Reliability Evaluation

import { ReliabilityEval } from "@agentium/eval";
import { Agent, openai } from "@agentium/core";

const agent = new Agent({
  name: "tool-agent",
  model: openai("gpt-4o"),
  tools: [searchTool, calcTool],
});

const eval = new ReliabilityEval({
  name: "tool-reliability",
  agent,
  cases: [
    { name: "uses-search", input: "Search for latest news", expectedTools: ["search"] },
    { name: "handles-error", input: "Divide by zero", shouldError: true },
  ],
});

const result = await eval.run();

import { EvalSuite, toolCallMatch } from "@agentium/eval";

const suite = new EvalSuite({
  name: "tools-test",
  agent,
  scorers: [toolCallMatch(["search", "calculate"])],
  cases: [{ name: "test", input: "Search and calculate" }],
});