openai 4.98.0 → 4.99.0

package/src/resources/evals/evals.ts

@@ -105,11 +105,7 @@ export interface EvalCustomDataSourceConfig {
 }
 
 /**
- * A StoredCompletionsDataSourceConfig which specifies the metadata property of
- * your stored completions query. This is usually metadata like `usecase=chatbot`
- * or `prompt-version=v2`, etc. The schema returned by this data source config is
- * used to defined what variables are available in your evals. `item` and `sample`
- * are both defined when using this data source config.
+ * @deprecated Deprecated in favor of LogsDataSourceConfig.
  */
 export interface EvalStoredCompletionsDataSourceConfig {
   /**
@@ -119,9 +115,9 @@ export interface EvalStoredCompletionsDataSourceConfig {
   schema: Record<string, unknown>;
 
   /**
-   * The type of data source. Always `stored_completions`.
+   * The type of data source. Always `stored-completions`.
    */
-  type: 'stored_completions';
+  type: 'stored-completions';
 
   /**
    * Set of 16 key-value pairs that can be attached to an object. This can be useful
@@ -156,7 +152,10 @@ export interface EvalCreateResponse {
   /**
    * Configuration of data sources used in runs of the evaluation.
    */
-  data_source_config: EvalCustomDataSourceConfig | EvalStoredCompletionsDataSourceConfig;
+  data_source_config:
+    | EvalCustomDataSourceConfig
+    | EvalCreateResponse.Logs
+    | EvalStoredCompletionsDataSourceConfig;
 
   /**
    * Set of 16 key-value pairs that can be attached to an object. This can be useful
@@ -191,6 +190,36 @@ export interface EvalCreateResponse {
 }
 
 export namespace EvalCreateResponse {
+  /**
+   * A LogsDataSourceConfig which specifies the metadata property of your logs query.
+   * This is usually metadata like `usecase=chatbot` or `prompt-version=v2`, etc. The
+   * schema returned by this data source config is used to defined what variables are
+   * available in your evals. `item` and `sample` are both defined when using this
+   * data source config.
+   */
+  export interface Logs {
+    /**
+     * The json schema for the run data source items. Learn how to build JSON schemas
+     * [here](https://json-schema.org/).
+     */
+    schema: Record<string, unknown>;
+
+    /**
+     * The type of data source. Always `logs`.
+     */
+    type: 'logs';
+
+    /**
+     * 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?: Shared.Metadata | null;
+  }
+
   /**
    * A TextSimilarityGrader object which grades text based on similarity metrics.
    */
@@ -244,7 +273,10 @@ export interface EvalRetrieveResponse {
   /**
    * Configuration of data sources used in runs of the evaluation.
    */
-  data_source_config: EvalCustomDataSourceConfig | EvalStoredCompletionsDataSourceConfig;
+  data_source_config:
+    | EvalCustomDataSourceConfig
+    | EvalRetrieveResponse.Logs
+    | EvalStoredCompletionsDataSourceConfig;
 
   /**
    * Set of 16 key-value pairs that can be attached to an object. This can be useful
@@ -279,6 +311,36 @@ export interface EvalRetrieveResponse {
 }
 
 export namespace EvalRetrieveResponse {
+  /**
+   * A LogsDataSourceConfig which specifies the metadata property of your logs query.
+   * This is usually metadata like `usecase=chatbot` or `prompt-version=v2`, etc. The
+   * schema returned by this data source config is used to defined what variables are
+   * available in your evals. `item` and `sample` are both defined when using this
+   * data source config.
+   */
+  export interface Logs {
+    /**
+     * The json schema for the run data source items. Learn how to build JSON schemas
+     * [here](https://json-schema.org/).
+     */
+    schema: Record<string, unknown>;
+
+    /**
+     * The type of data source. Always `logs`.
+     */
+    type: 'logs';
+
+    /**
+     * 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?: Shared.Metadata | null;
+  }
+
   /**
    * A TextSimilarityGrader object which grades text based on similarity metrics.
    */
@@ -332,7 +394,10 @@ export interface EvalUpdateResponse {
   /**
    * Configuration of data sources used in runs of the evaluation.
    */
-  data_source_config: EvalCustomDataSourceConfig | EvalStoredCompletionsDataSourceConfig;
+  data_source_config:
+    | EvalCustomDataSourceConfig
+    | EvalUpdateResponse.Logs
+    | EvalStoredCompletionsDataSourceConfig;
 
   /**
    * Set of 16 key-value pairs that can be attached to an object. This can be useful
@@ -367,6 +432,36 @@ export interface EvalUpdateResponse {
 }
 
 export namespace EvalUpdateResponse {
+  /**
+   * A LogsDataSourceConfig which specifies the metadata property of your logs query.
+   * This is usually metadata like `usecase=chatbot` or `prompt-version=v2`, etc. The
+   * schema returned by this data source config is used to defined what variables are
+   * available in your evals. `item` and `sample` are both defined when using this
+   * data source config.
+   */
+  export interface Logs {
+    /**
+     * The json schema for the run data source items. Learn how to build JSON schemas
+     * [here](https://json-schema.org/).
+     */
+    schema: Record<string, unknown>;
+
+    /**
+     * The type of data source. Always `logs`.
+     */
+    type: 'logs';
+
+    /**
+     * 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?: Shared.Metadata | null;
+  }
+
   /**
    * A TextSimilarityGrader object which grades text based on similarity metrics.
    */
@@ -420,7 +515,10 @@ export interface EvalListResponse {
   /**
    * Configuration of data sources used in runs of the evaluation.
    */
-  data_source_config: EvalCustomDataSourceConfig | EvalStoredCompletionsDataSourceConfig;
+  data_source_config:
+    | EvalCustomDataSourceConfig
+    | EvalListResponse.Logs
+    | EvalStoredCompletionsDataSourceConfig;
 
   /**
    * Set of 16 key-value pairs that can be attached to an object. This can be useful
@@ -455,6 +553,36 @@ export interface EvalListResponse {
 }
 
 export namespace EvalListResponse {
+  /**
+   * A LogsDataSourceConfig which specifies the metadata property of your logs query.
+   * This is usually metadata like `usecase=chatbot` or `prompt-version=v2`, etc. The
+   * schema returned by this data source config is used to defined what variables are
+   * available in your evals. `item` and `sample` are both defined when using this
+   * data source config.
+   */
+  export interface Logs {
+    /**
+     * The json schema for the run data source items. Learn how to build JSON schemas
+     * [here](https://json-schema.org/).
+     */
+    schema: Record<string, unknown>;
+
+    /**
+     * The type of data source. Always `logs`.
+     */
+    type: 'logs';
+
+    /**
+     * 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?: Shared.Metadata | null;
+  }
+
   /**
    * A TextSimilarityGrader object which grades text based on similarity metrics.
    */
@@ -498,7 +626,7 @@ export interface EvalCreateParams {
   /**
    * The configuration for the data source used for the evaluation runs.
    */
-  data_source_config: EvalCreateParams.Custom | EvalCreateParams.StoredCompletions;
+  data_source_config: EvalCreateParams.Custom | EvalCreateParams.Logs | EvalCreateParams.StoredCompletions;
 
   /**
    * A list of graders for all eval runs in this group.
@@ -555,15 +683,29 @@ export namespace EvalCreateParams {
   }
 
   /**
-   * A data source config which specifies the metadata property of your stored
-   * completions query. This is usually metadata like `usecase=chatbot` or
-   * `prompt-version=v2`, etc.
+   * A data source config which specifies the metadata property of your logs query.
+   * This is usually metadata like `usecase=chatbot` or `prompt-version=v2`, etc.
+   */
+  export interface Logs {
+    /**
+     * The type of data source. Always `logs`.
+     */
+    type: 'logs';
+
+    /**
+     * Metadata filters for the logs data source.
+     */
+    metadata?: Record<string, unknown>;
+  }
+
+  /**
+   * Deprecated in favor of LogsDataSourceConfig.
    */
   export interface StoredCompletions {
     /**
-     * The type of data source. Always `stored_completions`.
+     * The type of data source. Always `stored-completions`.
      */
-    type: 'stored_completions';
+    type: 'stored-completions';
 
     /**
      * Metadata filters for the stored completions data source.

package/src/resources/evals/runs/runs.ts

@@ -356,7 +356,7 @@ export interface RunCreateResponse {
   data_source:
     | CreateEvalJSONLRunDataSource
     | CreateEvalCompletionsRunDataSource
-    | RunCreateResponse.Completions;
+    | RunCreateResponse.Responses;
 
   /**
    * An object representing an error response from the Eval API.
@@ -423,28 +423,28 @@ export namespace RunCreateResponse {
   /**
    * A ResponsesRunDataSource object describing a model sampling configuration.
    */
-  export interface Completions {
+  export interface Responses {
     /**
      * A EvalResponsesSource object describing a run data source configuration.
      */
-    source: Completions.FileContent | Completions.FileID | Completions.Responses;
+    source: Responses.FileContent | Responses.FileID | Responses.Responses;
 
     /**
-     * The type of run data source. Always `completions`.
+     * The type of run data source. Always `responses`.
      */
-    type: 'completions';
+    type: 'responses';
 
-    input_messages?: Completions.Template | Completions.ItemReference;
+    input_messages?: Responses.Template | Responses.ItemReference;
 
     /**
      * The name of the model to use for generating completions (e.g. "o3-mini").
      */
     model?: string;
 
-    sampling_params?: Completions.SamplingParams;
+    sampling_params?: Responses.SamplingParams;
   }
 
-  export namespace Completions {
+  export namespace Responses {
     export interface FileContent {
       /**
        * The content of the jsonl file.
@@ -486,12 +486,6 @@ export namespace RunCreateResponse {
        */
       type: 'responses';
 
-      /**
-       * Whether to allow parallel tool calls. This is a query parameter used to select
-       * responses.
-       */
-      allow_parallel_tool_calls?: boolean | null;
-
       /**
        * Only include items created after this timestamp (inclusive). This is a query
        * parameter used to select responses.
@@ -511,8 +505,8 @@ export namespace RunCreateResponse {
       has_tool_calls?: boolean | null;
 
       /**
-       * Optional search string for instructions. This is a query parameter used to
-       * select responses.
+       * Optional string to search the 'instructions' field. This is a query parameter
+       * used to select responses.
        */
       instructions_search?: string | null;
 
@@ -539,6 +533,11 @@ export namespace RunCreateResponse {
        */
       temperature?: number | null;
 
+      /**
+       * List of tool names. This is a query parameter used to select responses.
+       */
+      tools?: Array<string> | null;
+
       /**
        * Nucleus sampling parameter. This is a query parameter used to select responses.
        */
@@ -749,7 +748,7 @@ export interface RunRetrieveResponse {
   data_source:
     | CreateEvalJSONLRunDataSource
     | CreateEvalCompletionsRunDataSource
-    | RunRetrieveResponse.Completions;
+    | RunRetrieveResponse.Responses;
 
   /**
    * An object representing an error response from the Eval API.
@@ -816,28 +815,28 @@ export namespace RunRetrieveResponse {
   /**
    * A ResponsesRunDataSource object describing a model sampling configuration.
    */
-  export interface Completions {
+  export interface Responses {
     /**
      * A EvalResponsesSource object describing a run data source configuration.
      */
-    source: Completions.FileContent | Completions.FileID | Completions.Responses;
+    source: Responses.FileContent | Responses.FileID | Responses.Responses;
 
     /**
-     * The type of run data source. Always `completions`.
+     * The type of run data source. Always `responses`.
      */
-    type: 'completions';
+    type: 'responses';
 
-    input_messages?: Completions.Template | Completions.ItemReference;
+    input_messages?: Responses.Template | Responses.ItemReference;
 
     /**
      * The name of the model to use for generating completions (e.g. "o3-mini").
      */
     model?: string;
 
-    sampling_params?: Completions.SamplingParams;
+    sampling_params?: Responses.SamplingParams;
   }
 
-  export namespace Completions {
+  export namespace Responses {
     export interface FileContent {
       /**
        * The content of the jsonl file.
@@ -879,12 +878,6 @@ export namespace RunRetrieveResponse {
        */
       type: 'responses';
 
-      /**
-       * Whether to allow parallel tool calls. This is a query parameter used to select
-       * responses.
-       */
-      allow_parallel_tool_calls?: boolean | null;
-
       /**
        * Only include items created after this timestamp (inclusive). This is a query
        * parameter used to select responses.
@@ -904,8 +897,8 @@ export namespace RunRetrieveResponse {
       has_tool_calls?: boolean | null;
 
       /**
-       * Optional search string for instructions. This is a query parameter used to
-       * select responses.
+       * Optional string to search the 'instructions' field. This is a query parameter
+       * used to select responses.
        */
       instructions_search?: string | null;
 
@@ -932,6 +925,11 @@ export namespace RunRetrieveResponse {
        */
       temperature?: number | null;
 
+      /**
+       * List of tool names. This is a query parameter used to select responses.
+       */
+      tools?: Array<string> | null;
+
       /**
        * Nucleus sampling parameter. This is a query parameter used to select responses.
        */
@@ -1139,10 +1137,7 @@ export interface RunListResponse {
   /**
    * Information about the run's data source.
    */
-  data_source:
-    | CreateEvalJSONLRunDataSource
-    | CreateEvalCompletionsRunDataSource
-    | RunListResponse.Completions;
+  data_source: CreateEvalJSONLRunDataSource | CreateEvalCompletionsRunDataSource | RunListResponse.Responses;
 
   /**
    * An object representing an error response from the Eval API.
@@ -1209,28 +1204,28 @@ export namespace RunListResponse {
   /**
    * A ResponsesRunDataSource object describing a model sampling configuration.
    */
-  export interface Completions {
+  export interface Responses {
     /**
      * A EvalResponsesSource object describing a run data source configuration.
      */
-    source: Completions.FileContent | Completions.FileID | Completions.Responses;
+    source: Responses.FileContent | Responses.FileID | Responses.Responses;
 
     /**
-     * The type of run data source. Always `completions`.
+     * The type of run data source. Always `responses`.
      */
-    type: 'completions';
+    type: 'responses';
 
-    input_messages?: Completions.Template | Completions.ItemReference;
+    input_messages?: Responses.Template | Responses.ItemReference;
 
     /**
      * The name of the model to use for generating completions (e.g. "o3-mini").
      */
     model?: string;
 
-    sampling_params?: Completions.SamplingParams;
+    sampling_params?: Responses.SamplingParams;
   }
 
-  export namespace Completions {
+  export namespace Responses {
     export interface FileContent {
       /**
        * The content of the jsonl file.
@@ -1272,12 +1267,6 @@ export namespace RunListResponse {
        */
       type: 'responses';
 
-      /**
-       * Whether to allow parallel tool calls. This is a query parameter used to select
-       * responses.
-       */
-      allow_parallel_tool_calls?: boolean | null;
-
       /**
        * Only include items created after this timestamp (inclusive). This is a query
        * parameter used to select responses.
@@ -1297,8 +1286,8 @@ export namespace RunListResponse {
       has_tool_calls?: boolean | null;
 
       /**
-       * Optional search string for instructions. This is a query parameter used to
-       * select responses.
+       * Optional string to search the 'instructions' field. This is a query parameter
+       * used to select responses.
        */
       instructions_search?: string | null;
 
@@ -1325,6 +1314,11 @@ export namespace RunListResponse {
        */
       temperature?: number | null;
 
+      /**
+       * List of tool names. This is a query parameter used to select responses.
+       */
+      tools?: Array<string> | null;
+
       /**
        * Nucleus sampling parameter. This is a query parameter used to select responses.
        */
@@ -1543,7 +1537,7 @@ export interface RunCancelResponse {
   data_source:
     | CreateEvalJSONLRunDataSource
     | CreateEvalCompletionsRunDataSource
-    | RunCancelResponse.Completions;
+    | RunCancelResponse.Responses;
 
   /**
    * An object representing an error response from the Eval API.
@@ -1610,28 +1604,28 @@ export namespace RunCancelResponse {
   /**
    * A ResponsesRunDataSource object describing a model sampling configuration.
    */
-  export interface Completions {
+  export interface Responses {
     /**
      * A EvalResponsesSource object describing a run data source configuration.
      */
-    source: Completions.FileContent | Completions.FileID | Completions.Responses;
+    source: Responses.FileContent | Responses.FileID | Responses.Responses;
 
     /**
-     * The type of run data source. Always `completions`.
+     * The type of run data source. Always `responses`.
      */
-    type: 'completions';
+    type: 'responses';
 
-    input_messages?: Completions.Template | Completions.ItemReference;
+    input_messages?: Responses.Template | Responses.ItemReference;
 
     /**
      * The name of the model to use for generating completions (e.g. "o3-mini").
      */
     model?: string;
 
-    sampling_params?: Completions.SamplingParams;
+    sampling_params?: Responses.SamplingParams;
   }
 
-  export namespace Completions {
+  export namespace Responses {
     export interface FileContent {
       /**
        * The content of the jsonl file.
@@ -1673,12 +1667,6 @@ export namespace RunCancelResponse {
        */
       type: 'responses';
 
-      /**
-       * Whether to allow parallel tool calls. This is a query parameter used to select
-       * responses.
-       */
-      allow_parallel_tool_calls?: boolean | null;
-
       /**
        * Only include items created after this timestamp (inclusive). This is a query
        * parameter used to select responses.
@@ -1698,8 +1686,8 @@ export namespace RunCancelResponse {
       has_tool_calls?: boolean | null;
 
       /**
-       * Optional search string for instructions. This is a query parameter used to
-       * select responses.
+       * Optional string to search the 'instructions' field. This is a query parameter
+       * used to select responses.
        */
       instructions_search?: string | null;
 
@@ -1726,6 +1714,11 @@ export namespace RunCancelResponse {
        */
       temperature?: number | null;
 
+      /**
+       * List of tool names. This is a query parameter used to select responses.
+       */
+      tools?: Array<string> | null;
+
       /**
        * Nucleus sampling parameter. This is a query parameter used to select responses.
        */
@@ -1955,9 +1948,9 @@ export namespace RunCreateParams {
       | CreateEvalResponsesRunDataSource.Responses;
 
     /**
-     * The type of run data source. Always `completions`.
+     * The type of run data source. Always `responses`.
      */
-    type: 'completions';
+    type: 'responses';
 
     input_messages?:
       | CreateEvalResponsesRunDataSource.Template
@@ -2013,12 +2006,6 @@ export namespace RunCreateParams {
        */
       type: 'responses';
 
-      /**
-       * Whether to allow parallel tool calls. This is a query parameter used to select
-       * responses.
-       */
-      allow_parallel_tool_calls?: boolean | null;
-
       /**
        * Only include items created after this timestamp (inclusive). This is a query
        * parameter used to select responses.
@@ -2038,8 +2025,8 @@ export namespace RunCreateParams {
       has_tool_calls?: boolean | null;
 
       /**
-       * Optional search string for instructions. This is a query parameter used to
-       * select responses.
+       * Optional string to search the 'instructions' field. This is a query parameter
+       * used to select responses.
        */
       instructions_search?: string | null;
 
@@ -2066,6 +2053,11 @@ export namespace RunCreateParams {
        */
       temperature?: number | null;
 
+      /**
+       * List of tool names. This is a query parameter used to select responses.
+       */
+      tools?: Array<string> | null;
+
       /**
        * Nucleus sampling parameter. This is a query parameter used to select responses.
        */

package/src/resources/fine-tuning/jobs/jobs.ts

@@ -302,7 +302,7 @@ export namespace FineTuningJob {
      * Number of examples in each batch. A larger batch size means that model
      * parameters are updated less frequently, but with lower variance.
      */
-    batch_size?: 'auto' | number;
+    batch_size?: unknown | 'auto' | number | null;
 
     /**
      * Scaling factor for the learning rate. A smaller learning rate may be useful to

package/src/resources/graders/grader-models.ts

@@ -103,7 +103,7 @@ export interface MultiGrader {
   name: string;
 
   /**
-   * The type of grader.
+   * The object type, which is always `multi`.
    */
   type: 'multi';
 }

package/src/resources/shared.ts

@@ -41,6 +41,7 @@ export type ChatModel =
   | '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'

package/src/version.ts

@@ -1 +1 @@
-export const VERSION = '4.98.0'; // x-release-please-version
+export const VERSION = '4.99.0'; // x-release-please-version

package/version.d.ts

@@ -1,2 +1,2 @@
-export declare const VERSION = "4.98.0";
+export declare const VERSION = "4.99.0";
 //# sourceMappingURL=version.d.ts.map

package/version.js

@@ -1,5 +1,5 @@
 "use strict";
 Object.defineProperty(exports, "__esModule", { value: true });
 exports.VERSION = void 0;
-exports.VERSION = '4.98.0'; // x-release-please-version
+exports.VERSION = '4.99.0'; // x-release-please-version
 //# sourceMappingURL=version.js.map

package/version.mjs

@@ -1,2 +1,2 @@
-export const VERSION = '4.98.0'; // x-release-please-version
+export const VERSION = '4.99.0'; // x-release-please-version
 //# sourceMappingURL=version.mjs.map