools has failed.
+   */
+  export interface BetaResponseMcpListToolsWsFailed extends BetaResponseMcpListToolsFailedEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when the system is in the process of retrieving the list of available
+   * MCP tools.
+   */
+  export interface BetaResponseMcpListToolsInWsProgress extends BetaResponseMcpListToolsInProgressEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when an annotation is added to output text content.
+   */
+  export interface BetaResponseOutputTextAnnotationWsAdded extends BetaResponseOutputTextAnnotationAddedEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
+
+  /**
+   * Emitted when a response is queued and waiting to be processed.
+   */
+  export interface BetaResponseWsQueued extends BetaResponseQueuedEvent {
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    top_p?: number | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Event representing a delta (partial update) to the input of a custom tool call.
+   */
+  export interface BetaResponseCustomToolCallInputWsDelta extends BetaResponseCustomToolCallInputDeltaEvent {
     /**
-     * @deprecated The truncation strategy to use for the model response.
-     *
-     * - `auto`: If the input to this Response exceeds the model's context window size,
-     *   the model will truncate the response to fit the context window by dropping
-     *   items from the beginning of the conversation.
-     * - `disabled` (default): If the input size will exceed the context window size
-     *   for a model, the request will fail with a 400 error.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    truncation?: 'auto' | 'disabled' | null;
+    stream_id?: string;
+  }
 
+  /**
+   * Event indicating that input for a custom tool call is complete.
+   */
+  export interface BetaResponseCustomToolCallInputWsDone extends BetaResponseCustomToolCallInputDoneEvent {
     /**
-     * @deprecated This field is being replaced by `safety_identifier` and
-     * `prompt_cache_key`. Use `prompt_cache_key` instead to maintain caching
-     * optimizations. A stable identifier for your end-users. Used to boost cache hit
-     * rates by better bucketing similar requests and to help OpenAI detect and prevent
-     * abuse.
-     * [Learn more](https://platform.openai.com/docs/guides/safety-best-practices#safety-identifiers).
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    user?: string;
+    stream_id?: string;
   }
 
-  export namespace ResponseCreate {
-    export interface ContextManagement {
-      /**
-       * The context management entry type. Currently only 'compaction' is supported.
-       */
-      type: string;
-
-      /**
-       * Token threshold at which compaction should be triggered for this entry.
-       */
-      compact_threshold?: number | null;
-    }
-
+  /**
+   * Emitted when an error occurs while streaming a response over the WebSocket.
+   */
+  export interface BetaResponseWsStreamingError extends BetaResponseErrorEvent {
     /**
-     * Configuration for running moderation on the input and output of this response.
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
      */
-    export interface Moderation {
-      /**
-       * The moderation model to use for moderated completions, e.g.
-       * 'omni-moderation-latest'.
-       */
-      model: string;
-
-      /**
-       * The policy to apply to moderated response input and output.
-       */
-      policy?: Moderation.Policy | null;
-    }
-
-    export namespace Moderation {
-      /**
-       * The policy to apply to moderated response input and output.
-       */
-      export interface Policy {
-        /**
-         * The moderation policy for the response input.
-         */
-        input?: Policy.Input | null;
-
-        /**
-         * The moderation policy for the response output.
-         */
-        output?: Policy.Output | null;
-      }
+    stream_id?: string;
+  }
 
-      export namespace Policy {
-        /**
-         * The moderation policy for the response input.
-         */
-        export interface Input {
-          mode: 'score' | 'block';
-        }
+  /**
+   * Emitted when an error occurs while processing a Responses WebSocket request.
+   */
+  export interface BetaResponseWsError {
+    /**
+     * Details about the error.
+     */
+    error: BetaResponseWsError.Error;
 
-        /**
-         * The moderation policy for the response output.
-         */
-        export interface Output {
-          mode: 'score' | 'block';
-        }
-      }
-    }
+    /**
+     * The type of the event. Always `error`.
+     */
+    type: 'error';
 
     /**
-     * Configuration for server-hosted multi-agent execution.
+     * The agent that owns this multi-agent streaming event.
      */
-    export interface MultiAgent {
-      /**
-       * Whether to enable server-hosted multi-agent execution for this response.
-       */
-      enabled: boolean;
+    agent?: BetaResponseWsError.Agent | null;
 
-      /**
-       * `max_concurrent_subagents` sets the maximum number of subagents that can be
-       * active simultaneously across the entire agent tree. It includes all
-       * descendants—children, grandchildren, and deeper subagents—but excludes the root
-       * agent. The API does not impose a fixed upper bound on this setting. The default
-       * is `3`, which is recommended for most workloads. Multi-agent runs also have no
-       * fixed limit on tree depth or the total number of subagents created during a run.
-       */
-      max_concurrent_subagents?: number;
-    }
+    /**
+     * The sequence number of an error emitted by the response stream.
+     */
+    sequence_number?: number;
 
     /**
-     * Options for prompt caching. Supported for `gpt-5.6` and later models. By
-     * default, OpenAI automatically chooses one implicit cache breakpoint. You can add
-     * explicit breakpoints to content blocks with `prompt_cache_breakpoint`. Each
-     * request can write up to four breakpoints. For cache matching, OpenAI considers
-     * up to the latest 80 breakpoints in the conversation, without a content-block
-     * lookback limit. Set `mode` to `explicit` to disable the implicit breakpoint. The
-     * `ttl` defaults to `30m`, which is currently the only supported value. See the
-     * [prompt caching guide](https://platform.openai.com/docs/guides/prompt-caching)
-     * for current details.
+     * The HTTP status code associated with a WebSocket protocol error.
      */
-    export interface PromptCacheOptions {
-      /**
-       * Controls whether OpenAI automatically creates an implicit cache breakpoint.
-       * Defaults to `implicit`. With `implicit`, OpenAI creates one implicit breakpoint
-       * and writes up to the latest three explicit breakpoints in the request. With
-       * `explicit`, OpenAI does not create an implicit breakpoint and writes up to the
-       * latest four explicit breakpoints. If there are no explicit breakpoints, the
-       * request does not use prompt caching.
-       */
-      mode?: 'implicit' | 'explicit';
+    status?: number;
 
-      /**
-       * The minimum lifetime applied to every implicit and explicit cache breakpoint
-       * written by the request. Defaults to `30m`, which is currently the only supported
-       * value. The backend may retain cache entries for longer.
-       */
-      ttl?: '30m';
-    }
+    /**
+     * The WebSocket lane that emitted this event. This field is present when the
+     * originating `response.create` event supplied a `stream_id`.
+     */
+    stream_id?: string;
+  }
 
+  export namespace BetaResponseWsError {
     /**
-     * **gpt-5 and o-series models only**
-     *
-     * Configuration options for
-     * [reasoning models](https://platform.openai.com/docs/guides/reasoning).
+     * Details about the error.
      */
-    export interface Reasoning {
+    export interface Error {
       /**
-       * Controls which reasoning items are rendered back to the model on later turns. If
-       * omitted or set to `auto`, the model determines the context mode. The `gpt-5.6`
-       * model family defaults to `all_turns`; earlier models default to `current_turn`.
-       *
-       * When returned on a response, this is the effective reasoning context mode used
-       * for the response.
+       * The error code that was emitted, if any.
        */
-      context?: 'auto' | 'current_turn' | 'all_turns' | null;
+      code: string | null;
 
       /**
-       * Constrains effort on reasoning for reasoning models. Currently supported values
-       * are `none`, `minimal`, `low`, `medium`, `high`, `xhigh`, and `max`. Reducing
-       * reasoning effort can result in faster responses and fewer tokens used on
-       * reasoning in a response. Not all reasoning models support every value. See the
-       * [reasoning guide](https://platform.openai.com/docs/guides/reasoning) for
-       * model-specific support.
+       * The human-readable error message that was emitted.
        */
-      effort?: 'none' | 'minimal' | 'low' | 'medium' | 'high' | 'xhigh' | 'max' | null;
+      message: string;
 
       /**
-       * @deprecated **Deprecated:** use `summary` instead.
-       *
-       * A summary of the reasoning performed by the model. This can be useful for
-       * debugging and understanding the model's reasoning process. One of `auto`,
-       * `concise`, or `detailed`.
+       * The parameter name that was associated with the error, if any.
        */
-      generate_summary?: 'auto' | 'concise' | 'detailed' | null;
+      param: string | null;
 
       /**
-       * Controls the reasoning execution mode for the request.
-       *
-       * When returned on a response, this is the effective execution mode.
+       * The error type that was emitted.
        */
-      mode?: (string & {}) | 'standard' | 'pro';
+      type: string;
 
       /**
-       * A summary of the reasoning performed by the model. This can be useful for
-       * debugging and understanding the model's reasoning process. One of `auto`,
-       * `concise`, or `detailed`.
-       *
-       * `concise` is supported for `computer-use-preview` models and all reasoning
-       * models after `gpt-5`.
+       * The response headers that were emitted with the error, if any.
        */
-      summary?: 'auto' | 'concise' | 'detailed' | null;
+      headers?: { [key: string]: string };
     }
 
     /**
-     * Options for streaming responses. Only set this when you set `stream: true`.
+     * The agent that owns this multi-agent streaming event.
      */
-    export interface StreamOptions {
-      /**
-       * When true, stream obfuscation will be enabled. Stream obfuscation adds random
-       * characters to an `obfuscation` field on streaming delta events to normalize
-       * payload sizes as a mitigation to certain side-channel attacks. These obfuscation
-       * fields are included by default, but add a small amount of overhead to the data
-       * stream. You can set `include_obfuscation` to false to optimize for bandwidth if
-       * you trust the network links between your application and the OpenAI API.
-       */
-      include_obfuscation?: boolean;
-    }
-
-    export interface BetaSpecificProgrammaticToolCallingParam {
+    export interface Agent {
       /**
-       * The tool to call. Always `programmatic_tool_calling`.
+       * The canonical name of the agent that produced this item.
        */
-      type: 'programmatic_tool_calling';
+      agent_name: string;
     }
   }
 }
 
 /**
- * Server events emitted by the Responses WebSocket server.
- */
-export type BetaResponsesServerEvent =
-  | BetaResponseAudioDeltaEvent
-  | BetaResponseAudioDoneEvent
-  | BetaResponseAudioTranscriptDeltaEvent
-  | BetaResponseAudioTranscriptDoneEvent
-  | BetaResponseCodeInterpreterCallCodeDeltaEvent
-  | BetaResponseCodeInterpreterCallCodeDoneEvent
-  | BetaResponseCodeInterpreterCallCompletedEvent
-  | BetaResponseCodeInterpreterCallInProgressEvent
-  | BetaResponseCodeInterpreterCallInterpretingEvent
-  | BetaResponseCompletedEvent
-  | BetaResponseContentPartAddedEvent
-  | BetaResponseContentPartDoneEvent
-  | BetaResponseCreatedEvent
-  | BetaResponseErrorEvent
-  | BetaResponseFileSearchCallCompletedEvent
-  | BetaResponseFileSearchCallInProgressEvent
-  | BetaResponseFileSearchCallSearchingEvent
-  | BetaResponseFunctionCallArgumentsDeltaEvent
-  | BetaResponseFunctionCallArgumentsDoneEvent
-  | BetaResponseInProgressEvent
-  | BetaResponseFailedEvent
-  | BetaResponseIncompleteEvent
-  | BetaResponseOutputItemAddedEvent
-  | BetaResponseOutputItemDoneEvent
-  | BetaResponseReasoningSummaryPartAddedEvent
-  | BetaResponseReasoningSummaryPartDoneEvent
-  | BetaResponseReasoningSummaryTextDeltaEvent
-  | BetaResponseReasoningSummaryTextDoneEvent
-  | BetaResponseReasoningTextDeltaEvent
-  | BetaResponseReasoningTextDoneEvent
-  | BetaResponseRefusalDeltaEvent
-  | BetaResponseRefusalDoneEvent
-  | BetaResponseTextDeltaEvent
-  | BetaResponseTextDoneEvent
-  | BetaResponseWebSearchCallCompletedEvent
-  | BetaResponseWebSearchCallInProgressEvent
-  | BetaResponseWebSearchCallSearchingEvent
-  | BetaResponseImageGenCallCompletedEvent
-  | BetaResponseImageGenCallGeneratingEvent
-  | BetaResponseImageGenCallInProgressEvent
-  | BetaResponseImageGenCallPartialImageEvent
-  | BetaResponseMcpCallArgumentsDeltaEvent
-  | BetaResponseMcpCallArgumentsDoneEvent
-  | BetaResponseMcpCallCompletedEvent
-  | BetaResponseMcpCallFailedEvent
-  | BetaResponseMcpCallInProgressEvent
-  | BetaResponseMcpListToolsCompletedEvent
-  | BetaResponseMcpListToolsFailedEvent
-  | BetaResponseMcpListToolsInProgressEvent
-  | BetaResponseOutputTextAnnotationAddedEvent
-  | BetaResponseQueuedEvent
-  | BetaResponseCustomToolCallInputDeltaEvent
-  | BetaResponseCustomToolCallInputDoneEvent
-  | BetaResponseInjectCreatedEvent
-  | BetaResponseInjectFailedEvent;
+ * Specifies the processing type used for serving the request.
+ *
+ * - If set to 'auto', then the request will be processed with the service tier
+ *   configured in the Project settings. Unless otherwise configured, the Project
+ *   will use 'default'.
+ * - If set to 'default', then the request will be processed with the standard
+ *   pricing and performance for the selected model.
+ * - If set to '[flex](https://platform.openai.com/docs/guides/flex-processing)',
+ *   then the request will be processed with the Flex Processing service tier.
+ * - To opt-in to [Fast mode](/api/docs/guides/fast-mode) at the request level,
+ *   include the `service_tier=fast` or `service_tier=priority` parameter for
+ *   Responses or Chat Completions. The response will show `service_tier=priority`
+ *   regardless of if you specify `service_tier=fast` or `priority` in your
+ *   request.
+ * - If set to 'ultrafast', then the request will be processed with the
+ *   access-controlled Ultrafast Processing service tier. This tier is currently
+ *   available for `gpt-5.6-sol`; a response served through it will show
+ *   `service_tier=ultrafast`.
+ * - When not set, the default behavior is 'auto'.
+ *
+ * When the `service_tier` parameter is set, the response body will include the
+ * `service_tier` value based on the processing mode actually used to serve the
+ * request. This response value may be different from the value set in the
+ * parameter.
+ */
+export type BetaServiceTier =
+  | 'auto'
+  | 'default'
+  | 'flex'
+  | 'scale'
+  | 'priority'
+  | 'fast'
+  | 'ultrafast'
+  | null;
 
 export interface BetaSkillReference {
   /**
@@ -11146,18 +12438,13 @@ export namespace BetaTool {
     action?: 'generate' | 'edit' | 'auto';
 
     /**
-     * Allows to set transparency for the background of the generated image(s). This
-     * parameter is only supported for GPT image models that support transparent
-     * backgrounds. Must be one of `transparent`, `opaque`, or `auto` (default value).
-     * When `auto` is used, the model will automatically determine the best background
-     * for the image.
+     * Allows to set transparency for the background of the generated image(s). Must be
+     * one of `transparent`, `opaque`, or `auto` (default value). When `auto` is used,
+     * the model will automatically determine the best background for the image.
      *
-     * `gpt-image-2` and `gpt-image-2-2026-04-21` do not support transparent
-     * backgrounds. Requests with `background` set to `transparent` will return an
-     * error for these models; use `opaque` or `auto` instead.
-     *
-     * If `transparent`, the output format needs to support transparency, so it should
-     * be set to either `png` (default value) or `webp`.
+     * Transparent backgrounds are available for supported GPT Image models. For
+     * `gpt-image-2` and `gpt-image-2-2026-04-21`, this support is in preview. When
+     * using `transparent`, set the output format to `png` or `webp`.
      */
     background?: 'transparent' | 'opaque' | 'auto';
 
@@ -11176,7 +12463,9 @@ export namespace BetaTool {
     input_image_mask?: ImageGeneration.InputImageMask;
 
     /**
-     * The image generation model to use. Default: `gpt-image-1`.
+     * The image generation model to use. One of `gpt-image-1`, `gpt-image-1-mini`,
+     * `gpt-image-1.5`, `gpt-image-2`, `gpt-image-2-2026-04-21`, or
+     * `chatgpt-image-latest`. Default: `gpt-image-1`.
      */
     model?:
       | (string & {})
@@ -11503,6 +12792,13 @@ export interface BetaWebSearchTool {
    */
   type: 'web_search' | 'web_search_2025_08_26';
 
+  /**
+   * Allow live internet access for web search. Defaults to true when omitted. When
+   * false, the web search tool runs in offline/cache-only mode and will not fetch
+   * new external content.
+   */
+  external_web_access?: boolean;
+
   /**
    * Filters for the search.
    */
@@ -11671,6 +12967,7 @@ export interface ResponseCreateParamsBase {
     | 'gpt-5.6-terra'
     | 'gpt-5.6-luna'
     | 'gpt-5.5'
+    | 'gpt-5.5-2026-04-23'
     | 'gpt-5.4'
     | 'gpt-5.4-mini'
     | 'gpt-5.4-nano'
@@ -11759,10 +13056,15 @@ export interface ResponseCreateParamsBase {
     | 'o4-mini-deep-research-2025-06-26'
     | 'computer-use-preview'
     | 'computer-use-preview-2025-03-11'
+    | 'gpt-5.5-pro'
+    | 'gpt-5.5-pro-2026-04-23'
     | 'gpt-5-codex'
     | 'gpt-5-pro'
     | 'gpt-5-pro-2025-10-06'
     | 'gpt-5.1-codex-max'
+    | 'gpt-daybreak-blue-latest'
+    | 'gpt-daybreak-red-latest'
+    | 'gpt-5.6-cyber'
     | (string & {});
 
   /**
@@ -11870,6 +13172,10 @@ export interface ResponseCreateParamsBase {
    *   Responses or Chat Completions. The response will show `service_tier=priority`
    *   regardless of if you specify `service_tier=fast` or `priority` in your
    *   request.
+   * - If set to 'ultrafast', then the request will be processed with the
+   *   access-controlled Ultrafast Processing service tier. This tier is currently
+   *   available for `gpt-5.6-sol`; a response served through it will show
+   *   `service_tier=ultrafast`.
    * - When not set, the default behavior is 'auto'.
    *
    * When the `service_tier` parameter is set, the response body will include the
@@ -11877,7 +13183,7 @@ export interface ResponseCreateParamsBase {
    * request. This response value may be different from the value set in the
    * parameter.
    */
-  service_tier?: 'auto' | 'default' | 'flex' | 'scale' | 'priority' | 'fast' | null;
+  service_tier?: BetaServiceTier | null;
 
   /**
    * Body param: Whether to store the generated model response for later retrieval
@@ -12315,6 +13621,7 @@ export interface ResponseCompactParams {
     | 'gpt-5.6-terra'
     | 'gpt-5.6-luna'
     | 'gpt-5.5'
+    | 'gpt-5.5-2026-04-23'
     | 'gpt-5.4'
     | 'gpt-5.4-mini'
     | 'gpt-5.4-nano'
@@ -12403,10 +13710,15 @@ export interface ResponseCompactParams {
     | 'o4-mini-deep-research-2025-06-26'
     | 'computer-use-preview'
     | 'computer-use-preview-2025-03-11'
+    | 'gpt-5.5-pro'
+    | 'gpt-5.5-pro-2026-04-23'
     | 'gpt-5-codex'
     | 'gpt-5-pro'
     | 'gpt-5-pro-2025-10-06'
     | 'gpt-5.1-codex-max'
+    | 'gpt-daybreak-blue-latest'
+    | 'gpt-daybreak-red-latest'
+    | 'gpt-5.6-cyber'
     | (string & {})
     | null;
 
@@ -12535,10 +13847,12 @@ export declare namespace Responses {
     type BetaFileSearchTool as BetaFileSearchTool,
     type BetaFunctionShellTool as BetaFunctionShellTool,
     type BetaFunctionTool as BetaFunctionTool,
+    type BetaImageDetail as BetaImageDetail,
     type BetaInlineSkill as BetaInlineSkill,
     type BetaInlineSkillSource as BetaInlineSkillSource,
     type BetaLocalEnvironment as BetaLocalEnvironment,
     type BetaLocalSkill as BetaLocalSkill,
+    type BetaMcpToolCallError as BetaMcpToolCallError,
     type BetaNamespaceTool as BetaNamespaceTool,
     type BetaResponse as BetaResponse,
     type BetaResponseApplyPatchToolCall as BetaResponseApplyPatchToolCall,
@@ -12642,6 +13956,11 @@ export declare namespace Responses {
     type BetaResponseReasoningTextDoneEvent as BetaResponseReasoningTextDoneEvent,
     type BetaResponseRefusalDeltaEvent as BetaResponseRefusalDeltaEvent,
     type BetaResponseRefusalDoneEvent as BetaResponseRefusalDoneEvent,
+    type BetaResponseShellCallCommandAddedEvent as BetaResponseShellCallCommandAddedEvent,
+    type BetaResponseShellCallCommandDeltaEvent as BetaResponseShellCallCommandDeltaEvent,
+    type BetaResponseShellCallCommandDoneEvent as BetaResponseShellCallCommandDoneEvent,
+    type BetaResponseShellCallOutputContentDeltaEvent as BetaResponseShellCallOutputContentDeltaEvent,
+    type BetaResponseShellCallOutputContentDoneEvent as BetaResponseShellCallOutputContentDoneEvent,
     type BetaResponseStatus as BetaResponseStatus,
     type BetaResponseStreamEvent as BetaResponseStreamEvent,
     type BetaResponseTextConfig as BetaResponseTextConfig,
@@ -12656,6 +13975,7 @@ export declare namespace Responses {
     type BetaResponseWebSearchCallSearchingEvent as BetaResponseWebSearchCallSearchingEvent,
     type BetaResponsesClientEvent as BetaResponsesClientEvent,
     type BetaResponsesServerEvent as BetaResponsesServerEvent,
+    type BetaServiceTier as BetaServiceTier,
     type BetaSkillReference as BetaSkillReference,
     type BetaTool as BetaTool,
     type BetaToolChoiceAllowed as BetaToolChoiceAllowed,