feat(api): add new text parameters, expiration options

Author: stainless-app[bot]

.stats.yml

@@ -1,4 +1,4 @@
 configured_endpoints: 111
-openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-9cadfad609f94f20ebf74fdc06a80302f1a324dc69700a309a8056aabca82fd2.yml
-openapi_spec_hash: 3eb8d86c06f0bb5e1190983e5acfc9ba
-config_hash: 68337b532875626269c304372a669f67
+openapi_spec_url: https://storage.googleapis.com/stainless-sdk-openapi-specs/openai%2Fopenai-24be531010b354303d741fc9247c1f84f75978f9f7de68aca92cb4f240a04722.yml
+openapi_spec_hash: 3e46f439f6a863beadc71577eb4efa15
+config_hash: ed87b9139ac595a04a2162d754df2fed

src/resources/batches.ts

@@ -244,6 +244,33 @@ export interface BatchCreateParams {
    * a maximum length of 512 characters.
    */
   metadata?: Shared.Metadata | null;
+
+  /**
+   * The expiration policy for the output and/or error file that are generated for a
+   * batch.
+   */
+  output_expires_after?: BatchCreateParams.OutputExpiresAfter;
+}
+
+export namespace BatchCreateParams {
+  /**
+   * The expiration policy for the output and/or error file that are generated for a
+   * batch.
+   */
+  export interface OutputExpiresAfter {
+    /**
+     * Anchor timestamp after which the expiration policy applies. Supported anchors:
+     * `created_at`. Note that the anchor is the file creation time, not the time the
+     * batch is created.
+     */
+    anchor: 'created_at';
+
+    /**
+     * The number of seconds after the anchor time that the file will expire. Must be
+     * between 3600 (1 hour) and 2592000 (30 days).
+     */
+    seconds: number;
+  }
 }
 
 export interface BatchListParams extends CursorPageParams {}

src/resources/beta/realtime/realtime.ts

@@ -1545,7 +1545,8 @@ export interface ResponseAudioTranscriptDoneEvent {
 
 /**
  * Send this event to cancel an in-progress response. The server will respond with
- * a `response.cancelled` event or an error if there is no response to cancel.
+ * a `response.done` event with a status of `response.status=cancelled`. If there
+ * is no response to cancel, the server will respond with an error.
  */
 export interface ResponseCancelEvent {
   /**
@@ -2287,7 +2288,7 @@ export namespace SessionUpdateEvent {
      * set to `null` to turn off, in which case the client must manually trigger model
      * response. Server VAD means that the model will detect the start and end of
      * speech based on audio volume and respond at the end of user speech. Semantic VAD
-     * is more advanced and uses a turn detection model (in conjuction with VAD) to
+     * is more advanced and uses a turn detection model (in conjunction with VAD) to
      * semantically estimate whether the user has finished speaking, then dynamically
      * sets a timeout based on this probability. For example, if user audio trails off
      * with "uhhm", the model will score a low probability of turn end and wait longer
@@ -2435,7 +2436,7 @@ export namespace SessionUpdateEvent {
      * set to `null` to turn off, in which case the client must manually trigger model
      * response. Server VAD means that the model will detect the start and end of
      * speech based on audio volume and respond at the end of user speech. Semantic VAD
-     * is more advanced and uses a turn detection model (in conjuction with VAD) to
+     * is more advanced and uses a turn detection model (in conjunction with VAD) to
      * semantically estimate whether the user has finished speaking, then dynamically
      * sets a timeout based on this probability. For example, if user audio trails off
      * with "uhhm", the model will score a low probability of turn end and wait longer
@@ -2583,7 +2584,7 @@ export namespace TranscriptionSessionUpdate {
      * set to `null` to turn off, in which case the client must manually trigger model
      * response. Server VAD means that the model will detect the start and end of
      * speech based on audio volume and respond at the end of user speech. Semantic VAD
-     * is more advanced and uses a turn detection model (in conjuction with VAD) to
+     * is more advanced and uses a turn detection model (in conjunction with VAD) to
      * semantically estimate whether the user has finished speaking, then dynamically
      * sets a timeout based on this probability. For example, if user audio trails off
      * with "uhhm", the model will score a low probability of turn end and wait longer
@@ -2673,7 +2674,7 @@ export namespace TranscriptionSessionUpdate {
      * set to `null` to turn off, in which case the client must manually trigger model
      * response. Server VAD means that the model will detect the start and end of
      * speech based on audio volume and respond at the end of user speech. Semantic VAD
-     * is more advanced and uses a turn detection model (in conjuction with VAD) to
+     * is more advanced and uses a turn detection model (in conjunction with VAD) to
      * semantically estimate whether the user has finished speaking, then dynamically
      * sets a timeout based on this probability. For example, if user audio trails off
      * with "uhhm", the model will score a low probability of turn end and wait longer

src/resources/beta/realtime/sessions.ts

@@ -150,7 +150,7 @@ export interface Session {
    * set to `null` to turn off, in which case the client must manually trigger model
    * response. Server VAD means that the model will detect the start and end of
    * speech based on audio volume and respond at the end of user speech. Semantic VAD
-   * is more advanced and uses a turn detection model (in conjuction with VAD) to
+   * is more advanced and uses a turn detection model (in conjunction with VAD) to
    * semantically estimate whether the user has finished speaking, then dynamically
    * sets a timeout based on this probability. For example, if user audio trails off
    * with "uhhm", the model will score a low probability of turn end and wait longer
@@ -269,7 +269,7 @@ export namespace Session {
    * set to `null` to turn off, in which case the client must manually trigger model
    * response. Server VAD means that the model will detect the start and end of
    * speech based on audio volume and respond at the end of user speech. Semantic VAD
-   * is more advanced and uses a turn detection model (in conjuction with VAD) to
+   * is more advanced and uses a turn detection model (in conjunction with VAD) to
    * semantically estimate whether the user has finished speaking, then dynamically
    * sets a timeout based on this probability. For example, if user audio trails off
    * with "uhhm", the model will score a low probability of turn end and wait longer
@@ -325,7 +325,7 @@ export namespace Session {
 }
 
 /**
- * A new Realtime session configuration, with an ephermeral key. Default TTL for
+ * A new Realtime session configuration, with an ephemeral key. Default TTL for
  * keys is one minute.
  */
 export interface SessionCreateResponse {
@@ -657,7 +657,7 @@ export interface SessionCreateParams {
    * set to `null` to turn off, in which case the client must manually trigger model
    * response. Server VAD means that the model will detect the start and end of
    * speech based on audio volume and respond at the end of user speech. Semantic VAD
-   * is more advanced and uses a turn detection model (in conjuction with VAD) to
+   * is more advanced and uses a turn detection model (in conjunction with VAD) to
    * semantically estimate whether the user has finished speaking, then dynamically
    * sets a timeout based on this probability. For example, if user audio trails off
    * with "uhhm", the model will score a low probability of turn end and wait longer
@@ -805,7 +805,7 @@ export namespace SessionCreateParams {
    * set to `null` to turn off, in which case the client must manually trigger model
    * response. Server VAD means that the model will detect the start and end of
    * speech based on audio volume and respond at the end of user speech. Semantic VAD
-   * is more advanced and uses a turn detection model (in conjuction with VAD) to
+   * is more advanced and uses a turn detection model (in conjunction with VAD) to
    * semantically estimate whether the user has finished speaking, then dynamically
    * sets a timeout based on this probability. For example, if user audio trails off
    * with "uhhm", the model will score a low probability of turn end and wait longer

src/resources/beta/realtime/transcription-sessions.ts

@@ -194,7 +194,7 @@ export interface TranscriptionSessionCreateParams {
    * set to `null` to turn off, in which case the client must manually trigger model
    * response. Server VAD means that the model will detect the start and end of
    * speech based on audio volume and respond at the end of user speech. Semantic VAD
-   * is more advanced and uses a turn detection model (in conjuction with VAD) to
+   * is more advanced and uses a turn detection model (in conjunction with VAD) to
    * semantically estimate whether the user has finished speaking, then dynamically
    * sets a timeout based on this probability. For example, if user audio trails off
    * with "uhhm", the model will score a low probability of turn end and wait longer
@@ -284,7 +284,7 @@ export namespace TranscriptionSessionCreateParams {
    * set to `null` to turn off, in which case the client must manually trigger model
    * response. Server VAD means that the model will detect the start and end of
    * speech based on audio volume and respond at the end of user speech. Semantic VAD
-   * is more advanced and uses a turn detection model (in conjuction with VAD) to
+   * is more advanced and uses a turn detection model (in conjunction with VAD) to
    * semantically estimate whether the user has finished speaking, then dynamically
    * sets a timeout based on this probability. For example, if user audio trails off
    * with "uhhm", the model will score a low probability of turn end and wait longer

src/resources/beta/threads/runs/runs.ts

@@ -502,7 +502,7 @@ export interface Run {
 
   /**
    * Controls for how a thread will be truncated prior to the run. Use this to
-   * control the intial context window of the run.
+   * control the initial context window of the run.
    */
   truncation_strategy: Run.TruncationStrategy | null;
 
@@ -581,7 +581,7 @@ export namespace Run {
 
   /**
    * Controls for how a thread will be truncated prior to the run. Use this to
-   * control the intial context window of the run.
+   * control the initial context window of the run.
    */
   export interface TruncationStrategy {
     /**
@@ -799,7 +799,7 @@ export interface RunCreateParamsBase {
 
   /**
    * Body param: Controls for how a thread will be truncated prior to the run. Use
-   * this to control the intial context window of the run.
+   * this to control the initial context window of the run.
    */
   truncation_strategy?: RunCreateParams.TruncationStrategy | null;
 }
@@ -862,7 +862,7 @@ export namespace RunCreateParams {
 
   /**
    * Controls for how a thread will be truncated prior to the run. Use this to
-   * control the intial context window of the run.
+   * control the initial context window of the run.
    */
   export interface TruncationStrategy {
     /**

src/resources/beta/threads/threads.ts

@@ -703,7 +703,7 @@ export interface ThreadCreateAndRunParamsBase {
 
   /**
    * Controls for how a thread will be truncated prior to the run. Use this to
-   * control the intial context window of the run.
+   * control the initial context window of the run.
    */
   truncation_strategy?: ThreadCreateAndRunParams.TruncationStrategy | null;
 }
@@ -938,7 +938,7 @@ export namespace ThreadCreateAndRunParams {
 
   /**
    * Controls for how a thread will be truncated prior to the run. Use this to
-   * control the intial context window of the run.
+   * control the initial context window of the run.
    */
   export interface TruncationStrategy {
     /**

src/resources/chat/completions/completions.ts

@@ -281,9 +281,8 @@ export interface ChatCompletion {
    * - 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)' or
-   *   'priority', then the request will be processed with the corresponding service
-   *   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
-   *   Priority processing.
+   *   '[priority](https://openai.com/api-priority-processing/)', then the request
+   *   will be processed with the corresponding service tier.
    * - When not set, the default behavior is 'auto'.
    *
    * When the `service_tier` parameter is set, the response body will include the
@@ -294,7 +293,8 @@ export interface ChatCompletion {
   service_tier?: 'auto' | 'default' | 'flex' | 'scale' | 'priority' | null;
 
   /**
-   * This fingerprint represents the backend configuration that the model runs with.
+   * @deprecated This fingerprint represents the backend configuration that the model
+   * runs with.
    *
    * Can be used in conjunction with the `seed` request parameter to understand when
    * backend changes have been made that might impact determinism.
@@ -535,9 +535,8 @@ export interface ChatCompletionChunk {
    * - 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)' or
-   *   'priority', then the request will be processed with the corresponding service
-   *   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
-   *   Priority processing.
+   *   '[priority](https://openai.com/api-priority-processing/)', then the request
+   *   will be processed with the corresponding service tier.
    * - When not set, the default behavior is 'auto'.
    *
    * When the `service_tier` parameter is set, the response body will include the
@@ -548,9 +547,9 @@ export interface ChatCompletionChunk {
   service_tier?: 'auto' | 'default' | 'flex' | 'scale' | 'priority' | null;
 
   /**
-   * This fingerprint represents the backend configuration that the model runs with.
-   * Can be used in conjunction with the `seed` request parameter to understand when
-   * backend changes have been made that might impact determinism.
+   * @deprecated This fingerprint represents the backend configuration that the model
+   * runs with. Can be used in conjunction with the `seed` request parameter to
+   * understand when backend changes have been made that might impact determinism.
    */
   system_fingerprint?: string;
 
@@ -1664,11 +1663,11 @@ export interface ChatCompletionCreateParamsBase {
   safety_identifier?: string;
 
   /**
-   * This feature is in Beta. If specified, our system will make a best effort to
-   * sample deterministically, such that repeated requests with the same `seed` and
-   * parameters should return the same result. Determinism is not guaranteed, and you
-   * should refer to the `system_fingerprint` response parameter to monitor changes
-   * in the backend.
+   * @deprecated This feature is in Beta. If specified, our system will make a best
+   * effort to sample deterministically, such that repeated requests with the same
+   * `seed` and parameters should return the same result. Determinism is not
+   * guaranteed, and you should refer to the `system_fingerprint` response parameter
+   * to monitor changes in the backend.
    */
   seed?: number | null;
 
@@ -1681,9 +1680,8 @@ export interface ChatCompletionCreateParamsBase {
    * - 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)' or
-   *   'priority', then the request will be processed with the corresponding service
-   *   tier. [Contact sales](https://openai.com/contact-sales) to learn more about
-   *   Priority processing.
+   *   '[priority](https://openai.com/api-priority-processing/)', then the request
+   *   will be processed with the corresponding service tier.
    * - When not set, the default behavior is 'auto'.
    *
    * When the `service_tier` parameter is set, the response body will include the
@@ -1735,6 +1733,8 @@ export interface ChatCompletionCreateParamsBase {
    */
   temperature?: number | null;
 
+  text?: ChatCompletionCreateParams.Text;
+
   /**
    * Controls which (if any) tool is called by the model. `none` means the model will
    * not call any tool and instead generates a message. `auto` means the model can
@@ -1825,6 +1825,15 @@ export namespace ChatCompletionCreateParams {
     parameters?: Shared.FunctionParameters;
   }
 
+  export interface Text {
+    /**
+     * 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`.
+     */
+    verbosity?: 'low' | 'medium' | 'high' | null;
+  }
+
   /**
    * This tool searches the web for relevant results to use in a response. Learn more
    * about the

src/resources/files.ts

@@ -15,7 +15,7 @@ export class Files extends APIResource {
   /**
    * Upload a file that can be used across various endpoints. Individual files can be
    * up to 512 MB, and the size of all files uploaded by one organization can be up
-   * to 100 GB.
+   * to 1 TB.
    *
    * The Assistants API supports files up to 2 million tokens and of specific file
    * types. See the
@@ -196,6 +196,32 @@ export interface FileCreateParams {
    * Flexible file type for any purpose - `evals`: Used for eval data sets
    */
   purpose: FilePurpose;
+
+  /**
+   * The expiration policy for a file. By default, files with `purpose=batch` expire
+   * after 30 days and all other files are persisted until they are manually deleted.
+   */
+  expires_after?: FileCreateParams.ExpiresAfter;
+}
+
+export namespace FileCreateParams {
+  /**
+   * The expiration policy for a file. By default, files with `purpose=batch` expire
+   * after 30 days and all other files are persisted until they are manually deleted.
+   */
+  export interface ExpiresAfter {
+    /**
+     * Anchor timestamp after which the expiration policy applies. Supported anchors:
+     * `created_at`.
+     */
+    anchor: 'created_at';
+
+    /**
+     * The number of seconds after the anchor time that the file will expire. Must be
+     * between 3600 (1 hour) and 2592000 (30 days).
+     */
+    seconds: number;
+  }
 }
 
 export interface FileListParams extends CursorPageParams {