@iblai/iblai-api 4.253.3-ai → 4.254.0-ai

package/dist/index.cjs.js

@@ -110,7 +110,7 @@ class CancelablePromise {
 
 const OpenAPI = {
   BASE: 'https://base.manager.iblai.app',
-  VERSION: '4.253.3-ai-plus',
+  VERSION: '4.254.0-ai-plus',
   WITH_CREDENTIALS: false,
   CREDENTIALS: 'include',
   TOKEN: undefined,
@@ -405,6 +405,36 @@ exports.CreditTransactionHistoryStatusEnum = void 0;
   CreditTransactionHistoryStatusEnum["CANCELLED"] = "cancelled";
 })(exports.CreditTransactionHistoryStatusEnum || (exports.CreditTransactionHistoryStatusEnum = {}));
 
+/* generated using openapi-typescript-codegen -- do not edit */
+/* istanbul ignore file */
+/* tslint:disable */
+/* eslint-disable */
+/**
+ * * `ACTIVE` - ACTIVE
+ * * `ARCHIVED` - ARCHIVED
+ */
+exports.DatasetItemUpdateStatusEnum = void 0;
+(function (DatasetItemUpdateStatusEnum) {
+  DatasetItemUpdateStatusEnum["ACTIVE"] = "ACTIVE";
+  DatasetItemUpdateStatusEnum["ARCHIVED"] = "ARCHIVED";
+})(exports.DatasetItemUpdateStatusEnum || (exports.DatasetItemUpdateStatusEnum = {}));
+
+/* generated using openapi-typescript-codegen -- do not edit */
+/* istanbul ignore file */
+/* tslint:disable */
+/* eslint-disable */
+/**
+ * * `NUMERIC` - NUMERIC
+ * * `BOOLEAN` - BOOLEAN
+ * * `CATEGORICAL` - CATEGORICAL
+ */
+exports.DataTypeEnum = void 0;
+(function (DataTypeEnum) {
+  DataTypeEnum["NUMERIC"] = "NUMERIC";
+  DataTypeEnum["BOOLEAN"] = "BOOLEAN";
+  DataTypeEnum["CATEGORICAL"] = "CATEGORICAL";
+})(exports.DataTypeEnum || (exports.DataTypeEnum = {}));
+
 /* generated using openapi-typescript-codegen -- do not edit */
 /* istanbul ignore file */
 /* tslint:disable */
@@ -19899,386 +19929,6 @@ class AiMentorService {
       }
     });
   }
-  /**
-   * List datasets belonging to the tenant.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsRetrieve({
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'GET',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/',
-      path: {
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Create a new dataset.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsCreate({
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'POST',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/',
-      path: {
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Get a single dataset by name.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsRetrieve2({
-    datasetName,
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'GET',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/',
-      path: {
-        'dataset_name': datasetName,
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * List items in a dataset.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsItemsRetrieve({
-    datasetName,
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'GET',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/items/',
-      path: {
-        'dataset_name': datasetName,
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Add items to a dataset from direct input or trace IDs.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsItemsCreate({
-    datasetName,
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'POST',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/items/',
-      path: {
-        'dataset_name': datasetName,
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Update a dataset item.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsItemsUpdate({
-    datasetName,
-    itemId,
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'PUT',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/items/{item_id}/',
-      path: {
-        'dataset_name': datasetName,
-        'item_id': itemId,
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Delete a dataset item.
-   * @returns void
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsItemsDestroy({
-    datasetName,
-    itemId,
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'DELETE',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/items/{item_id}/',
-      path: {
-        'dataset_name': datasetName,
-        'item_id': itemId,
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Upload a CSV file to create dataset items.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsItemsUploadCreate({
-    datasetName,
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'POST',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/items/upload/',
-      path: {
-        'dataset_name': datasetName,
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * List experiment runs for a dataset.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsRunsRetrieve({
-    datasetName,
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'GET',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/',
-      path: {
-        'dataset_name': datasetName,
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Start an experiment — dispatches a Celery task.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsRunsCreate({
-    datasetName,
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'POST',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/',
-      path: {
-        'dataset_name': datasetName,
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Get experiment run details.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsRunsRetrieve2({
-    datasetName,
-    org,
-    runName,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'GET',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/{run_name}/',
-      path: {
-        'dataset_name': datasetName,
-        'org': org,
-        'run_name': runName,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Delete an experiment run.
-   * @returns void
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsRunsDestroy({
-    datasetName,
-    org,
-    runName,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'DELETE',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/{run_name}/',
-      path: {
-        'dataset_name': datasetName,
-        'org': org,
-        'run_name': runName,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Trigger LLM-as-Judge evaluation on a completed experiment run.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsRunsEvaluateCreate({
-    datasetName,
-    org,
-    runName,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'POST',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/{run_name}/evaluate/',
-      path: {
-        'dataset_name': datasetName,
-        'org': org,
-        'run_name': runName,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Export experiment results as CSV.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsDatasetsRunsExportRetrieve({
-    datasetName,
-    org,
-    runName,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'GET',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/{run_name}/export/',
-      path: {
-        'dataset_name': datasetName,
-        'org': org,
-        'run_name': runName,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * List score configurations.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsScoreConfigsRetrieve({
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'GET',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/score-configs/',
-      path: {
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Create a score configuration.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsScoreConfigsCreate({
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'POST',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/score-configs/',
-      path: {
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * List scores with optional filters.
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsScoresRetrieve({
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'GET',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/scores/',
-      path: {
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Create a score (human annotation).
-   * @returns any No response body
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsScoresCreate({
-    org,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'POST',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/scores/',
-      path: {
-        'org': org,
-        'user_id': userId
-      }
-    });
-  }
-  /**
-   * Delete a score.
-   * @returns void
-   * @throws ApiError
-   */
-  static aiMentorOrgsUsersEvaluationsScoresDestroy({
-    org,
-    scoreId,
-    userId
-  }) {
-    return request(OpenAPI, {
-      method: 'DELETE',
-      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/scores/{score_id}/',
-      path: {
-        'org': org,
-        'score_id': scoreId,
-        'user_id': userId
-      }
-    });
-  }
   /**
    * Retrieve the count of free usage credits available to a user.
    *
@@ -44210,6 +43860,627 @@ class CustomDomainsService {
   }
 }
 
+class EvaluationsService {
+  /**
+   * List datasets
+   * List datasets belonging to the tenant. Supports server-side filtering by name substring and creator email (matched against the cached `created_by_email` in Langfuse metadata).
+   * @returns PaginatedDatasetList
+   * @throws ApiError
+   */
+  static evaluationsDatasetsList({
+    org,
+    userId,
+    limit,
+    name,
+    page,
+    userEmail
+  }) {
+    return request(OpenAPI, {
+      method: 'GET',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/',
+      path: {
+        'org': org,
+        'user_id': userId
+      },
+      query: {
+        'limit': limit,
+        'name': name,
+        'page': page,
+        'user_email': userEmail
+      }
+    });
+  }
+  /**
+   * Create a dataset
+   * Create a Langfuse dataset under the tenant. The creator's `username` and `user_email` are captured into metadata so future list responses can attribute the row without an extra DB lookup.
+   * @returns Dataset
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsDatasetsCreate({
+    org,
+    userId,
+    requestBody
+  }) {
+    return request(OpenAPI, {
+      method: 'POST',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/',
+      path: {
+        'org': org,
+        'user_id': userId
+      },
+      body: requestBody,
+      mediaType: 'application/json',
+      errors: {
+        400: `Validation error.`
+      }
+    });
+  }
+  /**
+   * Retrieve a dataset
+   * Get a single dataset by name.
+   * @returns Dataset
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsDatasetsRetrieve({
+    datasetName,
+    org,
+    userId
+  }) {
+    return request(OpenAPI, {
+      method: 'GET',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/',
+      path: {
+        'dataset_name': datasetName,
+        'org': org,
+        'user_id': userId
+      },
+      errors: {
+        403: `Authenticated, but the resource belongs to another tenant.`,
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * List dataset items
+   * List items in a dataset. Pass `?include_trace=true` to attach `trace_input` / `trace_output` for items linked to a source trace (one bulk ClickHouse query for the page — no per-row fan-out).
+   * @returns PaginatedDatasetItemList
+   * @throws ApiError
+   */
+  static evaluationsDatasetItemsList({
+    datasetName,
+    org,
+    userId,
+    includeTrace,
+    limit,
+    page
+  }) {
+    return request(OpenAPI, {
+      method: 'GET',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/items/',
+      path: {
+        'dataset_name': datasetName,
+        'org': org,
+        'user_id': userId
+      },
+      query: {
+        'include_trace': includeTrace,
+        'limit': limit,
+        'page': page
+      },
+      errors: {
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * Add dataset items
+   * Add items to a dataset. Provide either an `items` array of `{input, expected_output}` objects OR a `trace_ids` array to seed items from existing traces (input/expected are then copied from the trace). Exactly one of the two must be present.
+   * @returns DatasetItemBulkCreateResponse
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsDatasetsItemsCreate({
+    datasetName,
+    org,
+    userId,
+    requestBody
+  }) {
+    return request(OpenAPI, {
+      method: 'POST',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/items/',
+      path: {
+        'dataset_name': datasetName,
+        'org': org,
+        'user_id': userId
+      },
+      body: requestBody,
+      mediaType: 'application/json',
+      errors: {
+        400: `Validation error.`,
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * Retrieve a dataset item
+   * Retrieve a single dataset item. `trace_input` / `trace_output` are always populated when the item has a `source_trace_id` (single-row case, no fan-out concern).
+   * @returns DatasetItem
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsDatasetsItemsRetrieve({
+    datasetName,
+    itemId,
+    org,
+    userId
+  }) {
+    return request(OpenAPI, {
+      method: 'GET',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/items/{item_id}/',
+      path: {
+        'dataset_name': datasetName,
+        'item_id': itemId,
+        'org': org,
+        'user_id': userId
+      },
+      errors: {
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * Update a dataset item
+   * Update any subset of `input`, `expected_output`, `metadata`, or `status` on a dataset item. Uses Langfuse's id-based upsert.
+   * @returns DatasetItem
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsDatasetsItemsUpdate({
+    datasetName,
+    itemId,
+    org,
+    userId,
+    requestBody
+  }) {
+    return request(OpenAPI, {
+      method: 'PUT',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/items/{item_id}/',
+      path: {
+        'dataset_name': datasetName,
+        'item_id': itemId,
+        'org': org,
+        'user_id': userId
+      },
+      body: requestBody,
+      mediaType: 'application/json',
+      errors: {
+        400: `Validation error.`,
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * Delete a dataset item
+   * Delete a dataset item.
+   * @returns void
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsDatasetsItemsDestroy({
+    datasetName,
+    itemId,
+    org,
+    userId
+  }) {
+    return request(OpenAPI, {
+      method: 'DELETE',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/items/{item_id}/',
+      path: {
+        'dataset_name': datasetName,
+        'item_id': itemId,
+        'org': org,
+        'user_id': userId
+      },
+      errors: {
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * Upload a CSV of dataset items
+   * Bulk-create items from a CSV (multipart `file` field). The CSV must have an `input` column; `expected_output` is optional. Rows with empty `input` are skipped.
+   * @returns DatasetItemBulkCreateResponse
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsDatasetsItemsUploadCreate({
+    datasetName,
+    org,
+    userId,
+    formData
+  }) {
+    return request(OpenAPI, {
+      method: 'POST',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/items/upload/',
+      path: {
+        'dataset_name': datasetName,
+        'org': org,
+        'user_id': userId
+      },
+      formData: formData,
+      mediaType: 'multipart/form-data',
+      errors: {
+        400: `Validation error.`,
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * List experiment runs
+   * List runs for a dataset. The response merges Langfuse-persisted runs with in-flight `EvaluationTaskRecord` rows (status `pending` / `in_progress`), deduplicated by `run_name`. `pending_count` reports how many pending entries are in the page so the UI can badge in-flight work.
+   * @returns PaginatedRunList
+   * @throws ApiError
+   */
+  static evaluationsRunsList({
+    datasetName,
+    org,
+    userId,
+    limit,
+    page,
+    userEmail
+  }) {
+    return request(OpenAPI, {
+      method: 'GET',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/',
+      path: {
+        'dataset_name': datasetName,
+        'org': org,
+        'user_id': userId
+      },
+      query: {
+        'limit': limit,
+        'page': page,
+        'user_email': userEmail
+      },
+      errors: {
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * Start an experiment run
+   * Dispatch a Celery task that runs the chosen mentor against every item in the dataset. Returns immediately (HTTP 202) with the new task record. Poll the list endpoint (or the run-detail endpoint once Langfuse persists the run) to watch the `pending → in_progress → completed` transition.
+   * @returns Run
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsDatasetsRunsCreate({
+    datasetName,
+    org,
+    userId,
+    requestBody
+  }) {
+    return request(OpenAPI, {
+      method: 'POST',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/',
+      path: {
+        'dataset_name': datasetName,
+        'org': org,
+        'user_id': userId
+      },
+      body: requestBody,
+      mediaType: 'application/json',
+      errors: {
+        400: `Validation error.`,
+        404: `Dataset or mentor not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * Retrieve experiment run details
+   * Returns the run header plus every `dataset_run_item` fully expanded with `input`, `expected_output`, `actual_output`, `trace_id`, and per-item `scores`. Also embeds a `pending_judges` array for any in-flight LLM-as-Judge evaluations against this run.
+   *
+   * Cost: 1 PG query + 2 ClickHouse queries + 1 score query regardless of run size.
+   * @returns RunDetailResponse
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsDatasetsRunsRetrieve({
+    datasetName,
+    org,
+    runName,
+    userId
+  }) {
+    return request(OpenAPI, {
+      method: 'GET',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/{run_name}/',
+      path: {
+        'dataset_name': datasetName,
+        'org': org,
+        'run_name': runName,
+        'user_id': userId
+      },
+      errors: {
+        403: `Authenticated, but the resource belongs to another tenant.`,
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * Delete an experiment run
+   * Delete an experiment run.
+   * @returns void
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsDatasetsRunsDestroy({
+    datasetName,
+    org,
+    runName,
+    userId
+  }) {
+    return request(OpenAPI, {
+      method: 'DELETE',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/{run_name}/',
+      path: {
+        'dataset_name': datasetName,
+        'org': org,
+        'run_name': runName,
+        'user_id': userId
+      },
+      errors: {
+        403: `Authenticated, but the resource belongs to another tenant.`,
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * List LLM-as-Judge evaluations for a run
+   * Returns every judge task record (any status) targeting this run. Useful for showing an 'Evaluations' history on a run-detail view, including failed and pending ones.
+   * @returns PaginatedJudgeList
+   * @throws ApiError
+   */
+  static evaluationsRunJudgesList({
+    datasetName,
+    org,
+    runName,
+    userId,
+    limit,
+    page,
+    status,
+    userEmail
+  }) {
+    return request(OpenAPI, {
+      method: 'GET',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/{run_name}/evaluate/',
+      path: {
+        'dataset_name': datasetName,
+        'org': org,
+        'run_name': runName,
+        'user_id': userId
+      },
+      query: {
+        'limit': limit,
+        'page': page,
+        'status': status,
+        'user_email': userEmail
+      }
+    });
+  }
+  /**
+   * Start an LLM-as-Judge evaluation
+   * Dispatch a Celery task that runs a separate LLM over every item in the run, scoring the actual output against the input + expected output using the provided criteria. The judge's score lands in Langfuse with `score_name`, and its reasoning is stored in the score's `comment`.
+   *
+   * Returns immediately (HTTP 202) with the new task record. The task transitions through `pending → in_progress → completed` (or `failed`); poll the list endpoint or the run-detail endpoint to watch.
+   * @returns JudgeRecord
+   * @throws ApiError
+   */
+  static evaluationsRunJudgeCreate({
+    datasetName,
+    org,
+    runName,
+    userId,
+    requestBody
+  }) {
+    return request(OpenAPI, {
+      method: 'POST',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/{run_name}/evaluate/',
+      path: {
+        'dataset_name': datasetName,
+        'org': org,
+        'run_name': runName,
+        'user_id': userId
+      },
+      body: requestBody,
+      mediaType: 'application/json',
+      errors: {
+        400: `Empty run or invalid input.`,
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * Export experiment results as CSV
+   * Download the run as a CSV. Columns: `item_id`, `input`, `expected_output`, `trace_id`, `actual_output`, and one `score_<name>` column per distinct score name in the run.
+   * @returns binary CSV file download.
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsDatasetsRunsExportRetrieve({
+    datasetName,
+    org,
+    runName,
+    userId
+  }) {
+    return request(OpenAPI, {
+      method: 'GET',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/datasets/{dataset_name}/runs/{run_name}/export/',
+      path: {
+        'dataset_name': datasetName,
+        'org': org,
+        'run_name': runName,
+        'user_id': userId
+      },
+      errors: {
+        403: `Authenticated, but the resource belongs to another tenant.`,
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+  /**
+   * List LLM-as-Judge evaluations (tenant-wide)
+   * Returns every judge task record in the tenant, across all datasets and runs. Useful for a tenant-wide 'Evaluations' inbox.
+   * @returns PaginatedJudgeList
+   * @throws ApiError
+   */
+  static evaluationsJudgesGlobalList({
+    org,
+    userId,
+    datasetName,
+    limit,
+    page,
+    status,
+    userEmail
+  }) {
+    return request(OpenAPI, {
+      method: 'GET',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/judges/',
+      path: {
+        'org': org,
+        'user_id': userId
+      },
+      query: {
+        'dataset_name': datasetName,
+        'limit': limit,
+        'page': page,
+        'status': status,
+        'user_email': userEmail
+      }
+    });
+  }
+  /**
+   * List score configurations
+   * Score configurations define reusable rubrics (numeric ranges, boolean, or categorical labels). They are optional — scores work without one — but useful for enforcing consistent grading.
+   * @returns PaginatedScoreConfigList
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsScoreConfigsRetrieve({
+    org,
+    userId,
+    limit,
+    page
+  }) {
+    return request(OpenAPI, {
+      method: 'GET',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/score-configs/',
+      path: {
+        'org': org,
+        'user_id': userId
+      },
+      query: {
+        'limit': limit,
+        'page': page
+      }
+    });
+  }
+  /**
+   * Create a score configuration
+   * Create a score configuration.
+   * @returns ScoreConfig
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsScoreConfigsCreate({
+    org,
+    userId,
+    requestBody
+  }) {
+    return request(OpenAPI, {
+      method: 'POST',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/score-configs/',
+      path: {
+        'org': org,
+        'user_id': userId
+      },
+      body: requestBody,
+      mediaType: 'application/json',
+      errors: {
+        400: `Validation error.`
+      }
+    });
+  }
+  /**
+   * List scores
+   * List scores (human annotations and LLM-judge results) with optional filters. Pair `dataset_run_id` with a run id to scope to one experiment; pass `trace_id` to scope to a single chat turn or mentor invocation.
+   * @returns PaginatedScoreList
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsScoresRetrieve({
+    org,
+    userId,
+    datasetRunId,
+    limit,
+    name,
+    page,
+    traceId
+  }) {
+    return request(OpenAPI, {
+      method: 'GET',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/scores/',
+      path: {
+        'org': org,
+        'user_id': userId
+      },
+      query: {
+        'dataset_run_id': datasetRunId,
+        'limit': limit,
+        'name': name,
+        'page': page,
+        'trace_id': traceId
+      }
+    });
+  }
+  /**
+   * Create a score
+   * Create a score on a trace or observation. Use this to record human grading of a single chat message (pass the chat frame's `generation_id` as `trace_id`) or to score an experiment-run item (also pass `dataset_run_id` so the score shows up in the run's CSV export).
+   * @returns ScoreCreateResponse
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsScoresCreate({
+    org,
+    userId,
+    requestBody
+  }) {
+    return request(OpenAPI, {
+      method: 'POST',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/scores/',
+      path: {
+        'org': org,
+        'user_id': userId
+      },
+      body: requestBody,
+      mediaType: 'application/json',
+      errors: {
+        400: `Validation error.`
+      }
+    });
+  }
+  /**
+   * Delete a score
+   * Delete a score.
+   * @returns void
+   * @throws ApiError
+   */
+  static aiMentorOrgsUsersEvaluationsScoresDestroy({
+    org,
+    scoreId,
+    userId
+  }) {
+    return request(OpenAPI, {
+      method: 'DELETE',
+      url: '/api/ai-mentor/orgs/{org}/users/{user_id}/evaluations/scores/{score_id}/',
+      path: {
+        'org': org,
+        'score_id': scoreId,
+        'user_id': userId
+      },
+      errors: {
+        404: `Not found within the tenant.`
+      }
+    });
+  }
+}
+
 class FeaturesService {
   /**
    * Returns a list of the apps that the user has access to.
@@ -48097,6 +48368,7 @@ exports.CoreService = CoreService;
 exports.CredentialsService = CredentialsService;
 exports.CreditsService = CreditsService;
 exports.CustomDomainsService = CustomDomainsService;
+exports.EvaluationsService = EvaluationsService;
 exports.FeaturesService = FeaturesService;
 exports.ItemsService = ItemsService;
 exports.MediaService = MediaService;