scorecard-ai-mcp 2.1.0 → 2.2.0

package/src/tools/metrics/update-metrics.ts

@@ -126,7 +126,7 @@ export const tool: Tool = {
           },
           guidelines: {
             type: 'string',
-            description: 'Optional guidelines for heuristic evaluation logic.',
+            description: 'Guidelines for heuristic evaluation logic.',
           },
           name: {
             type: 'string',
@@ -139,6 +139,124 @@ export const tool: Tool = {
         },
         required: ['metricId', 'evalType', 'outputType'],
       },
+      {
+        type: 'object',
+        properties: {
+          metricId: {
+            type: 'string',
+          },
+          evalType: {
+            type: 'string',
+            description: 'AI-based evaluation type.',
+            enum: ['ai'],
+          },
+          outputType: {
+            type: 'string',
+            description: 'Float output type (0-1).',
+            enum: ['float'],
+          },
+          description: {
+            type: 'string',
+            description: 'The description of the Metric.',
+          },
+          evalModelName: {
+            type: 'string',
+            description: 'The AI model to use for evaluation.',
+          },
+          guidelines: {
+            type: 'string',
+            description: 'Guidelines for AI evaluation on how to score the metric.',
+          },
+          name: {
+            type: 'string',
+            description: 'The name of the Metric.',
+          },
+          passingThreshold: {
+            type: 'number',
+            description: 'Threshold for determining pass/fail from float scores (0.0-1.0).',
+          },
+          promptTemplate: {
+            type: 'string',
+            description:
+              'The complete prompt template for AI evaluation. Should include placeholders for dynamic content.',
+          },
+          temperature: {
+            type: 'number',
+            description: 'The temperature for AI evaluation (0-2).',
+          },
+        },
+        required: ['metricId', 'evalType', 'outputType'],
+      },
+      {
+        type: 'object',
+        properties: {
+          metricId: {
+            type: 'string',
+          },
+          evalType: {
+            type: 'string',
+            description: 'Human-based evaluation type.',
+            enum: ['human'],
+          },
+          outputType: {
+            type: 'string',
+            description: 'Float output type (0-1).',
+            enum: ['float'],
+          },
+          description: {
+            type: 'string',
+            description: 'The description of the Metric.',
+          },
+          guidelines: {
+            type: 'string',
+            description: 'Guidelines for human evaluators.',
+          },
+          name: {
+            type: 'string',
+            description: 'The name of the Metric.',
+          },
+          passingThreshold: {
+            type: 'number',
+            description: 'Threshold for determining pass/fail from float scores (0.0-1.0).',
+          },
+        },
+        required: ['metricId', 'evalType', 'outputType'],
+      },
+      {
+        type: 'object',
+        properties: {
+          metricId: {
+            type: 'string',
+          },
+          evalType: {
+            type: 'string',
+            description: 'Heuristic-based evaluation type.',
+            enum: ['heuristic'],
+          },
+          outputType: {
+            type: 'string',
+            description: 'Float output type (0-1).',
+            enum: ['float'],
+          },
+          description: {
+            type: 'string',
+            description: 'The description of the Metric.',
+          },
+          guidelines: {
+            type: 'string',
+            description: 'Guidelines for heuristic evaluation logic.',
+          },
+          name: {
+            type: 'string',
+            description: 'The name of the Metric.',
+          },
+          passingThreshold: {
+            type: 'number',
+            description: 'Threshold for determining pass/fail from float scores (0.0-1.0).',
+          },
+        },
+        required: ['metricId', 'evalType', 'outputType'],
+      },
       {
         type: 'object',
         properties: {
@@ -236,7 +354,7 @@ export const tool: Tool = {
           },
           guidelines: {
             type: 'string',
-            description: 'Optional guidelines for heuristic evaluation logic.',
+            description: 'Guidelines for heuristic evaluation logic.',
           },
           name: {
             type: 'string',

package/src/tools/records/list-records.ts

@@ -0,0 +1,58 @@
+// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+import { maybeFilter } from 'scorecard-ai-mcp/filtering';
+import { Metadata, asTextContentResult } from 'scorecard-ai-mcp/tools/types';
+
+import { Tool } from '@modelcontextprotocol/sdk/types.js';
+import Scorecard from 'scorecard-ai';
+
+export const metadata: Metadata = {
+  resource: 'records',
+  operation: 'read',
+  tags: [],
+  httpMethod: 'get',
+  httpPath: '/runs/{runId}/records',
+  operationId: 'listRecords',
+};
+
+export const tool: Tool = {
+  name: 'list_records',
+  description:
+    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nRetrieve a paginated list of Records for a Run, including all scores for each record.\n\n# Response Schema\n```json\n{\n  type: 'object',\n  properties: {\n    data: {\n      type: 'array',\n      items: {\n        $ref: '#/$defs/record_list_response'\n      }\n    },\n    hasMore: {\n      type: 'boolean'\n    },\n    nextCursor: {\n      type: 'string'\n    },\n    total: {\n      type: 'integer'\n    }\n  },\n  required: [    'data',\n    'hasMore',\n    'nextCursor'\n  ],\n  $defs: {\n    record_list_response: {\n      allOf: [        {\n          $ref: '#/$defs/record'\n        }\n      ],\n      description: 'A record with all its associated scores.'\n    },\n    record: {\n      type: 'object',\n      description: 'A record of a system execution in the Scorecard system.',\n      properties: {\n        id: {\n          type: 'string',\n          description: 'The ID of the Record.'\n        },\n        expected: {\n          type: 'object',\n          description: 'The expected outputs for the Testcase.',\n          additionalProperties: true\n        },\n        inputs: {\n          type: 'object',\n          description: 'The actual inputs sent to the system, which should match the system\\'s input schema.',\n          additionalProperties: true\n        },\n        outputs: {\n          type: 'object',\n          description: 'The actual outputs from the system.',\n          additionalProperties: true\n        },\n        runId: {\n          type: 'string',\n          description: 'The ID of the Run containing this Record.'\n        },\n        testcaseId: {\n          type: 'string',\n          description: 'The ID of the Testcase.'\n        }\n      },\n      required: [        'id',\n        'expected',\n        'inputs',\n        'outputs',\n        'runId'\n      ]\n    }\n  }\n}\n```",
+  inputSchema: {
+    type: 'object',
+    properties: {
+      runId: {
+        type: 'string',
+      },
+      cursor: {
+        type: 'string',
+        description:
+          'Cursor for pagination. Pass the `nextCursor` from the previous response to get the next page of results.',
+      },
+      limit: {
+        type: 'integer',
+        description:
+          'Maximum number of items to return (1-100). Use with `cursor` for pagination through large sets.',
+      },
+      jq_filter: {
+        type: 'string',
+        title: 'jq Filter',
+        description:
+          'A jq filter to apply to the response to include certain fields. Consult the output schema in the tool description to see the fields that are available.\n\nFor example: to include only the `name` field in every object of a results array, you can provide ".results[].name".\n\nFor more information, see the [jq documentation](https://jqlang.org/manual/).',
+      },
+    },
+    required: ['runId'],
+  },
+  annotations: {
+    readOnlyHint: true,
+  },
+};
+
+export const handler = async (client: Scorecard, args: Record<string, unknown> | undefined) => {
+  const { runId, jq_filter, ...body } = args as any;
+  const response = await client.records.list(runId, body).asResponse();
+  return asTextContentResult(await maybeFilter(jq_filter, await response.json()));
+};
+
+export default { metadata, tool, handler };

package/src/tools/runs/create-runs.ts

@@ -18,7 +18,7 @@ export const metadata: Metadata = {
 export const tool: Tool = {
   name: 'create_runs',
   description:
-    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nCreate a new Run.\n\n# Response Schema\n```json\n{\n  $ref: '#/$defs/run',\n  $defs: {\n    run: {\n      type: 'object',\n      description: 'A Run in the Scorecard system.',\n      properties: {\n        id: {\n          type: 'string',\n          description: 'The ID of the Run.'\n        },\n        metricIds: {\n          type: 'array',\n          description: 'The IDs of the metrics this Run is using.',\n          items: {\n            type: 'string'\n          }\n        },\n        status: {\n          type: 'string',\n          description: 'The status of the Run.',\n          enum: [            'pending',\n            'awaiting_execution',\n            'running_execution',\n            'awaiting_scoring',\n            'running_scoring',\n            'awaiting_human_scoring',\n            'completed'\n          ]\n        },\n        testsetId: {\n          type: 'string',\n          description: 'The ID of the Testset this Run is testing.'\n        },\n        systemVersionId: {\n          type: 'string',\n          description: 'The ID of the system version this Run is using.'\n        }\n      },\n      required: [        'id',\n        'metricIds',\n        'status',\n        'testsetId'\n      ]\n    }\n  }\n}\n```",
+    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nCreate a new Run.\n\n# Response Schema\n```json\n{\n  $ref: '#/$defs/run',\n  $defs: {\n    run: {\n      type: 'object',\n      description: 'A Run in the Scorecard system.',\n      properties: {\n        id: {\n          type: 'string',\n          description: 'The ID of the Run.'\n        },\n        metricIds: {\n          type: 'array',\n          description: 'The IDs of the metrics this Run is using.',\n          items: {\n            type: 'string'\n          }\n        },\n        metricVersionIds: {\n          type: 'array',\n          description: 'The IDs of the metric versions this Run is using.',\n          items: {\n            type: 'string'\n          }\n        },\n        numExpectedRecords: {\n          type: 'number',\n          description: 'The number of expected records in the Run. Determined by the number of testcases in the Run\\'s Testset at the time of Run creation.'\n        },\n        numRecords: {\n          type: 'number',\n          description: 'The number of records in the Run.'\n        },\n        numScores: {\n          type: 'number',\n          description: 'The number of completed scores in the Run so far.'\n        },\n        status: {\n          type: 'string',\n          description: 'The status of the Run.',\n          enum: [            'pending',\n            'awaiting_execution',\n            'running_execution',\n            'awaiting_scoring',\n            'running_scoring',\n            'awaiting_human_scoring',\n            'completed'\n          ]\n        },\n        systemId: {\n          type: 'string',\n          description: 'The ID of the system this Run is using.'\n        },\n        systemVersionId: {\n          type: 'string',\n          description: 'The ID of the system version this Run is using.'\n        },\n        testsetId: {\n          type: 'string',\n          description: 'The ID of the Testset this Run is testing.'\n        }\n      },\n      required: [        'id',\n        'metricIds',\n        'metricVersionIds',\n        'numExpectedRecords',\n        'numRecords',\n        'numScores',\n        'status',\n        'systemId',\n        'systemVersionId',\n        'testsetId'\n      ]\n    }\n  }\n}\n```",
   inputSchema: {
     type: 'object',
     properties: {

package/src/tools/runs/get-runs.ts

@@ -0,0 +1,47 @@
+// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+import { maybeFilter } from 'scorecard-ai-mcp/filtering';
+import { Metadata, asTextContentResult } from 'scorecard-ai-mcp/tools/types';
+
+import { Tool } from '@modelcontextprotocol/sdk/types.js';
+import Scorecard from 'scorecard-ai';
+
+export const metadata: Metadata = {
+  resource: 'runs',
+  operation: 'read',
+  tags: [],
+  httpMethod: 'get',
+  httpPath: '/runs/{runId}',
+  operationId: 'getRun',
+};
+
+export const tool: Tool = {
+  name: 'get_runs',
+  description:
+    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nRetrieve a specific Run by ID.\n\n# Response Schema\n```json\n{\n  $ref: '#/$defs/run',\n  $defs: {\n    run: {\n      type: 'object',\n      description: 'A Run in the Scorecard system.',\n      properties: {\n        id: {\n          type: 'string',\n          description: 'The ID of the Run.'\n        },\n        metricIds: {\n          type: 'array',\n          description: 'The IDs of the metrics this Run is using.',\n          items: {\n            type: 'string'\n          }\n        },\n        metricVersionIds: {\n          type: 'array',\n          description: 'The IDs of the metric versions this Run is using.',\n          items: {\n            type: 'string'\n          }\n        },\n        numExpectedRecords: {\n          type: 'number',\n          description: 'The number of expected records in the Run. Determined by the number of testcases in the Run\\'s Testset at the time of Run creation.'\n        },\n        numRecords: {\n          type: 'number',\n          description: 'The number of records in the Run.'\n        },\n        numScores: {\n          type: 'number',\n          description: 'The number of completed scores in the Run so far.'\n        },\n        status: {\n          type: 'string',\n          description: 'The status of the Run.',\n          enum: [            'pending',\n            'awaiting_execution',\n            'running_execution',\n            'awaiting_scoring',\n            'running_scoring',\n            'awaiting_human_scoring',\n            'completed'\n          ]\n        },\n        systemId: {\n          type: 'string',\n          description: 'The ID of the system this Run is using.'\n        },\n        systemVersionId: {\n          type: 'string',\n          description: 'The ID of the system version this Run is using.'\n        },\n        testsetId: {\n          type: 'string',\n          description: 'The ID of the Testset this Run is testing.'\n        }\n      },\n      required: [        'id',\n        'metricIds',\n        'metricVersionIds',\n        'numExpectedRecords',\n        'numRecords',\n        'numScores',\n        'status',\n        'systemId',\n        'systemVersionId',\n        'testsetId'\n      ]\n    }\n  }\n}\n```",
+  inputSchema: {
+    type: 'object',
+    properties: {
+      runId: {
+        type: 'string',
+      },
+      jq_filter: {
+        type: 'string',
+        title: 'jq Filter',
+        description:
+          'A jq filter to apply to the response to include certain fields. Consult the output schema in the tool description to see the fields that are available.\n\nFor example: to include only the `name` field in every object of a results array, you can provide ".results[].name".\n\nFor more information, see the [jq documentation](https://jqlang.org/manual/).',
+      },
+    },
+    required: ['runId'],
+  },
+  annotations: {
+    readOnlyHint: true,
+  },
+};
+
+export const handler = async (client: Scorecard, args: Record<string, unknown> | undefined) => {
+  const { runId, jq_filter, ...body } = args as any;
+  return asTextContentResult(await maybeFilter(jq_filter, await client.runs.get(runId)));
+};
+
+export default { metadata, tool, handler };

package/src/tools/runs/list-runs.ts

@@ -0,0 +1,58 @@
+// File generated from our OpenAPI spec by Stainless. See CONTRIBUTING.md for details.
+
+import { maybeFilter } from 'scorecard-ai-mcp/filtering';
+import { Metadata, asTextContentResult } from 'scorecard-ai-mcp/tools/types';
+
+import { Tool } from '@modelcontextprotocol/sdk/types.js';
+import Scorecard from 'scorecard-ai';
+
+export const metadata: Metadata = {
+  resource: 'runs',
+  operation: 'read',
+  tags: [],
+  httpMethod: 'get',
+  httpPath: '/projects/{projectId}/runs',
+  operationId: 'listRuns',
+};
+
+export const tool: Tool = {
+  name: 'list_runs',
+  description:
+    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nRetrieve a paginated list of all Runs for a Project. Runs are ordered by creation date, most recent first.\n\n# Response Schema\n```json\n{\n  type: 'object',\n  properties: {\n    data: {\n      type: 'array',\n      items: {\n        $ref: '#/$defs/run'\n      }\n    },\n    hasMore: {\n      type: 'boolean'\n    },\n    nextCursor: {\n      type: 'string'\n    },\n    total: {\n      type: 'integer'\n    }\n  },\n  required: [    'data',\n    'hasMore',\n    'nextCursor'\n  ],\n  $defs: {\n    run: {\n      type: 'object',\n      description: 'A Run in the Scorecard system.',\n      properties: {\n        id: {\n          type: 'string',\n          description: 'The ID of the Run.'\n        },\n        metricIds: {\n          type: 'array',\n          description: 'The IDs of the metrics this Run is using.',\n          items: {\n            type: 'string'\n          }\n        },\n        metricVersionIds: {\n          type: 'array',\n          description: 'The IDs of the metric versions this Run is using.',\n          items: {\n            type: 'string'\n          }\n        },\n        numExpectedRecords: {\n          type: 'number',\n          description: 'The number of expected records in the Run. Determined by the number of testcases in the Run\\'s Testset at the time of Run creation.'\n        },\n        numRecords: {\n          type: 'number',\n          description: 'The number of records in the Run.'\n        },\n        numScores: {\n          type: 'number',\n          description: 'The number of completed scores in the Run so far.'\n        },\n        status: {\n          type: 'string',\n          description: 'The status of the Run.',\n          enum: [            'pending',\n            'awaiting_execution',\n            'running_execution',\n            'awaiting_scoring',\n            'running_scoring',\n            'awaiting_human_scoring',\n            'completed'\n          ]\n        },\n        systemId: {\n          type: 'string',\n          description: 'The ID of the system this Run is using.'\n        },\n        systemVersionId: {\n          type: 'string',\n          description: 'The ID of the system version this Run is using.'\n        },\n        testsetId: {\n          type: 'string',\n          description: 'The ID of the Testset this Run is testing.'\n        }\n      },\n      required: [        'id',\n        'metricIds',\n        'metricVersionIds',\n        'numExpectedRecords',\n        'numRecords',\n        'numScores',\n        'status',\n        'systemId',\n        'systemVersionId',\n        'testsetId'\n      ]\n    }\n  }\n}\n```",
+  inputSchema: {
+    type: 'object',
+    properties: {
+      projectId: {
+        type: 'string',
+      },
+      cursor: {
+        type: 'string',
+        description:
+          'Cursor for pagination. Pass the `nextCursor` from the previous response to get the next page of results.',
+      },
+      limit: {
+        type: 'integer',
+        description:
+          'Maximum number of items to return (1-100). Use with `cursor` for pagination through large sets.',
+      },
+      jq_filter: {
+        type: 'string',
+        title: 'jq Filter',
+        description:
+          'A jq filter to apply to the response to include certain fields. Consult the output schema in the tool description to see the fields that are available.\n\nFor example: to include only the `name` field in every object of a results array, you can provide ".results[].name".\n\nFor more information, see the [jq documentation](https://jqlang.org/manual/).',
+      },
+    },
+    required: ['projectId'],
+  },
+  annotations: {
+    readOnlyHint: true,
+  },
+};
+
+export const handler = async (client: Scorecard, args: Record<string, unknown> | undefined) => {
+  const { projectId, jq_filter, ...body } = args as any;
+  const response = await client.runs.list(projectId, body).asResponse();
+  return asTextContentResult(await maybeFilter(jq_filter, await response.json()));
+};
+
+export default { metadata, tool, handler };

package/src/tools/systems/delete-systems.ts

@@ -18,7 +18,7 @@ export const metadata: Metadata = {
 export const tool: Tool = {
   name: 'delete_systems',
   description:
-    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nDelete a system definition by ID. This will not delete associated system versions.\n\n# Response Schema\n```json\n{\n  type: 'object',\n  properties: {\n    success: {\n      type: 'boolean',\n      description: 'Whether the deletion was successful.'\n    }\n  },\n  required: [    'success'\n  ]\n}\n```",
+    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nDelete a system definition by ID. This will not delete associated system versions.\n\n# Response Schema\n```json\n{\n  $ref: '#/$defs/system_delete_response',\n  $defs: {\n    system_delete_response: {\n      type: 'object',\n      properties: {\n        success: {\n          type: 'boolean',\n          description: 'Whether the deletion was successful.'\n        }\n      },\n      required: [        'success'\n      ]\n    }\n  }\n}\n```",
   inputSchema: {
     type: 'object',
     properties: {

package/src/tools/testcases/create-testcases.ts

@@ -18,7 +18,7 @@ export const metadata: Metadata = {
 export const tool: Tool = {
   name: 'create_testcases',
   description:
-    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nCreate multiple Testcases in the specified Testset.\n\n# Response Schema\n```json\n{\n  type: 'object',\n  properties: {\n    items: {\n      type: 'array',\n      items: {\n        $ref: '#/$defs/testcase'\n      }\n    }\n  },\n  required: [    'items'\n  ],\n  $defs: {\n    testcase: {\n      type: 'object',\n      description: 'A test case in the Scorecard system. Contains JSON data that is validated against the schema defined by its Testset.\\nThe `inputs` and `expected` fields are derived from the `data` field based on the Testset\\'s `fieldMapping`, and include all mapped fields, including those with validation errors.\\nTestcases are stored regardless of validation results, with any validation errors included in the `validationErrors` field.',\n      properties: {\n        id: {\n          type: 'string',\n          description: 'The ID of the Testcase.'\n        },\n        expected: {\n          type: 'object',\n          description: 'Derived from data based on the Testset\\'s fieldMapping. Contains all fields marked as expected outputs, including those with validation errors.',\n          additionalProperties: true\n        },\n        inputs: {\n          type: 'object',\n          description: 'Derived from data based on the Testset\\'s fieldMapping. Contains all fields marked as inputs, including those with validation errors.',\n          additionalProperties: true\n        },\n        jsonData: {\n          type: 'object',\n          description: 'The JSON data of the Testcase, which is validated against the Testset\\'s schema.',\n          additionalProperties: true\n        },\n        testsetId: {\n          type: 'string',\n          description: 'The ID of the Testset this Testcase belongs to.'\n        },\n        validationErrors: {\n          type: 'array',\n          description: 'Validation errors found in the Testcase data. If present, the Testcase doesn\\'t fully conform to its Testset\\'s schema.',\n          items: {\n            type: 'object',\n            properties: {\n              message: {\n                type: 'string',\n                description: 'Human-readable error description.'\n              },\n              path: {\n                type: 'string',\n                description: 'JSON Pointer to the field with the validation error.'\n              }\n            },\n            required: [              'message',\n              'path'\n            ]\n          }\n        }\n      },\n      required: [        'id',\n        'expected',\n        'inputs',\n        'jsonData',\n        'testsetId'\n      ]\n    }\n  }\n}\n```",
+    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nCreate multiple Testcases in the specified Testset.\n\n# Response Schema\n```json\n{\n  $ref: '#/$defs/testcase_create_response',\n  $defs: {\n    testcase_create_response: {\n      type: 'object',\n      properties: {\n        items: {\n          type: 'array',\n          items: {\n            $ref: '#/$defs/testcase'\n          }\n        }\n      },\n      required: [        'items'\n      ]\n    },\n    testcase: {\n      type: 'object',\n      description: 'A test case in the Scorecard system. Contains JSON data that is validated against the schema defined by its Testset.\\nThe `inputs` and `expected` fields are derived from the `data` field based on the Testset\\'s `fieldMapping`, and include all mapped fields, including those with validation errors.\\nTestcases are stored regardless of validation results, with any validation errors included in the `validationErrors` field.',\n      properties: {\n        id: {\n          type: 'string',\n          description: 'The ID of the Testcase.'\n        },\n        expected: {\n          type: 'object',\n          description: 'Derived from data based on the Testset\\'s fieldMapping. Contains all fields marked as expected outputs, including those with validation errors.',\n          additionalProperties: true\n        },\n        inputs: {\n          type: 'object',\n          description: 'Derived from data based on the Testset\\'s fieldMapping. Contains all fields marked as inputs, including those with validation errors.',\n          additionalProperties: true\n        },\n        jsonData: {\n          type: 'object',\n          description: 'The JSON data of the Testcase, which is validated against the Testset\\'s schema.',\n          additionalProperties: true\n        },\n        testsetId: {\n          type: 'string',\n          description: 'The ID of the Testset this Testcase belongs to.'\n        },\n        validationErrors: {\n          type: 'array',\n          description: 'Validation errors found in the Testcase data. If present, the Testcase doesn\\'t fully conform to its Testset\\'s schema.',\n          items: {\n            type: 'object',\n            properties: {\n              message: {\n                type: 'string',\n                description: 'Human-readable error description.'\n              },\n              path: {\n                type: 'string',\n                description: 'JSON Pointer to the field with the validation error.'\n              }\n            },\n            required: [              'message',\n              'path'\n            ]\n          }\n        }\n      },\n      required: [        'id',\n        'expected',\n        'inputs',\n        'jsonData',\n        'testsetId'\n      ]\n    }\n  }\n}\n```",
   inputSchema: {
     type: 'object',
     properties: {

package/src/tools/testcases/delete-testcases.ts

@@ -18,7 +18,7 @@ export const metadata: Metadata = {
 export const tool: Tool = {
   name: 'delete_testcases',
   description:
-    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nDelete multiple Testcases by their IDs.\n\n# Response Schema\n```json\n{\n  type: 'object',\n  properties: {\n    success: {\n      type: 'boolean',\n      description: 'Whether the deletion was successful.'\n    }\n  },\n  required: [    'success'\n  ]\n}\n```",
+    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nDelete multiple Testcases by their IDs.\n\n# Response Schema\n```json\n{\n  $ref: '#/$defs/testcase_delete_response',\n  $defs: {\n    testcase_delete_response: {\n      type: 'object',\n      properties: {\n        success: {\n          type: 'boolean',\n          description: 'Whether the deletion was successful.'\n        }\n      },\n      required: [        'success'\n      ]\n    }\n  }\n}\n```",
   inputSchema: {
     type: 'object',
     properties: {

package/src/tools/testsets/delete-testsets.ts

@@ -18,7 +18,7 @@ export const metadata: Metadata = {
 export const tool: Tool = {
   name: 'delete_testsets',
   description:
-    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nDelete Testset\n\n# Response Schema\n```json\n{\n  type: 'object',\n  properties: {\n    success: {\n      type: 'boolean',\n      description: 'Whether the deletion was successful.'\n    }\n  },\n  required: [    'success'\n  ]\n}\n```",
+    "When using this tool, always use the `jq_filter` parameter to reduce the response size and improve performance.\n\nOnly omit if you're sure you don't need the data.\n\nDelete Testset\n\n# Response Schema\n```json\n{\n  $ref: '#/$defs/testset_delete_response',\n  $defs: {\n    testset_delete_response: {\n      type: 'object',\n      properties: {\n        success: {\n          type: 'boolean',\n          description: 'Whether the deletion was successful.'\n        }\n      },\n      required: [        'success'\n      ]\n    }\n  }\n}\n```",
   inputSchema: {
     type: 'object',
     properties: {

package/tools/index.d.mts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.mts","sourceRoot":"","sources":["../src/tools/index.ts"],"names":[],"mappings":"OAEO,EAAE,QAAQ,EAAE,QAAQ,EAAE,eAAe,EAAE;AAE9C,OAAO,EAAE,QAAQ,EAAE,QAAQ,EAAE,eAAe,EAAE,CAAC;AA2B/C,eAAO,MAAM,SAAS,EAAE,QAAQ,EAAO,CAAC;AA+BxC,MAAM,MAAM,MAAM,GAAG;IACnB,IAAI,EAAE,UAAU,GAAG,WAAW,GAAG,KAAK,GAAG,MAAM,CAAC;IAChD,EAAE,EAAE,SAAS,GAAG,SAAS,CAAC;IAC1B,KAAK,EAAE,MAAM,CAAC;CACf,CAAC;AAEF,wBAAgB,KAAK,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,QAAQ,EAAE,GAAG,QAAQ,EAAE,CA4B1E"}
+{"version":3,"file":"index.d.mts","sourceRoot":"","sources":["../src/tools/index.ts"],"names":[],"mappings":"OAEO,EAAE,QAAQ,EAAE,QAAQ,EAAE,eAAe,EAAE;AAE9C,OAAO,EAAE,QAAQ,EAAE,QAAQ,EAAE,eAAe,EAAE,CAAC;AAgC/C,eAAO,MAAM,SAAS,EAAE,QAAQ,EAAO,CAAC;AAoCxC,MAAM,MAAM,MAAM,GAAG;IACnB,IAAI,EAAE,UAAU,GAAG,WAAW,GAAG,KAAK,GAAG,MAAM,CAAC;IAChD,EAAE,EAAE,SAAS,GAAG,SAAS,CAAC;IAC1B,KAAK,EAAE,MAAM,CAAC;CACf,CAAC;AAEF,wBAAgB,KAAK,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,QAAQ,EAAE,GAAG,QAAQ,EAAE,CA4B1E"}

package/tools/index.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/tools/index.ts"],"names":[],"mappings":"OAEO,EAAE,QAAQ,EAAE,QAAQ,EAAE,eAAe,EAAE;AAE9C,OAAO,EAAE,QAAQ,EAAE,QAAQ,EAAE,eAAe,EAAE,CAAC;AA2B/C,eAAO,MAAM,SAAS,EAAE,QAAQ,EAAO,CAAC;AA+BxC,MAAM,MAAM,MAAM,GAAG;IACnB,IAAI,EAAE,UAAU,GAAG,WAAW,GAAG,KAAK,GAAG,MAAM,CAAC;IAChD,EAAE,EAAE,SAAS,GAAG,SAAS,CAAC;IAC1B,KAAK,EAAE,MAAM,CAAC;CACf,CAAC;AAEF,wBAAgB,KAAK,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,QAAQ,EAAE,GAAG,QAAQ,EAAE,CA4B1E"}
+{"version":3,"file":"index.d.ts","sourceRoot":"","sources":["../src/tools/index.ts"],"names":[],"mappings":"OAEO,EAAE,QAAQ,EAAE,QAAQ,EAAE,eAAe,EAAE;AAE9C,OAAO,EAAE,QAAQ,EAAE,QAAQ,EAAE,eAAe,EAAE,CAAC;AAgC/C,eAAO,MAAM,SAAS,EAAE,QAAQ,EAAO,CAAC;AAoCxC,MAAM,MAAM,MAAM,GAAG;IACnB,IAAI,EAAE,UAAU,GAAG,WAAW,GAAG,KAAK,GAAG,MAAM,CAAC;IAChD,EAAE,EAAE,SAAS,GAAG,SAAS,CAAC;IAC1B,KAAK,EAAE,MAAM,CAAC;CACf,CAAC;AAEF,wBAAgB,KAAK,CAAC,OAAO,EAAE,MAAM,EAAE,EAAE,SAAS,EAAE,QAAQ,EAAE,GAAG,QAAQ,EAAE,CA4B1E"}

package/tools/index.js

@@ -19,9 +19,14 @@ const list_testcases_1 = __importDefault(require("./testcases/list-testcases.js"
 const delete_testcases_1 = __importDefault(require("./testcases/delete-testcases.js"));
 const get_testcases_1 = __importDefault(require("./testcases/get-testcases.js"));
 const create_runs_1 = __importDefault(require("./runs/create-runs.js"));
+const list_runs_1 = __importDefault(require("./runs/list-runs.js"));
+const get_runs_1 = __importDefault(require("./runs/get-runs.js"));
 const create_metrics_1 = __importDefault(require("./metrics/create-metrics.js"));
 const update_metrics_1 = __importDefault(require("./metrics/update-metrics.js"));
+const list_metrics_1 = __importDefault(require("./metrics/list-metrics.js"));
+const get_metrics_1 = __importDefault(require("./metrics/get-metrics.js"));
 const create_records_1 = __importDefault(require("./records/create-records.js"));
+const list_records_1 = __importDefault(require("./records/list-records.js"));
 const upsert_scores_1 = __importDefault(require("./scores/upsert-scores.js"));
 const update_systems_1 = __importDefault(require("./systems/update-systems.js"));
 const list_systems_1 = __importDefault(require("./systems/list-systems.js"));
@@ -47,9 +52,14 @@ addEndpoint(list_testcases_1.default);
 addEndpoint(delete_testcases_1.default);
 addEndpoint(get_testcases_1.default);
 addEndpoint(create_runs_1.default);
+addEndpoint(list_runs_1.default);
+addEndpoint(get_runs_1.default);
 addEndpoint(create_metrics_1.default);
 addEndpoint(update_metrics_1.default);
+addEndpoint(list_metrics_1.default);
+addEndpoint(get_metrics_1.default);
 addEndpoint(create_records_1.default);
+addEndpoint(list_records_1.default);
 addEndpoint(upsert_scores_1.default);
 addEndpoint(update_systems_1.default);
 addEndpoint(list_systems_1.default);

package/tools/index.js.map

@@ -1 +1 @@
-{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/tools/index.ts"],"names":[],"mappings":";AAAA,sFAAsF;;;;;;AAoEtF,sBA4BC;AA1FD,oFAAyD;AACzD,gFAAqD;AACrD,oFAAyD;AACzD,oFAAyD;AACzD,gFAAqD;AACrD,oFAAyD;AACzD,8EAAmD;AACnD,uFAA4D;AAC5D,uFAA4D;AAC5D,mFAAwD;AACxD,uFAA4D;AAC5D,iFAAsD;AACtD,wEAA6C;AAC7C,iFAAsD;AACtD,iFAAsD;AACtD,iFAAsD;AACtD,8EAAmD;AACnD,iFAAsD;AACtD,6EAAkD;AAClD,iFAAsD;AACtD,2EAAgD;AAChD,iFAAsD;AACtD,sGAA2E;AAC3E,4GAAiF;AAEpE,QAAA,SAAS,GAAe,EAAE,CAAC;AAExC,SAAS,WAAW,CAAC,QAAkB;IACrC,iBAAS,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;AAC3B,CAAC;AAED,WAAW,CAAC,yBAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,uBAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,yBAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,yBAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,uBAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,yBAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,sBAAY,CAAC,CAAC;AAC1B,WAAW,CAAC,0BAAgB,CAAC,CAAC;AAC9B,WAAW,CAAC,0BAAgB,CAAC,CAAC;AAC9B,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,0BAAgB,CAAC,CAAC;AAC9B,WAAW,CAAC,uBAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,qBAAW,CAAC,CAAC;AACzB,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,uBAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,sBAAY,CAAC,CAAC;AAC1B,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,qBAAW,CAAC,CAAC;AACzB,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,8BAAoB,CAAC,CAAC;AAClC,WAAW,CAAC,iCAAuB,CAAC,CAAC;AAQrC,SAAgB,KAAK,CAAC,OAAiB,EAAE,SAAqB;IAC5D,MAAM,WAAW,GAAG,OAAO,CAAC,MAAM,GAAG,CAAC,IAAI,OAAO,CAAC,KAAK,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,EAAE,KAAK,SAAS,CAAC,CAAC;IAC7F,MAAM,gBAAgB,GAAG,IAAI,GAAG,CAAC,OAAO,CAAC,CAAC;IAE1C,MAAM,QAAQ,GAAG,SAAS,CAAC,MAAM,CAAC,CAAC,QAAkB,EAAE,EAAE;QACvD,IAAI,QAAQ,GAAG,KAAK,IAAI,WAAW,CAAC;QAEpC,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;YAC7B,IAAI,KAAK,CAAC,MAAM,EAAE,QAAQ,CAAC,EAAE,CAAC;gBAC5B,gBAAgB,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;gBAChC,QAAQ,GAAG,MAAM,CAAC,EAAE,KAAK,SAAS,CAAC;YACrC,CAAC;QACH,CAAC;QAED,OAAO,QAAQ,CAAC;IAClB,CAAC,CAAC,CAAC;IAEH,oCAAoC;IACpC,MAAM,SAAS,GAAG,KAAK,CAAC,IAAI,CAAC,gBAAgB,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,MAAM,IAAI,CAAC,CAAC,IAAI,KAAK,UAAU,CAAC,CAAC;IACzG,IAAI,SAAS,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACzB,MAAM,IAAI,KAAK,CACb,sDAAsD,SAAS;aAC5D,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,CAAC,IAAI,IAAI,CAAC,CAAC,KAAK,EAAE,CAAC;aAClC,IAAI,CAAC,IAAI,CAAC,EAAE,CAChB,CAAC;IACJ,CAAC;IAED,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED,SAAS,KAAK,CAAC,EAAE,IAAI,EAAE,KAAK,EAAU,EAAE,QAAkB;IACxD,QAAQ,IAAI,EAAE,CAAC;QACb,KAAK,UAAU,CAAC,CAAC,CAAC;YAChB,MAAM,QAAQ,GAAG,GAAG,GAAG,iBAAiB,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC,GAAG,GAAG,CAAC;YAC3E,MAAM,KAAK,GAAG,IAAI,MAAM,CAAC,QAAQ,CAAC,CAAC;YACnC,OAAO,KAAK,CAAC,IAAI,CAAC,iBAAiB,CAAC,QAAQ,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC;QACnE,CAAC;QACD,KAAK,WAAW;YACd,OAAO,QAAQ,CAAC,QAAQ,CAAC,SAAS,KAAK,KAAK,CAAC;QAC/C,KAAK,KAAK;YACR,OAAO,QAAQ,CAAC,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC;QAChD,KAAK,MAAM;YACT,OAAO,QAAQ,CAAC,IAAI,CAAC,IAAI,KAAK,KAAK,CAAC;IACxC,CAAC;AACH,CAAC;AAED,SAAS,iBAAiB,CAAC,QAAgB;IACzC,OAAO,QAAQ,CAAC,WAAW,EAAE,CAAC,OAAO,CAAC,eAAe,EAAE,EAAE,CAAC,CAAC;AAC7D,CAAC"}
+{"version":3,"file":"index.js","sourceRoot":"","sources":["../src/tools/index.ts"],"names":[],"mappings":";AAAA,sFAAsF;;;;;;AA8EtF,sBA4BC;AApGD,oFAAyD;AACzD,gFAAqD;AACrD,oFAAyD;AACzD,oFAAyD;AACzD,gFAAqD;AACrD,oFAAyD;AACzD,8EAAmD;AACnD,uFAA4D;AAC5D,uFAA4D;AAC5D,mFAAwD;AACxD,uFAA4D;AAC5D,iFAAsD;AACtD,wEAA6C;AAC7C,oEAAyC;AACzC,kEAAuC;AACvC,iFAAsD;AACtD,iFAAsD;AACtD,6EAAkD;AAClD,2EAAgD;AAChD,iFAAsD;AACtD,6EAAkD;AAClD,8EAAmD;AACnD,iFAAsD;AACtD,6EAAkD;AAClD,iFAAsD;AACtD,2EAAgD;AAChD,iFAAsD;AACtD,sGAA2E;AAC3E,4GAAiF;AAEpE,QAAA,SAAS,GAAe,EAAE,CAAC;AAExC,SAAS,WAAW,CAAC,QAAkB;IACrC,iBAAS,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;AAC3B,CAAC;AAED,WAAW,CAAC,yBAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,uBAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,yBAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,yBAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,uBAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,yBAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,sBAAY,CAAC,CAAC;AAC1B,WAAW,CAAC,0BAAgB,CAAC,CAAC;AAC9B,WAAW,CAAC,0BAAgB,CAAC,CAAC;AAC9B,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,0BAAgB,CAAC,CAAC;AAC9B,WAAW,CAAC,uBAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,qBAAW,CAAC,CAAC;AACzB,WAAW,CAAC,mBAAS,CAAC,CAAC;AACvB,WAAW,CAAC,kBAAQ,CAAC,CAAC;AACtB,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,sBAAY,CAAC,CAAC;AAC1B,WAAW,CAAC,qBAAW,CAAC,CAAC;AACzB,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,sBAAY,CAAC,CAAC;AAC1B,WAAW,CAAC,uBAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,sBAAY,CAAC,CAAC;AAC1B,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,qBAAW,CAAC,CAAC;AACzB,WAAW,CAAC,wBAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,8BAAoB,CAAC,CAAC;AAClC,WAAW,CAAC,iCAAuB,CAAC,CAAC;AAQrC,SAAgB,KAAK,CAAC,OAAiB,EAAE,SAAqB;IAC5D,MAAM,WAAW,GAAG,OAAO,CAAC,MAAM,GAAG,CAAC,IAAI,OAAO,CAAC,KAAK,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,EAAE,KAAK,SAAS,CAAC,CAAC;IAC7F,MAAM,gBAAgB,GAAG,IAAI,GAAG,CAAC,OAAO,CAAC,CAAC;IAE1C,MAAM,QAAQ,GAAG,SAAS,CAAC,MAAM,CAAC,CAAC,QAAkB,EAAE,EAAE;QACvD,IAAI,QAAQ,GAAG,KAAK,IAAI,WAAW,CAAC;QAEpC,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;YAC7B,IAAI,KAAK,CAAC,MAAM,EAAE,QAAQ,CAAC,EAAE,CAAC;gBAC5B,gBAAgB,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;gBAChC,QAAQ,GAAG,MAAM,CAAC,EAAE,KAAK,SAAS,CAAC;YACrC,CAAC;QACH,CAAC;QAED,OAAO,QAAQ,CAAC;IAClB,CAAC,CAAC,CAAC;IAEH,oCAAoC;IACpC,MAAM,SAAS,GAAG,KAAK,CAAC,IAAI,CAAC,gBAAgB,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,MAAM,IAAI,CAAC,CAAC,IAAI,KAAK,UAAU,CAAC,CAAC;IACzG,IAAI,SAAS,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACzB,MAAM,IAAI,KAAK,CACb,sDAAsD,SAAS;aAC5D,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,CAAC,IAAI,IAAI,CAAC,CAAC,KAAK,EAAE,CAAC;aAClC,IAAI,CAAC,IAAI,CAAC,EAAE,CAChB,CAAC;IACJ,CAAC;IAED,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED,SAAS,KAAK,CAAC,EAAE,IAAI,EAAE,KAAK,EAAU,EAAE,QAAkB;IACxD,QAAQ,IAAI,EAAE,CAAC;QACb,KAAK,UAAU,CAAC,CAAC,CAAC;YAChB,MAAM,QAAQ,GAAG,GAAG,GAAG,iBAAiB,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC,GAAG,GAAG,CAAC;YAC3E,MAAM,KAAK,GAAG,IAAI,MAAM,CAAC,QAAQ,CAAC,CAAC;YACnC,OAAO,KAAK,CAAC,IAAI,CAAC,iBAAiB,CAAC,QAAQ,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC;QACnE,CAAC;QACD,KAAK,WAAW;YACd,OAAO,QAAQ,CAAC,QAAQ,CAAC,SAAS,KAAK,KAAK,CAAC;QAC/C,KAAK,KAAK;YACR,OAAO,QAAQ,CAAC,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC;QAChD,KAAK,MAAM;YACT,OAAO,QAAQ,CAAC,IAAI,CAAC,IAAI,KAAK,KAAK,CAAC;IACxC,CAAC;AACH,CAAC;AAED,SAAS,iBAAiB,CAAC,QAAgB;IACzC,OAAO,QAAQ,CAAC,WAAW,EAAE,CAAC,OAAO,CAAC,eAAe,EAAE,EAAE,CAAC,CAAC;AAC7D,CAAC"}

package/tools/index.mjs

@@ -12,9 +12,14 @@ import list_testcases from "./testcases/list-testcases.mjs";
 import delete_testcases from "./testcases/delete-testcases.mjs";
 import get_testcases from "./testcases/get-testcases.mjs";
 import create_runs from "./runs/create-runs.mjs";
+import list_runs from "./runs/list-runs.mjs";
+import get_runs from "./runs/get-runs.mjs";
 import create_metrics from "./metrics/create-metrics.mjs";
 import update_metrics from "./metrics/update-metrics.mjs";
+import list_metrics from "./metrics/list-metrics.mjs";
+import get_metrics from "./metrics/get-metrics.mjs";
 import create_records from "./records/create-records.mjs";
+import list_records from "./records/list-records.mjs";
 import upsert_scores from "./scores/upsert-scores.mjs";
 import update_systems from "./systems/update-systems.mjs";
 import list_systems from "./systems/list-systems.mjs";
@@ -40,9 +45,14 @@ addEndpoint(list_testcases);
 addEndpoint(delete_testcases);
 addEndpoint(get_testcases);
 addEndpoint(create_runs);
+addEndpoint(list_runs);
+addEndpoint(get_runs);
 addEndpoint(create_metrics);
 addEndpoint(update_metrics);
+addEndpoint(list_metrics);
+addEndpoint(get_metrics);
 addEndpoint(create_records);
+addEndpoint(list_records);
 addEndpoint(upsert_scores);
 addEndpoint(update_systems);
 addEndpoint(list_systems);

package/tools/index.mjs.map

@@ -1 +1 @@
-{"version":3,"file":"index.mjs","sourceRoot":"","sources":["../src/tools/index.ts"],"names":[],"mappings":"AAAA,sFAAsF;OAM/E,eAAe;OACf,aAAa;OACb,eAAe;OACf,eAAe;OACf,aAAa;OACb,eAAe;OACf,YAAY;OACZ,gBAAgB;OAChB,gBAAgB;OAChB,cAAc;OACd,gBAAgB;OAChB,aAAa;OACb,WAAW;OACX,cAAc;OACd,cAAc;OACd,cAAc;OACd,aAAa;OACb,cAAc;OACd,YAAY;OACZ,cAAc;OACd,WAAW;OACX,cAAc;OACd,oBAAoB;OACpB,uBAAuB;AAE9B,MAAM,CAAC,MAAM,SAAS,GAAe,EAAE,CAAC;AAExC,SAAS,WAAW,CAAC,QAAkB;IACrC,SAAS,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;AAC3B,CAAC;AAED,WAAW,CAAC,eAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,aAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,eAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,eAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,aAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,eAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,YAAY,CAAC,CAAC;AAC1B,WAAW,CAAC,gBAAgB,CAAC,CAAC;AAC9B,WAAW,CAAC,gBAAgB,CAAC,CAAC;AAC9B,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,gBAAgB,CAAC,CAAC;AAC9B,WAAW,CAAC,aAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,WAAW,CAAC,CAAC;AACzB,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,aAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,YAAY,CAAC,CAAC;AAC1B,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,WAAW,CAAC,CAAC;AACzB,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,oBAAoB,CAAC,CAAC;AAClC,WAAW,CAAC,uBAAuB,CAAC,CAAC;AAQrC,MAAM,UAAU,KAAK,CAAC,OAAiB,EAAE,SAAqB;IAC5D,MAAM,WAAW,GAAG,OAAO,CAAC,MAAM,GAAG,CAAC,IAAI,OAAO,CAAC,KAAK,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,EAAE,KAAK,SAAS,CAAC,CAAC;IAC7F,MAAM,gBAAgB,GAAG,IAAI,GAAG,CAAC,OAAO,CAAC,CAAC;IAE1C,MAAM,QAAQ,GAAG,SAAS,CAAC,MAAM,CAAC,CAAC,QAAkB,EAAE,EAAE;QACvD,IAAI,QAAQ,GAAG,KAAK,IAAI,WAAW,CAAC;QAEpC,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;YAC7B,IAAI,KAAK,CAAC,MAAM,EAAE,QAAQ,CAAC,EAAE,CAAC;gBAC5B,gBAAgB,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;gBAChC,QAAQ,GAAG,MAAM,CAAC,EAAE,KAAK,SAAS,CAAC;YACrC,CAAC;QACH,CAAC;QAED,OAAO,QAAQ,CAAC;IAClB,CAAC,CAAC,CAAC;IAEH,oCAAoC;IACpC,MAAM,SAAS,GAAG,KAAK,CAAC,IAAI,CAAC,gBAAgB,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,MAAM,IAAI,CAAC,CAAC,IAAI,KAAK,UAAU,CAAC,CAAC;IACzG,IAAI,SAAS,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACzB,MAAM,IAAI,KAAK,CACb,sDAAsD,SAAS;aAC5D,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,CAAC,IAAI,IAAI,CAAC,CAAC,KAAK,EAAE,CAAC;aAClC,IAAI,CAAC,IAAI,CAAC,EAAE,CAChB,CAAC;IACJ,CAAC;IAED,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED,SAAS,KAAK,CAAC,EAAE,IAAI,EAAE,KAAK,EAAU,EAAE,QAAkB;IACxD,QAAQ,IAAI,EAAE,CAAC;QACb,KAAK,UAAU,CAAC,CAAC,CAAC;YAChB,MAAM,QAAQ,GAAG,GAAG,GAAG,iBAAiB,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC,GAAG,GAAG,CAAC;YAC3E,MAAM,KAAK,GAAG,IAAI,MAAM,CAAC,QAAQ,CAAC,CAAC;YACnC,OAAO,KAAK,CAAC,IAAI,CAAC,iBAAiB,CAAC,QAAQ,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC;QACnE,CAAC;QACD,KAAK,WAAW;YACd,OAAO,QAAQ,CAAC,QAAQ,CAAC,SAAS,KAAK,KAAK,CAAC;QAC/C,KAAK,KAAK;YACR,OAAO,QAAQ,CAAC,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC;QAChD,KAAK,MAAM;YACT,OAAO,QAAQ,CAAC,IAAI,CAAC,IAAI,KAAK,KAAK,CAAC;IACxC,CAAC;AACH,CAAC;AAED,SAAS,iBAAiB,CAAC,QAAgB;IACzC,OAAO,QAAQ,CAAC,WAAW,EAAE,CAAC,OAAO,CAAC,eAAe,EAAE,EAAE,CAAC,CAAC;AAC7D,CAAC"}
+{"version":3,"file":"index.mjs","sourceRoot":"","sources":["../src/tools/index.ts"],"names":[],"mappings":"AAAA,sFAAsF;OAM/E,eAAe;OACf,aAAa;OACb,eAAe;OACf,eAAe;OACf,aAAa;OACb,eAAe;OACf,YAAY;OACZ,gBAAgB;OAChB,gBAAgB;OAChB,cAAc;OACd,gBAAgB;OAChB,aAAa;OACb,WAAW;OACX,SAAS;OACT,QAAQ;OACR,cAAc;OACd,cAAc;OACd,YAAY;OACZ,WAAW;OACX,cAAc;OACd,YAAY;OACZ,aAAa;OACb,cAAc;OACd,YAAY;OACZ,cAAc;OACd,WAAW;OACX,cAAc;OACd,oBAAoB;OACpB,uBAAuB;AAE9B,MAAM,CAAC,MAAM,SAAS,GAAe,EAAE,CAAC;AAExC,SAAS,WAAW,CAAC,QAAkB;IACrC,SAAS,CAAC,IAAI,CAAC,QAAQ,CAAC,CAAC;AAC3B,CAAC;AAED,WAAW,CAAC,eAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,aAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,eAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,eAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,aAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,eAAe,CAAC,CAAC;AAC7B,WAAW,CAAC,YAAY,CAAC,CAAC;AAC1B,WAAW,CAAC,gBAAgB,CAAC,CAAC;AAC9B,WAAW,CAAC,gBAAgB,CAAC,CAAC;AAC9B,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,gBAAgB,CAAC,CAAC;AAC9B,WAAW,CAAC,aAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,WAAW,CAAC,CAAC;AACzB,WAAW,CAAC,SAAS,CAAC,CAAC;AACvB,WAAW,CAAC,QAAQ,CAAC,CAAC;AACtB,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,YAAY,CAAC,CAAC;AAC1B,WAAW,CAAC,WAAW,CAAC,CAAC;AACzB,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,YAAY,CAAC,CAAC;AAC1B,WAAW,CAAC,aAAa,CAAC,CAAC;AAC3B,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,YAAY,CAAC,CAAC;AAC1B,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,WAAW,CAAC,CAAC;AACzB,WAAW,CAAC,cAAc,CAAC,CAAC;AAC5B,WAAW,CAAC,oBAAoB,CAAC,CAAC;AAClC,WAAW,CAAC,uBAAuB,CAAC,CAAC;AAQrC,MAAM,UAAU,KAAK,CAAC,OAAiB,EAAE,SAAqB;IAC5D,MAAM,WAAW,GAAG,OAAO,CAAC,MAAM,GAAG,CAAC,IAAI,OAAO,CAAC,KAAK,CAAC,CAAC,MAAM,EAAE,EAAE,CAAC,MAAM,CAAC,EAAE,KAAK,SAAS,CAAC,CAAC;IAC7F,MAAM,gBAAgB,GAAG,IAAI,GAAG,CAAC,OAAO,CAAC,CAAC;IAE1C,MAAM,QAAQ,GAAG,SAAS,CAAC,MAAM,CAAC,CAAC,QAAkB,EAAE,EAAE;QACvD,IAAI,QAAQ,GAAG,KAAK,IAAI,WAAW,CAAC;QAEpC,KAAK,MAAM,MAAM,IAAI,OAAO,EAAE,CAAC;YAC7B,IAAI,KAAK,CAAC,MAAM,EAAE,QAAQ,CAAC,EAAE,CAAC;gBAC5B,gBAAgB,CAAC,MAAM,CAAC,MAAM,CAAC,CAAC;gBAChC,QAAQ,GAAG,MAAM,CAAC,EAAE,KAAK,SAAS,CAAC;YACrC,CAAC;QACH,CAAC;QAED,OAAO,QAAQ,CAAC;IAClB,CAAC,CAAC,CAAC;IAEH,oCAAoC;IACpC,MAAM,SAAS,GAAG,KAAK,CAAC,IAAI,CAAC,gBAAgB,CAAC,CAAC,MAAM,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,CAAC,CAAC,IAAI,KAAK,MAAM,IAAI,CAAC,CAAC,IAAI,KAAK,UAAU,CAAC,CAAC;IACzG,IAAI,SAAS,CAAC,MAAM,GAAG,CAAC,EAAE,CAAC;QACzB,MAAM,IAAI,KAAK,CACb,sDAAsD,SAAS;aAC5D,GAAG,CAAC,CAAC,CAAC,EAAE,EAAE,CAAC,GAAG,CAAC,CAAC,IAAI,IAAI,CAAC,CAAC,KAAK,EAAE,CAAC;aAClC,IAAI,CAAC,IAAI,CAAC,EAAE,CAChB,CAAC;IACJ,CAAC;IAED,OAAO,QAAQ,CAAC;AAClB,CAAC;AAED,SAAS,KAAK,CAAC,EAAE,IAAI,EAAE,KAAK,EAAU,EAAE,QAAkB;IACxD,QAAQ,IAAI,EAAE,CAAC;QACb,KAAK,UAAU,CAAC,CAAC,CAAC;YAChB,MAAM,QAAQ,GAAG,GAAG,GAAG,iBAAiB,CAAC,KAAK,CAAC,CAAC,OAAO,CAAC,KAAK,EAAE,IAAI,CAAC,GAAG,GAAG,CAAC;YAC3E,MAAM,KAAK,GAAG,IAAI,MAAM,CAAC,QAAQ,CAAC,CAAC;YACnC,OAAO,KAAK,CAAC,IAAI,CAAC,iBAAiB,CAAC,QAAQ,CAAC,QAAQ,CAAC,QAAQ,CAAC,CAAC,CAAC;QACnE,CAAC;QACD,KAAK,WAAW;YACd,OAAO,QAAQ,CAAC,QAAQ,CAAC,SAAS,KAAK,KAAK,CAAC;QAC/C,KAAK,KAAK;YACR,OAAO,QAAQ,CAAC,QAAQ,CAAC,IAAI,CAAC,QAAQ,CAAC,KAAK,CAAC,CAAC;QAChD,KAAK,MAAM;YACT,OAAO,QAAQ,CAAC,IAAI,CAAC,IAAI,KAAK,KAAK,CAAC;IACxC,CAAC;AACH,CAAC;AAED,SAAS,iBAAiB,CAAC,QAAgB;IACzC,OAAO,QAAQ,CAAC,WAAW,EAAE,CAAC,OAAO,CAAC,eAAe,EAAE,EAAE,CAAC,CAAC;AAC7D,CAAC"}

package/tools/metrics/create-metrics.d.mts.map

@@ -1 +1 @@
-{"version":3,"file":"create-metrics.d.mts","sourceRoot":"","sources":["../../src/tools/metrics/create-metrics.ts"],"names":[],"mappings":"OAEO,EAAE,QAAQ,EAAuB,MAAM,8BAA8B;OAErE,EAAE,IAAI,EAAE,MAAM,oCAAoC;OAClD,SAAS,MAAM,cAAc;AAEpC,eAAO,MAAM,QAAQ,EAAE,QAOtB,CAAC;AAEF,eAAO,MAAM,IAAI,EAAE,IA0OlB,CAAC;AAEF,eAAO,MAAM,OAAO,GAAU,QAAQ,SAAS,EAAE,MAAM,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,SAAS,mEAGzF,CAAC;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;sBAHoC,SAAS,QAAQ,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,SAAS;;AAK1F,wBAA2C"}
+{"version":3,"file":"create-metrics.d.mts","sourceRoot":"","sources":["../../src/tools/metrics/create-metrics.ts"],"names":[],"mappings":"OAEO,EAAE,QAAQ,EAAuB,MAAM,8BAA8B;OAErE,EAAE,IAAI,EAAE,MAAM,oCAAoC;OAClD,SAAS,MAAM,cAAc;AAEpC,eAAO,MAAM,QAAQ,EAAE,QAOtB,CAAC;AAEF,eAAO,MAAM,IAAI,EAAE,IAgWlB,CAAC;AAEF,eAAO,MAAM,OAAO,GAAU,QAAQ,SAAS,EAAE,MAAM,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,SAAS,mEAGzF,CAAC;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;sBAHoC,SAAS,QAAQ,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,SAAS;;AAK1F,wBAA2C"}

package/tools/metrics/create-metrics.d.ts.map

@@ -1 +1 @@
-{"version":3,"file":"create-metrics.d.ts","sourceRoot":"","sources":["../../src/tools/metrics/create-metrics.ts"],"names":[],"mappings":"OAEO,EAAE,QAAQ,EAAuB,MAAM,8BAA8B;OAErE,EAAE,IAAI,EAAE,MAAM,oCAAoC;OAClD,SAAS,MAAM,cAAc;AAEpC,eAAO,MAAM,QAAQ,EAAE,QAOtB,CAAC;AAEF,eAAO,MAAM,IAAI,EAAE,IA0OlB,CAAC;AAEF,eAAO,MAAM,OAAO,GAAU,QAAQ,SAAS,EAAE,MAAM,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,SAAS,mEAGzF,CAAC;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;sBAHoC,SAAS,QAAQ,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,SAAS;;AAK1F,wBAA2C"}
+{"version":3,"file":"create-metrics.d.ts","sourceRoot":"","sources":["../../src/tools/metrics/create-metrics.ts"],"names":[],"mappings":"OAEO,EAAE,QAAQ,EAAuB,MAAM,8BAA8B;OAErE,EAAE,IAAI,EAAE,MAAM,oCAAoC;OAClD,SAAS,MAAM,cAAc;AAEpC,eAAO,MAAM,QAAQ,EAAE,QAOtB,CAAC;AAEF,eAAO,MAAM,IAAI,EAAE,IAgWlB,CAAC;AAEF,eAAO,MAAM,OAAO,GAAU,QAAQ,SAAS,EAAE,MAAM,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,SAAS,mEAGzF,CAAC;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;;sBAHoC,SAAS,QAAQ,MAAM,CAAC,MAAM,EAAE,OAAO,CAAC,GAAG,SAAS;;AAK1F,wBAA2C"}