geo/apps/desktop-client/src/main/adapters/wenxin.test.ts

import { describe, expect, it } from "vitest";

import { __wenxinTestUtils } from "./wenxin";

const {
  buildSourceItem,
  htmlTableToMarkdown,
  isObservationComplete,
  normalizeUrl,
  parseWenxinHistoryResponse,
  parseWenxinSSEBody,
} = __wenxinTestUtils;

describe("wenxin adapter helpers", () => {
  it("parses conversation stream major and message events", () => {
    const sseBody = [
      "event:major",
      "data:{\"logId\":\"major-log\",\"data\":{\"createChatResponseVoCommonResult\":{\"data\":{\"chat\":{\"id\":\"user-1\",\"message\":[{\"content\":\"问题\"}]},\"botChat\":{\"id\":\"bot-1\",\"message\":[{\"content\":\"正在生成中...\"}],\"messageId\":\"msg-1\",\"modelSign\":\"EB45T\"}}},\"createSessionResponseVoCommonResult\":{\"data\":{\"sessionId\":\"session-1\",\"model\":\"EB45T\"}}}}",
      "",
      "event:message",
      "data:{\"code\":0,\"data\":{\"chat_id\":\"bot-1\",\"content\":\"第一段\",\"is_end\":false}}",
      "",
      "event:message",
      "data:{\"code\":0,\"data\":{\"chat_id\":\"bot-1\",\"tokens_all\":\"第一段\\n第二段\",\"is_end\":true}}",
    ].join("\n");

    expect(parseWenxinSSEBody(sseBody, true, null)).toMatchObject({
      sessionId: "session-1",
      botChatId: "bot-1",
      providerModel: "EB45T",
      providerRequestID: "msg-1",
      answer: "第一段\n第二段",
      isEnded: true,
      captureDone: true,
    });
  });

  it("extracts withdraw text from stream", () => {
    const sseBody = [
      "event:major",
      "data:{\"data\":{\"createChatResponseVoCommonResult\":{\"data\":{\"isWithdraw\":true,\"withdrawText\":\"当前访问环境存在异常，请更换浏览器再尝试提问\",\"sessionDel\":true}}}}",
      "",
      "ERR:AbortError: BodyStreamBuffer was aborted",
    ].join("\n");

    expect(parseWenxinSSEBody(sseBody, true, "AbortError: BodyStreamBuffer was aborted")).toMatchObject({
      withdrawText: "当前访问环境存在异常，请更换浏览器再尝试提问",
      sessionDel: true,
    });
  });

  it("converts html tables to markdown", () => {
    const markdown = htmlTableToMarkdown("<table><tr><th>品牌</th><th>均价</th></tr><tr><td>A</td><td>999</td></tr></table>");

    expect(markdown).toBe(
      [
        "| 品牌 | 均价 |",
        "| --- | --- |",
        "| A | 999 |",
      ].join("\n"),
    );
  });

  it("extracts answer text, citations, search results, and tables from history payload", () => {
    const history = parseWenxinHistoryResponse({
      code: 0,
      msg: "success",
      data: {
        state: 1,
        chats: [
          {
            id: "user-1",
            role: "user",
            message: [
              {
                contentType: "text",
                content: "问题",
              },
            ],
          },
          {
            id: "bot-1",
            role: "robot",
            stop: 1,
            mode: "history",
            modelSign: "EB45T",
            messageId: "msg-1",
            citations: [
              {
                url: "https://example.com/article",
                title: "示例文章",
                siteName: "示例站点",
              },
            ],
            searchCitations: {
              total: 1,
              list: [
                {
                  url: "https://search.example.com/result",
                  title: "搜索结果",
                  site: "搜索站点",
                },
              ],
            },
            message: [
              {
                contentType: "text",
                content: "推荐如下：",
              },
              {
                contentType: "table",
                content: "<table><tr><th>品牌</th><th>价格</th></tr><tr><td>A</td><td>1000</td></tr></table>",
              },
            ],
          },
        ],
      },
    }, "session-1");

    expect(history.answer).toContain("推荐如下：");
    expect(history.answer).toContain("| 品牌 | 价格 |");
    expect(history.citations).toHaveLength(2);
    expect(history.searchResults).toHaveLength(1);
    expect(history.providerModel).toBe("EB45T");
    expect(history.providerRequestID).toBe("msg-1");
    expect(history.generating).toBe(false);
  });

  it("falls back to nested web list sources when search citations are not on the latest chat root", () => {
    const history = parseWenxinHistoryResponse({
      code: 0,
      msg: "success",
      data: {
        state: 1,
        webListData: {
          list: [
            {
              url: "https://fallback.example.com/article",
              title: "回退网页",
              name: "回退站点",
            },
          ],
        },
        chats: [
          {
            id: "bot-1",
            role: "robot",
            stop: 1,
            mode: "history",
            modelSign: "EB45T",
            messageId: "msg-2",
            message: [
              {
                contentType: "text",
                content: "这是答案",
              },
            ],
          },
        ],
      },
    }, "session-2");

    expect(history.searchResults).toHaveLength(1);
    expect(history.searchResults[0]?.url).toBe("https://fallback.example.com/article");
    expect(history.citations[0]?.url).toBe("https://fallback.example.com/article");
  });

  it("unwraps Wenxin reference redirect urls", () => {
    expect(normalizeUrl("https://yiyan.baidu.com/eb/link?target=https%3A%2F%2Fwww.example.com%2Farticle%23ref")).toBe(
      "https://www.example.com/article",
    );

    expect(buildSourceItem({
      pageUrl: "https://yiyan.baidu.com/eb/link?url=https%3A%2F%2Fsource.example.com%2Fnews%3Fid%3D1",
      title: "引用来源标题",
      source: "来源站点",
    })).toMatchObject({
      url: "https://source.example.com/news?id=1",
      title: "引用来源标题",
      site_name: "来源站点",
      host: "source.example.com",
    });
  });

  it("extracts web page references from Wenxin reference list fields", () => {
    const history = parseWenxinHistoryResponse({
      code: 0,
      msg: "success",
      data: {
        state: 1,
        chats: [
          {
            id: "bot-1",
            role: "robot",
            stop: 1,
            modelSign: "EB45T",
            message: [
              {
                contentType: "text",
                content: "这是答案",
              },
            ],
            webPages: [
              {
                targetUrl: "https://yiyan.baidu.com/eb/link?target=https%3A%2F%2Fwww.reference-source.com%2Fa%23section",
                title: "参考网页 A",
                siteName: "reference-source.com",
              },
            ],
          },
        ],
      },
    }, "session-3");

    expect(history.citations).toHaveLength(1);
    expect(history.searchResults).toHaveLength(1);
    expect(history.citations[0]).toMatchObject({
      url: "https://www.reference-source.com/a",
      title: "参考网页 A",
      site_name: "reference-source.com",
    });
  });

  it("does not treat error-only observations as complete", () => {
    expect(isObservationComplete({
      sessionId: "session-1",
      providerModel: "EB45T",
      providerRequestID: "msg-1",
      answer: null,
      answerBlocks: [],
      citations: [],
      searchResults: [],
      withdrawText: null,
      errorMessage: "temporary stream issue",
      historyGenerating: false,
      streamDone: false,
      signature: "sig-1",
    })).toBe(false);

    expect(isObservationComplete({
      sessionId: "session-1",
      providerModel: "EB45T",
      providerRequestID: "msg-1",
      answer: null,
      answerBlocks: [],
      citations: [],
      searchResults: [],
      withdrawText: "内容暂不可用",
      errorMessage: null,
      historyGenerating: false,
      streamDone: false,
      signature: "sig-2",
    })).toBe(false);
  });
});