🪢 Open source agent evals & observability: Trace, evaluate, and improve LLM applications with one open platform.
TypeScript analyticsautogenevaluationlangchainlarge-language-modelsllama-indexllmllm-evaluationllm-observabilityllmopsmonitoringobservabilityopen-sourceopenaiplaygroundprompt-engineeringprompt-managementself-hostedycombinator
import { GetDatasetRunsV1Response } from "@/src/features/public-api/types/datasets";
import { listDatasetRunsByDatasetIdForApi } from "@/src/features/datasets/server/publicDatasetService";
import { defineTool } from "../../../core/define-tool";
import { buildDatasetRunUrl } from "@langfuse/shared/src/server";
import { runMcpTool } from "../../../core/run-mcp-tool";
import { rejectDatasetRunToolsInEventsOnlyMode } from "../events-only-guard";
import { GetDatasetRunsMcpInput } from "../schema";
export const [listDatasetRunsTool, handleListDatasetRuns] = defineTool({
name: "listDatasetRuns",
description:
"List dataset runs, each experiment or evaluation execution over a dataset, by dataset ID.",
action: "datasets:read",
baseSchema: GetDatasetRunsMcpInput,
inputSchema: GetDatasetRunsMcpInput,
handler: async (input, context) =>
runMcpTool({
spanName: "mcp.dataset_runs.list",
context,
attributes: { "mcp.dataset_id": input.datasetId },
fn: async () => {
rejectDatasetRunToolsInEventsOnlyMode();
const result = await listDatasetRunsByDatasetIdForApi({
projectId: context.projectId,
datasetId: input.datasetId,
page: input.page,
limit: input.limit,
});
const parsed = GetDatasetRunsV1Response.parse(result);
return {
...parsed,
data: parsed.data.map((datasetRun) => ({
...datasetRun,
url: buildDatasetRunUrl({
projectId: context.projectId,
datasetId: datasetRun.datasetId,
datasetRunId: datasetRun.id,
}),
})),
};
},
}),
readOnlyHint: true,
});