eval-studio-client 1.2.4a2__py3-none-any.whl → 1.3.0__py3-none-any.whl

eval_studio_client/gen/openapiv2/eval_studio.swagger.json

@@ -8,9 +8,15 @@
     {
       "name": "AdversarialInputsService"
     },
+    {
+      "name": "DashboardReportService"
+    },
     {
       "name": "DashboardService"
     },
+    {
+      "name": "DashboardTestCaseAnnotationService"
+    },
     {
       "name": "DocumentService"
     },
@@ -32,6 +38,9 @@
     {
       "name": "LeaderboardService"
     },
+    {
+      "name": "LeaderboardTestCaseAnnotationService"
+    },
     {
       "name": "ModelService"
     },
@@ -566,7 +575,7 @@
           },
           {
             "name": "model.type",
-            "description": "Immutable. Type of this Model.\n\n - MODEL_TYPE_UNSPECIFIED: Unspecified type.\n - MODEL_TYPE_H2OGPTE_RAG: h2oGPTe RAG.\n - MODEL_TYPE_OPENAI_RAG: OpenAI Assistant RAG.\n - MODEL_TYPE_H2OGPTE_LLM: h2oGPTe LLM.\n - MODEL_TYPE_H2OGPT_LLM: h2oGPT LLM.\n - MODEL_TYPE_OPENAI_CHAT: OpenAI chat.\n - MODEL_TYPE_AZURE_OPENAI_CHAT: Microsoft Azure hosted OpenAI Chat.\n - MODEL_TYPE_OPENAI_API_CHAT: OpenAI API chat.\n - MODEL_TYPE_H2OLLMOPS: H2O LLMOps.\n - MODEL_TYPE_OLLAMA: Ollama.\n - MODEL_TYPE_AMAZON_BEDROCK: Amazon Bedrock.",
+            "description": "Immutable. Type of this Model.\n\n - MODEL_TYPE_UNSPECIFIED: Unspecified type.\n - MODEL_TYPE_H2OGPTE_RAG: h2oGPTe RAG.\n - MODEL_TYPE_OPENAI_RAG: OpenAI Assistant RAG.\n - MODEL_TYPE_H2OGPTE_LLM: h2oGPTe LLM.\n - MODEL_TYPE_H2OGPT_LLM: h2oGPT LLM.\n - MODEL_TYPE_OPENAI_CHAT: OpenAI chat.\n - MODEL_TYPE_AZURE_OPENAI_CHAT: Microsoft Azure hosted OpenAI Chat.\n - MODEL_TYPE_OPENAI_API_CHAT: OpenAI API chat.\n - MODEL_TYPE_H2OLLMOPS: H2O LLMOps.\n - MODEL_TYPE_OLLAMA: Ollama.\n - MODEL_TYPE_AMAZON_BEDROCK: Amazon Bedrock.\n - MODEL_TYPE_ANTHROPIC_CLAUDE: Anthropic Claude chat.",
             "in": "query",
             "required": false,
             "type": "string",
@@ -581,7 +590,8 @@
               "MODEL_TYPE_OPENAI_API_CHAT",
               "MODEL_TYPE_H2OLLMOPS",
               "MODEL_TYPE_OLLAMA",
-              "MODEL_TYPE_AMAZON_BEDROCK"
+              "MODEL_TYPE_AMAZON_BEDROCK",
+              "MODEL_TYPE_ANTHROPIC_CLAUDE"
             ],
             "default": "MODEL_TYPE_UNSPECIFIED"
           },
@@ -713,7 +723,7 @@
           },
           {
             "name": "model.type",
-            "description": "Immutable. Type of this Model.\n\n - MODEL_TYPE_UNSPECIFIED: Unspecified type.\n - MODEL_TYPE_H2OGPTE_RAG: h2oGPTe RAG.\n - MODEL_TYPE_OPENAI_RAG: OpenAI Assistant RAG.\n - MODEL_TYPE_H2OGPTE_LLM: h2oGPTe LLM.\n - MODEL_TYPE_H2OGPT_LLM: h2oGPT LLM.\n - MODEL_TYPE_OPENAI_CHAT: OpenAI chat.\n - MODEL_TYPE_AZURE_OPENAI_CHAT: Microsoft Azure hosted OpenAI Chat.\n - MODEL_TYPE_OPENAI_API_CHAT: OpenAI API chat.\n - MODEL_TYPE_H2OLLMOPS: H2O LLMOps.\n - MODEL_TYPE_OLLAMA: Ollama.\n - MODEL_TYPE_AMAZON_BEDROCK: Amazon Bedrock.",
+            "description": "Immutable. Type of this Model.\n\n - MODEL_TYPE_UNSPECIFIED: Unspecified type.\n - MODEL_TYPE_H2OGPTE_RAG: h2oGPTe RAG.\n - MODEL_TYPE_OPENAI_RAG: OpenAI Assistant RAG.\n - MODEL_TYPE_H2OGPTE_LLM: h2oGPTe LLM.\n - MODEL_TYPE_H2OGPT_LLM: h2oGPT LLM.\n - MODEL_TYPE_OPENAI_CHAT: OpenAI chat.\n - MODEL_TYPE_AZURE_OPENAI_CHAT: Microsoft Azure hosted OpenAI Chat.\n - MODEL_TYPE_OPENAI_API_CHAT: OpenAI API chat.\n - MODEL_TYPE_H2OLLMOPS: H2O LLMOps.\n - MODEL_TYPE_OLLAMA: Ollama.\n - MODEL_TYPE_AMAZON_BEDROCK: Amazon Bedrock.\n - MODEL_TYPE_ANTHROPIC_CLAUDE: Anthropic Claude chat.",
             "in": "query",
             "required": false,
             "type": "string",
@@ -728,7 +738,8 @@
               "MODEL_TYPE_OPENAI_API_CHAT",
               "MODEL_TYPE_H2OLLMOPS",
               "MODEL_TYPE_OLLAMA",
-              "MODEL_TYPE_AMAZON_BEDROCK"
+              "MODEL_TYPE_AMAZON_BEDROCK",
+              "MODEL_TYPE_ANTHROPIC_CLAUDE"
             ],
             "default": "MODEL_TYPE_UNSPECIFIED"
           },
@@ -874,6 +885,38 @@
         ]
       }
     },
+    "/v1/leaderboardReports:compare": {
+      "post": {
+        "operationId": "LeaderboardReportService_CmpLeaderboardReports",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1CmpLeaderboardReportsResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "body",
+            "in": "body",
+            "required": true,
+            "schema": {
+              "$ref": "#/definitions/v1CmpLeaderboardReportsRequest"
+            }
+          }
+        ],
+        "tags": [
+          "LeaderboardReportService"
+        ]
+      }
+    },
     "/v1/leaderboards": {
       "get": {
         "operationId": "LeaderboardService_ListLeaderboards",
@@ -1004,6 +1047,38 @@
         ]
       }
     },
+    "/v1/leaderboards:batchCreateWithoutCache": {
+      "post": {
+        "operationId": "LeaderboardService_BatchCreateLeaderboardsWithoutCache",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1BatchCreateLeaderboardsWithoutCacheResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "body",
+            "in": "body",
+            "required": true,
+            "schema": {
+              "$ref": "#/definitions/v1BatchCreateLeaderboardsWithoutCacheRequest"
+            }
+          }
+        ],
+        "tags": [
+          "LeaderboardService"
+        ]
+      }
+    },
     "/v1/leaderboards:batchDelete": {
       "post": {
         "operationId": "LeaderboardService_BatchDeleteLeaderboards",
@@ -1117,6 +1192,38 @@
         ]
       }
     },
+    "/v1/leaderboards:deepCompare": {
+      "post": {
+        "operationId": "LeaderboardService_DeepCompareLeaderboards",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1DeepCompareLeaderboardsResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "body",
+            "in": "body",
+            "required": true,
+            "schema": {
+              "$ref": "#/definitions/v1DeepCompareLeaderboardsRequest"
+            }
+          }
+        ],
+        "tags": [
+          "LeaderboardService"
+        ]
+      }
+    },
     "/v1/leaderboards:import": {
       "post": {
         "operationId": "LeaderboardService_ImportLeaderboard",
@@ -1506,6 +1613,16 @@
             }
           }
         },
+        "parameters": [
+          {
+            "name": "pageSize",
+            "description": "The maximum number of Operations to return. The service may return fewer than this value, even\nif more are available. If unspecified, the default page size is unlimited.",
+            "in": "query",
+            "required": false,
+            "type": "integer",
+            "format": "int32"
+          }
+        ],
         "tags": [
           "OperationService"
         ]
@@ -1546,6 +1663,86 @@
         ]
       }
     },
+    "/v1/operations:batchMarkSeenByCreator": {
+      "post": {
+        "operationId": "OperationService_BatchMarkOperationSeenByCreator",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1BatchMarkOperationSeenByCreatorResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "names",
+            "description": "Required. The names of the Operations to mark as seen. A maximum of 1000 can be specified.",
+            "in": "query",
+            "required": false,
+            "type": "array",
+            "items": {
+              "type": "string"
+            },
+            "collectionFormat": "multi"
+          }
+        ],
+        "tags": [
+          "OperationService"
+        ]
+      }
+    },
+    "/v1/operations:unseen": {
+      "get": {
+        "operationId": "OperationService_ListUnseenOperations",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1ListUnseenOperationsResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "pageSize",
+            "description": "The maximum number of Operations to return. The service may return fewer than this value, even\nif more are available. If unspecified, the default page size is unlimited.",
+            "in": "query",
+            "required": false,
+            "type": "integer",
+            "format": "int32"
+          },
+          {
+            "name": "view",
+            "description": "The level of detail for each Operation in the response. Defaults to OPERATION_VIEW_FULL.\n\n - OPERATION_VIEW_UNSPECIFIED: Default / unset value. The API will default to the OPERATION_VIEW_FULL.\n - OPERATION_VIEW_BASIC: Include basic metadata about the Operation, but not the response.\n - OPERATION_VIEW_FULL: Include everything.",
+            "in": "query",
+            "required": false,
+            "type": "string",
+            "enum": [
+              "OPERATION_VIEW_UNSPECIFIED",
+              "OPERATION_VIEW_BASIC",
+              "OPERATION_VIEW_FULL"
+            ],
+            "default": "OPERATION_VIEW_UNSPECIFIED"
+          }
+        ],
+        "tags": [
+          "OperationService"
+        ]
+      }
+    },
     "/v1/perturbators": {
       "get": {
         "operationId": "PerturbatorService_ListPerturbators",
@@ -1646,7 +1843,7 @@
           },
           {
             "name": "defaultH2ogpteModel.type",
-            "description": "Immutable. Type of this Model.\n\n - MODEL_TYPE_UNSPECIFIED: Unspecified type.\n - MODEL_TYPE_H2OGPTE_RAG: h2oGPTe RAG.\n - MODEL_TYPE_OPENAI_RAG: OpenAI Assistant RAG.\n - MODEL_TYPE_H2OGPTE_LLM: h2oGPTe LLM.\n - MODEL_TYPE_H2OGPT_LLM: h2oGPT LLM.\n - MODEL_TYPE_OPENAI_CHAT: OpenAI chat.\n - MODEL_TYPE_AZURE_OPENAI_CHAT: Microsoft Azure hosted OpenAI Chat.\n - MODEL_TYPE_OPENAI_API_CHAT: OpenAI API chat.\n - MODEL_TYPE_H2OLLMOPS: H2O LLMOps.\n - MODEL_TYPE_OLLAMA: Ollama.\n - MODEL_TYPE_AMAZON_BEDROCK: Amazon Bedrock.",
+            "description": "Immutable. Type of this Model.\n\n - MODEL_TYPE_UNSPECIFIED: Unspecified type.\n - MODEL_TYPE_H2OGPTE_RAG: h2oGPTe RAG.\n - MODEL_TYPE_OPENAI_RAG: OpenAI Assistant RAG.\n - MODEL_TYPE_H2OGPTE_LLM: h2oGPTe LLM.\n - MODEL_TYPE_H2OGPT_LLM: h2oGPT LLM.\n - MODEL_TYPE_OPENAI_CHAT: OpenAI chat.\n - MODEL_TYPE_AZURE_OPENAI_CHAT: Microsoft Azure hosted OpenAI Chat.\n - MODEL_TYPE_OPENAI_API_CHAT: OpenAI API chat.\n - MODEL_TYPE_H2OLLMOPS: H2O LLMOps.\n - MODEL_TYPE_OLLAMA: Ollama.\n - MODEL_TYPE_AMAZON_BEDROCK: Amazon Bedrock.\n - MODEL_TYPE_ANTHROPIC_CLAUDE: Anthropic Claude chat.",
             "in": "query",
             "required": false,
             "type": "string",
@@ -1661,7 +1858,8 @@
               "MODEL_TYPE_OPENAI_API_CHAT",
               "MODEL_TYPE_H2OLLMOPS",
               "MODEL_TYPE_OLLAMA",
-              "MODEL_TYPE_AMAZON_BEDROCK"
+              "MODEL_TYPE_AMAZON_BEDROCK",
+              "MODEL_TYPE_ANTHROPIC_CLAUDE"
             ],
             "default": "MODEL_TYPE_UNSPECIFIED"
           },
@@ -2151,6 +2349,38 @@
         ]
       }
     },
+    "/v1/tests:createTestFromTestCases": {
+      "post": {
+        "operationId": "TestService_CreateTestFromTestCases",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1CreateTestFromTestCasesResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "body",
+            "in": "body",
+            "required": true,
+            "schema": {
+              "$ref": "#/definitions/v1CreateTestFromTestCasesRequest"
+            }
+          }
+        ],
+        "tags": [
+          "TestService"
+        ]
+      }
+    },
     "/v1/tests:mostRecent": {
       "get": {
         "operationId": "TestService_ListMostRecentTests",
@@ -2575,14 +2805,14 @@
         ]
       }
     },
-    "/v1/{document.name}": {
-      "patch": {
-        "operationId": "DocumentService_UpdateDocument",
+    "/v1/{dashboardTestCaseAnnotation.name}": {
+      "post": {
+        "operationId": "DashboardTestCaseAnnotationService_UpdateDashboardTestCaseAnnotation",
         "responses": {
           "200": {
             "description": "A successful response.",
             "schema": {
-              "$ref": "#/definitions/v1UpdateDocumentResponse"
+              "$ref": "#/definitions/v1UpdateDashboardTestCaseAnnotationResponse"
             }
           },
           "default": {
@@ -2594,16 +2824,16 @@
         },
         "parameters": [
           {
-            "name": "document.name",
-            "description": "Output only. Name of the Document resource. e.g.: \"documents/\u003cUUID\u003e\"",
+            "name": "dashboardTestCaseAnnotation.name",
+            "description": "Output only. Name of the DashboardTestCaseAnnotation resource. e.g.: \"dashboards/\u003cUUID\u003e/testCases/\u003cUUID\u003e/annotations/\u003cUUID\u003e\"",
             "in": "path",
             "required": true,
             "type": "string",
-            "pattern": "documents/[^/]+"
+            "pattern": "dashboards/[^/]+/testCases/[^/]+/annotations/[^/]+"
           },
           {
-            "name": "document",
-            "description": "Required. The Document to update.\n\nThe Document's name field is used to identify the Document to be updated. Format:\ndocuments/{document}",
+            "name": "dashboardTestCaseAnnotation",
+            "description": "Required. The DashboardTestCaseAnnotation to update.",
             "in": "body",
             "required": true,
             "schema": {
@@ -2612,67 +2842,68 @@
                 "createTime": {
                   "type": "string",
                   "format": "date-time",
-                  "description": "Output only. Timestamp when the Document was created.",
+                  "description": "Output only. Timestamp when the DashboardTestCaseAnnotation was created.",
                   "readOnly": true
                 },
                 "creator": {
                   "type": "string",
-                  "description": "Output only. Name of the user or service that requested creation of the Document.",
+                  "description": "Output only. Name of the user or service that requested creation of the DashboardTestCaseAnnotation.",
                   "readOnly": true
                 },
                 "updateTime": {
                   "type": "string",
                   "format": "date-time",
-                  "description": "Output only. Optional. Timestamp when the Document was last updated.",
+                  "description": "Output only. Optional. Timestamp when the DashboardTestCaseAnnotation was last updated.",
                   "readOnly": true
                 },
                 "updater": {
                   "type": "string",
-                  "description": "Output only. Optional. Name of the user or service that requested update of the Document.",
-                  "readOnly": true
-                },
-                "deleteTime": {
-                  "type": "string",
-                  "format": "date-time",
-                  "description": "Output only. Optional. Set when the Document is deleted. When set Document should be considered\nas deleted.",
-                  "readOnly": true
-                },
-                "deleter": {
-                  "type": "string",
-                  "description": "Output only. Optional. Name of the user or service that requested deletion of the Document.",
+                  "description": "Output only. Optional. Name of the user or service that requested update of the DashboardTestCaseAnnotation.",
                   "readOnly": true
                 },
-                "displayName": {
+                "parent": {
                   "type": "string",
-                  "description": "Human readable name of the Document."
+                  "description": "Parent Dashboard Test Case resource name. e.g.: \"dashboards/\u003cUUID\u003e/testCases/\u003cUUID\u003e\"."
                 },
-                "description": {
+                "key": {
                   "type": "string",
-                  "description": "Optional. Arbitrary description of the Document."
+                  "description": "Immutable. Annotation key."
                 },
-                "url": {
-                  "type": "string",
-                  "description": "Required. Immutable. Absolute URL where the document can be downloaded. The format\n'//eval-studio/documents/\u003cUUID\u003e' is used for documents uploaded to Eval Studio. It is the\nresponsibility of the client to convert this to a valid URL before downloading."
+                "value": {
+                  "description": "Annotation value."
                 }
               },
-              "description": "The Document's name field is used to identify the Document to be updated. Format:\ndocuments/{document}",
-              "title": "Required. The Document to update."
+              "title": "Required. The DashboardTestCaseAnnotation to update."
             }
+          },
+          {
+            "name": "updateMask",
+            "description": "Optional. The list of fields to update. If empty, all modifiable fields will be updated. The\nfollowing fields can be updated:\n\n- value",
+            "in": "query",
+            "required": false,
+            "type": "string"
+          },
+          {
+            "name": "allowMissing",
+            "description": "Optional. If true, the request is allowed to create a new DashboardTestCaseAnnotation if it\nis not found.",
+            "in": "query",
+            "required": false,
+            "type": "boolean"
           }
         ],
         "tags": [
-          "DocumentService"
+          "DashboardTestCaseAnnotationService"
         ]
       }
     },
-    "/v1/{leaderboard.name}": {
+    "/v1/{document.name}": {
       "patch": {
-        "operationId": "LeaderboardService_UpdateLeaderboard",
+        "operationId": "DocumentService_UpdateDocument",
         "responses": {
           "200": {
             "description": "A successful response.",
             "schema": {
-              "$ref": "#/definitions/v1UpdateLeaderboardResponse"
+              "$ref": "#/definitions/v1UpdateDocumentResponse"
             }
           },
           "default": {
@@ -2684,16 +2915,106 @@
         },
         "parameters": [
           {
-            "name": "leaderboard.name",
-            "description": "Output only. Name of the Leaderboard resource. e.g.: \"leaderboards/\u003cUUID\u003e\"",
+            "name": "document.name",
+            "description": "Output only. Name of the Document resource. e.g.: \"documents/\u003cUUID\u003e\"",
             "in": "path",
             "required": true,
             "type": "string",
-            "pattern": "leaderboards/[^/]+"
+            "pattern": "documents/[^/]+"
           },
           {
-            "name": "leaderboard",
-            "description": "Required. The Leaderboard to update.\n\nThe Leaderboard's `name` field is used to identify the Leaderboard to update.\nFormat: leaderboards/{leaderboard}",
+            "name": "document",
+            "description": "Required. The Document to update.\n\nThe Document's name field is used to identify the Document to be updated. Format:\ndocuments/{document}",
+            "in": "body",
+            "required": true,
+            "schema": {
+              "type": "object",
+              "properties": {
+                "createTime": {
+                  "type": "string",
+                  "format": "date-time",
+                  "description": "Output only. Timestamp when the Document was created.",
+                  "readOnly": true
+                },
+                "creator": {
+                  "type": "string",
+                  "description": "Output only. Name of the user or service that requested creation of the Document.",
+                  "readOnly": true
+                },
+                "updateTime": {
+                  "type": "string",
+                  "format": "date-time",
+                  "description": "Output only. Optional. Timestamp when the Document was last updated.",
+                  "readOnly": true
+                },
+                "updater": {
+                  "type": "string",
+                  "description": "Output only. Optional. Name of the user or service that requested update of the Document.",
+                  "readOnly": true
+                },
+                "deleteTime": {
+                  "type": "string",
+                  "format": "date-time",
+                  "description": "Output only. Optional. Set when the Document is deleted. When set Document should be considered\nas deleted.",
+                  "readOnly": true
+                },
+                "deleter": {
+                  "type": "string",
+                  "description": "Output only. Optional. Name of the user or service that requested deletion of the Document.",
+                  "readOnly": true
+                },
+                "displayName": {
+                  "type": "string",
+                  "description": "Human readable name of the Document."
+                },
+                "description": {
+                  "type": "string",
+                  "description": "Optional. Arbitrary description of the Document."
+                },
+                "url": {
+                  "type": "string",
+                  "description": "Required. Immutable. Absolute URL where the document can be downloaded. The format\n'//eval-studio/documents/\u003cUUID\u003e' is used for documents uploaded to Eval Studio. It is the\nresponsibility of the client to convert this to a valid URL before downloading."
+                }
+              },
+              "description": "The Document's name field is used to identify the Document to be updated. Format:\ndocuments/{document}",
+              "title": "Required. The Document to update."
+            }
+          }
+        ],
+        "tags": [
+          "DocumentService"
+        ]
+      }
+    },
+    "/v1/{leaderboard.name}": {
+      "patch": {
+        "operationId": "LeaderboardService_UpdateLeaderboard",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1UpdateLeaderboardResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "leaderboard.name",
+            "description": "Output only. Name of the Leaderboard resource. e.g.: \"leaderboards/\u003cUUID\u003e\"",
+            "in": "path",
+            "required": true,
+            "type": "string",
+            "pattern": "leaderboards/[^/]+"
+          },
+          {
+            "name": "leaderboard",
+            "description": "Required. The Leaderboard to update.\n\nThe Leaderboard's `name` field is used to identify the Leaderboard to update.\nFormat: leaderboards/{leaderboard}",
             "in": "body",
             "required": true,
             "schema": {
@@ -2828,6 +3149,10 @@
                 "testLab": {
                   "type": "string",
                   "description": "Optional. Resource name of the TestLab if Leaderboard was created from a imported TestLab."
+                },
+                "evaluationType": {
+                  "$ref": "#/definitions/v1EvaluationType",
+                  "description": "Optional. Type of the evaluation. If not specified, defaults to type of the Model used, or LLM if unspecified."
                 }
               },
               "description": "The Leaderboard's `name` field is used to identify the Leaderboard to update.\nFormat: leaderboards/{leaderboard}",
@@ -2840,6 +3165,97 @@
         ]
       }
     },
+    "/v1/{leaderboardTestCaseAnnotation.name}": {
+      "post": {
+        "operationId": "LeaderboardTestCaseAnnotationService_UpdateLeaderboardTestCaseAnnotation",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1UpdateLeaderboardTestCaseAnnotationResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "leaderboardTestCaseAnnotation.name",
+            "description": "Output only. Name of the LeaderboardTestCaseAnnotation resource. e.g.: \"leaderboards/\u003cUUID\u003e/testCases/\u003cUUID\u003e/annotations/\u003cUUID\u003e\"",
+            "in": "path",
+            "required": true,
+            "type": "string",
+            "pattern": "leaderboards/[^/]+/testCases/[^/]+/annotations/[^/]+"
+          },
+          {
+            "name": "leaderboardTestCaseAnnotation",
+            "description": "Required. The LeaderboardTestCaseAnnotation to update.",
+            "in": "body",
+            "required": true,
+            "schema": {
+              "type": "object",
+              "properties": {
+                "createTime": {
+                  "type": "string",
+                  "format": "date-time",
+                  "description": "Output only. Timestamp when the LeaderboardTestCaseAnnotation was created.",
+                  "readOnly": true
+                },
+                "creator": {
+                  "type": "string",
+                  "description": "Output only. Name of the user or service that requested creation of the LeaderboardTestCaseAnnotation.",
+                  "readOnly": true
+                },
+                "updateTime": {
+                  "type": "string",
+                  "format": "date-time",
+                  "description": "Output only. Optional. Timestamp when the LeaderboardTestCaseAnnotation was last updated.",
+                  "readOnly": true
+                },
+                "updater": {
+                  "type": "string",
+                  "description": "Output only. Optional. Name of the user or service that requested update of the LeaderboardTestCaseAnnotation.",
+                  "readOnly": true
+                },
+                "parent": {
+                  "type": "string",
+                  "description": "Parent Leaderboard Test Case resource name. e.g.: \"leaderboards/\u003cUUID\u003e/testCases/\u003cUUID\u003e\"."
+                },
+                "key": {
+                  "type": "string",
+                  "description": "Immutable. Annotation key."
+                },
+                "value": {
+                  "description": "Annotation value."
+                }
+              },
+              "title": "Required. The LeaderboardTestCaseAnnotation to update."
+            }
+          },
+          {
+            "name": "updateMask",
+            "description": "Optional. The list of fields to update. If empty, all modifiable fields will be updated. The\nfollowing fields can be updated:\n\n- value",
+            "in": "query",
+            "required": false,
+            "type": "string"
+          },
+          {
+            "name": "allowMissing",
+            "description": "Optional. If true, the request is allowed to create a new LeaderboardTestCaseAnnotation if it\nis not found.",
+            "in": "query",
+            "required": false,
+            "type": "boolean"
+          }
+        ],
+        "tags": [
+          "LeaderboardTestCaseAnnotationService"
+        ]
+      }
+    },
     "/v1/{model.name}": {
       "patch": {
         "operationId": "ModelService_UpdateModel",
@@ -2947,6 +3363,38 @@
       }
     },
     "/v1/{name_10}": {
+      "get": {
+        "operationId": "TestClassService_GetTestClass",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1GetTestClassResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "name_10",
+            "description": "The name of the TestClass to retrieve.\nFormat: testClasses/\u003cUUID\u003e",
+            "in": "path",
+            "required": true,
+            "type": "string",
+            "pattern": "testClasses/[^/]+"
+          }
+        ],
+        "tags": [
+          "TestClassService"
+        ]
+      }
+    },
+    "/v1/{name_11}": {
       "get": {
         "operationId": "TestService_GetTest",
         "responses": {
@@ -2965,7 +3413,7 @@
         },
         "parameters": [
           {
-            "name": "name_10",
+            "name": "name_11",
             "description": "Required. The name of the Test to retrieve.",
             "in": "path",
             "required": true,
@@ -2978,7 +3426,7 @@
         ]
       }
     },
-    "/v1/{name_11}": {
+    "/v1/{name_12}": {
       "get": {
         "summary": "GetWorkflowNode retrieves a WorkflowNode by name. Deleted WorkflowNode is returned without\nerror, it has a delete_time and deleter fields set.",
         "operationId": "WorkflowNodeService_GetWorkflowNode",
@@ -2998,7 +3446,7 @@
         },
         "parameters": [
           {
-            "name": "name_11",
+            "name": "name_12",
             "description": "Required. The name of the WorkflowNode to retrieve.",
             "in": "path",
             "required": true,
@@ -3024,7 +3472,7 @@
         ]
       }
     },
-    "/v1/{name_12}": {
+    "/v1/{name_13}": {
       "get": {
         "summary": "GetWorkflow retrieves a Workflow by name. Deleted Workflow is returned without error, it has a\ndelete_time and deleter fields set.",
         "operationId": "WorkflowService_GetWorkflow",
@@ -3044,7 +3492,7 @@
         },
         "parameters": [
           {
-            "name": "name_12",
+            "name": "name_13",
             "description": "Required. The name of the Workflow to retrieve.",
             "in": "path",
             "required": true,
@@ -3059,12 +3507,12 @@
     },
     "/v1/{name_1}": {
       "get": {
-        "operationId": "DocumentService_GetDocument",
+        "operationId": "DashboardService_GetDashboard",
         "responses": {
           "200": {
             "description": "A successful response.",
             "schema": {
-              "$ref": "#/definitions/v1GetDocumentResponse"
+              "$ref": "#/definitions/v1GetDashboardResponse"
             }
           },
           "default": {
@@ -3077,15 +3525,15 @@
         "parameters": [
           {
             "name": "name_1",
-            "description": "Required. The name of the Document to retrieve.",
+            "description": "Required. The name of the Dashboard to retrieve.",
             "in": "path",
             "required": true,
             "type": "string",
-            "pattern": "documents/[^/]+"
+            "pattern": "dashboards/[^/]+"
           }
         ],
         "tags": [
-          "DocumentService"
+          "DashboardService"
         ]
       },
       "delete": {
@@ -3316,12 +3764,12 @@
     },
     "/v1/{name_2}": {
       "get": {
-        "operationId": "EvaluatorService_GetEvaluator",
+        "operationId": "DocumentService_GetDocument",
         "responses": {
           "200": {
             "description": "A successful response.",
             "schema": {
-              "$ref": "#/definitions/v1GetEvaluatorResponse"
+              "$ref": "#/definitions/v1GetDocumentResponse"
             }
           },
           "default": {
@@ -3334,15 +3782,15 @@
         "parameters": [
           {
             "name": "name_2",
-            "description": "Required. The name of the Evaluator to retrieve.",
+            "description": "Required. The name of the Document to retrieve.",
             "in": "path",
             "required": true,
             "type": "string",
-            "pattern": "evaluators/[^/]+"
+            "pattern": "documents/[^/]+"
           }
         ],
         "tags": [
-          "EvaluatorService"
+          "DocumentService"
         ]
       },
       "delete": {
@@ -3513,12 +3961,12 @@
     },
     "/v1/{name_3}": {
       "get": {
-        "operationId": "LeaderboardReportService_GetLeaderboardReport",
+        "operationId": "EvaluatorService_GetEvaluator",
         "responses": {
           "200": {
             "description": "A successful response.",
             "schema": {
-              "$ref": "#/definitions/v1GetLeaderboardReportResponse"
+              "$ref": "#/definitions/v1GetEvaluatorResponse"
             }
           },
           "default": {
@@ -3531,15 +3979,15 @@
         "parameters": [
           {
             "name": "name_3",
-            "description": "Required. The name of the Leaderboard to retrieve.",
+            "description": "Required. The name of the Evaluator to retrieve.",
             "in": "path",
             "required": true,
             "type": "string",
-            "pattern": "leaderboardReports/[^/]+"
+            "pattern": "evaluators/[^/]+"
           }
         ],
         "tags": [
-          "LeaderboardReportService"
+          "EvaluatorService"
         ]
       },
       "delete": {
@@ -3575,12 +4023,12 @@
     },
     "/v1/{name_4}": {
       "get": {
-        "operationId": "LeaderboardService_GetLeaderboard",
+        "operationId": "LeaderboardReportService_GetLeaderboardReport",
         "responses": {
           "200": {
             "description": "A successful response.",
             "schema": {
-              "$ref": "#/definitions/v1GetLeaderboardResponse"
+              "$ref": "#/definitions/v1GetLeaderboardReportResponse"
             }
           },
           "default": {
@@ -3597,11 +4045,24 @@
             "in": "path",
             "required": true,
             "type": "string",
-            "pattern": "leaderboards/[^/]+"
+            "pattern": "leaderboardReports/[^/]+"
+          },
+          {
+            "name": "view",
+            "description": "Optional. The view of the leaderboard report results to return. Defaults to\nLEADERBOARD_REPORT_RESULT_VIEW_FULL.\n\n - LEADERBOARD_REPORT_RESULT_VIEW_UNSPECIFIED: Default value. The basic view with essential fields.\n - LEADERBOARD_REPORT_RESULT_VIEW_FULL: Full view with all fields populated.\n - LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY: Summary view with only key fields.",
+            "in": "query",
+            "required": false,
+            "type": "string",
+            "enum": [
+              "LEADERBOARD_REPORT_RESULT_VIEW_UNSPECIFIED",
+              "LEADERBOARD_REPORT_RESULT_VIEW_FULL",
+              "LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY"
+            ],
+            "default": "LEADERBOARD_REPORT_RESULT_VIEW_UNSPECIFIED"
           }
         ],
         "tags": [
-          "LeaderboardService"
+          "LeaderboardReportService"
         ]
       },
       "delete": {
@@ -3637,12 +4098,12 @@
     },
     "/v1/{name_5}": {
       "get": {
-        "operationId": "ModelService_GetModel",
+        "operationId": "LeaderboardService_GetLeaderboard",
         "responses": {
           "200": {
             "description": "A successful response.",
             "schema": {
-              "$ref": "#/definitions/v1GetModelResponse"
+              "$ref": "#/definitions/v1GetLeaderboardResponse"
             }
           },
           "default": {
@@ -3655,15 +4116,15 @@
         "parameters": [
           {
             "name": "name_5",
-            "description": "Required. The name of the Model to retrieve.",
+            "description": "Required. The name of the Leaderboard to retrieve.",
             "in": "path",
             "required": true,
             "type": "string",
-            "pattern": "models/[^/]+"
+            "pattern": "leaderboards/[^/]+"
           }
         ],
         "tags": [
-          "ModelService"
+          "LeaderboardService"
         ]
       },
       "delete": {
@@ -3699,12 +4160,12 @@
     },
     "/v1/{name_6}": {
       "get": {
-        "operationId": "OperationService_GetOperation",
+        "operationId": "ModelService_GetModel",
         "responses": {
           "200": {
             "description": "A successful response.",
             "schema": {
-              "$ref": "#/definitions/v1GetOperationResponse"
+              "$ref": "#/definitions/v1GetModelResponse"
             }
           },
           "default": {
@@ -3717,15 +4178,15 @@
         "parameters": [
           {
             "name": "name_6",
-            "description": "Required. The name of the Operation to retrieve.",
+            "description": "Required. The name of the Model to retrieve.",
             "in": "path",
             "required": true,
             "type": "string",
-            "pattern": "operations/[^/]+"
+            "pattern": "models/[^/]+"
           }
         ],
         "tags": [
-          "OperationService"
+          "ModelService"
         ]
       },
       "delete": {
@@ -3768,12 +4229,12 @@
     },
     "/v1/{name_7}": {
       "get": {
-        "operationId": "PerturbatorService_GetPerturbator",
+        "operationId": "OperationService_GetOperation",
         "responses": {
           "200": {
             "description": "A successful response.",
             "schema": {
-              "$ref": "#/definitions/v1GetPerturbatorResponse"
+              "$ref": "#/definitions/v1GetOperationResponse"
             }
           },
           "default": {
@@ -3786,15 +4247,15 @@
         "parameters": [
           {
             "name": "name_7",
-            "description": "Required. The name of the Perturbator to retrieve.",
+            "description": "Required. The name of the Operation to retrieve.",
             "in": "path",
             "required": true,
             "type": "string",
-            "pattern": "perturbators/[^/]+"
+            "pattern": "operations/[^/]+"
           }
         ],
         "tags": [
-          "PerturbatorService"
+          "OperationService"
         ]
       },
       "delete": {
@@ -3831,12 +4292,12 @@
     },
     "/v1/{name_8}": {
       "get": {
-        "operationId": "TestCaseService_GetTestCase",
+        "operationId": "PerturbatorService_GetPerturbator",
         "responses": {
           "200": {
             "description": "A successful response.",
             "schema": {
-              "$ref": "#/definitions/v1GetTestCaseResponse"
+              "$ref": "#/definitions/v1GetPerturbatorResponse"
             }
           },
           "default": {
@@ -3849,15 +4310,15 @@
         "parameters": [
           {
             "name": "name_8",
-            "description": "The name of the TestCase to retrieve.\nFormat: tests/\u003cUUID\u003e/testCases/\u003cUUID\u003e",
+            "description": "Required. The name of the Perturbator to retrieve.",
             "in": "path",
             "required": true,
             "type": "string",
-            "pattern": "tests/[^/]+/testCases/[^/]+"
+            "pattern": "perturbators/[^/]+"
           }
         ],
         "tags": [
-          "TestCaseService"
+          "PerturbatorService"
         ]
       },
       "delete": {
@@ -3895,12 +4356,12 @@
     },
     "/v1/{name_9}": {
       "get": {
-        "operationId": "TestClassService_GetTestClass",
+        "operationId": "TestCaseService_GetTestCase",
         "responses": {
           "200": {
             "description": "A successful response.",
             "schema": {
-              "$ref": "#/definitions/v1GetTestClassResponse"
+              "$ref": "#/definitions/v1GetTestCaseResponse"
             }
           },
           "default": {
@@ -3913,15 +4374,15 @@
         "parameters": [
           {
             "name": "name_9",
-            "description": "The name of the TestClass to retrieve.\nFormat: testClasses/\u003cUUID\u003e",
+            "description": "The name of the TestCase to retrieve.\nFormat: tests/\u003cUUID\u003e/testCases/\u003cUUID\u003e",
             "in": "path",
             "required": true,
             "type": "string",
-            "pattern": "testClasses/[^/]+"
+            "pattern": "tests/[^/]+/testCases/[^/]+"
           }
         ],
         "tags": [
-          "TestClassService"
+          "TestCaseService"
         ]
       },
       "delete": {
@@ -3958,12 +4419,12 @@
     },
     "/v1/{name}": {
       "get": {
-        "operationId": "DashboardService_GetDashboard",
+        "operationId": "DashboardReportService_GetDashboardReport",
         "responses": {
           "200": {
             "description": "A successful response.",
             "schema": {
-              "$ref": "#/definitions/v1GetDashboardResponse"
+              "$ref": "#/definitions/v1GetDashboardReportResponse"
             }
           },
           "default": {
@@ -3980,11 +4441,11 @@
             "in": "path",
             "required": true,
             "type": "string",
-            "pattern": "dashboards/[^/]+"
+            "pattern": "dashboardReports/[^/]+"
           }
         ],
         "tags": [
-          "DashboardService"
+          "DashboardReportService"
         ]
       },
       "delete": {
@@ -4735,6 +5196,38 @@
         ]
       }
     },
+    "/v1/{name}:markSeenByCreator": {
+      "post": {
+        "operationId": "OperationService_MarkOperationSeenByCreator",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1MarkOperationSeenByCreatorResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "name",
+            "description": "Required. The name of the Operation to mark as seen.",
+            "in": "path",
+            "required": true,
+            "type": "string",
+            "pattern": "operations/[^/]+"
+          }
+        ],
+        "tags": [
+          "OperationService"
+        ]
+      }
+    },
     "/v1/{name}:nodeDependencies": {
       "get": {
         "summary": "ListWorkflowDependencies lists workflow nodes and map of the node dependencies.",
@@ -5226,6 +5719,12 @@
                 "response": {
                   "$ref": "#/definitions/protobufAny",
                   "description": "The normal response of the operation in case of success.  If the original\nmethod returns no data on success, such as `Delete`, the response is\n`google.protobuf.Empty`.  If the original method is standard\n`Get`/`Create`/`Update`, the response should be the resource.  For other\nmethods, the response should have the type `XxxResponse`, where `Xxx`\nis the original method name.  For example, if the original method name\nis `TakeSnapshot()`, the inferred response type is\n`TakeSnapshotResponse`."
+                },
+                "seenByCreatorTime": {
+                  "type": "string",
+                  "format": "date-time",
+                  "description": "Output only. Optional. Timestamp when the creator marked the Operation as seen.\nOnce set, this field cannot be changed. Set via MarkOperationSeenByCreator method.",
+                  "readOnly": true
                 }
               },
               "description": "The Operation's `name` field is used to identify the Operation to update.\nFormat: operations/{operation}",
@@ -5320,6 +5819,12 @@
                 "response": {
                   "$ref": "#/definitions/protobufAny",
                   "description": "The normal response of the operation in case of success.  If the original\nmethod returns no data on success, such as `Delete`, the response is\n`google.protobuf.Empty`.  If the original method is standard\n`Get`/`Create`/`Update`, the response should be the resource.  For other\nmethods, the response should have the type `XxxResponse`, where `Xxx`\nis the original method name.  For example, if the original method name\nis `TakeSnapshot()`, the inferred response type is\n`TakeSnapshotResponse`."
+                },
+                "seenByCreatorTime": {
+                  "type": "string",
+                  "format": "date-time",
+                  "description": "Output only. Optional. Timestamp when the creator marked the Operation as seen.\nOnce set, this field cannot be changed. Set via MarkOperationSeenByCreator method.",
+                  "readOnly": true
                 }
               },
               "description": "The Operation's `name` field is used to identify the Operation to finalize.\nFormat: operations/{operation}",
@@ -5332,6 +5837,70 @@
         ]
       }
     },
+    "/v1/{parent_1}/annotations": {
+      "get": {
+        "operationId": "LeaderboardTestCaseAnnotationService_ListLeaderboardTestCaseAnnotations",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1ListLeaderboardTestCaseAnnotationsResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "parent_1",
+            "description": "Required. The parent resource name. Format:\n`leaderboards/{leaderboard}/testCases/{test_case}`. Use\n`leaderboards/{leaderboard}/testCases/-` to list across all test cases of a leaderboard. See\nhttps://google.aip.dev/159 for more details.",
+            "in": "path",
+            "required": true,
+            "type": "string",
+            "pattern": "leaderboards/[^/]+/testCases/[^/]+"
+          }
+        ],
+        "tags": [
+          "LeaderboardTestCaseAnnotationService"
+        ]
+      }
+    },
+    "/v1/{parent}/annotations": {
+      "get": {
+        "operationId": "DashboardTestCaseAnnotationService_ListDashboardTestCaseAnnotations",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1ListDashboardTestCaseAnnotationsResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "parent",
+            "description": "Required. The parent resource name. Format:\n`dashboards/{dashboard}/testCases/{test_case}`.\n\nWildcard support: Use the special value `-` for test_case to list annotations\nacross all test cases within the specified dashboard:\n`dashboards/{dashboard}/testCases/-`\n\nSee https://google.aip.dev/159 for more details on collection identifiers.",
+            "in": "path",
+            "required": true,
+            "type": "string",
+            "pattern": "dashboards/[^/]+/testCases/[^/]+"
+          }
+        ],
+        "tags": [
+          "DashboardTestCaseAnnotationService"
+        ]
+      }
+    },
     "/v1/{parent}/edges": {
       "post": {
         "summary": "CreateWorkflowEdge creates a new WorkflowEdge.",
@@ -5621,6 +6190,56 @@
         ]
       }
     },
+    "/v1/{parent}/testCases:append": {
+      "post": {
+        "operationId": "TestCaseService_AppendTestCases",
+        "responses": {
+          "200": {
+            "description": "A successful response.",
+            "schema": {
+              "$ref": "#/definitions/v1AppendTestCasesResponse"
+            }
+          },
+          "default": {
+            "description": "An unexpected error response.",
+            "schema": {
+              "$ref": "#/definitions/rpcStatus"
+            }
+          }
+        },
+        "parameters": [
+          {
+            "name": "parent",
+            "description": "Required. The parent Test where the TestCases will be imported. Format: tests/\u003cUUID\u003e",
+            "in": "path",
+            "required": true,
+            "type": "string",
+            "pattern": "tests/[^/]+"
+          },
+          {
+            "name": "body",
+            "in": "body",
+            "required": true,
+            "schema": {
+              "type": "object",
+              "properties": {
+                "testCasesJson": {
+                  "type": "string",
+                  "description": "Test Cases in JSON format."
+                },
+                "url": {
+                  "type": "string",
+                  "description": "URL pointing to the Test Cases in JSON format to import."
+                }
+              }
+            }
+          }
+        ],
+        "tags": [
+          "TestCaseService"
+        ]
+      }
+    },
     "/v1/{parent}/testCases:batchDelete": {
       "post": {
         "operationId": "TestCaseService_BatchDeleteTestCases",
@@ -6020,7 +6639,14 @@
                   "additionalProperties": {
                     "$ref": "#/definitions/v1MetricScores"
                   },
-                  "description": "Required. Map of baseline metrics from the evaluator to the metric scores for the evaluator."
+                  "description": "Required. Map of baseline metrics from the evaluator to the average metric scores for the evaluator."
+                },
+                "allBaselineMetricsScores": {
+                  "type": "object",
+                  "additionalProperties": {
+                    "$ref": "#/definitions/v1AllMetricScores"
+                  },
+                  "description": "Required. Map of baseline metric to all and every test case metric score."
                 }
               }
             }
@@ -6264,88 +6890,384 @@
         }
       }
     },
-    "v1BatchCreateLeaderboardsRequest": {
+    "v1ActualOutputMeta": {
       "type": "object",
       "properties": {
-        "requests": {
+        "tokenization": {
+          "type": "string",
+          "description": "Tokenization method."
+        },
+        "data": {
           "type": "array",
           "items": {
             "type": "object",
-            "$ref": "#/definitions/v1CreateLeaderboardRequest"
+            "$ref": "#/definitions/v1DataFragment"
           },
-          "description": "Required. Contains list of requests for leaderboards to be created."
-        },
-        "dashboardDisplayName": {
-          "type": "string",
-          "description": "Optional. Display name for the dashboard that will group the leaderboards."
-        },
-        "dashboardDescription": {
-          "type": "string",
-          "description": "Optional. Description for the dashboard that will group the leaderboards."
-        }
-      }
-    },
-    "v1BatchCreateLeaderboardsResponse": {
-      "type": "object",
-      "properties": {
-        "operation": {
-          "$ref": "#/definitions/v1Operation",
-          "description": "Output only. Long-running operation shared for all of the leaderboards. The operation contains\nmetadata about the dashboard that's grouping the leaderboards.",
-          "readOnly": true
+          "description": "Data fragments."
         }
-      }
+      },
+      "title": "Actual output metadata"
     },
-    "v1BatchDeleteDashboardsRequest": {
+    "v1ActualOutputMetaDiff": {
       "type": "object",
       "properties": {
-        "names": {
+        "sentences": {
           "type": "array",
           "items": {
             "type": "string"
           },
-          "description": "Required. The names of the Dashboards to delete. A maximum of 1000 can be specified."
-        }
-      }
-    },
-    "v1BatchDeleteDashboardsResponse": {
-      "type": "object",
-      "properties": {
-        "dashboards": {
+          "description": "Sentences."
+        },
+        "sentencesCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Sentence count."
+        },
+        "commonSentences": {
           "type": "array",
           "items": {
-            "type": "object",
-            "$ref": "#/definitions/v1Dashboard"
+            "type": "string"
           },
-          "description": "The deleted Dashboards."
-        }
-      }
-    },
-    "v1BatchDeleteDocumentsRequest": {
-      "type": "object",
-      "properties": {
-        "names": {
+          "description": "Common sentences between baseline and current."
+        },
+        "commonCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Common sentence count."
+        },
+        "uniqueSentences": {
           "type": "array",
           "items": {
             "type": "string"
           },
-          "description": "Required. The names of the Documents to delete. A maximum of 1000 can be specified."
+          "description": "Unique sentences."
+        },
+        "uniqueCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Unique sentence count."
+        },
+        "identical": {
+          "type": "boolean",
+          "description": "Whether outputs are identical."
+        },
+        "sentenceSimilarity": {
+          "type": "object",
+          "additionalProperties": {
+            "type": "number",
+            "format": "double"
+          },
+          "description": "Sentence similarity scores."
         }
-      }
+      },
+      "title": "Actual output metadata diff"
     },
-    "v1BatchDeleteDocumentsResponse": {
+    "v1AgentChatActivityDiagram": {
       "type": "object",
       "properties": {
-        "documents": {
+        "rows": {
           "type": "array",
           "items": {
             "type": "object",
-            "$ref": "#/definitions/v1Document"
+            "$ref": "#/definitions/v1AgentChatActivityDiagramRow"
           },
-          "description": "The Documents that were deleted."
-        }
-      }
-    },
-    "v1BatchDeleteEvaluatorsRequest": {
+          "description": "Output only. List of rows in the activity diagram.",
+          "readOnly": true
+        },
+        "edges": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1AgentChatActivityDiagramEdge"
+          },
+          "description": "Output only. List of edges connecting nodes in the activity diagram.",
+          "readOnly": true
+        }
+      },
+      "description": "AgentChatActivityDiagram represents the activity diagram for agent chat interactions."
+    },
+    "v1AgentChatActivityDiagramEdge": {
+      "type": "object",
+      "properties": {
+        "from": {
+          "type": "string",
+          "description": "Output only. Source node ID.",
+          "readOnly": true
+        },
+        "to": {
+          "type": "string",
+          "description": "Output only. Target node ID.",
+          "readOnly": true
+        },
+        "label": {
+          "type": "string",
+          "description": "Output only. Label for the edge.",
+          "readOnly": true
+        }
+      },
+      "description": "AgentChatActivityDiagramEdge represents an edge connecting two nodes."
+    },
+    "v1AgentChatActivityDiagramNode": {
+      "type": "object",
+      "properties": {
+        "id": {
+          "type": "string",
+          "description": "Output only. Unique identifier for the node.",
+          "readOnly": true
+        },
+        "role": {
+          "type": "string",
+          "description": "Output only. Role of the node (runtime, user, agent, assistant, etc.).",
+          "readOnly": true
+        },
+        "label": {
+          "type": "string",
+          "description": "Output only. Label for the node.",
+          "readOnly": true
+        }
+      },
+      "description": "AgentChatActivityDiagramNode represents a node in the activity diagram."
+    },
+    "v1AgentChatActivityDiagramRow": {
+      "type": "object",
+      "properties": {
+        "nodes": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1AgentChatActivityDiagramNode"
+          },
+          "description": "Output only. List of nodes in this row.",
+          "readOnly": true
+        }
+      },
+      "description": "AgentChatActivityDiagramRow represents a row in the activity diagram."
+    },
+    "v1AgentChatScriptUsage": {
+      "type": "object",
+      "properties": {
+        "name": {
+          "type": "string",
+          "description": "Output only. Name of the script.",
+          "readOnly": true
+        },
+        "successCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Output only. Number of successful executions.",
+          "readOnly": true
+        },
+        "failureCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Output only. Number of failed executions.",
+          "readOnly": true
+        },
+        "totalCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Output only. Total number of executions.",
+          "readOnly": true
+        }
+      },
+      "description": "AgentChatScriptUsage represents usage statistics for a single script."
+    },
+    "v1AgentChatScriptsBarChart": {
+      "type": "object",
+      "properties": {
+        "scripts": {
+          "type": "object",
+          "additionalProperties": {
+            "$ref": "#/definitions/v1AgentChatScriptUsage"
+          },
+          "description": "Output only. Map of script name to script usage statistics.",
+          "readOnly": true
+        }
+      },
+      "description": "AgentChatScriptsBarChart represents the bar chart for agent chat scripts usage."
+    },
+    "v1AgentChatToolUsage": {
+      "type": "object",
+      "properties": {
+        "name": {
+          "type": "string",
+          "description": "Output only. Name of the tool.",
+          "readOnly": true
+        },
+        "successCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Output only. Number of successful invocations.",
+          "readOnly": true
+        },
+        "failureCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Output only. Number of failed invocations.",
+          "readOnly": true
+        },
+        "totalCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Output only. Total number of invocations.",
+          "readOnly": true
+        }
+      },
+      "description": "AgentChatToolUsage represents usage statistics for a single tool."
+    },
+    "v1AgentChatToolsBarChart": {
+      "type": "object",
+      "properties": {
+        "tools": {
+          "type": "object",
+          "additionalProperties": {
+            "$ref": "#/definitions/v1AgentChatToolUsage"
+          },
+          "description": "Output only. Map of tool name to tool usage statistics.",
+          "readOnly": true
+        }
+      },
+      "description": "AgentChatToolsBarChart represents the bar chart for agent chat tools usage."
+    },
+    "v1AllMetricScores": {
+      "type": "object",
+      "properties": {
+        "scores": {
+          "type": "array",
+          "items": {
+            "type": "number",
+            "format": "double"
+          },
+          "description": "Required. Metric scores for all baseline test cases."
+        }
+      }
+    },
+    "v1AppendTestCasesResponse": {
+      "type": "object",
+      "properties": {
+        "testCases": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1TestCase"
+          },
+          "description": "The list of added TestCases."
+        }
+      }
+    },
+    "v1BatchCreateLeaderboardsRequest": {
+      "type": "object",
+      "properties": {
+        "requests": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1CreateLeaderboardRequest"
+          },
+          "description": "Required. Contains list of requests for leaderboards to be created."
+        },
+        "dashboardDisplayName": {
+          "type": "string",
+          "description": "Optional. Display name for the dashboard that will group the leaderboards."
+        },
+        "dashboardDescription": {
+          "type": "string",
+          "description": "Optional. Description for the dashboard that will group the leaderboards."
+        }
+      }
+    },
+    "v1BatchCreateLeaderboardsResponse": {
+      "type": "object",
+      "properties": {
+        "operation": {
+          "$ref": "#/definitions/v1Operation",
+          "description": "Output only. Long-running operation shared for all of the leaderboards. The operation contains\nmetadata about the dashboard that's grouping the leaderboards.",
+          "readOnly": true
+        }
+      }
+    },
+    "v1BatchCreateLeaderboardsWithoutCacheRequest": {
+      "type": "object",
+      "properties": {
+        "requests": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1CreateLeaderboardRequest"
+          },
+          "description": "Required. Contains list of requests for leaderboards to be created."
+        },
+        "dashboardDisplayName": {
+          "type": "string",
+          "description": "Optional. Display name for the dashboard that will group the leaderboards."
+        },
+        "dashboardDescription": {
+          "type": "string",
+          "description": "Optional. Description for the dashboard that will group the leaderboards."
+        }
+      }
+    },
+    "v1BatchCreateLeaderboardsWithoutCacheResponse": {
+      "type": "object",
+      "properties": {
+        "operation": {
+          "$ref": "#/definitions/v1Operation",
+          "description": "Output only. Long-running operation shared for all of the leaderboards. The operation contains\nmetadata about the dashboard that's grouping the leaderboards.",
+          "readOnly": true
+        }
+      }
+    },
+    "v1BatchDeleteDashboardsRequest": {
+      "type": "object",
+      "properties": {
+        "names": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Required. The names of the Dashboards to delete. A maximum of 1000 can be specified."
+        }
+      }
+    },
+    "v1BatchDeleteDashboardsResponse": {
+      "type": "object",
+      "properties": {
+        "dashboards": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1Dashboard"
+          },
+          "description": "The deleted Dashboards."
+        }
+      }
+    },
+    "v1BatchDeleteDocumentsRequest": {
+      "type": "object",
+      "properties": {
+        "names": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Required. The names of the Documents to delete. A maximum of 1000 can be specified."
+        }
+      }
+    },
+    "v1BatchDeleteDocumentsResponse": {
+      "type": "object",
+      "properties": {
+        "documents": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1Document"
+          },
+          "description": "The Documents that were deleted."
+        }
+      }
+    },
+    "v1BatchDeleteEvaluatorsRequest": {
       "type": "object",
       "properties": {
         "names": {
@@ -6683,6 +7605,19 @@
         }
       }
     },
+    "v1BatchMarkOperationSeenByCreatorResponse": {
+      "type": "object",
+      "properties": {
+        "operations": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1Operation"
+          },
+          "description": "The updated Operations."
+        }
+      }
+    },
     "v1CheckBaseModelsResponse": {
       "type": "object",
       "properties": {
@@ -6714,6 +7649,40 @@
         }
       }
     },
+    "v1CmpLeaderboardReportsRequest": {
+      "type": "object",
+      "properties": {
+        "leaderboardReportBaseline": {
+          "type": "string",
+          "description": "Required. The baseline Leaderboard Report to compare against (JSON string)."
+        },
+        "leaderboardReportCurrent": {
+          "type": "string",
+          "description": "Required. The current Leaderboard Report to compare (JSON string)."
+        },
+        "textSimilarityMetric": {
+          "$ref": "#/definitions/v1TextSimilarityMetric",
+          "description": "Optional. The text similarity metric to use for string/sentence matching. Defaults to EXACT_MATCH."
+        },
+        "llmModelNameBaseline": {
+          "type": "string",
+          "description": "Required. The baseline LLM model name to compare."
+        },
+        "llmModelNameCurrent": {
+          "type": "string",
+          "description": "Required. The current LLM model name to compare."
+        }
+      }
+    },
+    "v1CmpLeaderboardReportsResponse": {
+      "type": "object",
+      "properties": {
+        "leaderboardCmpReport": {
+          "$ref": "#/definitions/v1LeaderboardCmpReport",
+          "description": "The comparison result of the two Leaderboard Reports."
+        }
+      }
+    },
     "v1CollectionInfo": {
       "type": "object",
       "properties": {
@@ -6735,7 +7704,111 @@
           "description": "Required.The number of documents in the collection."
         }
       },
-      "description": "CollectionInfo represents the information about a collection in the H2OGPTE."
+      "description": "CollectionInfo represents the information about a collection in the H2OGPTE."
+    },
+    "v1ComparisonItem": {
+      "type": "object",
+      "properties": {
+        "question": {
+          "type": "string",
+          "description": "The question being evaluated."
+        },
+        "diffFlippedMetrics": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1FlippedMetric"
+          },
+          "description": "List of metrics that flipped between baseline and current."
+        },
+        "baselineTestCaseResult": {
+          "$ref": "#/definitions/v1TestCaseResult",
+          "description": "Baseline test case result."
+        },
+        "baselineDiffActualOutputMeta": {
+          "$ref": "#/definitions/v1ActualOutputMetaDiff",
+          "description": "Baseline actual output metadata diff."
+        },
+        "baselineDiffRetrievedContext": {
+          "$ref": "#/definitions/v1RetrievedContextDiff",
+          "description": "Baseline retrieved context diff."
+        },
+        "currentTestCaseResult": {
+          "$ref": "#/definitions/v1TestCaseResult",
+          "description": "Current test case result."
+        },
+        "currentDiffActualOutputMeta": {
+          "$ref": "#/definitions/v1ActualOutputMetaDiff",
+          "description": "Current actual output metadata diff."
+        },
+        "currentDiffRetrievedContext": {
+          "$ref": "#/definitions/v1RetrievedContextDiff",
+          "description": "Current retrieved context diff."
+        }
+      },
+      "title": "A single comparison item showing differences between baseline and current"
+    },
+    "v1ComparisonMetricScore": {
+      "type": "object",
+      "properties": {
+        "metricName": {
+          "type": "string",
+          "description": "Metric name."
+        },
+        "metricScore": {
+          "type": "number",
+          "format": "double",
+          "description": "Metric score value."
+        }
+      },
+      "title": "Comparison metric score information (specific to comparison reports)"
+    },
+    "v1ComparisonResult": {
+      "type": "object",
+      "properties": {
+        "diffs": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1DiffItem"
+          },
+          "description": "List of differences between leaderboards."
+        },
+        "leaderboards": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1LeaderboardInfo"
+          },
+          "description": "Leaderboard information."
+        },
+        "metricsMeta": {
+          "type": "object",
+          "additionalProperties": {
+            "$ref": "#/definitions/v1MetricMeta"
+          },
+          "description": "Metadata about metrics."
+        }
+      },
+      "title": "Complete comparison result structure"
+    },
+    "v1ComparisonSummary": {
+      "type": "object",
+      "properties": {
+        "recommendationWinner": {
+          "type": "string",
+          "description": "Winner of the comparison (baseline, current, or tie)."
+        },
+        "recommendation": {
+          "type": "string",
+          "description": "Recommendation text."
+        },
+        "recommendationConfidence": {
+          "type": "string",
+          "description": "Confidence level of the recommendation."
+        }
+      },
+      "title": "Comparison summary"
     },
     "v1Context": {
       "type": "object",
@@ -6854,6 +7927,10 @@
         "defaultH2ogpteModel": {
           "$ref": "#/definitions/v1Model",
           "description": "Optional. The default h2oGPTe model host."
+        },
+        "evaluationType": {
+          "$ref": "#/definitions/v1EvaluationType",
+          "description": "Optional. Type of the evaluation. If not specified, defaults to type of the Model used, or LLM if unspecified."
         }
       }
     },
@@ -6920,6 +7997,36 @@
         }
       }
     },
+    "v1CreateTestFromTestCasesRequest": {
+      "type": "object",
+      "properties": {
+        "testsJson": {
+          "type": "string",
+          "description": "Test Cases in JSON format."
+        },
+        "url": {
+          "type": "string",
+          "description": "URL pointing to the Test Cases in JSON format to import."
+        },
+        "testDisplayName": {
+          "type": "string",
+          "description": "Required. Display name of the newly created Test."
+        },
+        "testDescription": {
+          "type": "string",
+          "description": "Optional. Description of the newly created Tests."
+        }
+      }
+    },
+    "v1CreateTestFromTestCasesResponse": {
+      "type": "object",
+      "properties": {
+        "test": {
+          "$ref": "#/definitions/v1Test",
+          "description": "The new Test created from Test Cases."
+        }
+      }
+    },
     "v1CreateTestLabResponse": {
       "type": "object",
       "properties": {
@@ -7042,6 +8149,96 @@
         }
       }
     },
+    "v1DashboardReport": {
+      "type": "object",
+      "properties": {
+        "results": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1DashboardReportResult"
+          },
+          "description": "Output only. List of per test case results.",
+          "readOnly": true
+        },
+        "evaluator": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1LeaderboardReportEvaluator"
+          },
+          "description": "Output only. Details of the evaluators which evaluated the model outputs to create the results.",
+          "readOnly": true
+        }
+      },
+      "description": "DashboardReport represents the dashboard report which is formed by the results, models and\nevaluator."
+    },
+    "v1DashboardReportResult": {
+      "type": "object",
+      "properties": {
+        "key": {
+          "type": "string",
+          "description": "Output only. Composite unique key of the result formed by the model key and test case key.",
+          "readOnly": true
+        },
+        "input": {
+          "type": "string",
+          "description": "Output only. Input prompt or text to be processed.",
+          "readOnly": true
+        },
+        "expectedOutput": {
+          "type": "string",
+          "description": "Output only. Expected output or target result.",
+          "readOnly": true
+        },
+        "actualOutput": {
+          "type": "string",
+          "description": "Output only. Actual output produced by the model.",
+          "readOnly": true
+        },
+        "modelKey": {
+          "type": "string",
+          "description": "Output only. Unique identifier for the model used.",
+          "readOnly": true
+        },
+        "testCaseKey": {
+          "type": "string",
+          "description": "Output only. Unique identifier for the test case.",
+          "readOnly": true
+        },
+        "metrics": {
+          "type": "object",
+          "additionalProperties": {
+            "$ref": "#/definitions/v1MetricScores"
+          },
+          "description": "Optional. All metrics values for the result. Maps evaluator ID to MetricScore."
+        },
+        "resultErrorMap": {
+          "type": "object",
+          "additionalProperties": {
+            "type": "string"
+          },
+          "description": "Output only. Error message if processing resulted in failure. Maps evaluator ID to error\nmessage.",
+          "readOnly": true
+        },
+        "humanDecision": {
+          "$ref": "#/definitions/v1HumanDecision",
+          "description": "Output only. Human decision whether the result was approved or rejected by human.",
+          "readOnly": true
+        },
+        "comment": {
+          "type": "string",
+          "description": "Output only. Optional comment about the result.",
+          "readOnly": true
+        },
+        "annotations": {
+          "type": "object",
+          "additionalProperties": {},
+          "description": "Output only. Additional annotations for the result.",
+          "readOnly": true
+        }
+      }
+    },
     "v1DashboardStatus": {
       "type": "string",
       "enum": [
@@ -7053,6 +8250,49 @@
       "default": "DASHBOARD_STATUS_UNSPECIFIED",
       "description": " - DASHBOARD_STATUS_UNSPECIFIED: Unspecified status.\n - DASHBOARD_STATUS_PROCESSING: Dashboard is being processed. At least one of the leaderboard has a processing status (but no failed status).\n - DASHBOARD_STATUS_COMPLETED: Dashboard is completed successfully. All of the leaderboards are completed.\n - DASHBOARD_STATUS_FAILED: Dashboard failed. At least one of the leaderboard failed."
     },
+    "v1DashboardTestCaseAnnotation": {
+      "type": "object",
+      "properties": {
+        "name": {
+          "type": "string",
+          "title": "Output only. Name of the DashboardTestCaseAnnotation resource. e.g.: \"dashboards/\u003cUUID\u003e/testCases/\u003cUUID\u003e/annotations/\u003cUUID\u003e\"",
+          "readOnly": true
+        },
+        "createTime": {
+          "type": "string",
+          "format": "date-time",
+          "description": "Output only. Timestamp when the DashboardTestCaseAnnotation was created.",
+          "readOnly": true
+        },
+        "creator": {
+          "type": "string",
+          "description": "Output only. Name of the user or service that requested creation of the DashboardTestCaseAnnotation.",
+          "readOnly": true
+        },
+        "updateTime": {
+          "type": "string",
+          "format": "date-time",
+          "description": "Output only. Optional. Timestamp when the DashboardTestCaseAnnotation was last updated.",
+          "readOnly": true
+        },
+        "updater": {
+          "type": "string",
+          "description": "Output only. Optional. Name of the user or service that requested update of the DashboardTestCaseAnnotation.",
+          "readOnly": true
+        },
+        "parent": {
+          "type": "string",
+          "description": "Parent Dashboard Test Case resource name. e.g.: \"dashboards/\u003cUUID\u003e/testCases/\u003cUUID\u003e\"."
+        },
+        "key": {
+          "type": "string",
+          "description": "Immutable. Annotation key."
+        },
+        "value": {
+          "description": "Annotation value."
+        }
+      }
+    },
     "v1DashboardType": {
       "type": "string",
       "enum": [
@@ -7063,6 +8303,65 @@
       "default": "DASHBOARD_TYPE_UNSPECIFIED",
       "description": " - DASHBOARD_TYPE_UNSPECIFIED: Unspecified type.\n - DASHBOARD_TYPE_STANDALONE: Standalone dashboard.\n - DASHBOARD_TYPE_WORKFLOW: Dashboard is part of a dashboard group."
     },
+    "v1DataFragment": {
+      "type": "object",
+      "properties": {
+        "text": {
+          "type": "string",
+          "description": "Text content."
+        },
+        "metrics": {
+          "type": "object",
+          "additionalProperties": {
+            "type": "number",
+            "format": "double"
+          },
+          "description": "Metrics for this fragment."
+        },
+        "meta": {
+          "type": "object",
+          "additionalProperties": {
+            "type": "string"
+          },
+          "description": "Additional metadata."
+        }
+      },
+      "title": "Data fragment"
+    },
+    "v1DeepCompareLeaderboardsRequest": {
+      "type": "object",
+      "properties": {
+        "leaderboardBaselineName": {
+          "type": "string",
+          "description": "Required. The resource name of the baseline leaderboard to compare against."
+        },
+        "leaderboardCurrentName": {
+          "type": "string",
+          "description": "Required. The resource name of the current leaderboard to compare."
+        },
+        "textSimilarityMetric": {
+          "$ref": "#/definitions/v1TextSimilarityMetric",
+          "description": "Optional. The text similarity metric to use for string/sentence matching. Defaults to EXACT_MATCH."
+        },
+        "llmModelBaselineName": {
+          "type": "string",
+          "description": "Required. The baseline LLM model name to compare."
+        },
+        "llmModelCurrentName": {
+          "type": "string",
+          "description": "Required. The current LLM model name to compare."
+        }
+      }
+    },
+    "v1DeepCompareLeaderboardsResponse": {
+      "type": "object",
+      "properties": {
+        "leaderboardCmpReport": {
+          "$ref": "#/definitions/v1LeaderboardCmpReport",
+          "description": "The comparison report containing structured comparison results."
+        }
+      }
+    },
     "v1DeleteDashboardResponse": {
       "type": "object",
       "properties": {
@@ -7170,6 +8469,52 @@
         }
       }
     },
+    "v1DiffItem": {
+      "type": "object",
+      "properties": {
+        "diffKey": {
+          "type": "string",
+          "description": "Unique key identifying the diff (format: \"baseline_id|current_id\")."
+        },
+        "items": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1ComparisonItem"
+          },
+          "description": "List of comparison items."
+        },
+        "summary": {
+          "$ref": "#/definitions/v1ComparisonSummary",
+          "description": "Summary of the comparison."
+        },
+        "modelsOverview": {
+          "$ref": "#/definitions/v1ModelsOverview",
+          "description": "Overview of the models being compared."
+        },
+        "modelsComparisons": {
+          "$ref": "#/definitions/v1ModelsComparisons",
+          "description": "Model comparison statistics."
+        },
+        "modelsComparisonsMetrics": {
+          "$ref": "#/definitions/v1ModelsComparisonsMetrics",
+          "description": "Detailed metrics comparisons."
+        },
+        "technicalMetrics": {
+          "$ref": "#/definitions/v1TechnicalMetrics",
+          "description": "Technical metrics (cost, duration)."
+        },
+        "testCasesLeaderboard": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1TestCaseLeaderboardItem"
+          },
+          "description": "Test cases leaderboard."
+        }
+      },
+      "title": "A single diff item comparing two leaderboards"
+    },
     "v1Document": {
       "type": "object",
       "properties": {
@@ -7284,6 +8629,17 @@
       },
       "description": "EvaluationTest defines a single test in a suite, with materialized corpus (documents) and test cases."
     },
+    "v1EvaluationType": {
+      "type": "string",
+      "enum": [
+        "EVALUATION_TYPE_UNSPECIFIED",
+        "EVALUATION_TYPE_LLM",
+        "EVALUATION_TYPE_RAG",
+        "EVALUATION_TYPE_AGENT"
+      ],
+      "default": "EVALUATION_TYPE_UNSPECIFIED",
+      "description": " - EVALUATION_TYPE_UNSPECIFIED: Unspecified type.\n - EVALUATION_TYPE_LLM: LLM Evaluation, where evaluated model doesn't retrieve any context.\n - EVALUATION_TYPE_RAG: RAG Evaluation, where evaluated model retrieves context from a given collection.\n - EVALUATION_TYPE_AGENT: Agent Evaluation, where evaluated model is an agent that can interact with tools."
+    },
     "v1Evaluator": {
       "type": "object",
       "properties": {
@@ -7533,6 +8889,26 @@
         }
       }
     },
+    "v1FlippedMetric": {
+      "type": "object",
+      "properties": {
+        "metricName": {
+          "type": "string",
+          "description": "Metric name."
+        },
+        "baselineValue": {
+          "type": "number",
+          "format": "double",
+          "description": "Baseline value."
+        },
+        "currentValue": {
+          "type": "number",
+          "format": "double",
+          "description": "Current value."
+        }
+      },
+      "title": "Flipped metric information"
+    },
     "v1GenerateTestCasesResponse": {
       "type": "object",
       "properties": {
@@ -7542,6 +8918,15 @@
         }
       }
     },
+    "v1GetDashboardReportResponse": {
+      "type": "object",
+      "properties": {
+        "dashboardReport": {
+          "$ref": "#/definitions/v1DashboardReport",
+          "description": "The requested Dashboard Report."
+        }
+      }
+    },
     "v1GetDashboardResponse": {
       "type": "object",
       "properties": {
@@ -7779,6 +9164,16 @@
     "v1GrantWorkflowAccessResponse": {
       "type": "object"
     },
+    "v1HumanDecision": {
+      "type": "string",
+      "enum": [
+        "HUMAN_DECISION_UNSPECIFIED",
+        "HUMAN_DECISION_APPROVED",
+        "HUMAN_DECISION_REJECTED"
+      ],
+      "default": "HUMAN_DECISION_UNSPECIFIED",
+      "description": "HumanDecision represents the human decision on the result.\n\n - HUMAN_DECISION_UNSPECIFIED: Default value, means no decision has been made.\n - HUMAN_DECISION_APPROVED: The result was approved by human.\n - HUMAN_DECISION_REJECTED: The result was rejected by human."
+    },
     "v1ImportEvaluationRequest": {
       "type": "object",
       "properties": {
@@ -7958,6 +9353,13 @@
         "experimentalFeaturesEnabled": {
           "type": "boolean",
           "description": "Whether the experimental features are enabled."
+        },
+        "modelTypeAllowlist": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Allowlist of model types for UI that can be hosted in Eval Studio. E.g.\nMODEL_TYPE_H2OGPTE_RAG, MODEL_TYPE_OPENAI_CHAT, MODEL_TYPE_AMAZON_BEDROCK.\nUse \"*\" to allow all model types."
         }
       }
     },
@@ -8184,8 +9586,63 @@
         "testLab": {
           "type": "string",
           "description": "Optional. Resource name of the TestLab if Leaderboard was created from a imported TestLab."
+        },
+        "evaluationType": {
+          "$ref": "#/definitions/v1EvaluationType",
+          "description": "Optional. Type of the evaluation. If not specified, defaults to type of the Model used, or LLM if unspecified."
+        }
+      }
+    },
+    "v1LeaderboardCmpReport": {
+      "type": "object",
+      "properties": {
+        "summary": {
+          "type": "string",
+          "description": "Summary of the comparison."
+        },
+        "comparisonResult": {
+          "$ref": "#/definitions/v1ComparisonResult",
+          "description": "Structured comparison result."
+        }
+      }
+    },
+    "v1LeaderboardComparisonItem": {
+      "type": "object",
+      "properties": {
+        "wins": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Number of wins."
+        },
+        "question": {
+          "type": "string",
+          "description": "Question text."
+        },
+        "changedMetricsCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Count of changed metrics."
+        }
+      },
+      "title": "Leaderboard comparison item"
+    },
+    "v1LeaderboardInfo": {
+      "type": "object",
+      "properties": {
+        "key": {
+          "type": "string",
+          "description": "Unique key identifying the leaderboard pair (format: \"baseline_id|current_id\")."
+        },
+        "items": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1LeaderboardComparisonItem"
+          },
+          "description": "List of leaderboard comparison items."
         }
-      }
+      },
+      "title": "Leaderboard information"
     },
     "v1LeaderboardReport": {
       "type": "object",
@@ -8237,8 +9694,7 @@
       "properties": {
         "tokenization": {
           "type": "string",
-          "description": "Output only. Actual output data tokenization like sentence_level_punkt.",
-          "readOnly": true
+          "description": "Optional. Actual output data tokenization like sentence_level_punkt."
         },
         "data": {
           "type": "array",
@@ -8246,11 +9702,22 @@
             "type": "object",
             "$ref": "#/definitions/v1LeaderboardReportActualOutputData"
           },
-          "description": "Output only. Actual output data - list of text fragments coupled with the metric values.",
-          "readOnly": true
+          "description": "Optional. Actual output data - list of text fragments coupled with the metric values."
+        },
+        "agentChatActivityDiagram": {
+          "$ref": "#/definitions/v1AgentChatActivityDiagram",
+          "description": "Optional. Actual output data - agent chat activity diagram."
+        },
+        "agentChatToolsBarChart": {
+          "$ref": "#/definitions/v1AgentChatToolsBarChart",
+          "description": "Optional. Actual output data - agent chat tools usage bar chart."
+        },
+        "agentChatScriptsBarChart": {
+          "$ref": "#/definitions/v1AgentChatScriptsBarChart",
+          "description": "Optional. Actual output data - agent chat scripts bar chart."
         }
       },
-      "description": "ActualOutputMeta represents the metadata about the actual output."
+      "description": "ActualOutputMeta represents the metadata about the actual output.\nEach instance can contain any combination of the fields below."
     },
     "v1LeaderboardReportEvaluator": {
       "type": "object",
@@ -8567,7 +10034,7 @@
           "items": {
             "type": "string"
           },
-          "description": "Output only. Collection of corpus documents to be used during evaluation.",
+          "description": "Output only. Collection of corpus documents to be used during evaluation. Omitted if\nLEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used.",
           "readOnly": true
         },
         "context": {
@@ -8575,7 +10042,7 @@
           "items": {
             "type": "string"
           },
-          "description": "Output only. List of contextual information or references.",
+          "description": "Output only. List of contextual information or references. Omitted if\nLEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used.",
           "readOnly": true
         },
         "categories": {
@@ -8583,7 +10050,7 @@
           "items": {
             "type": "string"
           },
-          "description": "Output only. List of categories or labels for classification.",
+          "description": "Output only. List of categories or labels for classification. Omitted if\nLEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used.",
           "readOnly": true
         },
         "relationships": {
@@ -8592,7 +10059,7 @@
             "type": "object",
             "$ref": "#/definitions/v1LeaderboardReportResultRelationship"
           },
-          "description": "Output only. List of relationships or associations between entities.",
+          "description": "Output only. List of relationships or associations between entities. Omitted if\nLEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used.",
           "readOnly": true
         },
         "expectedOutput": {
@@ -8605,12 +10072,12 @@
           "items": {
             "type": "string"
           },
-          "description": "Output only. List of constraints that should be applied to the output.",
+          "description": "Output only. List of constraints that should be applied to the output. Omitted if\nLEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used.",
           "readOnly": true
         },
         "outputCondition": {
           "type": "string",
-          "description": "Output only. Condition that output should satisfy.",
+          "description": "Output only. Condition that output should satisfy. Omitted if\nLEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used.",
           "readOnly": true
         },
         "actualOutput": {
@@ -8621,13 +10088,13 @@
         "actualDuration": {
           "type": "number",
           "format": "double",
-          "description": "Output only. Duration of processing in seconds.",
+          "description": "Output only. Duration of processing in seconds. Omitted if\nLEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used.",
           "readOnly": true
         },
         "cost": {
           "type": "number",
           "format": "double",
-          "description": "Output only. Cost of processing in currency units.",
+          "description": "Output only. Cost of processing in currency units. Omitted if\nLEADERBOARD_REPORT_RESULT_VIEW_SUMMARY is used.",
           "readOnly": true
         },
         "modelKey": {
@@ -8661,6 +10128,22 @@
           },
           "description": "Output only. Additional metadata about the actual output.",
           "readOnly": true
+        },
+        "humanDecision": {
+          "$ref": "#/definitions/v1HumanDecision",
+          "description": "Output only. Human decision whether the result was approved or rejected by human.",
+          "readOnly": true
+        },
+        "comment": {
+          "type": "string",
+          "description": "Output only. Optional comment about the result.",
+          "readOnly": true
+        },
+        "annotations": {
+          "type": "object",
+          "additionalProperties": {},
+          "description": "Output only. Annotations associated with the test case result.",
+          "readOnly": true
         }
       }
     },
@@ -8685,6 +10168,16 @@
       },
       "description": "Relationship represents the relationship between result entries."
     },
+    "v1LeaderboardReportResultView": {
+      "type": "string",
+      "enum": [
+        "LEADERBOARD_REPORT_RESULT_VIEW_UNSPECIFIED",
+        "LEADERBOARD_REPORT_RESULT_VIEW_FULL",
+        "LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY"
+      ],
+      "default": "LEADERBOARD_REPORT_RESULT_VIEW_UNSPECIFIED",
+      "description": " - LEADERBOARD_REPORT_RESULT_VIEW_UNSPECIFIED: Default value. The basic view with essential fields.\n - LEADERBOARD_REPORT_RESULT_VIEW_FULL: Full view with all fields populated.\n - LEADERBOARD_REPORT_RESULT_VIEW_SUMMARY: Summary view with only key fields."
+    },
     "v1LeaderboardStatus": {
       "type": "string",
       "enum": [
@@ -8696,6 +10189,49 @@
       "default": "LEADERBOARD_STATUS_UNSPECIFIED",
       "description": " - LEADERBOARD_STATUS_UNSPECIFIED: Unspecified status.\n - LEADERBOARD_STATUS_PROCESSING: Leaderboard is being processed. See the Operation for details.\n - LEADERBOARD_STATUS_COMPLETED: Leaderboard is completed successfully.\n - LEADERBOARD_STATUS_FAILED: Leaderboard failed. See the Operation for details."
     },
+    "v1LeaderboardTestCaseAnnotation": {
+      "type": "object",
+      "properties": {
+        "name": {
+          "type": "string",
+          "title": "Output only. Name of the LeaderboardTestCaseAnnotation resource. e.g.: \"leaderboards/\u003cUUID\u003e/testCases/\u003cUUID\u003e/annotations/\u003cUUID\u003e\"",
+          "readOnly": true
+        },
+        "createTime": {
+          "type": "string",
+          "format": "date-time",
+          "description": "Output only. Timestamp when the LeaderboardTestCaseAnnotation was created.",
+          "readOnly": true
+        },
+        "creator": {
+          "type": "string",
+          "description": "Output only. Name of the user or service that requested creation of the LeaderboardTestCaseAnnotation.",
+          "readOnly": true
+        },
+        "updateTime": {
+          "type": "string",
+          "format": "date-time",
+          "description": "Output only. Optional. Timestamp when the LeaderboardTestCaseAnnotation was last updated.",
+          "readOnly": true
+        },
+        "updater": {
+          "type": "string",
+          "description": "Output only. Optional. Name of the user or service that requested update of the LeaderboardTestCaseAnnotation.",
+          "readOnly": true
+        },
+        "parent": {
+          "type": "string",
+          "description": "Parent Leaderboard Test Case resource name. e.g.: \"leaderboards/\u003cUUID\u003e/testCases/\u003cUUID\u003e\"."
+        },
+        "key": {
+          "type": "string",
+          "description": "Immutable. Annotation key."
+        },
+        "value": {
+          "description": "Annotation value."
+        }
+      }
+    },
     "v1LeaderboardType": {
       "type": "string",
       "enum": [
@@ -8744,6 +10280,19 @@
         }
       }
     },
+    "v1ListDashboardTestCaseAnnotationsResponse": {
+      "type": "object",
+      "properties": {
+        "dashboardTestCaseAnnotations": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1DashboardTestCaseAnnotation"
+          },
+          "description": "The list of DashboardTestCaseAnnotations."
+        }
+      }
+    },
     "v1ListDashboardsResponse": {
       "type": "object",
       "properties": {
@@ -8808,6 +10357,19 @@
         }
       }
     },
+    "v1ListLeaderboardTestCaseAnnotationsResponse": {
+      "type": "object",
+      "properties": {
+        "leaderboardTestCaseAnnotations": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1LeaderboardTestCaseAnnotation"
+          },
+          "description": "The list of LeaderboardTestCaseAnnotations."
+        }
+      }
+    },
     "v1ListLeaderboardsResponse": {
       "type": "object",
       "properties": {
@@ -8913,6 +10475,11 @@
             "$ref": "#/definitions/v1Operation"
           },
           "description": "The list of Operations."
+        },
+        "totalSize": {
+          "type": "integer",
+          "format": "int32",
+          "description": "The total number of Operations that match the request, irrespective of pagination."
         }
       }
     },
@@ -9046,6 +10613,24 @@
         }
       }
     },
+    "v1ListUnseenOperationsResponse": {
+      "type": "object",
+      "properties": {
+        "operations": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1Operation"
+          },
+          "description": "The list of Operations that the user has not seen."
+        },
+        "totalSize": {
+          "type": "integer",
+          "format": "int32",
+          "description": "The total number of unseen Operations that match the request, irrespective of pagination."
+        }
+      }
+    },
     "v1ListWorkflowAccessResponse": {
       "type": "object",
       "properties": {
@@ -9106,6 +10691,137 @@
         }
       }
     },
+    "v1MarkOperationSeenByCreatorResponse": {
+      "type": "object",
+      "properties": {
+        "operation": {
+          "$ref": "#/definitions/v1Operation",
+          "description": "The updated Operation."
+        }
+      }
+    },
+    "v1Metric": {
+      "type": "object",
+      "properties": {
+        "key": {
+          "type": "string",
+          "description": "Metric key."
+        },
+        "value": {
+          "type": "number",
+          "format": "double",
+          "description": "Metric value (optional)."
+        }
+      },
+      "title": "Metric information"
+    },
+    "v1MetricAverage": {
+      "type": "object",
+      "properties": {
+        "metricKey": {
+          "type": "string",
+          "description": "Metric key."
+        },
+        "baselineAvg": {
+          "type": "number",
+          "format": "double",
+          "description": "Baseline average."
+        },
+        "currentAvg": {
+          "type": "number",
+          "format": "double",
+          "description": "Current average."
+        },
+        "diff": {
+          "type": "number",
+          "format": "double",
+          "description": "Difference between current and baseline."
+        },
+        "baselineBetterWins": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Baseline better wins count."
+        },
+        "currentBetterWins": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Current better wins count."
+        },
+        "baselineRankAvg": {
+          "type": "number",
+          "format": "double",
+          "description": "Baseline rank average."
+        },
+        "currentRankAvg": {
+          "type": "number",
+          "format": "double",
+          "description": "Current rank average."
+        }
+      },
+      "title": "Metric average comparison"
+    },
+    "v1MetricMeta": {
+      "type": "object",
+      "properties": {
+        "key": {
+          "type": "string",
+          "description": "Metric key."
+        },
+        "displayName": {
+          "type": "string",
+          "description": "Display name."
+        },
+        "dataType": {
+          "type": "string",
+          "description": "Data type."
+        },
+        "displayValue": {
+          "type": "string",
+          "description": "Display value format."
+        },
+        "description": {
+          "type": "string",
+          "description": "Description."
+        },
+        "valueRange": {
+          "type": "array",
+          "items": {
+            "type": "number",
+            "format": "double"
+          },
+          "description": "Value range (min, max)."
+        },
+        "valueEnum": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Value enum (null if not applicable)."
+        },
+        "higherIsBetter": {
+          "type": "boolean",
+          "description": "Whether higher is better."
+        },
+        "threshold": {
+          "type": "number",
+          "format": "double",
+          "description": "Threshold value."
+        },
+        "isPrimaryMetric": {
+          "type": "boolean",
+          "description": "Is primary metric."
+        },
+        "parentMetric": {
+          "type": "string",
+          "description": "Parent metric."
+        },
+        "exclude": {
+          "type": "boolean",
+          "description": "Exclude flag."
+        }
+      },
+      "title": "Metric metadata"
+    },
     "v1MetricScore": {
       "type": "object",
       "properties": {
@@ -9116,7 +10832,8 @@
         "value": {
           "type": "number",
           "format": "double",
-          "description": "Required. Metric value - consider NaN, Infinity or -Infinity for float representation."
+          "x-nullable": true,
+          "description": "Optional. Metric value. May be omitted if the metric could not be computed.\nValid values include normal floats, as well as special values: NaN, Infinity, or -Infinity."
         }
       },
       "description": "MetricScore represents the metric score."
@@ -9130,7 +10847,7 @@
             "type": "object",
             "$ref": "#/definitions/v1MetricScore"
           },
-          "description": "Required. The metric scores."
+          "description": "Repeated. List of metric scores."
         }
       }
     },
@@ -9181,48 +10898,145 @@
         },
         "description": {
           "type": "string",
-          "description": "Optional. Arbitrary description of the Model."
+          "description": "Optional. Arbitrary description of the Model."
+        },
+        "url": {
+          "type": "string",
+          "description": "Optional. Immutable. Absolute URL to the Model."
+        },
+        "apiKey": {
+          "type": "string",
+          "description": "Optional. API key used to access the Model. Not set for read calls (i.e. get, list) by public\nclients (front-end). Set only for internal (server-to-worker) communication."
+        },
+        "type": {
+          "$ref": "#/definitions/v1ModelType",
+          "description": "Immutable. Type of this Model."
+        },
+        "parameters": {
+          "type": "string",
+          "description": "Optional. Model specific parameters in JSON format."
+        },
+        "demo": {
+          "type": "boolean",
+          "description": "Output only. Whether the Model is a demo resource or not. Demo resources are read only.",
+          "readOnly": true
+        }
+      }
+    },
+    "v1ModelType": {
+      "type": "string",
+      "enum": [
+        "MODEL_TYPE_UNSPECIFIED",
+        "MODEL_TYPE_H2OGPTE_RAG",
+        "MODEL_TYPE_OPENAI_RAG",
+        "MODEL_TYPE_H2OGPTE_LLM",
+        "MODEL_TYPE_H2OGPT_LLM",
+        "MODEL_TYPE_OPENAI_CHAT",
+        "MODEL_TYPE_AZURE_OPENAI_CHAT",
+        "MODEL_TYPE_OPENAI_API_CHAT",
+        "MODEL_TYPE_H2OLLMOPS",
+        "MODEL_TYPE_OLLAMA",
+        "MODEL_TYPE_AMAZON_BEDROCK",
+        "MODEL_TYPE_ANTHROPIC_CLAUDE"
+      ],
+      "default": "MODEL_TYPE_UNSPECIFIED",
+      "description": " - MODEL_TYPE_UNSPECIFIED: Unspecified type.\n - MODEL_TYPE_H2OGPTE_RAG: h2oGPTe RAG.\n - MODEL_TYPE_OPENAI_RAG: OpenAI Assistant RAG.\n - MODEL_TYPE_H2OGPTE_LLM: h2oGPTe LLM.\n - MODEL_TYPE_H2OGPT_LLM: h2oGPT LLM.\n - MODEL_TYPE_OPENAI_CHAT: OpenAI chat.\n - MODEL_TYPE_AZURE_OPENAI_CHAT: Microsoft Azure hosted OpenAI Chat.\n - MODEL_TYPE_OPENAI_API_CHAT: OpenAI API chat.\n - MODEL_TYPE_H2OLLMOPS: H2O LLMOps.\n - MODEL_TYPE_OLLAMA: Ollama.\n - MODEL_TYPE_AMAZON_BEDROCK: Amazon Bedrock.\n - MODEL_TYPE_ANTHROPIC_CLAUDE: Anthropic Claude chat."
+    },
+    "v1ModelsComparisons": {
+      "type": "object",
+      "properties": {
+        "testCaseRanksBaseline": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Test case ranks for baseline."
+        },
+        "testCaseRanksCurrent": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Test case ranks for current."
+        },
+        "testCaseWinsBaseline": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Test case wins for baseline."
+        },
+        "testCaseWinsCurrent": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Test case wins for current."
+        }
+      },
+      "title": "Models comparison statistics"
+    },
+    "v1ModelsComparisonsMetrics": {
+      "type": "object",
+      "properties": {
+        "metricsRanksBaseline": {
+          "type": "number",
+          "format": "double",
+          "description": "Metrics ranks for baseline."
+        },
+        "metricsRanksCurrent": {
+          "type": "number",
+          "format": "double",
+          "description": "Metrics ranks for current."
+        },
+        "metricsWinsBaseline": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Metrics wins for baseline."
+        },
+        "metricsWinsCurrent": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Metrics wins for current."
+        },
+        "metricsAverages": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1MetricAverage"
+          },
+          "description": "Metrics averages."
+        }
+      },
+      "title": "Detailed metrics comparisons"
+    },
+    "v1ModelsOverview": {
+      "type": "object",
+      "properties": {
+        "baselineModelKey": {
+          "type": "string",
+          "description": "Baseline model key."
         },
-        "url": {
+        "currentModelKey": {
           "type": "string",
-          "description": "Optional. Immutable. Absolute URL to the Model."
+          "description": "Current model key."
         },
-        "apiKey": {
+        "baselineModelName": {
           "type": "string",
-          "description": "Optional. API key used to access the Model. Not set for read calls (i.e. get, list) by public\nclients (front-end). Set only for internal (server-to-worker) communication."
+          "description": "Baseline model name."
         },
-        "type": {
-          "$ref": "#/definitions/v1ModelType",
-          "description": "Immutable. Type of this Model."
+        "baselineCollectionId": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Baseline collection IDs."
         },
-        "parameters": {
+        "currentModelName": {
           "type": "string",
-          "description": "Optional. Model specific parameters in JSON format."
+          "description": "Current model name."
         },
-        "demo": {
-          "type": "boolean",
-          "description": "Output only. Whether the Model is a demo resource or not. Demo resources are read only.",
-          "readOnly": true
+        "currentCollectionId": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Current collection IDs."
         }
-      }
-    },
-    "v1ModelType": {
-      "type": "string",
-      "enum": [
-        "MODEL_TYPE_UNSPECIFIED",
-        "MODEL_TYPE_H2OGPTE_RAG",
-        "MODEL_TYPE_OPENAI_RAG",
-        "MODEL_TYPE_H2OGPTE_LLM",
-        "MODEL_TYPE_H2OGPT_LLM",
-        "MODEL_TYPE_OPENAI_CHAT",
-        "MODEL_TYPE_AZURE_OPENAI_CHAT",
-        "MODEL_TYPE_OPENAI_API_CHAT",
-        "MODEL_TYPE_H2OLLMOPS",
-        "MODEL_TYPE_OLLAMA",
-        "MODEL_TYPE_AMAZON_BEDROCK"
-      ],
-      "default": "MODEL_TYPE_UNSPECIFIED",
-      "description": " - MODEL_TYPE_UNSPECIFIED: Unspecified type.\n - MODEL_TYPE_H2OGPTE_RAG: h2oGPTe RAG.\n - MODEL_TYPE_OPENAI_RAG: OpenAI Assistant RAG.\n - MODEL_TYPE_H2OGPTE_LLM: h2oGPTe LLM.\n - MODEL_TYPE_H2OGPT_LLM: h2oGPT LLM.\n - MODEL_TYPE_OPENAI_CHAT: OpenAI chat.\n - MODEL_TYPE_AZURE_OPENAI_CHAT: Microsoft Azure hosted OpenAI Chat.\n - MODEL_TYPE_OPENAI_API_CHAT: OpenAI API chat.\n - MODEL_TYPE_H2OLLMOPS: H2O LLMOps.\n - MODEL_TYPE_OLLAMA: Ollama.\n - MODEL_TYPE_AMAZON_BEDROCK: Amazon Bedrock."
+      },
+      "title": "Models overview"
     },
     "v1Operation": {
       "type": "object",
@@ -9280,6 +11094,12 @@
         "response": {
           "$ref": "#/definitions/protobufAny",
           "description": "The normal response of the operation in case of success.  If the original\nmethod returns no data on success, such as `Delete`, the response is\n`google.protobuf.Empty`.  If the original method is standard\n`Get`/`Create`/`Update`, the response should be the resource.  For other\nmethods, the response should have the type `XxxResponse`, where `Xxx`\nis the original method name.  For example, if the original method name\nis `TakeSnapshot()`, the inferred response type is\n`TakeSnapshotResponse`."
+        },
+        "seenByCreatorTime": {
+          "type": "string",
+          "format": "date-time",
+          "description": "Output only. Optional. Timestamp when the creator marked the Operation as seen.\nOnce set, this field cannot be changed. Set via MarkOperationSeenByCreator method.",
+          "readOnly": true
         }
       },
       "description": "This resource represents a long-running operation that is the result of a\nnetwork API call."
@@ -9309,6 +11129,16 @@
         }
       }
     },
+    "v1OperationView": {
+      "type": "string",
+      "enum": [
+        "OPERATION_VIEW_UNSPECIFIED",
+        "OPERATION_VIEW_BASIC",
+        "OPERATION_VIEW_FULL"
+      ],
+      "default": "OPERATION_VIEW_UNSPECIFIED",
+      "description": " - OPERATION_VIEW_UNSPECIFIED: Default / unset value. The API will default to the OPERATION_VIEW_FULL.\n - OPERATION_VIEW_BASIC: Include basic metadata about the Operation, but not the response.\n - OPERATION_VIEW_FULL: Include everything."
+    },
     "v1PerturbTestInPlaceResponse": {
       "type": "object",
       "properties": {
@@ -9603,6 +11433,60 @@
         }
       }
     },
+    "v1RetrievedContextDiff": {
+      "type": "object",
+      "properties": {
+        "chunks": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Context chunks."
+        },
+        "chunksCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Chunk count."
+        },
+        "commonChunks": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Common chunks between baseline and current."
+        },
+        "commonCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Common chunk count."
+        },
+        "uniqueChunks": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Unique chunks."
+        },
+        "uniqueCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Unique chunk count."
+        },
+        "identical": {
+          "type": "boolean",
+          "description": "Whether contexts are identical."
+        },
+        "chunkSimilarity": {
+          "type": "object",
+          "additionalProperties": {
+            "type": "number",
+            "format": "double"
+          },
+          "description": "Chunk similarity scores."
+        }
+      },
+      "title": "Retrieved context diff"
+    },
     "v1RevokeDashboardAccessResponse": {
       "type": "object"
     },
@@ -9647,23 +11531,80 @@
           "type": "string",
           "format": "int64",
           "x-nullable": true,
-          "description": "Number of pending jobs in the topic modeling queue. It's marked as optional to always be part of the response, even when the value is zero."
+          "description": "Number of pending jobs in the topic modeling queue. It's marked as optional to always be part\nof the response, even when the value is zero."
         },
         "testValidationPendingJobs": {
           "type": "string",
           "format": "int64",
           "x-nullable": true,
-          "description": "Number of pending jobs in the test validation queue. It's marked as optional to always be part of the response, even when the value is zero."
+          "description": "Number of pending jobs in the test validation queue. It's marked as optional to always be part\nof the response, even when the value is zero."
         },
         "failureClusteringPendingJobs": {
           "type": "string",
           "format": "int64",
           "x-nullable": true,
-          "description": "Number of pending jobs in the failure clustering queue. It's marked as optional to always be part of the response, even when the value is zero."
+          "description": "Number of pending jobs in the failure clustering queue. It's marked as optional to always be\npart of the response, even when the value is zero."
+        },
+        "testCaseImportPendingJobs": {
+          "type": "string",
+          "format": "int64",
+          "x-nullable": true,
+          "description": "Number of pending jobs in the test case import queue. It's marked as optional to always be part\nof the response, even when the value is zero."
+        },
+        "evaluationWorkerQueueLength": {
+          "type": "string",
+          "format": "int64",
+          "x-nullable": true,
+          "description": "Number of pending jobs in the evaluation worker queue. It's marked as optional to always be\npart of the response, even when the value is zero."
         }
       },
       "description": "Stats represents statistics about the Eval Studio instance, jobs and utilization."
     },
+    "v1TechnicalMetrics": {
+      "type": "object",
+      "properties": {
+        "baseline": {
+          "$ref": "#/definitions/v1TechnicalMetricsDetail",
+          "description": "Baseline technical metrics."
+        },
+        "current": {
+          "$ref": "#/definitions/v1TechnicalMetricsDetail",
+          "description": "Current technical metrics."
+        }
+      },
+      "title": "Technical metrics for model performance"
+    },
+    "v1TechnicalMetricsDetail": {
+      "type": "object",
+      "properties": {
+        "costSum": {
+          "type": "number",
+          "format": "double",
+          "description": "Sum of costs."
+        },
+        "durationSum": {
+          "type": "number",
+          "format": "double",
+          "description": "Sum of durations."
+        },
+        "durationMin": {
+          "type": "number",
+          "format": "double",
+          "description": "Minimum duration."
+        },
+        "durationMax": {
+          "type": "number",
+          "format": "double",
+          "description": "Maximum duration."
+        },
+        "durationAvg": {
+          "type": "number",
+          "format": "double",
+          "description": "Average duration."
+        }
+      },
+      "title": "Technical metrics detail"
+    },
     "v1Test": {
       "type": "object",
       "properties": {
@@ -9825,6 +11766,26 @@
         }
       }
     },
+    "v1TestCaseLeaderboardItem": {
+      "type": "object",
+      "properties": {
+        "wins": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Number of wins."
+        },
+        "question": {
+          "type": "string",
+          "description": "Question text."
+        },
+        "changedMetricsCount": {
+          "type": "integer",
+          "format": "int32",
+          "description": "Count of changed metrics."
+        }
+      },
+      "title": "Test case leaderboard item"
+    },
     "v1TestCaseRelationship": {
       "type": "object",
       "properties": {
@@ -9842,6 +11803,143 @@
         }
       }
     },
+    "v1TestCaseRelationshipInfo": {
+      "type": "object",
+      "properties": {
+        "type": {
+          "type": "string",
+          "description": "Type of the relationship."
+        },
+        "target": {
+          "type": "string",
+          "description": "Target of the relationship."
+        },
+        "targetType": {
+          "type": "string",
+          "description": "Type of the target."
+        }
+      },
+      "title": "Test case relationship information"
+    },
+    "v1TestCaseResult": {
+      "type": "object",
+      "properties": {
+        "key": {
+          "type": "string",
+          "description": "Unique key for the test case."
+        },
+        "input": {
+          "type": "string",
+          "description": "Input text."
+        },
+        "corpus": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Corpus URLs."
+        },
+        "context": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Context texts."
+        },
+        "categories": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Categories."
+        },
+        "relationships": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1TestCaseRelationshipInfo"
+          },
+          "description": "Relationships."
+        },
+        "expectedOutput": {
+          "type": "string",
+          "description": "Expected output."
+        },
+        "outputConstraints": {
+          "type": "array",
+          "items": {
+            "type": "string"
+          },
+          "description": "Output constraints."
+        },
+        "outputCondition": {
+          "type": "string",
+          "description": "Output condition."
+        },
+        "actualOutput": {
+          "type": "string",
+          "description": "Actual output generated."
+        },
+        "actualDuration": {
+          "type": "number",
+          "format": "double",
+          "description": "Duration in seconds."
+        },
+        "cost": {
+          "type": "number",
+          "format": "double",
+          "description": "Cost of evaluation."
+        },
+        "modelKey": {
+          "type": "string",
+          "description": "Model key."
+        },
+        "testKey": {
+          "type": "string",
+          "description": "Test key."
+        },
+        "testCaseKey": {
+          "type": "string",
+          "description": "Test case key."
+        },
+        "metrics": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1Metric"
+          },
+          "description": "List of metrics."
+        },
+        "metricsMeta": {
+          "type": "object",
+          "additionalProperties": {
+            "type": "string"
+          },
+          "description": "Metadata for metrics."
+        },
+        "actualOutputMeta": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1ActualOutputMeta"
+          },
+          "description": "Actual output metadata."
+        },
+        "metricScores": {
+          "type": "array",
+          "items": {
+            "type": "object",
+            "$ref": "#/definitions/v1ComparisonMetricScore"
+          },
+          "description": "Metric scores."
+        },
+        "resultErrorMessage": {
+          "type": "string",
+          "description": "Error message if processing resulted in failure."
+        }
+      },
+      "title": "Test case result"
+    },
     "v1TestCasesGenerator": {
       "type": "string",
       "enum": [
@@ -10047,6 +12145,18 @@
       "default": "TEST_TYPE_UNSPECIFIED",
       "description": " - TEST_TYPE_UNSPECIFIED: Unspecified type.\n - TEST_TYPE_STANDALONE: Standalone test.\n - TEST_TYPE_WORKFLOW: Test is part of a dashboard."
     },
+    "v1TextSimilarityMetric": {
+      "type": "string",
+      "enum": [
+        "TEXT_SIMILARITY_METRIC_UNSPECIFIED",
+        "TEXT_SIMILARITY_METRIC_EXACT_MATCH",
+        "TEXT_SIMILARITY_METRIC_COSINE_DISTANCE",
+        "TEXT_SIMILARITY_METRIC_BERT_SCORE"
+      ],
+      "default": "TEXT_SIMILARITY_METRIC_UNSPECIFIED",
+      "description": "- TEXT_SIMILARITY_METRIC_UNSPECIFIED: Default value - must not be used\n - TEXT_SIMILARITY_METRIC_EXACT_MATCH: Exact string matching - sentences must be identical (default)\n - TEXT_SIMILARITY_METRIC_COSINE_DISTANCE: Cosine distance of sentence embeddings - semantic similarity\n - TEXT_SIMILARITY_METRIC_BERT_SCORE: BERTScore - contextual embeddings similarity using BERT",
+      "title": "Text similarity metric for string/sentence matching in leaderboard comparisons"
+    },
     "v1UpdateDashboardResponse": {
       "type": "object",
       "properties": {
@@ -10056,6 +12166,15 @@
         }
       }
     },
+    "v1UpdateDashboardTestCaseAnnotationResponse": {
+      "type": "object",
+      "properties": {
+        "dashboardTestCaseAnnotation": {
+          "$ref": "#/definitions/v1DashboardTestCaseAnnotation",
+          "description": "The updated DashboardTestCaseAnnotation."
+        }
+      }
+    },
     "v1UpdateDocumentResponse": {
       "type": "object",
       "properties": {
@@ -10074,6 +12193,15 @@
         }
       }
     },
+    "v1UpdateLeaderboardTestCaseAnnotationResponse": {
+      "type": "object",
+      "properties": {
+        "leaderboardTestCaseAnnotation": {
+          "$ref": "#/definitions/v1LeaderboardTestCaseAnnotation",
+          "description": "The updated LeaderboardTestCaseAnnotation."
+        }
+      }
+    },
     "v1UpdateModelResponse": {
       "type": "object",
       "properties": {
@@ -10569,7 +12697,8 @@
         "WORKFLOW_NODE_TYPE_MARGINAL_ANALYSIS",
         "WORKFLOW_NODE_TYPE_VALIDATION",
         "WORKFLOW_NODE_TYPE_ADVERSARIAL_INPUTS",
-        "WORKFLOW_NODE_TYPE_FAILURE_CLUSTERING"
+        "WORKFLOW_NODE_TYPE_FAILURE_CLUSTERING",
+        "WORKFLOW_NODE_TYPE_TEST_CASE_IMPORT"
       ],
       "default": "WORKFLOW_NODE_TYPE_UNSPECIFIED",
       "description": "WorkflowNodeType represents the type of a WorkflowNode."
@@ -10608,7 +12737,8 @@
       "type": "string",
       "enum": [
         "WORKFLOW_TYPE_UNSPECIFIED",
-        "WORKFLOW_TYPE_MRM"
+        "WORKFLOW_TYPE_MRM",
+        "WORKFLOW_TYPE_IMPORTED_TEST"
       ],
       "default": "WORKFLOW_TYPE_UNSPECIFIED",
       "description": "WorkflowType represents the type of a Workflow."