DiAL/tests/server/checker/runner/llm/output-expect.test.ts

import { describe, expect, test } from "bun:test";

import type { LlmCheckObservation } from "../../../../../src/server/checker/runner/llm/types";

import { runExpects } from "../../../../../src/server/checker/runner/llm/expect";
import { checkOutputRules } from "../../../../../src/server/checker/runner/llm/output";

function makeObservation(overrides?: Partial<LlmCheckObservation>): LlmCheckObservation {
  return {
    finishReason: "stop",
    http: { headers: {}, status: 200, statusText: "OK" },
    mode: "http",
    model: "gpt-4o-mini",
    outputText: "OK",
    provider: "openai",
    rawFinishReason: "stop",
    stream: null,
    usage: { inputTokens: 12, outputTokens: 2, totalTokens: 14 },
    warnings: [],
    ...overrides,
  };
}

describe("LLM output rules", () => {
  test("equals 严格匹配", () => {
    expect(checkOutputRules("OK", [{ equals: "OK" }]).matched).toBe(true);
    expect(checkOutputRules("OK\n", [{ equals: "OK" }]).matched).toBe(false);
    expect(checkOutputRules("OK ", [{ equals: "OK" }]).matched).toBe(false);
  });

  test("equals null 输出失败", () => {
    expect(checkOutputRules(null, [{ equals: "OK" }]).matched).toBe(false);
  });

  test("contains 匹配", () => {
    expect(checkOutputRules("Hello World", [{ contains: "World" }]).matched).toBe(true);
    expect(checkOutputRules("Hello", [{ contains: "World" }]).matched).toBe(false);
    expect(checkOutputRules(null, [{ contains: "World" }]).matched).toBe(false);
  });

  test("regex 匹配", () => {
    expect(checkOutputRules("status: ok", [{ regex: "^status:" }]).matched).toBe(true);
    expect(checkOutputRules("status: ok", [{ regex: "^error:" }]).matched).toBe(false);
    expect(checkOutputRules(null, [{ regex: "^status:" }]).matched).toBe(false);
  });

  test("json 匹配", () => {
    expect(checkOutputRules('{"status":"ok","code":200}', [{ json: { equals: "ok", path: "$.status" } }]).matched).toBe(
      true,
    );
    expect(checkOutputRules('{"status":"ok","code":200}', [{ json: { gte: 200, path: "$.code" } }]).matched).toBe(true);
    expect(checkOutputRules('{"status":"ok"}', [{ json: { exists: true, path: "$.code" } }]).matched).toBe(false);
  });

  test("json 非法 JSON 失败", () => {
    expect(checkOutputRules("not json", [{ json: { exists: true, path: "$.x" } }]).matched).toBe(false);
  });

  test("多规则按顺序快速失败", () => {
    const result = checkOutputRules("Hello World", [{ equals: "wrong" }, { contains: "World" }]);
    expect(result.matched).toBe(false);
    expect(result.failure?.phase).toBe("output");
  });

  test("undefined rules 返回通过", () => {
    expect(checkOutputRules("anything", undefined).matched).toBe(true);
    expect(checkOutputRules(null, undefined).matched).toBe(true);
  });
});

describe("LLM runExpects", () => {
  test("全部 expect 通过", () => {
    const observation = makeObservation();
    const result = runExpects(observation, {
      finishReason: "stop",
      output: [{ contains: "OK" }],
      status: [200],
    });
    expect(result.matched).toBe(true);
    expect(result.failure).toBeNull();
  });

  test("默认 status=200 通过", () => {
    const observation = makeObservation();
    const result = runExpects(observation, undefined);
    expect(result.matched).toBe(true);
  });

  test("status 不匹配失败", () => {
    const observation = makeObservation();
    const result = runExpects(observation, { status: [404] });
    expect(result.matched).toBe(false);
    expect(result.failure?.phase).toBe("status");
  });

  test("finishReason 不匹配失败", () => {
    const observation = makeObservation();
    const result = runExpects(observation, { finishReason: "length" });
    expect(result.matched).toBe(false);
    expect(result.failure?.phase).toBe("finishReason");
  });

  test("rawFinishReason 不匹配失败", () => {
    const observation = makeObservation();
    const result = runExpects(observation, { rawFinishReason: "end_turn" });
    expect(result.matched).toBe(false);
    expect(result.failure?.phase).toBe("rawFinishReason");
  });

  test("usage 不匹配失败", () => {
    const observation = makeObservation();
    const result = runExpects(observation, { usage: { totalTokens: { gte: 100 } } });
    expect(result.matched).toBe(false);
    expect(result.failure?.phase).toBe("usage");
  });

  test("usage 匹配通过", () => {
    const observation = makeObservation();
    const result = runExpects(observation, { usage: { totalTokens: { lte: 20 } } });
    expect(result.matched).toBe(true);
  });

  test("stream completed 匹配", () => {
    const observation = makeObservation({
      mode: "stream",
      stream: { completed: true, firstTokenMs: 500 },
    });
    const result = runExpects(observation, {
      stream: { completed: true },
    });
    expect(result.matched).toBe(true);
  });

  test("stream firstTokenMs 匹配", () => {
    const observation = makeObservation({
      mode: "stream",
      stream: { completed: true, firstTokenMs: 500 },
    });
    const result = runExpects(observation, {
      stream: { firstTokenMs: { lte: 1000 } },
    });
    expect(result.matched).toBe(true);
  });

  test("stream firstTokenMs 缺失失败", () => {
    const observation = makeObservation({
      mode: "stream",
      stream: { completed: true, firstTokenMs: null },
    });
    const result = runExpects(observation, {
      stream: { firstTokenMs: { lte: 1000 } },
    });
    expect(result.matched).toBe(false);
    expect(result.failure?.phase).toBe("stream");
  });

  test("headers 匹配通过", () => {
    const observation = makeObservation({
      http: { headers: { "content-type": "application/json" }, status: 200, statusText: "OK" },
    });
    const result = runExpects(observation, {
      headers: { "content-type": "application/json" },
    });
    expect(result.matched).toBe(true);
  });

  test("headers 不匹配失败", () => {
    const observation = makeObservation({
      http: { headers: { "content-type": "text/plain" }, status: 200, statusText: "OK" },
    });
    const result = runExpects(observation, {
      headers: { "content-type": "application/json" },
    });
    expect(result.matched).toBe(false);
    expect(result.failure?.phase).toBe("headers");
  });

  test("首个 expect 失败立即返回", () => {
    const observation = makeObservation();
    const result = runExpects(observation, {
      output: [{ contains: "OK" }],
      status: [404],
    });
    expect(result.matched).toBe(false);
    expect(result.failure?.phase).toBe("status");
  });

  test("APICallError 状态码 expect 通过", () => {
    const observation = makeObservation({
      finishReason: null,
      http: { headers: {}, status: 401, statusText: "Unauthorized" },
      outputText: null,
      usage: null,
    });
    const result = runExpects(observation, { status: [401] });
    expect(result.matched).toBe(true);
  });
});