新增样例验收报告工具

tests/e2e/sample-flow/reporting.ts

@@ -0,0 +1,130 @@
+import { mkdirSync, readFileSync, readdirSync, writeFileSync } from "node:fs";
+import { join, relative } from "node:path";
+
+import type { InvalidArticleSample, RunSummary, SampleResult } from "./types";
+
+interface AggregateInput {
+  startedAt: string;
+  finishedAt: string;
+  provider: string;
+  model: string;
+  baseURL: string;
+  reportDir: string;
+  samples: SampleResult[];
+  invalidSamples: InvalidArticleSample[];
+}
+
+export function writeSampleResult(reportDir: string, result: SampleResult) {
+  const sampleDir = join(reportDir, "samples", result.slug);
+  mkdirSync(sampleDir, { recursive: true });
+  writeFileSync(
+    join(sampleDir, "result.json"),
+    `${JSON.stringify(result, null, 2)}\n`,
+  );
+}
+
+export function readSampleResults(reportDir: string): SampleResult[] {
+  const samplesDir = join(reportDir, "samples");
+  try {
+    return readdirSync(samplesDir, { withFileTypes: true })
+      .filter((entry) => entry.isDirectory())
+      .map((entry) => join(samplesDir, entry.name, "result.json"))
+      .map(
+        (filePath) => JSON.parse(readFileSync(filePath, "utf8")) as SampleResult,
+      )
+      .sort((left, right) => left.file.localeCompare(right.file));
+  } catch {
+    return [];
+  }
+}
+
+export function aggregateSummary(input: AggregateInput): RunSummary {
+  const passed = input.samples.filter((sample) => sample.status === "passed").length;
+  const failed = input.samples.filter((sample) => sample.status === "failed").length;
+  const skipped =
+    input.samples.filter((sample) => sample.status === "skipped").length +
+    input.invalidSamples.length;
+
+  return {
+    started_at: input.startedAt,
+    finished_at: input.finishedAt,
+    mode: "live",
+    provider: input.provider,
+    model: input.model,
+    base_url: input.baseURL,
+    report_dir: input.reportDir,
+    totals: { passed, failed, skipped },
+    samples: input.samples,
+    invalid_samples: input.invalidSamples,
+  };
+}
+
+export function writeSummaryFiles(reportDir: string, summary: RunSummary) {
+  mkdirSync(reportDir, { recursive: true });
+  writeFileSync(
+    join(reportDir, "summary.json"),
+    `${JSON.stringify(summary, null, 2)}\n`,
+  );
+  writeFileSync(join(reportDir, "summary.md"), renderSummaryMarkdown(summary));
+}
+
+export function redactSensitiveText(
+  text: string,
+  secrets: Array<string | undefined>,
+) {
+  let redacted = text
+    .replace(/(x-api-key:\s*)([^\s]+)/gi, "$1[REDACTED]")
+    .replace(/(authorization:\s*bearer\s+)([^\s]+)/gi, "$1[REDACTED]")
+    .replace(
+      /((?:DEEPSEEK|OPENAI|API)_?[A-Z_]*KEY=)"?([^"\s]+)"?/g,
+      '$1"[REDACTED]"',
+    );
+
+  for (const secret of secrets) {
+    if (!secret) continue;
+    redacted = redacted.split(secret).join("[REDACTED]");
+  }
+
+  return redacted;
+}
+
+function renderSummaryMarkdown(summary: RunSummary) {
+  const lines = [
+    "# GEO 样例文章 E2E 测试报告",
+    "",
+    `- 模式：${summary.mode}`,
+    `- Provider：${summary.provider}`,
+    `- Model：${summary.model}`,
+    `- Base URL：${summary.base_url}`,
+    `- 报告目录：${summary.report_dir}`,
+    `- 结果：通过 ${summary.totals.passed}，失败 ${summary.totals.failed}，跳过 ${summary.totals.skipped}`,
+    "",
+    "| 样例 | 状态 | QA | 耗时 | 失败分类 |",
+    "| --- | --- | --- | ---: | --- |",
+    ...summary.samples
+      .map((sample) =>
+        [
+          sample.name,
+          sample.status,
+          sample.qa_status ?? "",
+          `${Math.round(sample.duration_ms / 1000)}s`,
+          sample.failure_category ?? "",
+        ].join(" | "),
+      )
+      .map((row) => `| ${row} |`),
+  ];
+
+  if (summary.invalid_samples.length > 0) {
+    lines.push("", "## 无效样例", "");
+    for (const sample of summary.invalid_samples) {
+      lines.push(`- ${sample.fileName}: ${sample.reason}`);
+    }
+  }
+
+  lines.push("");
+  return lines.join("\n");
+}
+
+export function relativeArtifactPath(reportDir: string, artifactPath: string) {
+  return relative(reportDir, artifactPath);
+}

tests/sample-flow/reporting.test.ts

@@ -0,0 +1,96 @@
+import { existsSync, mkdtempSync, readFileSync, rmSync } from "node:fs";
+import { tmpdir } from "node:os";
+import { join } from "node:path";
+
+import { afterEach, beforeEach, describe, expect, it } from "vitest";
+
+import {
+  aggregateSummary,
+  redactSensitiveText,
+  writeSampleResult,
+  writeSummaryFiles,
+} from "../e2e/sample-flow/reporting";
+import type { InvalidArticleSample, SampleResult } from "../e2e/sample-flow/types";
+
+describe("reporting helpers", () => {
+  let reportDir: string;
+
+  beforeEach(() => {
+    reportDir = mkdtempSync(join(tmpdir(), "geo-report-"));
+  });
+
+  afterEach(() => {
+    rmSync(reportDir, { recursive: true, force: true });
+  });
+
+  it("redacts API keys and authorization tokens", () => {
+    const redacted = redactSensitiveText(
+      'x-api-key: local-dev-key Authorization: Bearer secret DEEPSEEK_API_KEY="abc"',
+      ["local-dev-key", "abc"],
+    );
+
+    expect(redacted).toBe(
+      'x-api-key: [REDACTED] Authorization: Bearer [REDACTED] DEEPSEEK_API_KEY="[REDACTED]"',
+    );
+  });
+
+  it("writes per-sample results and aggregate summary files", () => {
+    const sample: SampleResult = {
+      file: "samples/articles/title-quality.json",
+      name: "Title quality",
+      slug: "title-quality",
+      status: "passed",
+      duration_ms: 1234,
+      job_id: "job_123",
+      qa_status: "warn",
+      qa_fail_rules: [],
+      qa_warn_rules: ["title_quality"],
+      expected_hard_failures: [],
+      expected_warnings: ["title_quality"],
+      exports: {
+        "optimized.md": "passed",
+        "optimized.docx": "passed",
+        "qa_report.json": "passed",
+      },
+      llm_tasks: ["fact_extractor", "article_optimizer", "quality_inspector"],
+      artifacts: {
+        final_screenshot: "samples/title-quality/final.png",
+      },
+    };
+    const invalid: InvalidArticleSample[] = [
+      {
+        filePath: "/repo/samples/articles/bad.json",
+        fileName: "bad.json",
+        reason: "input.body must be a non-empty string",
+      },
+    ];
+
+    writeSampleResult(reportDir, sample);
+    const summary = aggregateSummary({
+      startedAt: "2026-07-01T00:00:00.000Z",
+      finishedAt: "2026-07-01T00:01:00.000Z",
+      provider: "deepseek",
+      model: "deepseek-v4-pro",
+      baseURL: "http://127.0.0.1:3000",
+      reportDir,
+      samples: [sample],
+      invalidSamples: invalid,
+    });
+    writeSummaryFiles(reportDir, summary);
+
+    expect(
+      existsSync(join(reportDir, "samples", "title-quality", "result.json")),
+    ).toBe(true);
+    expect(
+      JSON.parse(readFileSync(join(reportDir, "summary.json"), "utf8")),
+    ).toEqual(
+      expect.objectContaining({
+        provider: "deepseek",
+        totals: { passed: 1, failed: 0, skipped: 1 },
+      }),
+    );
+    expect(readFileSync(join(reportDir, "summary.md"), "utf8")).toContain(
+      "| Title quality | passed | warn |",
+    );
+  });
+});