@ai-lighthouse/cli 1.0.0 → 1.0.2

package/dist/index.js

@@ -1,15 +1,2576 @@
-import { Command } from 'commander';
-import { auditCommand } from './commands/audit.js';
-import { crawlCommand } from './commands/crawl.js';
-import { reportCommand } from './commands/report.js';
-import { auditWizardCommand } from './commands/audit-wizard.js';
-const program = new Command();
-program
-    .name('ai-lighthouse')
-    .description('AI Lighthouse - Audit websites for AI readiness and SEO optimization')
-    .version('1.0.0');
-// Register commands
-auditWizardCommand(program); // Interactive wizard (recommended for new users)
+#!/usr/bin/env node
+
+// src/index.ts
+import { Command } from "commander";
+
+// src/commands/audit.ts
+import chalk2 from "chalk";
+import ora from "ora";
+import { analyzeUrlWithRules } from "@ai-lighthouse/scanner";
+import { calculateAIReadiness, formatAIReadinessReport } from "@ai-lighthouse/scanner";
+import { exportAuditReport, generateScoringSummary } from "@ai-lighthouse/scanner";
+import { writeFile, mkdir } from "fs/promises";
+import { join, resolve } from "path";
+import { existsSync } from "fs";
+import html_to_pdf from "html-pdf-node";
+
+// src/utils/comprehensive-formatter.ts
+import chalk from "chalk";
+function formatComprehensiveReport(result, aiReadiness) {
+  const sections = [];
+  if (result.llm) {
+    sections.push(formatLLMSection(result.llm));
+  }
+  if (result.chunking) {
+    sections.push(formatChunkingSection(result.chunking));
+  }
+  if (result.extractability) {
+    sections.push(formatExtractabilitySection(result.extractability));
+  }
+  if (result.hallucinationReport) {
+    sections.push(formatHallucinationSection(result.hallucinationReport));
+  }
+  if (result.mirrorReport) {
+    sections.push(formatMirrorReportSection(result.mirrorReport));
+  }
+  if (aiReadiness?.dimensions) {
+    sections.push(formatDimensionsSection(aiReadiness.dimensions));
+  }
+  if (aiReadiness?.quickWins && aiReadiness.quickWins.length > 0) {
+    sections.push(formatQuickWinsSection(aiReadiness.quickWins));
+  }
+  return sections.join("\n\n");
+}
+function formatLLMSection(llm) {
+  const lines = [];
+  lines.push(chalk.bold.blue("\u{1F4DD} AI Understanding Analysis"));
+  lines.push("\u2500".repeat(70));
+  if (llm.summary) {
+    lines.push(chalk.bold("Summary:"));
+    lines.push(`  ${llm.summary}`);
+    lines.push("");
+  }
+  if (llm.pageType) {
+    lines.push(chalk.bold("Inferred Page Type:"));
+    lines.push(`  ${chalk.magenta.bold(llm.pageType)}`);
+    if (llm.pageTypeInsights && llm.pageTypeInsights.length > 0) {
+      lines.push("");
+      lines.push(chalk.bold("\u{1F4A1} AI-Generated Insights:"));
+      llm.pageTypeInsights.forEach((insight) => {
+        lines.push(`  ${chalk.cyan("\u2022")} ${insight}`);
+      });
+    }
+    lines.push("");
+  }
+  if (llm.keyTopics && llm.keyTopics.length > 0) {
+    lines.push(chalk.bold("Key Topics:"));
+    lines.push(`  ${llm.keyTopics.map((t) => chalk.blue(t)).join(", ")}`);
+    lines.push("");
+  }
+  const metadata = [];
+  if (llm.readingLevel) {
+    metadata.push(`Reading Level: ${llm.readingLevel.description}`);
+  }
+  if (llm.sentiment) {
+    metadata.push(`Sentiment: ${llm.sentiment}`);
+  }
+  if (llm.technicalDepth) {
+    metadata.push(`Technical Depth: ${llm.technicalDepth}`);
+  }
+  if (metadata.length > 0) {
+    lines.push(chalk.bold("Metadata:"));
+    metadata.forEach((m) => lines.push(`  ${m}`));
+    lines.push("");
+  }
+  if (llm.topEntities && llm.topEntities.length > 0) {
+    lines.push(chalk.bold("\u{1F50D} Key Entities:"));
+    llm.topEntities.slice(0, 5).forEach((entity) => {
+      const relevance = entity.relevance ? ` - ${Math.round(entity.relevance * 100)}% relevance` : "";
+      lines.push(`  ${chalk.cyan("\u2022")} ${chalk.bold(entity.name)} ${chalk.dim(`(${entity.type})${relevance}`)}`);
+    });
+    lines.push("");
+  }
+  if (llm.questions && llm.questions.length > 0) {
+    lines.push(chalk.bold("\u2753 Questions AI Can Answer:"));
+    llm.questions.slice(0, 5).forEach((q, idx) => {
+      const difficulty = chalk.dim(`[${q.difficulty.toUpperCase()}]`);
+      lines.push(`  ${idx + 1}. ${difficulty} ${q.question}`);
+    });
+    lines.push("");
+  }
+  if (llm.suggestedFAQ && llm.suggestedFAQ.length > 0) {
+    lines.push(chalk.bold("\u{1F4A1} Suggested FAQs:"));
+    llm.suggestedFAQ.filter((f) => f.importance === "high").slice(0, 3).forEach((faq, idx) => {
+      lines.push(`  ${idx + 1}. Q: ${chalk.yellow(faq.question)}`);
+      lines.push(`     A: ${chalk.dim(faq.suggestedAnswer)}`);
+    });
+  }
+  return lines.join("\n");
+}
+function formatChunkingSection(chunking) {
+  const lines = [];
+  lines.push(chalk.bold.green("\u{1F4C4} Content Chunking Analysis"));
+  lines.push("\u2500".repeat(70));
+  const grid = [
+    ["Strategy", chunking.chunkingStrategy],
+    ["Total Chunks", chunking.totalChunks.toString()],
+    ["Avg Tokens/Chunk", chunking.averageTokensPerChunk.toString()],
+    ["Avg Noise Ratio", `${(chunking.averageNoiseRatio * 100).toFixed(1)}%`]
+  ];
+  grid.forEach(([label, value]) => {
+    lines.push(`  ${chalk.bold(label + ":").padEnd(25)} ${chalk.cyan(value)}`);
+  });
+  if (chunking.chunkingStrategy === "heading-based") {
+    lines.push("");
+    lines.push(chalk.green("  \u2713 Heading-based chunking is ideal for AI comprehension"));
+  } else if (chunking.chunkingStrategy === "paragraph-based") {
+    lines.push("");
+    lines.push(chalk.yellow("  \u26A0 Consider adding headings for better semantic structure"));
+  }
+  if (chunking.chunks && chunking.chunks.length > 0) {
+    lines.push("");
+    lines.push(chalk.bold("Chunk Distribution:"));
+    const tokenCounts = chunking.chunks.map((c) => c.tokenCount);
+    const min = Math.min(...tokenCounts);
+    const max = Math.max(...tokenCounts);
+    const avg = tokenCounts.reduce((a, b) => a + b, 0) / tokenCounts.length;
+    lines.push(`  Min Tokens: ${min}, Max Tokens: ${max}, Avg: ${avg.toFixed(0)}`);
+    const noiseRatios = chunking.chunks.map((c) => c.noiseRatio);
+    const avgNoise = noiseRatios.reduce((a, b) => a + b, 0) / noiseRatios.length;
+    lines.push(`  Avg Noise per Chunk: ${(avgNoise * 100).toFixed(1)}%`);
+  }
+  return lines.join("\n");
+}
+function formatExtractabilitySection(extractability) {
+  const lines = [];
+  lines.push(chalk.bold.yellow("\u{1F504} Extractability Analysis"));
+  lines.push("\u2500".repeat(70));
+  const grid = [
+    ["Overall Score", `${extractability.score.extractabilityScore}/100`],
+    ["Server-Rendered", `${extractability.score.serverRenderedPercent}%`]
+  ];
+  grid.forEach(([label, value]) => {
+    lines.push(`  ${chalk.bold(label + ":").padEnd(25)} ${chalk.cyan(value)}`);
+  });
+  lines.push("");
+  lines.push(chalk.bold("Content Type Extractability:"));
+  Object.entries(extractability.contentTypes).forEach(([type, data]) => {
+    const percentage = data.percentage;
+    const color = percentage >= 80 ? chalk.green : percentage >= 50 ? chalk.yellow : chalk.red;
+    lines.push(`  ${chalk.bold(type.charAt(0).toUpperCase() + type.slice(1) + ":").padEnd(15)} ${color(`${percentage}%`)} (${data.extractable}/${data.total})`);
+  });
+  const overallScore = extractability.score.extractabilityScore;
+  if (overallScore >= 80) {
+    lines.push("");
+    lines.push(chalk.green("  \u2713 Good extractability - AI can easily read your content"));
+  } else if (overallScore < 50) {
+    lines.push("");
+    lines.push(chalk.red("  \u26A0 Low extractability - Consider server-side rendering"));
+  }
+  return lines.join("\n");
+}
+function formatHallucinationSection(report) {
+  const lines = [];
+  lines.push(chalk.bold.red("\u26A0\uFE0F  Hallucination Risk Assessment"));
+  lines.push("\u2500".repeat(70));
+  const riskScore = report.hallucinationRiskScore;
+  const riskColor = riskScore >= 70 ? chalk.red : riskScore >= 40 ? chalk.yellow : chalk.green;
+  lines.push(`  ${chalk.bold("Risk Score:")} ${riskColor.bold(`${riskScore}/100`)}`);
+  if (report.factCheckSummary) {
+    lines.push("");
+    lines.push(chalk.bold("Fact Check Summary:"));
+    const summary = report.factCheckSummary;
+    lines.push(`  Total Facts:      ${chalk.cyan(summary.totalFacts)}`);
+    lines.push(`  Verified:         ${chalk.green(summary.verifiedFacts)}`);
+    lines.push(`  Unverified:       ${chalk.yellow(summary.unverifiedFacts)}`);
+    lines.push(`  Contradictions:   ${chalk.red(summary.contradictions)}`);
+    if (summary.ambiguities !== void 0) {
+      lines.push(`  Ambiguities:      ${chalk.yellow(summary.ambiguities)}`);
+    }
+  }
+  if (report.factCheckSummary && report.factCheckSummary.unverifiedFacts > 0) {
+    lines.push("");
+    lines.push(chalk.yellow("\u{1F4A1} Tip: Add citations and links to verify claims and reduce AI hallucination risk"));
+  }
+  if (report.triggers && report.triggers.length > 0) {
+    const highSeverityTriggers = report.triggers.filter(
+      (t) => t.severity === "high" || t.severity === "critical"
+    );
+    if (highSeverityTriggers.length > 0) {
+      lines.push("");
+      lines.push(chalk.bold("\u{1F6A8} High-Risk Triggers:"));
+      highSeverityTriggers.slice(0, 5).forEach((trigger, idx) => {
+        lines.push(`  ${idx + 1}. ${chalk.red(`[${trigger.severity.toUpperCase()}]`)} ${trigger.type}`);
+        lines.push(`     ${chalk.dim(trigger.description)}`);
+        if (trigger.confidence) {
+          lines.push(`     ${chalk.dim(`Confidence: ${Math.round(trigger.confidence * 100)}%`)}`);
+        }
+      });
+    }
+  }
+  if (report.recommendations && report.recommendations.length > 0) {
+    lines.push("");
+    lines.push(chalk.bold("\u{1F4A1} Recommendations:"));
+    report.recommendations.slice(0, 3).forEach((rec, idx) => {
+      lines.push(`  ${idx + 1}. ${rec}`);
+    });
+  }
+  return lines.join("\n");
+}
+function formatMirrorReportSection(report) {
+  const lines = [];
+  lines.push(chalk.bold.magenta("\u{1F50D} AI Misunderstanding Check"));
+  lines.push("\u2500".repeat(70));
+  const alignmentColor = report.summary.alignmentScore >= 80 ? chalk.green : report.summary.alignmentScore >= 60 ? chalk.yellow : chalk.red;
+  const clarityColor = report.summary.clarityScore >= 80 ? chalk.green : report.summary.clarityScore >= 60 ? chalk.yellow : chalk.red;
+  lines.push(`  ${chalk.bold("Alignment Score:").padEnd(25)} ${alignmentColor.bold(`${report.summary.alignmentScore}/100`)}`);
+  lines.push(`  ${chalk.bold("Clarity Score:").padEnd(25)} ${clarityColor.bold(`${report.summary.clarityScore}/100`)}`);
+  lines.push(`  ${chalk.bold("Critical Issues:").padEnd(25)} ${chalk.red(report.summary.critical)}`);
+  lines.push(`  ${chalk.bold("Major Issues:").padEnd(25)} ${chalk.yellow(report.summary.major)}`);
+  if (report.llmInterpretation) {
+    lines.push("");
+    lines.push(chalk.bold.blue("\u{1F916} What AI Actually Understood"));
+    lines.push(chalk.dim(`   (${Math.round(report.llmInterpretation.confidence * 100)}% confident)`));
+    if (report.llmInterpretation.productName) {
+      lines.push(`  ${chalk.bold("Product:")} ${report.llmInterpretation.productName}`);
+    }
+    if (report.llmInterpretation.purpose) {
+      lines.push(`  ${chalk.bold("Purpose:")} ${report.llmInterpretation.purpose}`);
+    }
+    if (report.llmInterpretation.valueProposition) {
+      lines.push(`  ${chalk.bold.magenta("\u{1F48E} Value:")} ${report.llmInterpretation.valueProposition}`);
+    }
+    if (report.llmInterpretation.keyBenefits && report.llmInterpretation.keyBenefits.length > 0) {
+      lines.push(`  ${chalk.bold("Benefits:")}`);
+      report.llmInterpretation.keyBenefits.forEach((benefit) => {
+        lines.push(`    \u2022 ${benefit}`);
+      });
+    }
+    if (report.llmInterpretation.keyFeatures && report.llmInterpretation.keyFeatures.length > 0) {
+      lines.push(`  ${chalk.bold("Features:")}`);
+      report.llmInterpretation.keyFeatures.slice(0, 3).forEach((feature) => {
+        lines.push(`    \u2022 ${feature}`);
+      });
+    }
+    if (report.llmInterpretation.targetAudience) {
+      lines.push(`  ${chalk.bold("Audience:")} ${report.llmInterpretation.targetAudience}`);
+    }
+  }
+  if (report.mismatches && report.mismatches.length > 0) {
+    const priorityMismatches = report.mismatches.filter(
+      (m) => m.severity === "critical" || m.severity === "major"
+    );
+    if (priorityMismatches.length > 0) {
+      lines.push("");
+      lines.push(chalk.bold("Priority Mismatches:"));
+      priorityMismatches.slice(0, 5).forEach((mismatch, idx) => {
+        const icon = mismatch.severity === "critical" ? "\u{1F534}" : "\u{1F7E1}";
+        lines.push(`  ${icon} ${idx + 1}. ${chalk.bold(mismatch.field)}`);
+        lines.push(`     ${chalk.dim(mismatch.description)}`);
+        lines.push(`     ${chalk.cyan("\u2192")} ${mismatch.recommendation}`);
+      });
+    }
+  }
+  if (report.recommendations && report.recommendations.length > 0) {
+    lines.push("");
+    lines.push(chalk.bold("\u{1F4A1} Top Recommendations:"));
+    report.recommendations.slice(0, 3).forEach((rec, idx) => {
+      lines.push(`  ${idx + 1}. ${rec}`);
+    });
+  }
+  return lines.join("\n");
+}
+function formatDimensionsSection(dimensions) {
+  const lines = [];
+  lines.push(chalk.bold.cyan("\u{1F3AF} Dimension Analysis"));
+  lines.push("\u2500".repeat(70));
+  const dimensionDescriptions = {
+    technical: "\u2699\uFE0F  Technical",
+    contentQuality: "\u{1F4DD} Content Quality",
+    crawlability: "\u{1F577}\uFE0F  Crawlability",
+    discoverability: "\u{1F50D} Discoverability",
+    knowledge: "\u{1F9E0} Knowledge",
+    extractability: "\u{1F504} Extractability",
+    comprehensibility: "\u{1F4A1} Comprehensibility",
+    trustworthiness: "\u2705 Trustworthiness",
+    accessibility: "\u267F Accessibility"
+  };
+  Object.entries(dimensions).forEach(([key, dim]) => {
+    const name = dimensionDescriptions[key] || key;
+    const scoreColor = dim.score >= 90 ? chalk.green : dim.score >= 75 ? chalk.yellow : dim.score >= 60 ? chalk.hex("#FFA500") : chalk.red;
+    lines.push("");
+    lines.push(`${name}: ${scoreColor.bold(`${Math.round(dim.score)}/100`)} ${chalk.dim(`(${dim.status})`)}`);
+    if (dim.strengths && dim.strengths.length > 0) {
+      lines.push(`  ${chalk.green("Strengths:")} ${dim.strengths.join(", ")}`);
+    }
+    if (dim.weaknesses && dim.weaknesses.length > 0) {
+      lines.push(`  ${chalk.yellow("Weaknesses:")} ${dim.weaknesses.join(", ")}`);
+    }
+    if (dim.recommendation) {
+      lines.push(`  ${chalk.cyan("\u2192")} ${dim.recommendation}`);
+    }
+  });
+  return lines.join("\n");
+}
+function formatQuickWinsSection(quickWins) {
+  const lines = [];
+  lines.push(chalk.bold.yellow("\u26A1 Quick Wins (High Impact, Low Effort)"));
+  lines.push("\u2500".repeat(70));
+  quickWins.slice(0, 5).forEach((win, idx) => {
+    lines.push("");
+    lines.push(`${chalk.bold(`${idx + 1}.`)} ${chalk.yellow(win.issue)}`);
+    lines.push(`   ${chalk.dim(`Impact: ${win.impact} \xB7 Effort: ${win.effort}`)}`);
+    lines.push(`   ${chalk.cyan("\u2192")} ${win.fix}`);
+  });
+  return lines.join("\n");
+}
+function formatDetailedIssues(issues) {
+  const lines = [];
+  lines.push(chalk.bold("\u26A0\uFE0F  All Issues"));
+  lines.push("\u2500".repeat(70));
+  const grouped = {
+    critical: issues.filter((i) => i.severity === "critical"),
+    high: issues.filter((i) => i.severity === "high"),
+    medium: issues.filter((i) => i.severity === "medium"),
+    low: issues.filter((i) => i.severity === "low")
+  };
+  lines.push("");
+  lines.push(chalk.bold("Issue Count by Severity:"));
+  lines.push(`  Critical: ${chalk.red.bold(grouped.critical.length)}`);
+  lines.push(`  High:     ${chalk.yellow.bold(grouped.high.length)}`);
+  lines.push(`  Medium:   ${chalk.blue.bold(grouped.medium.length)}`);
+  lines.push(`  Low:      ${chalk.dim(grouped.low.length)}`);
+  for (const [severity, severityIssues] of Object.entries(grouped)) {
+    if (severityIssues.length === 0) continue;
+    lines.push("");
+    lines.push(chalk.bold(`${severity.toUpperCase()} Issues:`));
+    severityIssues.forEach((issue, idx) => {
+      const icon = severity === "critical" ? "\u{1F534}" : severity === "high" ? "\u{1F7E0}" : severity === "medium" ? "\u{1F7E1}" : "\u{1F535}";
+      lines.push("");
+      lines.push(`${icon} ${idx + 1}. ${chalk.bold(issue.message || issue.title)}`);
+      lines.push(`   ${chalk.dim(`Category: ${issue.category} \xB7 Impact: ${issue.impact}`)}`);
+      if (issue.evidence) {
+        const evidenceText = typeof issue.evidence === "string" ? issue.evidence : issue.evidence.join(", ");
+        lines.push(`   ${chalk.dim(evidenceText.substring(0, 100))}${evidenceText.length > 100 ? "..." : ""}`);
+      }
+      if (issue.element) {
+        lines.push(`   ${chalk.dim(issue.element.substring(0, 100))}${issue.element.length > 100 ? "..." : ""}`);
+      }
+      lines.push(`   ${chalk.cyan("\u{1F4A1} Fix:")} ${issue.suggested_fix || issue.remediation}`);
+    });
+  }
+  return lines.join("\n");
+}
+
+// src/commands/audit.ts
+import { render } from "ink";
+import React10 from "react";
+
+// src/ui/AuditReportUI.tsx
+import React8, { useState as useState2 } from "react";
+import { Box as Box8, Text as Text8, useInput } from "ink";
+import Spinner from "ink-spinner";
+
+// src/ui/components/ScoreDisplay.tsx
+import React from "react";
+import { Box, Text } from "ink";
+import Gradient from "ink-gradient";
+import BigText from "ink-big-text";
+var ScoreDisplay = ({ score, grade, url }) => {
+  const getGradeColor = (grade2) => {
+    if (grade2.startsWith("A")) return "green";
+    if (grade2.startsWith("B")) return "blue";
+    if (grade2.startsWith("C")) return "yellow";
+    return "red";
+  };
+  const getScoreMessage = (score2) => {
+    if (score2 >= 90) return { status: "Excellent", message: "Your site is AI-ready!", color: "green" };
+    if (score2 >= 80) return { status: "Good", message: "Your site works well with AI", color: "blue" };
+    if (score2 >= 70) return { status: "Fair", message: "Room for improvement", color: "yellow" };
+    if (score2 >= 60) return { status: "Poor", message: "Needs significant work", color: "yellow" };
+    return { status: "Critical", message: "Major issues detected", color: "red" };
+  };
+  const { status, message, color } = getScoreMessage(score);
+  return /* @__PURE__ */ React.createElement(Box, { flexDirection: "column", paddingY: 1 }, /* @__PURE__ */ React.createElement(Box, { marginBottom: 1 }, /* @__PURE__ */ React.createElement(Gradient, { name: "rainbow" }, /* @__PURE__ */ React.createElement(BigText, { text: `${score}`, font: "block" }))), /* @__PURE__ */ React.createElement(Box, { marginBottom: 1 }, /* @__PURE__ */ React.createElement(Text, { bold: true, color: getGradeColor(grade) }, "Grade: ", grade, " \u2022 ", status)), /* @__PURE__ */ React.createElement(Box, { marginBottom: 1 }, /* @__PURE__ */ React.createElement(Text, { dimColor: true }, url)), /* @__PURE__ */ React.createElement(
+    Box,
+    {
+      borderStyle: "round",
+      borderColor: color,
+      paddingX: 2,
+      paddingY: 1
+    },
+    /* @__PURE__ */ React.createElement(Text, { color }, message)
+  ));
+};
+
+// src/ui/components/OverviewSection.tsx
+import React2 from "react";
+import { Box as Box2, Text as Text2 } from "ink";
+var OverviewSection = ({ aiReadiness }) => {
+  const getStatusColor = (status) => {
+    if (status === "excellent") return "green";
+    if (status === "good") return "blue";
+    if (status === "needs-work") return "yellow";
+    return "red";
+  };
+  const renderProgressBar = (score, width = 20) => {
+    const filled = Math.round(score / 100 * width);
+    const empty = width - filled;
+    const color = score >= 80 ? "green" : score >= 60 ? "yellow" : "red";
+    return /* @__PURE__ */ React2.createElement(Text2, { color }, "\u2588".repeat(filled), /* @__PURE__ */ React2.createElement(Text2, { dimColor: true }, "\u2591".repeat(empty)), ` ${Math.round(score)}%`);
+  };
+  return /* @__PURE__ */ React2.createElement(Box2, { flexDirection: "column", paddingY: 1 }, /* @__PURE__ */ React2.createElement(
+    Box2,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "cyan",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React2.createElement(Text2, { bold: true, color: "cyan" }, "\u{1F916} AI Agent Perspective"),
+    /* @__PURE__ */ React2.createElement(Box2, { marginTop: 1, flexDirection: "column" }, /* @__PURE__ */ React2.createElement(Box2, null, /* @__PURE__ */ React2.createElement(Text2, null, aiReadiness.aiPerspective?.canUnderstand ? "\u2705" : "\u274C", " Can Understand", aiReadiness.aiPerspective?.canExtract ? "\u2705" : "\u274C", " Can Extract")), /* @__PURE__ */ React2.createElement(Box2, null, /* @__PURE__ */ React2.createElement(Text2, null, aiReadiness.aiPerspective?.canIndex ? "\u2705" : "\u274C", " Can Index", aiReadiness.aiPerspective?.canAnswer ? "\u2705" : "\u274C", " Can Answer")), /* @__PURE__ */ React2.createElement(Box2, { marginTop: 1 }, /* @__PURE__ */ React2.createElement(Text2, { dimColor: true }, "Confidence: ", Math.round((aiReadiness.aiPerspective?.confidence || 0) * 100), "%"))),
+    aiReadiness.aiPerspective?.mainBlockers && aiReadiness.aiPerspective.mainBlockers.length > 0 && /* @__PURE__ */ React2.createElement(Box2, { marginTop: 1, flexDirection: "column" }, /* @__PURE__ */ React2.createElement(Text2, { bold: true, color: "red" }, "Main Blockers:"), aiReadiness.aiPerspective.mainBlockers.map((blocker, idx) => /* @__PURE__ */ React2.createElement(Text2, { key: idx, color: "red" }, "\u2022 ", blocker)))
+  ), /* @__PURE__ */ React2.createElement(Box2, { flexDirection: "column", marginTop: 1 }, /* @__PURE__ */ React2.createElement(Text2, { bold: true, underline: true }, "\u{1F3AF} Dimension Scores"), Object.entries(aiReadiness.dimensions || {}).map(([key, dim]) => /* @__PURE__ */ React2.createElement(Box2, { key, flexDirection: "column", marginTop: 1 }, /* @__PURE__ */ React2.createElement(Box2, { justifyContent: "space-between" }, /* @__PURE__ */ React2.createElement(Text2, { bold: true, color: getStatusColor(dim.status) }, getDimensionIcon(key), " ", formatDimensionName(key)), /* @__PURE__ */ React2.createElement(Text2, { color: getStatusColor(dim.status) }, Math.round(dim.score), "/100")), /* @__PURE__ */ React2.createElement(Box2, { marginTop: 0.5 }, renderProgressBar(dim.score)), dim.recommendation && /* @__PURE__ */ React2.createElement(Box2, { marginTop: 0.5 }, /* @__PURE__ */ React2.createElement(Text2, { dimColor: true }, "\u2192 ", dim.recommendation))))), aiReadiness.quickWins && aiReadiness.quickWins.length > 0 && /* @__PURE__ */ React2.createElement(
+    Box2,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "yellow",
+      paddingX: 2,
+      paddingY: 1,
+      marginTop: 1
+    },
+    /* @__PURE__ */ React2.createElement(Text2, { bold: true, color: "yellow" }, "\u26A1 Quick Wins (High Impact, Low Effort)"),
+    aiReadiness.quickWins.slice(0, 5).map((win, idx) => /* @__PURE__ */ React2.createElement(Box2, { key: idx, flexDirection: "column", marginTop: 1 }, /* @__PURE__ */ React2.createElement(Text2, { bold: true }, idx + 1, ". ", win.issue), /* @__PURE__ */ React2.createElement(Text2, { dimColor: true }, "Impact: ", win.impact, " \u2022 Effort: ", win.effort), /* @__PURE__ */ React2.createElement(Text2, { color: "cyan" }, "\u2192 ", win.fix)))
+  ));
+};
+function getDimensionIcon(key) {
+  const icons = {
+    technical: "\u2699\uFE0F",
+    contentQuality: "\u{1F4DD}",
+    crawlability: "\u{1F577}\uFE0F",
+    discoverability: "\u{1F50D}",
+    knowledge: "\u{1F9E0}",
+    extractability: "\u{1F504}",
+    comprehensibility: "\u{1F4A1}",
+    trustworthiness: "\u2705",
+    accessibility: "\u267F"
+  };
+  return icons[key] || "\u{1F4CC}";
+}
+function formatDimensionName(key) {
+  const names = {
+    technical: "Technical",
+    contentQuality: "Content Quality",
+    crawlability: "Crawlability",
+    discoverability: "Discoverability",
+    knowledge: "Knowledge",
+    extractability: "Extractability",
+    comprehensibility: "Comprehensibility",
+    trustworthiness: "Trustworthiness",
+    accessibility: "Accessibility"
+  };
+  return names[key] || key;
+}
+
+// src/ui/components/IssuesSection.tsx
+import React3, { useState } from "react";
+import { Box as Box3, Text as Text3 } from "ink";
+var IssuesSection = ({ issues }) => {
+  const [selectedSeverity, setSelectedSeverity] = useState("all");
+  const [expandedIssue, setExpandedIssue] = useState(null);
+  const getSeverityColor2 = (severity) => {
+    if (severity === "critical") return "red";
+    if (severity === "high") return "magenta";
+    if (severity === "medium") return "yellow";
+    return "blue";
+  };
+  const getSeverityIcon = (severity) => {
+    if (severity === "critical") return "\u{1F534}";
+    if (severity === "high") return "\u{1F7E0}";
+    if (severity === "medium") return "\u{1F7E1}";
+    return "\u{1F535}";
+  };
+  const grouped = {
+    critical: issues.filter((i) => i.severity === "critical"),
+    high: issues.filter((i) => i.severity === "high"),
+    medium: issues.filter((i) => i.severity === "medium"),
+    low: issues.filter((i) => i.severity === "low")
+  };
+  const filteredIssues = selectedSeverity === "all" ? issues : grouped[selectedSeverity] || [];
+  return /* @__PURE__ */ React3.createElement(Box3, { flexDirection: "column", paddingY: 1 }, /* @__PURE__ */ React3.createElement(
+    Box3,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "blue",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React3.createElement(Text3, { bold: true, color: "blue" }, "\u26A0\uFE0F  Issues Summary"),
+    /* @__PURE__ */ React3.createElement(Box3, { marginTop: 1 }, /* @__PURE__ */ React3.createElement(Box3, { flexDirection: "column", width: "50%" }, /* @__PURE__ */ React3.createElement(Text3, null, /* @__PURE__ */ React3.createElement(Text3, { color: "red", bold: true }, "Critical:"), " ", grouped.critical.length), /* @__PURE__ */ React3.createElement(Text3, null, /* @__PURE__ */ React3.createElement(Text3, { color: "magenta", bold: true }, "High:"), " ", grouped.high.length)), /* @__PURE__ */ React3.createElement(Box3, { flexDirection: "column", width: "50%" }, /* @__PURE__ */ React3.createElement(Text3, null, /* @__PURE__ */ React3.createElement(Text3, { color: "yellow", bold: true }, "Medium:"), " ", grouped.medium.length), /* @__PURE__ */ React3.createElement(Text3, null, /* @__PURE__ */ React3.createElement(Text3, { color: "blue", bold: true }, "Low:"), " ", grouped.low.length)))
+  ), /* @__PURE__ */ React3.createElement(Box3, { flexDirection: "column" }, /* @__PURE__ */ React3.createElement(Text3, { bold: true, underline: true }, selectedSeverity === "all" ? "All Issues" : `${selectedSeverity.toUpperCase()} Issues`, " (", filteredIssues.length, ")"), filteredIssues.map((issue, idx) => /* @__PURE__ */ React3.createElement(
+    Box3,
+    {
+      key: idx,
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: getSeverityColor2(issue.severity),
+      paddingX: 2,
+      paddingY: 1,
+      marginTop: 1
+    },
+    /* @__PURE__ */ React3.createElement(Box3, null, /* @__PURE__ */ React3.createElement(Text3, null, getSeverityIcon(issue.severity), " ", /* @__PURE__ */ React3.createElement(Text3, { bold: true, color: getSeverityColor2(issue.severity) }, issue.message || issue.title))),
+    /* @__PURE__ */ React3.createElement(Box3, { marginTop: 0.5 }, /* @__PURE__ */ React3.createElement(Text3, { dimColor: true }, "Category: ", issue.category, " \u2022 Impact: ", issue.impact)),
+    issue.evidence && /* @__PURE__ */ React3.createElement(Box3, { marginTop: 0.5 }, /* @__PURE__ */ React3.createElement(Text3, { dimColor: true }, typeof issue.evidence === "string" ? issue.evidence.substring(0, 100) : Array.isArray(issue.evidence) ? issue.evidence.join(", ").substring(0, 100) : "", (typeof issue.evidence === "string" ? issue.evidence : issue.evidence?.join(", ") || "").length > 100 ? "..." : "")),
+    /* @__PURE__ */ React3.createElement(
+      Box3,
+      {
+        marginTop: 1,
+        borderStyle: "single",
+        borderColor: "cyan",
+        paddingX: 1,
+        paddingY: 0.5
+      },
+      /* @__PURE__ */ React3.createElement(Text3, { color: "cyan" }, "\u{1F4A1} Fix: ", issue.suggested_fix || issue.remediation)
+    )
+  ))));
+};
+
+// src/ui/components/AIUnderstandingSection.tsx
+import React4 from "react";
+import { Box as Box4, Text as Text4 } from "ink";
+var AIUnderstandingSection = ({ llm }) => {
+  if (!llm || Object.keys(llm).length === 0) {
+    return /* @__PURE__ */ React4.createElement(Box4, { flexDirection: "column", paddingY: 1 }, /* @__PURE__ */ React4.createElement(
+      Box4,
+      {
+        flexDirection: "column",
+        borderStyle: "round",
+        borderColor: "yellow",
+        paddingX: 2,
+        paddingY: 1
+      },
+      /* @__PURE__ */ React4.createElement(Text4, { bold: true, color: "yellow" }, "\u{1F4A1} Enable AI Understanding Analysis"),
+      /* @__PURE__ */ React4.createElement(Box4, { marginTop: 1, flexDirection: "column" }, /* @__PURE__ */ React4.createElement(Text4, null, "LLM analysis is not enabled. To see AI understanding insights, run:"), /* @__PURE__ */ React4.createElement(Box4, { marginTop: 1, borderStyle: "single", paddingX: 1 }, /* @__PURE__ */ React4.createElement(Text4, { color: "cyan" }, "ai-lighthouse audit [URL] --enable-llm --llm-provider openai --llm-api-key YOUR_KEY")), /* @__PURE__ */ React4.createElement(Box4, { marginTop: 1 }, /* @__PURE__ */ React4.createElement(Text4, { dimColor: true }, "Supported providers: openai, anthropic, ollama, local")))
+    ));
+  }
+  return /* @__PURE__ */ React4.createElement(Box4, { flexDirection: "column", paddingY: 1 }, llm.pageType && /* @__PURE__ */ React4.createElement(
+    Box4,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "magenta",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React4.createElement(Text4, { bold: true, color: "magenta" }, "\u{1F4C4} Inferred Page Type"),
+    /* @__PURE__ */ React4.createElement(Text4, { color: "cyan" }, llm.pageType)
+  ), llm.pageTypeInsights && llm.pageTypeInsights.length > 0 && /* @__PURE__ */ React4.createElement(Box4, { flexDirection: "column", marginBottom: 1 }, /* @__PURE__ */ React4.createElement(Text4, { bold: true, underline: true, color: "blue" }, "\u{1F4A1} AI-Generated Insights"), llm.pageTypeInsights.map((insight, idx) => /* @__PURE__ */ React4.createElement(Box4, { key: idx, marginTop: 0.5 }, /* @__PURE__ */ React4.createElement(Text4, { color: "cyan" }, "\u2022 ", insight)))), llm.summary && /* @__PURE__ */ React4.createElement(Box4, { flexDirection: "column", marginBottom: 1 }, /* @__PURE__ */ React4.createElement(Text4, { bold: true, underline: true }, "Summary"), /* @__PURE__ */ React4.createElement(Box4, { marginTop: 0.5 }, /* @__PURE__ */ React4.createElement(Text4, null, llm.summary))), llm.keyTopics && llm.keyTopics.length > 0 && /* @__PURE__ */ React4.createElement(Box4, { flexDirection: "column", marginBottom: 1 }, /* @__PURE__ */ React4.createElement(Text4, { bold: true, underline: true }, "\u{1F3F7}\uFE0F  Key Topics"), /* @__PURE__ */ React4.createElement(Box4, { marginTop: 0.5 }, /* @__PURE__ */ React4.createElement(Text4, null, llm.keyTopics.map((t) => `[${t}]`).join(" ")))), /* @__PURE__ */ React4.createElement(Box4, { flexDirection: "column", marginBottom: 1 }, /* @__PURE__ */ React4.createElement(Text4, { bold: true, underline: true }, "Metadata"), /* @__PURE__ */ React4.createElement(Box4, { marginTop: 0.5, flexDirection: "column" }, llm.readingLevel && /* @__PURE__ */ React4.createElement(Text4, null, /* @__PURE__ */ React4.createElement(Text4, { bold: true }, "Reading Level:"), " ", llm.readingLevel.description), llm.sentiment && /* @__PURE__ */ React4.createElement(Text4, null, /* @__PURE__ */ React4.createElement(Text4, { bold: true }, "Sentiment:"), " ", llm.sentiment), llm.technicalDepth && /* @__PURE__ */ React4.createElement(Text4, null, /* @__PURE__ */ React4.createElement(Text4, { bold: true }, "Technical Depth:"), " ", llm.technicalDepth))), llm.topEntities && llm.topEntities.length > 0 && /* @__PURE__ */ React4.createElement(Box4, { flexDirection: "column", marginBottom: 1 }, /* @__PURE__ */ React4.createElement(Text4, { bold: true, underline: true }, "\u{1F50D} Key Entities"), llm.topEntities.slice(0, 5).map((entity, idx) => /* @__PURE__ */ React4.createElement(Box4, { key: idx, marginTop: 0.5 }, /* @__PURE__ */ React4.createElement(Text4, null, "\u2022 ", /* @__PURE__ */ React4.createElement(Text4, { bold: true }, entity.name), " ", /* @__PURE__ */ React4.createElement(Text4, { dimColor: true }, "(", entity.type, ") - ", Math.round((entity.relevance || 0) * 100), "% relevance"))))), llm.questions && llm.questions.length > 0 && /* @__PURE__ */ React4.createElement(Box4, { flexDirection: "column", marginBottom: 1 }, /* @__PURE__ */ React4.createElement(Text4, { bold: true, underline: true }, "\u2753 Questions AI Can Answer"), llm.questions.slice(0, 5).map((q, idx) => /* @__PURE__ */ React4.createElement(Box4, { key: idx, marginTop: 0.5 }, /* @__PURE__ */ React4.createElement(Text4, null, idx + 1, ". ", /* @__PURE__ */ React4.createElement(Text4, { dimColor: true }, "[", q.difficulty.toUpperCase(), "]"), " ", q.question)))), llm.suggestedFAQ && llm.suggestedFAQ.length > 0 && /* @__PURE__ */ React4.createElement(
+    Box4,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "yellow",
+      paddingX: 2,
+      paddingY: 1
+    },
+    /* @__PURE__ */ React4.createElement(Text4, { bold: true, color: "yellow" }, "\u{1F4A1} Suggested FAQs"),
+    llm.suggestedFAQ.filter((f) => f.importance === "high").slice(0, 3).map((faq, idx) => /* @__PURE__ */ React4.createElement(Box4, { key: idx, flexDirection: "column", marginTop: 1 }, /* @__PURE__ */ React4.createElement(Text4, null, /* @__PURE__ */ React4.createElement(Text4, { bold: true }, "Q:"), " ", faq.question), /* @__PURE__ */ React4.createElement(Text4, { dimColor: true }, /* @__PURE__ */ React4.createElement(Text4, { bold: true }, "A:"), " ", faq.suggestedAnswer)))
+  ));
+};
+
+// src/ui/components/HallucinationSection.tsx
+import React5 from "react";
+import { Box as Box5, Text as Text5 } from "ink";
+var HallucinationSection = ({ hallucinationReport }) => {
+  if (!hallucinationReport || Object.keys(hallucinationReport).length === 0) {
+    return /* @__PURE__ */ React5.createElement(Box5, { flexDirection: "column", paddingY: 1 }, /* @__PURE__ */ React5.createElement(
+      Box5,
+      {
+        flexDirection: "column",
+        borderStyle: "round",
+        borderColor: "yellow",
+        paddingX: 2,
+        paddingY: 1
+      },
+      /* @__PURE__ */ React5.createElement(Text5, { bold: true, color: "yellow" }, "\u{1F4A1} Enable Hallucination Detection"),
+      /* @__PURE__ */ React5.createElement(Box5, { marginTop: 1, flexDirection: "column" }, /* @__PURE__ */ React5.createElement(Text5, null, "Hallucination detection is not enabled. To see risk assessment, run:"), /* @__PURE__ */ React5.createElement(Box5, { marginTop: 1, borderStyle: "single", paddingX: 1 }, /* @__PURE__ */ React5.createElement(Text5, { color: "cyan" }, "ai-lighthouse audit [URL] --enable-hallucination --enable-llm --llm-provider openai --llm-api-key YOUR_KEY")), /* @__PURE__ */ React5.createElement(Box5, { marginTop: 1 }, /* @__PURE__ */ React5.createElement(Text5, { dimColor: true }, "Note: Hallucination detection requires LLM analysis to be enabled")))
+    ));
+  }
+  const riskScore = hallucinationReport.hallucinationRiskScore;
+  const getRiskColor = (score) => {
+    if (score >= 70) return "red";
+    if (score >= 40) return "yellow";
+    return "green";
+  };
+  return /* @__PURE__ */ React5.createElement(Box5, { flexDirection: "column", paddingY: 1 }, /* @__PURE__ */ React5.createElement(
+    Box5,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: getRiskColor(riskScore),
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React5.createElement(Text5, { bold: true, color: getRiskColor(riskScore) }, "\u26A0\uFE0F  Hallucination Risk Assessment"),
+    /* @__PURE__ */ React5.createElement(Box5, { marginTop: 1 }, /* @__PURE__ */ React5.createElement(Text5, null, /* @__PURE__ */ React5.createElement(Text5, { bold: true }, "Risk Score: "), /* @__PURE__ */ React5.createElement(Text5, { bold: true, color: getRiskColor(riskScore) }, riskScore, "/100")))
+  ), hallucinationReport.factCheckSummary && /* @__PURE__ */ React5.createElement(
+    Box5,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "blue",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React5.createElement(Text5, { bold: true, color: "blue" }, "\u{1F4CA} Fact Check Summary"),
+    /* @__PURE__ */ React5.createElement(Box5, { marginTop: 1, flexDirection: "column" }, /* @__PURE__ */ React5.createElement(Text5, null, /* @__PURE__ */ React5.createElement(Text5, { bold: true }, "Total Facts:"), " ", hallucinationReport.factCheckSummary.totalFacts), /* @__PURE__ */ React5.createElement(Text5, null, /* @__PURE__ */ React5.createElement(Text5, { bold: true, color: "green" }, "Verified:"), " ", hallucinationReport.factCheckSummary.verifiedFacts), /* @__PURE__ */ React5.createElement(Text5, null, /* @__PURE__ */ React5.createElement(Text5, { bold: true, color: "yellow" }, "Unverified:"), " ", hallucinationReport.factCheckSummary.unverifiedFacts), /* @__PURE__ */ React5.createElement(Text5, null, /* @__PURE__ */ React5.createElement(Text5, { bold: true, color: "red" }, "Contradictions:"), " ", hallucinationReport.factCheckSummary.contradictions), hallucinationReport.factCheckSummary.ambiguities !== void 0 && /* @__PURE__ */ React5.createElement(Text5, null, /* @__PURE__ */ React5.createElement(Text5, { bold: true, color: "yellow" }, "Ambiguities:"), " ", hallucinationReport.factCheckSummary.ambiguities))
+  ), hallucinationReport.factCheckSummary?.unverifiedFacts > 0 && /* @__PURE__ */ React5.createElement(
+    Box5,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "yellow",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React5.createElement(Text5, { color: "yellow" }, "\u{1F4A1} Tip: Add citations and links to verify claims and reduce AI hallucination risk")
+  ), hallucinationReport.triggers && hallucinationReport.triggers.length > 0 && /* @__PURE__ */ React5.createElement(React5.Fragment, null, hallucinationReport.triggers.filter((t) => t.severity === "high" || t.severity === "critical").length > 0 && /* @__PURE__ */ React5.createElement(Box5, { flexDirection: "column", marginBottom: 1 }, /* @__PURE__ */ React5.createElement(Text5, { bold: true, underline: true, color: "red" }, "\u{1F6A8} High-Risk Triggers"), hallucinationReport.triggers.filter((t) => t.severity === "high" || t.severity === "critical").slice(0, 5).map((trigger, idx) => /* @__PURE__ */ React5.createElement(
+    Box5,
+    {
+      key: idx,
+      flexDirection: "column",
+      borderStyle: "single",
+      borderColor: "red",
+      paddingX: 1,
+      paddingY: 0.5,
+      marginTop: 1
+    },
+    /* @__PURE__ */ React5.createElement(Text5, null, idx + 1, ". ", /* @__PURE__ */ React5.createElement(Text5, { bold: true, color: "red" }, "[", trigger.severity.toUpperCase(), "]"), " ", trigger.type),
+    /* @__PURE__ */ React5.createElement(Text5, { dimColor: true }, trigger.description),
+    trigger.confidence && /* @__PURE__ */ React5.createElement(Text5, { dimColor: true }, "Confidence: ", Math.round(trigger.confidence * 100), "%")
+  )))), hallucinationReport.recommendations && hallucinationReport.recommendations.length > 0 && /* @__PURE__ */ React5.createElement(Box5, { flexDirection: "column" }, /* @__PURE__ */ React5.createElement(Text5, { bold: true, underline: true, color: "cyan" }, "\u{1F4A1} Recommendations"), hallucinationReport.recommendations.slice(0, 3).map((rec, idx) => /* @__PURE__ */ React5.createElement(Box5, { key: idx, marginTop: 0.5 }, /* @__PURE__ */ React5.createElement(Text5, { color: "cyan" }, idx + 1, ". ", rec)))));
+};
+
+// src/ui/components/MessageAlignmentSection.tsx
+import React6 from "react";
+import { Box as Box6, Text as Text6 } from "ink";
+var MessageAlignmentSection = ({ mirrorReport }) => {
+  if (!mirrorReport || Object.keys(mirrorReport).length === 0) {
+    return /* @__PURE__ */ React6.createElement(Box6, { flexDirection: "column", paddingY: 1 }, /* @__PURE__ */ React6.createElement(
+      Box6,
+      {
+        flexDirection: "column",
+        borderStyle: "round",
+        borderColor: "yellow",
+        paddingX: 2,
+        paddingY: 1
+      },
+      /* @__PURE__ */ React6.createElement(Text6, { bold: true, color: "yellow" }, "\u{1F4A1} Enable Message Alignment Analysis"),
+      /* @__PURE__ */ React6.createElement(Box6, { marginTop: 1, flexDirection: "column" }, /* @__PURE__ */ React6.createElement(Text6, null, "Message alignment analysis is not available. To see what AI understands, run:"), /* @__PURE__ */ React6.createElement(Box6, { marginTop: 1, borderStyle: "single", paddingX: 1 }, /* @__PURE__ */ React6.createElement(Text6, { color: "cyan" }, "ai-lighthouse audit [URL] --enable-llm --llm-provider openai --llm-api-key YOUR_KEY")), /* @__PURE__ */ React6.createElement(Box6, { marginTop: 1 }, /* @__PURE__ */ React6.createElement(Text6, { dimColor: true }, "This requires LLM analysis to compare AI understanding with your intended message")))
+    ));
+  }
+  const getScoreColor = (score) => {
+    if (score >= 80) return "green";
+    if (score >= 60) return "yellow";
+    return "red";
+  };
+  return /* @__PURE__ */ React6.createElement(Box6, { flexDirection: "column", paddingY: 1 }, /* @__PURE__ */ React6.createElement(
+    Box6,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "magenta",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React6.createElement(Text6, { bold: true, color: "magenta" }, "\u{1F50D} AI Misunderstanding Check"),
+    /* @__PURE__ */ React6.createElement(Box6, { marginTop: 1, flexDirection: "column" }, /* @__PURE__ */ React6.createElement(Box6, null, /* @__PURE__ */ React6.createElement(Text6, null, /* @__PURE__ */ React6.createElement(Text6, { bold: true }, "Alignment Score:"), " ", /* @__PURE__ */ React6.createElement(Text6, { bold: true, color: getScoreColor(mirrorReport.summary.alignmentScore) }, mirrorReport.summary.alignmentScore, "/100"))), /* @__PURE__ */ React6.createElement(Box6, null, /* @__PURE__ */ React6.createElement(Text6, null, /* @__PURE__ */ React6.createElement(Text6, { bold: true }, "Clarity Score:"), " ", /* @__PURE__ */ React6.createElement(Text6, { bold: true, color: getScoreColor(mirrorReport.summary.clarityScore) }, mirrorReport.summary.clarityScore, "/100"))), /* @__PURE__ */ React6.createElement(Box6, null, /* @__PURE__ */ React6.createElement(Text6, null, /* @__PURE__ */ React6.createElement(Text6, { bold: true }, "Critical Issues:"), " ", /* @__PURE__ */ React6.createElement(Text6, { color: "red" }, mirrorReport.summary.critical))), /* @__PURE__ */ React6.createElement(Box6, null, /* @__PURE__ */ React6.createElement(Text6, null, /* @__PURE__ */ React6.createElement(Text6, { bold: true }, "Major Issues:"), " ", /* @__PURE__ */ React6.createElement(Text6, { color: "yellow" }, mirrorReport.summary.major))))
+  ), mirrorReport.llmInterpretation && /* @__PURE__ */ React6.createElement(
+    Box6,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "blue",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React6.createElement(Text6, { bold: true, color: "blue" }, "\u{1F916} What AI Actually Understood"),
+    /* @__PURE__ */ React6.createElement(Text6, { dimColor: true }, "(", Math.round(mirrorReport.llmInterpretation.confidence * 100), "% confident)"),
+    /* @__PURE__ */ React6.createElement(Box6, { marginTop: 1, flexDirection: "column" }, mirrorReport.llmInterpretation.productName && /* @__PURE__ */ React6.createElement(Text6, null, /* @__PURE__ */ React6.createElement(Text6, { bold: true }, "Product:"), " ", mirrorReport.llmInterpretation.productName), mirrorReport.llmInterpretation.purpose && /* @__PURE__ */ React6.createElement(Text6, null, /* @__PURE__ */ React6.createElement(Text6, { bold: true }, "Purpose:"), " ", mirrorReport.llmInterpretation.purpose), mirrorReport.llmInterpretation.valueProposition && /* @__PURE__ */ React6.createElement(Text6, null, /* @__PURE__ */ React6.createElement(Text6, { bold: true, color: "magenta" }, "\u{1F48E} Value:"), " ", mirrorReport.llmInterpretation.valueProposition)),
+    mirrorReport.llmInterpretation.keyBenefits && mirrorReport.llmInterpretation.keyBenefits.length > 0 && /* @__PURE__ */ React6.createElement(Box6, { marginTop: 1, flexDirection: "column" }, /* @__PURE__ */ React6.createElement(Text6, { bold: true }, "Benefits:"), mirrorReport.llmInterpretation.keyBenefits.map((benefit, idx) => /* @__PURE__ */ React6.createElement(Text6, { key: idx }, "\u2022 ", benefit))),
+    mirrorReport.llmInterpretation.keyFeatures && mirrorReport.llmInterpretation.keyFeatures.length > 0 && /* @__PURE__ */ React6.createElement(Box6, { marginTop: 1, flexDirection: "column" }, /* @__PURE__ */ React6.createElement(Text6, { bold: true }, "Features:"), mirrorReport.llmInterpretation.keyFeatures.slice(0, 3).map((feature, idx) => /* @__PURE__ */ React6.createElement(Text6, { key: idx }, "\u2022 ", feature))),
+    mirrorReport.llmInterpretation.targetAudience && /* @__PURE__ */ React6.createElement(Box6, { marginTop: 1 }, /* @__PURE__ */ React6.createElement(Text6, null, /* @__PURE__ */ React6.createElement(Text6, { bold: true }, "Audience:"), " ", mirrorReport.llmInterpretation.targetAudience))
+  ), mirrorReport.mismatches && mirrorReport.mismatches.length > 0 && /* @__PURE__ */ React6.createElement(React6.Fragment, null, mirrorReport.mismatches.filter((m) => m.severity === "critical" || m.severity === "major").length > 0 && /* @__PURE__ */ React6.createElement(Box6, { flexDirection: "column", marginBottom: 1 }, /* @__PURE__ */ React6.createElement(Text6, { bold: true, underline: true }, "Priority Mismatches"), mirrorReport.mismatches.filter((m) => m.severity === "critical" || m.severity === "major").slice(0, 5).map((mismatch, idx) => /* @__PURE__ */ React6.createElement(
+    Box6,
+    {
+      key: idx,
+      flexDirection: "column",
+      borderStyle: "single",
+      borderColor: mismatch.severity === "critical" ? "red" : "yellow",
+      paddingX: 1,
+      paddingY: 0.5,
+      marginTop: 1
+    },
+    /* @__PURE__ */ React6.createElement(Text6, null, mismatch.severity === "critical" ? "\u{1F534}" : "\u{1F7E1}", " ", idx + 1, ". ", /* @__PURE__ */ React6.createElement(Text6, { bold: true }, mismatch.field)),
+    /* @__PURE__ */ React6.createElement(Text6, { dimColor: true }, mismatch.description),
+    /* @__PURE__ */ React6.createElement(Box6, { marginTop: 0.5 }, /* @__PURE__ */ React6.createElement(Text6, { color: "cyan" }, "\u2192 ", mismatch.recommendation))
+  )))), mirrorReport.recommendations && mirrorReport.recommendations.length > 0 && /* @__PURE__ */ React6.createElement(Box6, { flexDirection: "column" }, /* @__PURE__ */ React6.createElement(Text6, { bold: true, underline: true, color: "cyan" }, "\u{1F4A1} Top Recommendations"), mirrorReport.recommendations.slice(0, 3).map((rec, idx) => /* @__PURE__ */ React6.createElement(Box6, { key: idx, marginTop: 0.5 }, /* @__PURE__ */ React6.createElement(Text6, { color: "cyan" }, idx + 1, ". ", rec)))));
+};
+
+// src/ui/components/TechnicalSection.tsx
+import React7 from "react";
+import { Box as Box7, Text as Text7 } from "ink";
+var TechnicalSection = ({ result, scoring }) => {
+  const renderProgressBar = (score, width = 20) => {
+    const filled = Math.round(score / 100 * width);
+    const empty = width - filled;
+    const color = score >= 80 ? "green" : score >= 60 ? "yellow" : "red";
+    return /* @__PURE__ */ React7.createElement(Text7, { color }, "\u2588".repeat(filled), /* @__PURE__ */ React7.createElement(Text7, { dimColor: true }, "\u2591".repeat(empty)), ` ${Math.round(score)}%`);
+  };
+  return /* @__PURE__ */ React7.createElement(Box7, { flexDirection: "column", paddingY: 1 }, /* @__PURE__ */ React7.createElement(
+    Box7,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "blue",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React7.createElement(Text7, { bold: true, color: "blue" }, "\u{1F4CA} Category Scores"),
+    /* @__PURE__ */ React7.createElement(Box7, { marginTop: 1, flexDirection: "column" }, scoring?.crawlability !== void 0 && /* @__PURE__ */ React7.createElement(Box7, { flexDirection: "column", marginTop: 0.5 }, /* @__PURE__ */ React7.createElement(Box7, { justifyContent: "space-between" }, /* @__PURE__ */ React7.createElement(Text7, { bold: true }, "\u{1F577}\uFE0F  Crawlability"), /* @__PURE__ */ React7.createElement(Text7, null, Math.round(scoring.crawlability), "/100")), /* @__PURE__ */ React7.createElement(Box7, { marginTop: 0.5 }, renderProgressBar(scoring.crawlability))), scoring?.structure !== void 0 && /* @__PURE__ */ React7.createElement(Box7, { flexDirection: "column", marginTop: 1 }, /* @__PURE__ */ React7.createElement(Box7, { justifyContent: "space-between" }, /* @__PURE__ */ React7.createElement(Text7, { bold: true }, "\u{1F4D0} Structure"), /* @__PURE__ */ React7.createElement(Text7, null, Math.round(scoring.structure), "/100")), /* @__PURE__ */ React7.createElement(Box7, { marginTop: 0.5 }, renderProgressBar(scoring.structure))), scoring?.schema_coverage !== void 0 && /* @__PURE__ */ React7.createElement(Box7, { flexDirection: "column", marginTop: 1 }, /* @__PURE__ */ React7.createElement(Box7, { justifyContent: "space-between" }, /* @__PURE__ */ React7.createElement(Text7, { bold: true }, "\u{1F3F7}\uFE0F  Schema Coverage"), /* @__PURE__ */ React7.createElement(Text7, null, Math.round(scoring.schema_coverage), "/100")), /* @__PURE__ */ React7.createElement(Box7, { marginTop: 0.5 }, renderProgressBar(scoring.schema_coverage))), scoring?.content_clarity !== void 0 && /* @__PURE__ */ React7.createElement(Box7, { flexDirection: "column", marginTop: 1 }, /* @__PURE__ */ React7.createElement(Box7, { justifyContent: "space-between" }, /* @__PURE__ */ React7.createElement(Text7, { bold: true }, "\u{1F4DD} Content Clarity"), /* @__PURE__ */ React7.createElement(Text7, null, Math.round(scoring.content_clarity), "/100")), /* @__PURE__ */ React7.createElement(Box7, { marginTop: 0.5 }, renderProgressBar(scoring.content_clarity))))
+  ), result.chunking && Object.keys(result.chunking).length > 0 ? /* @__PURE__ */ React7.createElement(
+    Box7,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "green",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React7.createElement(Text7, { bold: true, color: "green" }, "\u{1F4C4} Content Chunking Analysis"),
+    /* @__PURE__ */ React7.createElement(Box7, { marginTop: 1, flexDirection: "column" }, /* @__PURE__ */ React7.createElement(Text7, null, /* @__PURE__ */ React7.createElement(Text7, { bold: true }, "Strategy:"), " ", result.chunking.chunkingStrategy), /* @__PURE__ */ React7.createElement(Text7, null, /* @__PURE__ */ React7.createElement(Text7, { bold: true }, "Total Chunks:"), " ", result.chunking.totalChunks), /* @__PURE__ */ React7.createElement(Text7, null, /* @__PURE__ */ React7.createElement(Text7, { bold: true }, "Avg Tokens/Chunk:"), " ", result.chunking.averageTokensPerChunk), /* @__PURE__ */ React7.createElement(Text7, null, /* @__PURE__ */ React7.createElement(Text7, { bold: true }, "Avg Noise Ratio:"), " ", (result.chunking.averageNoiseRatio * 100).toFixed(1), "%")),
+    result.chunking.chunkingStrategy === "heading-based" && /* @__PURE__ */ React7.createElement(Box7, { marginTop: 1 }, /* @__PURE__ */ React7.createElement(Text7, { color: "green" }, "\u2713 Heading-based chunking is ideal for AI comprehension")),
+    result.chunking.chunkingStrategy === "paragraph-based" && /* @__PURE__ */ React7.createElement(Box7, { marginTop: 1 }, /* @__PURE__ */ React7.createElement(Text7, { color: "yellow" }, "\u26A0 Consider adding headings for better semantic structure"))
+  ) : /* @__PURE__ */ React7.createElement(
+    Box7,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "gray",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React7.createElement(Text7, { dimColor: true }, "\u{1F4A1} Enable chunking analysis with --enable-chunking to see how your content is divided for AI processing")
+  ), result.extractability && Object.keys(result.extractability).length > 0 ? /* @__PURE__ */ React7.createElement(
+    Box7,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "yellow",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React7.createElement(Text7, { bold: true, color: "yellow" }, "\u{1F504} Extractability Analysis"),
+    /* @__PURE__ */ React7.createElement(Box7, { marginTop: 1, flexDirection: "column" }, /* @__PURE__ */ React7.createElement(Text7, null, /* @__PURE__ */ React7.createElement(Text7, { bold: true }, "Overall Score:"), " ", result.extractability.score.extractabilityScore, "/100"), /* @__PURE__ */ React7.createElement(Text7, null, /* @__PURE__ */ React7.createElement(Text7, { bold: true }, "Server-Rendered:"), " ", result.extractability.score.serverRenderedPercent, "%")),
+    /* @__PURE__ */ React7.createElement(Box7, { marginTop: 1, flexDirection: "column" }, /* @__PURE__ */ React7.createElement(Text7, { bold: true, underline: true }, "Content Type Extractability:"), Object.entries(result.extractability.contentTypes).map(([type, data]) => {
+      const percentage = data.percentage;
+      const color = percentage >= 80 ? "green" : percentage >= 50 ? "yellow" : "red";
+      return /* @__PURE__ */ React7.createElement(Box7, { key: type, marginTop: 0.5 }, /* @__PURE__ */ React7.createElement(Text7, null, /* @__PURE__ */ React7.createElement(Text7, { bold: true }, type.charAt(0).toUpperCase() + type.slice(1), ":"), " ", /* @__PURE__ */ React7.createElement(Text7, { color }, percentage, "%"), " ", /* @__PURE__ */ React7.createElement(Text7, { dimColor: true }, "(", data.extractable, "/", data.total, ")")));
+    })),
+    result.extractability.score.extractabilityScore >= 80 && /* @__PURE__ */ React7.createElement(Box7, { marginTop: 1 }, /* @__PURE__ */ React7.createElement(Text7, { color: "green" }, "\u2713 Good extractability - AI can easily read your content")),
+    result.extractability.score.extractabilityScore < 50 && /* @__PURE__ */ React7.createElement(Box7, { marginTop: 1 }, /* @__PURE__ */ React7.createElement(Text7, { color: "red" }, "\u26A0 Low extractability - Consider server-side rendering"))
+  ) : /* @__PURE__ */ React7.createElement(
+    Box7,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "gray",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React7.createElement(Text7, { dimColor: true }, "\u{1F4A1} Enable extractability analysis with --enable-extractability to see how well AI can extract your content")
+  ));
+};
+
+// src/ui/AuditReportUI.tsx
+var AuditReportUI = ({
+  url,
+  result,
+  aiReadiness,
+  loading = false,
+  currentStep = ""
+}) => {
+  const [currentTab, setCurrentTab] = useState2("overview");
+  const tabs = [
+    { key: "overview", label: "Overview", icon: "\u{1F4CA}" },
+    { key: "issues", label: "Issues", icon: "\u26A0\uFE0F" },
+    { key: "ai-understanding", label: "AI Understanding", icon: "\u{1F9E0}" },
+    { key: "hallucination", label: "Hallucination Risk", icon: "\u26A0\uFE0F" },
+    { key: "message-alignment", label: "Message Alignment", icon: "\u{1F50D}" },
+    { key: "technical", label: "Technical", icon: "\u2699\uFE0F" }
+  ];
+  useInput((input, key) => {
+    if (loading) return;
+    if (key.leftArrow) {
+      const currentIndex = tabs.findIndex((t) => t.key === currentTab);
+      const prevIndex = currentIndex > 0 ? currentIndex - 1 : tabs.length - 1;
+      setCurrentTab(tabs[prevIndex].key);
+    }
+    if (key.rightArrow) {
+      const currentIndex = tabs.findIndex((t) => t.key === currentTab);
+      const nextIndex = currentIndex < tabs.length - 1 ? currentIndex + 1 : 0;
+      setCurrentTab(tabs[nextIndex].key);
+    }
+    const num = parseInt(input);
+    if (num >= 1 && num <= tabs.length) {
+      setCurrentTab(tabs[num - 1].key);
+    }
+  });
+  if (loading) {
+    return /* @__PURE__ */ React8.createElement(Box8, { flexDirection: "column", paddingY: 1 }, /* @__PURE__ */ React8.createElement(Box8, null, /* @__PURE__ */ React8.createElement(Text8, { color: "green" }, /* @__PURE__ */ React8.createElement(Spinner, { type: "dots" })), /* @__PURE__ */ React8.createElement(Text8, null, " ", currentStep || "Loading...")));
+  }
+  const overallScore = aiReadiness?.overall || 0;
+  const grade = aiReadiness?.grade || "N/A";
+  return /* @__PURE__ */ React8.createElement(Box8, { flexDirection: "column" }, /* @__PURE__ */ React8.createElement(
+    Box8,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "cyan",
+      paddingX: 2,
+      paddingY: 1
+    },
+    /* @__PURE__ */ React8.createElement(Text8, { bold: true, color: "cyan" }, "\u{1F6A8} AI Lighthouse Report")
+  ), /* @__PURE__ */ React8.createElement(ScoreDisplay, { score: overallScore, grade, url }), /* @__PURE__ */ React8.createElement(
+    Box8,
+    {
+      flexDirection: "row",
+      borderStyle: "single",
+      borderColor: "blue",
+      paddingX: 1,
+      marginTop: 1
+    },
+    tabs.map((tab, index) => {
+      const isActive = tab.key === currentTab;
+      return /* @__PURE__ */ React8.createElement(Box8, { key: tab.key, marginRight: 1 }, /* @__PURE__ */ React8.createElement(
+        Text8,
+        {
+          bold: isActive,
+          color: isActive ? "cyan" : "gray",
+          backgroundColor: isActive ? "blue" : void 0
+        },
+        ` ${index + 1}. ${tab.icon} ${tab.label} `
+      ));
+    })
+  ), /* @__PURE__ */ React8.createElement(Box8, { marginTop: 1, marginBottom: 1 }, /* @__PURE__ */ React8.createElement(Text8, { dimColor: true }, "Use \u2190 \u2192 arrow keys or numbers (1-", tabs.length, ") to navigate tabs")), /* @__PURE__ */ React8.createElement(Box8, { flexDirection: "column" }, currentTab === "overview" && /* @__PURE__ */ React8.createElement(OverviewSection, { aiReadiness }), currentTab === "issues" && /* @__PURE__ */ React8.createElement(IssuesSection, { issues: result.issues || [] }), currentTab === "ai-understanding" && /* @__PURE__ */ React8.createElement(AIUnderstandingSection, { llm: result.llm }), currentTab === "hallucination" && /* @__PURE__ */ React8.createElement(HallucinationSection, { hallucinationReport: result.hallucinationReport }), currentTab === "message-alignment" && /* @__PURE__ */ React8.createElement(MessageAlignmentSection, { mirrorReport: result.mirrorReport }), currentTab === "technical" && /* @__PURE__ */ React8.createElement(TechnicalSection, { result, scoring: result.scoring })), /* @__PURE__ */ React8.createElement(
+    Box8,
+    {
+      marginTop: 2,
+      borderStyle: "round",
+      borderColor: "gray",
+      paddingX: 2,
+      paddingY: 1
+    },
+    /* @__PURE__ */ React8.createElement(Text8, { dimColor: true }, "Press Ctrl+C to exit \u2022 Report generated at ", (/* @__PURE__ */ new Date()).toLocaleString())
+  ));
+};
+
+// src/ui/SetupWizard.tsx
+import React9, { useState as useState3 } from "react";
+import { Box as Box9, Text as Text9, useApp } from "ink";
+import TextInput from "ink-text-input";
+import SelectInput from "ink-select-input";
+var SetupWizard = ({ onComplete, initialUrl }) => {
+  const { exit } = useApp();
+  const [step, setStep] = useState3(initialUrl ? "features" : "url");
+  const [url, setUrl] = useState3(initialUrl || "");
+  const [selectedFeatures, setSelectedFeatures] = useState3([]);
+  const [llmProvider, setLlmProvider] = useState3("");
+  const [llmModel, setLlmModel] = useState3("");
+  const [llmApiKey, setLlmApiKey] = useState3("");
+  const [llmBaseUrl, setLlmBaseUrl] = useState3("");
+  const featureOptions = [
+    { label: "\u{1F9E0} AI Understanding (LLM Analysis)", value: "llm" },
+    { label: "\u{1F4C4} Content Chunking Analysis", value: "chunking" },
+    { label: "\u{1F504} Extractability Analysis", value: "extractability" },
+    { label: "\u26A0\uFE0F  Hallucination Detection", value: "hallucination" },
+    { label: "\u2705 Continue with selected features", value: "done" }
+  ];
+  const llmProviderOptions = [
+    { label: "OpenAI (GPT-4, GPT-3.5)", value: "openai" },
+    { label: "Anthropic (Claude)", value: "anthropic" },
+    { label: "Ollama (Local)", value: "ollama" },
+    { label: "Custom/Local Provider", value: "local" }
+  ];
+  const handleUrlSubmit = (value) => {
+    setUrl(value);
+    setStep("features");
+  };
+  const handleFeatureSelect = (item) => {
+    if (item.value === "done") {
+      if (selectedFeatures.includes("llm") || selectedFeatures.includes("hallucination")) {
+        setStep("llm-provider");
+      } else {
+        completeSetup();
+      }
+    } else {
+      if (selectedFeatures.includes(item.value)) {
+        setSelectedFeatures(selectedFeatures.filter((f) => f !== item.value));
+      } else {
+        setSelectedFeatures([...selectedFeatures, item.value]);
+      }
+    }
+  };
+  const handleLlmProviderSelect = (item) => {
+    setLlmProvider(item.value);
+    if (item.value === "ollama") {
+      setLlmBaseUrl("http://localhost:11434");
+    }
+    setStep("llm-model");
+  };
+  const handleLlmModelSubmit = (value) => {
+    setLlmModel(value);
+    if (llmProvider === "ollama") {
+      setStep("llm-base-url");
+    } else {
+      setStep("llm-api-key");
+    }
+  };
+  const handleLlmApiKeySubmit = (value) => {
+    setLlmApiKey(value);
+    if (llmProvider === "local" || llmProvider === "anthropic") {
+      setStep("llm-base-url");
+    } else {
+      completeSetup();
+    }
+  };
+  const handleLlmBaseUrlSubmit = (value) => {
+    setLlmBaseUrl(value);
+    completeSetup();
+  };
+  const completeSetup = () => {
+    const config = {
+      url,
+      enableLlm: selectedFeatures.includes("llm") || selectedFeatures.includes("hallucination"),
+      enableChunking: selectedFeatures.includes("chunking"),
+      enableExtractability: selectedFeatures.includes("extractability"),
+      enableHallucination: selectedFeatures.includes("hallucination")
+    };
+    if (config.enableLlm) {
+      config.llmProvider = llmProvider;
+      config.llmModel = llmModel;
+      config.llmApiKey = llmApiKey || void 0;
+      config.llmBaseUrl = llmBaseUrl || void 0;
+    }
+    onComplete(config);
+    exit();
+  };
+  const getModelPlaceholder = () => {
+    switch (llmProvider) {
+      case "openai":
+        return "gpt-4o-mini (default)";
+      case "anthropic":
+        return "claude-3-5-sonnet-20241022 (default)";
+      case "ollama":
+        return "qwen2.5:0.5b";
+      default:
+        return "model-name";
+    }
+  };
+  const getApiKeyPlaceholder = () => {
+    switch (llmProvider) {
+      case "openai":
+        return "sk-...";
+      case "anthropic":
+        return "sk-ant-...";
+      default:
+        return "your-api-key";
+    }
+  };
+  return /* @__PURE__ */ React9.createElement(Box9, { flexDirection: "column", paddingY: 1 }, /* @__PURE__ */ React9.createElement(
+    Box9,
+    {
+      flexDirection: "column",
+      borderStyle: "round",
+      borderColor: "cyan",
+      paddingX: 2,
+      paddingY: 1,
+      marginBottom: 1
+    },
+    /* @__PURE__ */ React9.createElement(Text9, { bold: true, color: "cyan" }, "\u{1F6A8} AI Lighthouse Setup Wizard"),
+    /* @__PURE__ */ React9.createElement(Text9, { dimColor: true }, "Configure your audit settings")
+  ), step === "url" && /* @__PURE__ */ React9.createElement(Box9, { flexDirection: "column" }, /* @__PURE__ */ React9.createElement(Text9, { bold: true }, "Enter the URL to audit:"), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(Text9, { color: "cyan" }, "URL: "), /* @__PURE__ */ React9.createElement(
+    TextInput,
+    {
+      value: url,
+      onChange: setUrl,
+      onSubmit: handleUrlSubmit,
+      placeholder: "https://example.com"
+    }
+  )), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(Text9, { dimColor: true }, "Press Enter to continue"))), step === "features" && /* @__PURE__ */ React9.createElement(Box9, { flexDirection: "column" }, /* @__PURE__ */ React9.createElement(Text9, { bold: true }, "Select features to enable:"), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(Text9, { dimColor: true }, "Selected: ", selectedFeatures.length === 0 ? "None (basic audit only)" : selectedFeatures.map((f) => {
+    const feature = featureOptions.find((opt) => opt.value === f);
+    return feature?.label.split(" ")[0];
+  }).join(", "))), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(
+    SelectInput,
+    {
+      items: featureOptions.map((opt) => ({
+        ...opt,
+        label: selectedFeatures.includes(opt.value) && opt.value !== "done" ? `\u2713 ${opt.label}` : opt.label
+      })),
+      onSelect: handleFeatureSelect
+    }
+  )), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(Text9, { dimColor: true }, "Use \u2191\u2193 to navigate, Enter to toggle/continue"))), step === "llm-provider" && /* @__PURE__ */ React9.createElement(Box9, { flexDirection: "column" }, /* @__PURE__ */ React9.createElement(Text9, { bold: true }, "Select LLM provider:"), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(SelectInput, { items: llmProviderOptions, onSelect: handleLlmProviderSelect })), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(Text9, { dimColor: true }, "Use \u2191\u2193 to navigate, Enter to select"))), step === "llm-model" && /* @__PURE__ */ React9.createElement(Box9, { flexDirection: "column" }, /* @__PURE__ */ React9.createElement(Text9, { bold: true }, "Enter LLM model name:"), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(Text9, { color: "cyan" }, "Model: "), /* @__PURE__ */ React9.createElement(
+    TextInput,
+    {
+      value: llmModel,
+      onChange: setLlmModel,
+      onSubmit: handleLlmModelSubmit,
+      placeholder: getModelPlaceholder()
+    }
+  )), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(Text9, { dimColor: true }, "Leave empty for default, or press Enter to continue"))), step === "llm-api-key" && /* @__PURE__ */ React9.createElement(Box9, { flexDirection: "column" }, /* @__PURE__ */ React9.createElement(Text9, { bold: true }, "Enter API key:"), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(Text9, { color: "cyan" }, "API Key: "), /* @__PURE__ */ React9.createElement(
+    TextInput,
+    {
+      value: llmApiKey,
+      onChange: setLlmApiKey,
+      onSubmit: handleLlmApiKeySubmit,
+      placeholder: getApiKeyPlaceholder(),
+      mask: "*"
+    }
+  )), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(Text9, { dimColor: true }, "Your API key will not be stored"))), step === "llm-base-url" && /* @__PURE__ */ React9.createElement(Box9, { flexDirection: "column" }, /* @__PURE__ */ React9.createElement(Text9, { bold: true }, "Enter API base URL (optional):"), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(Text9, { color: "cyan" }, "Base URL: "), /* @__PURE__ */ React9.createElement(
+    TextInput,
+    {
+      value: llmBaseUrl,
+      onChange: setLlmBaseUrl,
+      onSubmit: handleLlmBaseUrlSubmit,
+      placeholder: llmProvider === "ollama" ? "http://localhost:11434" : "https://api.example.com"
+    }
+  )), /* @__PURE__ */ React9.createElement(Box9, { marginTop: 1 }, /* @__PURE__ */ React9.createElement(Text9, { dimColor: true }, "Press Enter to continue (leave empty for default)"))));
+};
+
+// src/commands/audit.ts
+function auditCommand(program2) {
+  program2.command("audit").description("Audit a website for AI readiness").argument("<url>", "URL to audit").option("-o, --output <format>", "Output format: json, html, pdf, lhr, csv, interactive", "interactive").option("-r, --rules <preset>", "Rule preset: default, strict, minimal", "default").option("-d, --depth <number>", "Crawl depth (for multi-page audits)", parseInt, 1).option("-p, --pages <urls>", "Comma-separated list of specific pages to audit").option("--cache-ttl <seconds>", "Cache TTL in seconds to avoid re-fetching", parseInt).option("--threshold <score>", "Minimum score threshold (exit 1 if below)", parseInt).option("--max-chunk-tokens <number>", "Maximum tokens per content chunk", parseInt, 1200).option("--chunking-strategy <strategy>", "Chunking strategy: auto, heading-based, paragraph-based", "auto").option("--enable-chunking", "Enable detailed content chunking analysis", false).option("--enable-extractability", "Enable extractability mapping", false).option("--enable-hallucination", "Enable hallucination detection", false).option("--enable-llm", "Enable LLM comprehension analysis", false).option("--min-impact <number>", "Minimum impact score to include", parseInt, 8).option("--min-confidence <number>", "Minimum confidence to include (0-1)", parseFloat, 0.7).option("--max-issues <number>", "Maximum issues to return", parseInt, 20).option("--llm-provider <provider>", "LLM provider: openai, anthropic, ollama, local").option("--llm-model <model>", "LLM model name").option("--llm-base-url <url>", "LLM API base URL").option("--llm-api-key <key>", "LLM API key").action(async (url, options) => {
+    const hasFeatureFlags = options.enableChunking || options.enableExtractability || options.enableHallucination || options.enableLlm || options.llmProvider;
+    if (options.output === "interactive" && !hasFeatureFlags) {
+      const originalConsoleError = console.error;
+      const originalConsoleWarn = console.warn;
+      console.error = () => {
+      };
+      console.warn = () => {
+      };
+      let auditConfig = null;
+      const wizardRender = render(
+        React10.createElement(SetupWizard, {
+          initialUrl: url,
+          onComplete: (config) => {
+            auditConfig = config;
+          }
+        })
+      );
+      await wizardRender.waitUntilExit();
+      if (!auditConfig) {
+        console.error = originalConsoleError;
+        console.warn = originalConsoleWarn;
+        console.log("\nAudit cancelled.");
+        process.exit(0);
+      }
+      url = auditConfig.url;
+      options.enableChunking = auditConfig.enableChunking;
+      options.enableExtractability = auditConfig.enableExtractability;
+      options.enableHallucination = auditConfig.enableHallucination;
+      options.enableLlm = auditConfig.enableLlm;
+      options.llmProvider = auditConfig.llmProvider;
+      options.llmModel = auditConfig.llmModel;
+      options.llmApiKey = auditConfig.llmApiKey;
+      options.llmBaseUrl = auditConfig.llmBaseUrl;
+    }
+    if (options.output === "interactive") {
+      const originalConsoleError = console.error;
+      const originalConsoleWarn = console.warn;
+      console.error = () => {
+      };
+      console.warn = () => {
+      };
+      const { waitUntilExit, clear, rerender } = render(
+        React10.createElement(AuditReportUI, {
+          url,
+          result: {},
+          aiReadiness: {},
+          loading: true,
+          currentStep: "Starting audit..."
+        })
+      );
+      try {
+        const urlObj = new URL(url);
+        const scanOptions = {
+          maxChunkTokens: options.maxChunkTokens,
+          chunkingStrategy: options.chunkingStrategy,
+          enableChunking: options.enableChunking,
+          enableExtractability: options.enableExtractability,
+          enableHallucinationDetection: options.enableHallucination,
+          enableLLM: options.enableLlm,
+          minImpactScore: options.minImpact,
+          minConfidence: options.minConfidence,
+          maxIssues: options.maxIssues
+        };
+        if (options.enableLlm && options.llmProvider) {
+          scanOptions.llmConfig = {
+            provider: options.llmProvider,
+            model: options.llmModel,
+            baseUrl: options.llmBaseUrl,
+            apiKey: options.llmApiKey
+          };
+        }
+        rerender(
+          React10.createElement(AuditReportUI, {
+            url: urlObj.href,
+            result: {},
+            aiReadiness: {},
+            loading: true,
+            currentStep: "Scanning page..."
+          })
+        );
+        const result = await analyzeUrlWithRules(url, scanOptions);
+        rerender(
+          React10.createElement(AuditReportUI, {
+            url: urlObj.href,
+            result,
+            aiReadiness: {},
+            loading: true,
+            currentStep: "Calculating AI readiness scores..."
+          })
+        );
+        const aiReadiness = calculateAIReadiness(result);
+        clear();
+        const finalRender = render(
+          React10.createElement(AuditReportUI, {
+            url: urlObj.href,
+            result,
+            aiReadiness,
+            loading: false
+          })
+        );
+        await finalRender.waitUntilExit();
+        console.error = originalConsoleError;
+        console.warn = originalConsoleWarn;
+        if (options.threshold !== void 0) {
+          const overallScore = aiReadiness.overall;
+          if (overallScore !== void 0 && overallScore < options.threshold) {
+            process.exit(1);
+          }
+        }
+      } catch (error) {
+        console.error = originalConsoleError;
+        console.warn = originalConsoleWarn;
+        clear();
+        console.log("\n" + chalk2.bold.red("\u274C Audit Failed"));
+        console.log(chalk2.red("\u2500".repeat(70)));
+        console.log(chalk2.red(error instanceof Error ? error.message : String(error)));
+        console.log("\n" + chalk2.dim("Please check the URL and your configuration."));
+        process.exit(1);
+      }
+      return;
+    }
+    const spinner = ora("Starting audit...").start();
+    try {
+      const urlObj = new URL(url);
+      spinner.text = `Auditing ${chalk2.cyan(urlObj.href)}...`;
+      const scanOptions = {
+        maxChunkTokens: options.maxChunkTokens,
+        chunkingStrategy: options.chunkingStrategy,
+        enableChunking: options.enableChunking,
+        enableExtractability: options.enableExtractability,
+        enableHallucinationDetection: options.enableHallucination,
+        enableLLM: options.enableLlm,
+        minImpactScore: options.minImpact,
+        minConfidence: options.minConfidence,
+        maxIssues: options.maxIssues
+      };
+      if (options.enableLlm && options.llmProvider) {
+        scanOptions.llmConfig = {
+          provider: options.llmProvider,
+          model: options.llmModel,
+          baseUrl: options.llmBaseUrl,
+          apiKey: options.llmApiKey
+        };
+      }
+      spinner.text = "Scanning page...";
+      const result = await analyzeUrlWithRules(url, scanOptions);
+      spinner.text = "Calculating scores...";
+      const aiReadiness = calculateAIReadiness(result);
+      spinner.text = "Generating report...";
+      const auditReportJson = exportAuditReport(result);
+      const auditReport = JSON.parse(auditReportJson);
+      const outputDir = resolve(process.cwd(), ".ai-lighthouse");
+      if (!existsSync(outputDir)) {
+        await mkdir(outputDir, { recursive: true });
+      }
+      const timestamp = (/* @__PURE__ */ new Date()).toISOString().replace(/:/g, "-").split(".")[0];
+      const baseFilename = `audit_${new URL(url).hostname}_${timestamp}`;
+      if (options.output === "json") {
+        const jsonPath = join(outputDir, `${baseFilename}.json`);
+        await writeFile(jsonPath, auditReportJson);
+        spinner.succeed(chalk2.green("Audit complete!"));
+        console.log(chalk2.dim(`Report saved to: ${jsonPath}`));
+      } else if (options.output === "html") {
+        const htmlPath = join(outputDir, `${baseFilename}.html`);
+        const html = generateHTMLReport(auditReport, aiReadiness, result);
+        await writeFile(htmlPath, html);
+        spinner.succeed(chalk2.green("Audit complete!"));
+        console.log(chalk2.dim(`HTML report saved to: ${htmlPath}`));
+        console.log(chalk2.dim(`\u{1F4A1} Tip: Open the HTML file and use your browser's "Print > Save as PDF" to export as PDF`));
+      } else if (options.output === "pdf") {
+        spinner.text = "Generating PDF...";
+        const pdfPath = join(outputDir, `${baseFilename}.pdf`);
+        const html = generateHTMLReport(auditReport, aiReadiness, result);
+        const file = { content: html };
+        const pdfOptions = {
+          format: "A4",
+          printBackground: false
+        };
+        const pdfBuffer = await html_to_pdf.generatePdf(file, pdfOptions);
+        await writeFile(pdfPath, pdfBuffer);
+        spinner.succeed(chalk2.green("PDF generated!"));
+        console.log(chalk2.dim(`PDF report saved to: ${pdfPath}`));
+      } else if (options.output === "lhr") {
+        const lhrPath = join(outputDir, `${baseFilename}.lhr.json`);
+        const lhr = convertToLighthouseFormat(auditReport);
+        await writeFile(lhrPath, JSON.stringify(lhr, null, 2));
+        spinner.succeed(chalk2.green("Audit complete!"));
+        console.log(chalk2.dim(`Lighthouse-compatible report saved to: ${lhrPath}`));
+      } else if (options.output === "csv") {
+        const csvPath = join(outputDir, `${baseFilename}.csv`);
+        const csv = generateCSVReport(auditReport);
+        await writeFile(csvPath, csv);
+        spinner.succeed(chalk2.green("Audit complete!"));
+        console.log(chalk2.dim(`CSV report saved to: ${csvPath}`));
+      }
+      console.log("\n" + chalk2.bold("\u{1F4CA} AI Readiness Summary"));
+      console.log(formatAIReadinessReport(aiReadiness));
+      console.log("\n" + chalk2.bold("\u{1F4C8} Technical Scores"));
+      console.log(generateScoringSummary(result.scoring));
+      console.log("\n" + chalk2.bold("\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550"));
+      console.log(chalk2.bold.cyan("                    COMPREHENSIVE ANALYSIS                           "));
+      console.log(chalk2.bold("\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550\u2550"));
+      console.log(formatComprehensiveReport(result, aiReadiness));
+      if (result.issues && result.issues.length > 0) {
+        console.log("\n" + formatDetailedIssues(result.issues));
+      }
+      if (options.threshold !== void 0) {
+        const overallScore = auditReport?.scores?.overall;
+        if (overallScore !== void 0 && overallScore < options.threshold) {
+          console.log(chalk2.red(`
+\u274C Score ${overallScore} is below threshold ${options.threshold}`));
+          process.exit(1);
+        } else if (overallScore !== void 0) {
+          console.log(chalk2.green(`
+\u2705 Score ${overallScore} meets threshold ${options.threshold}`));
+        }
+      }
+    } catch (error) {
+      spinner.fail(chalk2.red("Audit failed"));
+      if (error instanceof Error) {
+        console.error(chalk2.red(error.message));
+      }
+      process.exit(1);
+    }
+  });
+}
+function generateHTMLReport(report, aiReadiness, scanResult) {
+  return `<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>AI Lighthouse Report - ${report.input?.requested_url}</title>
+  <style>
+    * { margin: 0; padding: 0; box-sizing: border-box; }
+    body { 
+      font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, Oxygen, Ubuntu, sans-serif;
+      line-height: 1.6;
+      color: #333;
+      background: #f5f5f5;
+      padding: 20px;
+    }
+    .container { color: #333; max-width: 1200px; margin: 0 auto; background: white; padding: 40px; border-radius: 8px; }
+    h1 { color: #2563eb; margin-bottom: 10px; font-size: 2em; }
+    h2 { color: #1e40af; margin-top: 30px; margin-bottom: 15px; border-bottom: 2px solid #dbeafe; padding-bottom: 10px; }
+    h3 { color: #1e40af; margin-top: 20px; margin-bottom: 10px; font-size: 1.2em; }
+    .header { margin-bottom: 30px; }
+    .url { color: #64748b; font-size: 0.95em; }
+    .timestamp { color: #94a3b8; font-size: 0.85em; }
+    
+    .ai-readiness-banner {
+      background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+      color: white;
+      padding: 30px;
+      border-radius: 8px;
+      margin: 20px 0;
+      box-shadow: 0 4px 6px rgba(0,0,0,0.1);
+    }
+    .ai-readiness-banner h2 { color: white; border: none; margin: 0 0 20px 0; }
+    .overall-score { font-size: 3em; font-weight: bold; margin: 10px 0; }
+    .grade-badge { background: rgba(255,255,255,0.2); padding: 8px 16px; border-radius: 20px; display: inline-block; margin: 10px 0; }
+    .agent-perspective { background: rgba(255,255,255,0.1); padding: 20px; border-radius: 8px; margin: 20px 0; }
+    .agent-status { display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 15px; margin: 15px 0; }
+    .agent-status-item { display: flex; align-items: center; gap: 10px; }
+    
+    .scores { display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 20px; margin: 20px 0; }
+    .score-card { 
+      background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+      color: white;
+      padding: 20px;
+      border-radius: 8px;
+      box-shadow: 0 4px 6px rgba(0,0,0,0.1);
+    }
+    .score-card h3 { font-size: 0.9em; opacity: 0.9; margin-bottom: 10px; }
+    .score-value { font-size: 2.5em; font-weight: bold; }
+    .grade { font-size: 1.2em; opacity: 0.8; margin-left: 10px; }
+    
+    .dimensions { display: grid; gap: 15px; margin: 20px 0; }
+    .dimension { background: #f8fafc; border-left: 4px solid #cbd5e1; padding: 20px; border-radius: 4px; }
+    .dimension.excellent { border-left-color: #10b981; }
+    .dimension.good { border-left-color: #84cc16; }
+    .dimension.needs-work { border-left-color: #f59e0b; }
+    .dimension.critical { border-left-color: #dc2626; }
+    .dimension-header { display: flex; justify-content: space-between; align-items: center; margin-bottom: 10px; }
+    .dimension-name { font-weight: 600; font-size: 1.1em; color: #1e293b; }
+    .dimension-score { font-size: 1.5em; font-weight: bold; }
+    .dimension-level { color: #64748b; font-size: 0.9em; margin-bottom: 10px; text-transform: uppercase; }
+    .dimension-recommendations { margin-top: 10px; padding-left: 20px; }
+    .dimension-recommendations li { margin: 5px 0; color: #475569; }
+    
+    .quick-wins { background: #fffbeb; border: 2px solid #fbbf24; padding: 20px; border-radius: 8px; margin: 20px 0; }
+    .quick-wins h3 { color: #92400e; margin-top: 0; }
+    .quick-win { background: white; padding: 15px; margin: 10px 0; border-radius: 4px; border-left: 3px solid #f59e0b; }
+    .quick-win-header { font-weight: 600; color: #1e293b; margin-bottom: 8px; }
+    .quick-win-meta { font-size: 0.85em; color: #64748b; }
+    
+    .priorities { margin: 20px 0; }
+    .priority-section { background: #f8fafc; padding: 20px; border-radius: 8px; margin: 15px 0; }
+    .priority-section.immediate { border-left: 4px solid #dc2626; }
+    .priority-section.short-term { border-left: 4px solid #f59e0b; }
+    .priority-section.long-term { border-left: 4px solid #3b82f6; }
+    .priority-item { margin: 10px 0; padding-left: 20px; }
+    
+    .issues { margin: 20px 0; }
+    .issue { 
+      background: #f8fafc;
+      border-left: 4px solid #cbd5e1;
+      padding: 15px;
+      margin-bottom: 15px;
+      border-radius: 4px;
+    }
+    .issue.critical { border-left-color: #dc2626; background: #fef2f2; }
+    .issue.high { border-left-color: #ea580c; background: #fff7ed; }
+    .issue.medium { border-left-color: #f59e0b; background: #fffbeb; }
+    .issue.low { border-left-color: #84cc16; background: #f7fee7; }
+    .issue-title { font-weight: 600; color: #1e293b; margin-bottom: 8px; }
+    .issue-meta { font-size: 0.85em; color: #64748b; margin-bottom: 8px; }
+    .issue-desc { color: #475569; margin-bottom: 8px; }
+    .issue-fix { color: #0f766e; background: #f0fdfa; padding: 10px; border-radius: 4px; font-size: 0.9em; }
+    
+    .entity-list { display: grid; gap: 15px; }
+    .entity { background: #f0f9ff; border: 1px solid #bae6fd; padding: 15px; border-radius: 4px; }
+    .entity-name { font-weight: 600; color: #0c4a6e; }
+    .entity-type { color: #0369a1; font-size: 0.85em; }
+    
+    .print-button { 
+      background: #2563eb; 
+      color: white; 
+      padding: 12px 24px; 
+      border: none; 
+      border-radius: 6px; 
+      cursor: pointer; 
+      font-size: 1em;
+      margin: 20px 0;
+      box-shadow: 0 2px 4px rgba(0,0,0,0.1);
+    }
+    .print-button:hover { background: #1e40af; }
+    
+    @media print {
+      body { background: white; padding: 0; }
+      .container { box-shadow: none; }
+      .print-button { display: none; }
+    }
+  </style>
+</head>
+<body>
+  <div class="container">
+    <div class="header">
+      <h1>\u{1F6A8} AI Lighthouse Report</h1>
+      <div class="url">${report.input?.requested_url}</div>
+      <div class="timestamp">Generated: ${new Date(report.scanned_at).toLocaleString()}</div>
+    </div>
+
+    ${aiReadiness ? `
+    <div class="ai-readiness-banner">
+      <h2>\u{1F916} AI Readiness Assessment</h2>
+      <div class="overall-score">${Math.round(aiReadiness.overall)}/100</div>
+      <div class="grade-badge">Grade: ${aiReadiness.grade}</div>
+      <div style="margin: 10px 0; opacity: 0.9;">
+        Top ${aiReadiness.benchmark?.topPercentile || 0}% of sites \u2022 
+        Improvement potential: +${Math.round(aiReadiness.benchmark?.improvement || 0)} points to best-in-class
+      </div>
+      
+      <div class="agent-perspective">
+        <strong>AI Agent Perspective:</strong>
+        <div class="agent-status">
+          <div class="agent-status-item">
+            <span>${aiReadiness.aiPerspective?.canUnderstand ? "\u2705" : "\u274C"}</span>
+            <span>Can Understand</span>
+          </div>
+          <div class="agent-status-item">
+            <span>${aiReadiness.aiPerspective?.canExtract ? "\u2705" : "\u274C"}</span>
+            <span>Can Extract</span>
+          </div>
+          <div class="agent-status-item">
+            <span>${aiReadiness.aiPerspective?.canIndex ? "\u2705" : "\u274C"}</span>
+            <span>Can Index</span>
+          </div>
+          <div class="agent-status-item">
+            <span>${aiReadiness.aiPerspective?.canAnswer ? "\u2705" : "\u274C"}</span>
+            <span>Can Answer Questions</span>
+          </div>
+        </div>
+        <div style="margin-top: 15px;">
+          <strong>Confidence Level:</strong> ${Math.round((aiReadiness.aiPerspective?.confidence || 0) * 100)}%
+        </div>
+      </div>
+      
+      ${(aiReadiness.aiPerspective?.mainBlockers || []).length > 0 ? `
+        <div style="margin-top: 20px;">
+          <strong>Main Blockers:</strong>
+          <ul style="margin: 10px 0; padding-left: 20px;">
+            ${(aiReadiness.aiPerspective?.mainBlockers || []).map((blocker) => `<li>${blocker}</li>`).join("")}
+          </ul>
+        </div>
+      ` : ""}
+    </div>
+    ` : ""}
+
+    <h2>\u{1F4CA} Technical Scores</h2>
+    <div class="scores">
+      <div class="score-card">
+        <h3>Overall Score</h3>
+        <div>
+          <span class="score-value">${report.scores?.overall || 0}</span>
+          <span class="grade">${getLetterGrade(report.scores?.overall || 0)}</span>
+        </div>
+      </div>
+      <div class="score-card">
+        <h3>AI Readiness</h3>
+        <div class="score-value">${report.scores?.ai_readiness || 0}</div>
+      </div>
+      <div class="score-card">
+        <h3>Crawlability</h3>
+        <div class="score-value">${report.scores?.crawlability || 0}</div>
+      </div>
+      <div class="score-card">
+        <h3>Content Clarity</h3>
+        <div class="score-value">${report.scores?.content_clarity || 0}</div>
+      </div>
+      <div class="score-card">
+        <h3>Schema Coverage</h3>
+        <div class="score-value">${report.scores?.schema_coverage || 0}</div>
+      </div>
+      <div class="score-card">
+        <h3>Structure</h3>
+        <div class="score-value">${report.scores?.structure || 0}</div>
+      </div>
+    </div>
+
+    ${aiReadiness?.dimensions ? `
+    <h2>\u{1F3AF} Dimension Analysis</h2>
+    <div class="dimensions">
+      ${Object.entries(aiReadiness.dimensions).map(([key, dim]) => `
+        <div class="dimension ${dim.status}">
+          <div class="dimension-header">
+            <div class="dimension-name">${getEmojiForDimension(key)} ${formatDimensionName2(key)}</div>
+            <div class="dimension-score">${Math.round(dim.score)}/100</div>
+          </div>
+          <div class="dimension-level">${dim.status}</div>
+          ${dim.strengths && dim.strengths.length > 0 ? `
+            <div><strong>Strengths:</strong> ${dim.strengths.join(", ")}</div>
+          ` : ""}
+          ${dim.weaknesses && dim.weaknesses.length > 0 ? `
+            <div style="margin-top: 8px;"><strong>Weaknesses:</strong> ${dim.weaknesses.join(", ")}</div>
+          ` : ""}
+          ${dim.recommendation ? `
+            <div class="dimension-recommendations">
+              <div style="margin-top: 10px;">\u2192 ${dim.recommendation}</div>
+            </div>
+          ` : ""}
+        </div>
+      `).join("")}
+    </div>
+    ` : ""}
+
+    ${aiReadiness?.quickWins && aiReadiness.quickWins.length > 0 ? `
+    <div class="quick-wins">
+      <h3>\u26A1 Quick Wins (High Impact, Low Effort)</h3>
+      ${aiReadiness.quickWins.slice(0, 5).map((win, idx) => `
+        <div class="quick-win">
+          <div class="quick-win-header">${idx + 1}. ${win.issue}</div>
+          <div class="quick-win-meta">Impact: ${win.impact} | Effort: ${win.effort}</div>
+          <div style="margin-top: 8px; color: #0f766e;">\u2192 ${win.fix}</div>
+        </div>
+      `).join("")}
+    </div>
+    ` : ""}
+
+    ${aiReadiness?.roadmap ? `
+    <h2>\u{1F4CB} Priority Roadmap</h2>
+    <div class="priorities">
+      ${aiReadiness.roadmap.immediate && aiReadiness.roadmap.immediate.length > 0 ? `
+        <div class="priority-section immediate">
+          <h3>\u{1F534} Immediate (&lt; 1 day)</h3>
+          ${aiReadiness.roadmap.immediate.slice(0, 5).map((item) => `
+            <div class="priority-item">\u2022 ${item}</div>
+          `).join("")}
+        </div>
+      ` : ""}
+      
+      ${aiReadiness.roadmap.shortTerm && aiReadiness.roadmap.shortTerm.length > 0 ? `
+        <div class="priority-section short-term">
+          <h3>\u{1F7E1} Short-term (1-7 days)</h3>
+          ${aiReadiness.roadmap.shortTerm.slice(0, 5).map((item) => `
+            <div class="priority-item">\u2022 ${item}</div>
+          `).join("")}
+        </div>
+      ` : ""}
+      
+      ${aiReadiness.roadmap.longTerm && aiReadiness.roadmap.longTerm.length > 0 ? `
+        <div class="priority-section long-term">
+          <h3>\u{1F535} Long-term (&gt; 7 days)</h3>
+          ${aiReadiness.roadmap.longTerm.slice(0, 5).map((item) => `
+            <div class="priority-item">\u2022 ${item}</div>
+          `).join("")}
+        </div>
+      ` : ""}
+    </div>
+    ` : ""}
+
+    ${scanResult?.llm ? `
+    <h2>\u{1F4DD} AI Understanding Analysis</h2>
+    <div style="background: #f0f9ff; border: 2px solid #0ea5e9; padding: 20px; border-radius: 8px; margin: 20px 0;">
+      <div style="margin-bottom: 15px;">
+        <strong>Summary:</strong> ${scanResult.llm.summary || "N/A"}
+      </div>
+      ${scanResult.llm.pageType ? `
+        <div style="margin-bottom: 15px;">
+          <strong>\u{1F4C4} Page Type:</strong> ${scanResult.llm.pageType}
+        </div>
+      ` : ""}
+      ${scanResult.llm.keyTopics && scanResult.llm.keyTopics.length > 0 ? `
+        <div style="margin-bottom: 15px;">
+          <strong>\u{1F3F7}\uFE0F Key Topics:</strong> ${scanResult.llm.keyTopics.join(", ")}
+        </div>
+      ` : ""}
+      <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 15px; margin-top: 15px;">
+        ${scanResult.llm.readingLevel ? `
+          <div><strong>\u{1F4CA} Reading Level:</strong> ${scanResult.llm.readingLevel.description}</div>
+        ` : ""}
+        ${scanResult.llm.sentiment ? `
+          <div><strong>\u{1F3AD} Sentiment:</strong> ${scanResult.llm.sentiment}</div>
+        ` : ""}
+        ${scanResult.llm.technicalDepth ? `
+          <div><strong>\u{1F3AF} Technical Depth:</strong> ${scanResult.llm.technicalDepth}</div>
+        ` : ""}
+      </div>
+      
+      ${scanResult.llm.pageTypeInsights && scanResult.llm.pageTypeInsights.length > 0 ? `
+        <div style="margin-top: 20px; background: #dbeafe; padding: 15px; border-radius: 4px; border-left: 4px solid #0ea5e9;">
+          <div style="font-weight: 600; margin-bottom: 10px;">\u{1F4A1} AI-Generated Insights for ${scanResult.llm.pageType || "This Page"}</div>
+          <ul style="margin: 0; padding-left: 20px;">
+            ${scanResult.llm.pageTypeInsights.map((insight) => `<li style="margin: 5px 0;">${insight}</li>`).join("")}
+          </ul>
+        </div>
+      ` : ""}
+      
+      
+      ${scanResult.llm.topEntities && scanResult.llm.topEntities.length > 0 ? `
+        <div style="margin-top: 20px;">
+          <strong>\u{1F50D} Key Entities:</strong>
+          <div style="margin-top: 10px; display: grid; gap: 10px;">
+            ${scanResult.llm.topEntities.slice(0, 5).map((entity) => `
+              <div style="background: white; padding: 10px; border-radius: 4px; border-left: 3px solid #0ea5e9;">
+                <strong>${entity.name}</strong> (${entity.type}) - ${Math.round((entity.relevance || 0) * 100)}% relevance
+              </div>
+            `).join("")}
+          </div>
+        </div>
+      ` : ""}
+      
+      ${scanResult.llm.questions && scanResult.llm.questions.length > 0 ? `
+        <div style="margin-top: 20px;">
+          <strong>\u2753 Key Questions AI Can Answer:</strong>
+          <ol style="margin-top: 10px; padding-left: 25px;">
+            ${scanResult.llm.questions.slice(0, 5).map((q) => `
+              <li style="margin: 8px 0;"><span style="text-transform: uppercase; font-size: 0.8em; background: #dbeafe; padding: 2px 6px; border-radius: 3px;">${q.difficulty}</span> ${q.question}</li>
+            `).join("")}
+          </ol>
+        </div>
+      ` : ""}
+      
+      ${scanResult.llm.suggestedFAQ && scanResult.llm.suggestedFAQ.length > 0 ? `
+        <div style="margin-top: 20px;">
+          <strong>\u{1F4A1} Suggested FAQs:</strong>
+          <div style="margin-top: 10px; display: grid; gap: 15px;">
+            ${scanResult.llm.suggestedFAQ.filter((f) => f.importance === "high").slice(0, 3).map((faq) => `
+              <div style="background: white; padding: 15px; border-radius: 4px; border-left: 3px solid #f59e0b;">
+                <div style="font-weight: 600; margin-bottom: 5px;">Q: ${faq.question}</div>
+                <div style="color: #64748b;">A: ${faq.suggestedAnswer}</div>
+              </div>
+            `).join("")}
+          </div>
+        </div>
+      ` : ""}
+    </div>
+    ` : ""}
+
+    ${scanResult?.chunking ? `
+    <h2>\u{1F4C4} Content Chunking Analysis</h2>
+    <div style="background: #f0fdf4; border: 2px solid #10b981; padding: 20px; border-radius: 8px; margin: 20px 0;">
+      <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 15px;">
+        <div><strong>Strategy:</strong> ${scanResult.chunking.chunkingStrategy}</div>
+        <div><strong>Total Chunks:</strong> ${scanResult.chunking.totalChunks}</div>
+        <div><strong>Avg Tokens/Chunk:</strong> ${scanResult.chunking.averageTokensPerChunk}</div>
+        <div><strong>Avg Noise:</strong> ${(scanResult.chunking.averageNoiseRatio * 100).toFixed(1)}%</div>
+      </div>
+    </div>
+    ` : ""}
+
+    ${scanResult?.extractability ? `
+    <h2>\u{1F504} Extractability Analysis</h2>
+    <div style="background: #fef3c7; border: 2px solid #f59e0b; padding: 20px; border-radius: 8px; margin: 20px 0;">
+      <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 15px; margin-bottom: 15px;">
+        <div><strong>Overall Score:</strong> ${scanResult.extractability.score.extractabilityScore}/100</div>
+        <div><strong>Server-Rendered:</strong> ${scanResult.extractability.score.serverRenderedPercent}%</div>
+      </div>
+      <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 15px;">
+        <div><strong>Text Extractable:</strong> ${scanResult.extractability.contentTypes.text.percentage}%</div>
+        <div><strong>Images Extractable:</strong> ${scanResult.extractability.contentTypes.images.percentage}%</div>
+      </div>
+    </div>
+    ` : ""}
+
+    ${scanResult?.hallucinationReport ? `
+    <h2>\u26A0\uFE0F Hallucination Risk Assessment</h2>
+    <div style="background: #fef2f2; border: 2px solid #ef4444; padding: 20px; border-radius: 8px; margin: 20px 0;">
+      <div style="font-size: 1.5em; font-weight: bold; margin-bottom: 15px;">
+        Risk Score: ${scanResult.hallucinationReport.hallucinationRiskScore}/100
+      </div>
+      
+      ${scanResult.hallucinationReport.factCheckSummary ? `
+        <div style="margin-top: 20px; background: white; padding: 15px; border-radius: 4px;">
+          <strong>\u{1F4CA} Fact Check Summary:</strong>
+          <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(150px, 1fr)); gap: 10px; margin-top: 10px;">
+            <div>\u2705 Verified: ${scanResult.hallucinationReport.factCheckSummary.verifiedFacts}</div>
+            <div>\u2753 Unverified: ${scanResult.hallucinationReport.factCheckSummary.unverifiedFacts}</div>
+            <div>\u26A0\uFE0F Contradictions: ${scanResult.hallucinationReport.factCheckSummary.contradictions}</div>
+            <div>\u{1F914} Ambiguities: ${scanResult.hallucinationReport.factCheckSummary.ambiguities}</div>
+          </div>
+        </div>
+      ` : ""}
+      
+      ${scanResult.hallucinationReport.factCheckSummary && scanResult.hallucinationReport.factCheckSummary.unverifiedFacts > 0 ? `
+        <div style="margin-top: 15px; background: #fef9c3; border-left: 4px solid #eab308; padding: 15px; border-radius: 4px;">
+          <div style="display: flex; align-items: start; gap: 10px;">
+            <span style="font-size: 1.5em;">\u{1F4A1}</span>
+            <div>
+              <div style="font-weight: 600; margin-bottom: 8px;">Why Some Facts Can't Be Verified</div>
+              <div style="color: #854d0e; margin-bottom: 8px;">
+                AI systems need external sources to verify claims. When information lacks citations, links, or 
+                references, it becomes difficult to confirm accuracy, increasing the risk of AI hallucination or misinformation.
+              </div>
+              <div style="font-weight: 600; margin-top: 12px; margin-bottom: 6px;">Best Practices:</div>
+              <ul style="margin: 0; padding-left: 20px; color: #854d0e;">
+                <li>Add source links directly in or near claim text</li>
+                <li>Include dates for time-sensitive information</li>
+                <li>Link to authoritative sources (research, official docs)</li>
+                <li>Provide context for statistics and data points</li>
+                <li>Use schema.org markup to specify citations</li>
+              </ul>
+            </div>
+          </div>
+        </div>
+      ` : ""}
+      
+      ${scanResult.hallucinationReport.triggers && scanResult.hallucinationReport.triggers.length > 0 ? `
+        <div style="margin-top: 20px;">
+          <strong>\u{1F6A8} Identified Triggers:</strong>
+          <div style="margin-top: 10px; display: grid; gap: 10px;">
+            ${scanResult.hallucinationReport.triggers.filter((t) => t.severity === "high" || t.severity === "critical").slice(0, 5).map((trigger) => `
+              <div style="background: white; padding: 15px; border-radius: 4px; border-left: 3px solid #dc2626;">
+                <div style="font-weight: 600; text-transform: uppercase; font-size: 0.85em; color: #dc2626;">${trigger.type} - ${trigger.severity}</div>
+                <div style="margin-top: 5px;">${trigger.description}</div>
+                <div style="margin-top: 5px; font-size: 0.9em; color: #64748b;">Confidence: ${Math.round((trigger.confidence || 0) * 100)}%</div>
+              </div>
+            `).join("")}
+          </div>
+        </div>
+      ` : ""}
+      
+      ${scanResult.hallucinationReport.recommendations && scanResult.hallucinationReport.recommendations.length > 0 ? `
+        <div style="margin-top: 20px;">
+          <strong>\u{1F4A1} Recommendations:</strong>
+          <ul style="margin-top: 10px; padding-left: 25px;">
+            ${scanResult.hallucinationReport.recommendations.slice(0, 3).map((rec) => `<li style="margin: 5px 0;">${rec}</li>`).join("")}
+          </ul>
+        </div>
+      ` : ""}
+    </div>
+    ` : ""}
+
+    ${scanResult?.mirrorReport ? `
+    <h2>\u{1F50D} AI Misunderstanding Check</h2>
+    <div style="background: #faf5ff; border: 2px solid #a855f7; padding: 20px; border-radius: 8px; margin: 20px 0;">
+      <div style="display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 15px; margin-bottom: 15px;">
+        <div><strong>\u{1F3AF} Alignment Score:</strong> ${scanResult.mirrorReport.summary.alignmentScore}/100</div>
+        <div><strong>\u{1F4D6} Clarity Score:</strong> ${scanResult.mirrorReport.summary.clarityScore}/100</div>
+        <div><strong>\u26A0\uFE0F Critical Issues:</strong> ${scanResult.mirrorReport.summary.critical}</div>
+        <div><strong>\u{1F7E1} Major Issues:</strong> ${scanResult.mirrorReport.summary.major}</div>
+      </div>
+      
+      ${scanResult.mirrorReport.llmInterpretation ? `
+        <div style="background: #dbeafe; padding: 16px; border-radius: 8px; margin-bottom: 16px; border: 1px solid #3b82f6;">
+          <div style="font-weight: bold; margin-bottom: 12px; color: #1e40af;">
+            \u{1F916} What AI Actually Understood (${Math.round(scanResult.mirrorReport.llmInterpretation.confidence * 100)}% confident)
+          </div>
+          
+          <div style="display: grid; grid-template-columns: repeat(2, 1fr); gap: 12px;">
+            ${scanResult.mirrorReport.llmInterpretation.productName ? `
+              <div>
+                <div style="font-size: 11px; font-weight: 600; color: #64748b; margin-bottom: 4px;">PRODUCT NAME</div>
+                <div style="font-size: 14px;">${scanResult.mirrorReport.llmInterpretation.productName}</div>
+              </div>
+            ` : ""}
+            
+            ${scanResult.mirrorReport.llmInterpretation.purpose ? `
+              <div style="grid-column: 1 / -1;">
+                <div style="font-size: 11px; font-weight: 600; color: #64748b; margin-bottom: 4px;">MAIN PURPOSE</div>
+                <div style="font-size: 14px;">${scanResult.mirrorReport.llmInterpretation.purpose}</div>
+              </div>
+            ` : ""}
+            
+            ${scanResult.mirrorReport.llmInterpretation.valueProposition ? `
+              <div style="grid-column: 1 / -1;">
+                <div style="font-size: 11px; font-weight: 600; color: #64748b; margin-bottom: 4px;">\u{1F48E} UNIQUE VALUE</div>
+                <div style="font-size: 14px; font-weight: 600; color: #7c3aed;">${scanResult.mirrorReport.llmInterpretation.valueProposition}</div>
+              </div>
+            ` : ""}
+            
+            ${scanResult.mirrorReport.llmInterpretation.keyBenefits && scanResult.mirrorReport.llmInterpretation.keyBenefits.length > 0 ? `
+              <div>
+                <div style="font-size: 11px; font-weight: 600; color: #64748b; margin-bottom: 4px;">KEY BENEFITS</div>
+                <ul style="font-size: 14px; margin: 0; padding-left: 20px;">
+                  ${scanResult.mirrorReport.llmInterpretation.keyBenefits.map((b) => `<li style="margin: 4px 0;">${b}</li>`).join("")}
+                </ul>
+              </div>
+            ` : ""}
+            
+            ${scanResult.mirrorReport.llmInterpretation.keyFeatures && scanResult.mirrorReport.llmInterpretation.keyFeatures.length > 0 ? `
+              <div>
+                <div style="font-size: 11px; font-weight: 600; color: #64748b; margin-bottom: 4px;">KEY FEATURES</div>
+                <ul style="font-size: 14px; margin: 0; padding-left: 20px;">
+                  ${scanResult.mirrorReport.llmInterpretation.keyFeatures.slice(0, 3).map((f) => `<li style="margin: 4px 0;">${f}</li>`).join("")}
+                </ul>
+              </div>
+            ` : ""}
+          </div>
+        </div>
+      ` : ""}
+      
+      ${scanResult.mirrorReport.mismatches && scanResult.mirrorReport.mismatches.length > 0 ? `
+        <div style="margin-top: 20px;">
+          <strong>Priority Mismatches:</strong>
+          <div style="margin-top: 10px; display: grid; gap: 10px;">
+            ${scanResult.mirrorReport.mismatches.filter((m) => m.severity === "critical" || m.severity === "major").slice(0, 5).map((mismatch) => `
+              <div style="background: white; padding: 15px; border-radius: 4px; border-left: 3px solid ${mismatch.severity === "critical" ? "#dc2626" : "#f59e0b"};">
+                <div style="font-weight: 600;">${mismatch.severity === "critical" ? "\u{1F534}" : "\u{1F7E1}"} ${mismatch.field}</div>
+                <div style="margin-top: 5px; color: #64748b;">${mismatch.description}</div>
+                <div style="margin-top: 10px; padding: 10px; background: #f0fdfa; border-radius: 4px;">
+                  <strong>Fix:</strong> ${mismatch.recommendation}
+                </div>
+              </div>
+            `).join("")}
+          </div>
+        </div>
+      ` : ""}
+      
+      ${scanResult.mirrorReport.recommendations && scanResult.mirrorReport.recommendations.length > 0 ? `
+        <div style="margin-top: 20px;">
+          <strong>\u{1F4A1} Top Recommendations:</strong>
+          <ul style="margin-top: 10px; padding-left: 25px;">
+            ${scanResult.mirrorReport.recommendations.slice(0, 3).map((rec) => `<li style="margin: 5px 0;">${rec}</li>`).join("")}
+          </ul>
+        </div>
+      ` : ""}
+    </div>
+    ` : ""}
+
+    <h2>\u26A0\uFE0F All Issues (${report.issues?.length || 0})</h2>
+    <div class="issues">
+      ${(report.issues || []).map((issue) => `
+        <div class="issue ${issue.severity}">
+          <div class="issue-title">${issue.message}</div>
+          <div class="issue-meta">
+            <span style="text-transform: uppercase; font-weight: 600;">${issue.severity}</span> 
+            \xB7 Impact: ${issue.impact} 
+            \xB7 Category: ${issue.category}
+          </div>
+          <div class="issue-desc">${issue.evidence || "No additional evidence"}</div>
+          <div class="issue-fix"><strong>Fix:</strong> ${issue.suggested_fix}</div>
+        </div>
+      `).join("")}
+    </div>
+
+    ${(report.entities || []).length > 0 ? `
+      <h2>\u{1F3F7}\uFE0F Detected Entities (${(report.entities || []).length})</h2>
+      <div class="entity-list">
+        ${(report.entities || []).map((entity) => `
+          <div class="entity">
+            <div class="entity-name">${entity.name}</div>
+            <div class="entity-type">${entity.type} \xB7 Source: ${entity.source}</div>
+            ${entity.description ? `<div style="margin-top: 8px; color: #334155;">${entity.description}</div>` : ""}
+          </div>
+        `).join("")}
+      </div>
+    ` : ""}
+  </div>
+</body>
+</html>`;
+}
+function getLetterGrade(score) {
+  if (score >= 90) return "A";
+  if (score >= 80) return "B";
+  if (score >= 70) return "C";
+  if (score >= 60) return "D";
+  return "F";
+}
+function getEmojiForDimension(name) {
+  const emojiMap = {
+    "contentQuality": "\u{1F4DD}",
+    "discoverability": "\u{1F50D}",
+    "extractability": "\u{1F504}",
+    "comprehensibility": "\u{1F9E0}",
+    "trustworthiness": "\u2705",
+    "structured": "\u{1F4CA}",
+    "semantic": "\u{1F3F7}\uFE0F"
+  };
+  return emojiMap[name] || "\u{1F4CC}";
+}
+function formatDimensionName2(key) {
+  const nameMap = {
+    "contentQuality": "Content Quality",
+    "discoverability": "Discoverability",
+    "extractability": "Extractability",
+    "comprehensibility": "Comprehensibility",
+    "trustworthiness": "Trustworthiness"
+  };
+  return nameMap[key] || key;
+}
+function convertToLighthouseFormat(report) {
+  return {
+    lighthouseVersion: "1.0.0",
+    userAgent: "AI-Lighthouse/1.0.0",
+    fetchTime: report.scanned_at,
+    requestedUrl: report.input?.requested_url,
+    finalUrl: report.input?.final_url,
+    categories: {
+      "ai-readiness": {
+        id: "ai-readiness",
+        title: "AI Readiness",
+        score: (report.scores?.ai_readiness || 0) / 100
+      },
+      "crawlability": {
+        id: "crawlability",
+        title: "Crawlability",
+        score: (report.scores?.crawlability || 0) / 100
+      },
+      "content-clarity": {
+        id: "content-clarity",
+        title: "Content Clarity",
+        score: (report.scores?.content_clarity || 0) / 100
+      }
+    },
+    audits: (report.issues || []).reduce((acc, issue, idx) => {
+      acc[`issue-${idx}`] = {
+        id: issue.id,
+        title: issue.message,
+        description: issue.evidence || "",
+        score: issue.severity === "critical" ? 0 : issue.severity === "high" ? 0.25 : 0.5,
+        displayValue: issue.suggested_fix
+      };
+      return acc;
+    }, {})
+  };
+}
+function generateCSVReport(report) {
+  const headers = ["ID", "Severity", "Category", "Message", "Impact", "Suggested Fix"];
+  const rows = (report.issues || []).map((issue) => [
+    issue.id,
+    issue.severity,
+    issue.category,
+    `"${issue.message.replace(/"/g, '""')}"`,
+    issue.impact,
+    `"${issue.suggested_fix.replace(/"/g, '""')}"`
+  ]);
+  return [headers.join(","), ...rows.map((r) => r.join(","))].join("\n");
+}
+
+// src/commands/crawl.ts
+import chalk3 from "chalk";
+import ora2 from "ora";
+import { analyzeUrlWithRules as analyzeUrlWithRules2 } from "@ai-lighthouse/scanner";
+import { writeFile as writeFile2, mkdir as mkdir2 } from "fs/promises";
+import { join as join2, resolve as resolve2 } from "path";
+import { existsSync as existsSync2 } from "fs";
+function crawlCommand(program2) {
+  program2.command("crawl").description("Crawl and audit multiple pages from a website").argument("<url>", "Starting URL to crawl from").option("-d, --depth <number>", "Maximum crawl depth", (val) => parseInt(val, 10), 2).option("--sitemap", "Parse sitemap.xml for URLs", false).option("--max-pages <number>", "Maximum number of pages to crawl", (val) => parseInt(val, 10), 50).option("-o, --output <format>", "Output format: json, html", "json").option("--follow-external", "Follow external links", false).option("--respect-robots", "Respect robots.txt rules", true).action(async (url, options) => {
+    const spinner = ora2("Starting crawl...").start();
+    try {
+      const urlObj = new URL(url);
+      const baseUrl = `${urlObj.protocol}//${urlObj.host}`;
+      spinner.text = "Discovering URLs...";
+      let urlsToCrawl = [];
+      if (options.sitemap) {
+        const sitemapUrl = `${baseUrl}/sitemap.xml`;
+        spinner.text = `Fetching sitemap from ${sitemapUrl}...`;
+        urlsToCrawl = await parseSitemap(sitemapUrl);
+        spinner.succeed(`Found ${urlsToCrawl.length} URLs in sitemap`);
+      } else {
+        urlsToCrawl = await crawlByDepth(url, options.depth, options.maxPages, options.followExternal);
+        spinner.succeed(`Discovered ${urlsToCrawl.length} URLs`);
+      }
+      if (urlsToCrawl.length > options.maxPages) {
+        urlsToCrawl = urlsToCrawl.slice(0, options.maxPages);
+      }
+      const results = [];
+      for (let i = 0; i < urlsToCrawl.length; i++) {
+        const pageUrl = urlsToCrawl[i];
+        spinner.text = `Auditing ${i + 1}/${urlsToCrawl.length}: ${pageUrl}`;
+        try {
+          const result = await analyzeUrlWithRules2(pageUrl, {
+            maxChunkTokens: 1200,
+            enableChunking: false,
+            enableExtractability: false,
+            enableLLM: false,
+            minImpactScore: 8
+          });
+          results.push(result);
+        } catch (error) {
+          console.error(chalk3.yellow(`
+\u26A0\uFE0F  Failed to audit ${pageUrl}: ${error}`));
+        }
+      }
+      spinner.text = "Generating crawl report...";
+      const crawlReport = {
+        crawl_id: generateId(),
+        crawled_at: (/* @__PURE__ */ new Date()).toISOString(),
+        base_url: baseUrl,
+        start_url: url,
+        total_pages: results.length,
+        crawl_depth: options.depth,
+        pages: results,
+        summary: {
+          avgOverallScore: average(results.map((r) => r.scoring.overallScore)),
+          avgAIReadinessScore: average(results.map((r) => r.scoring.categoryScores.find((c) => c.category === "AI Readiness")?.score || 0)),
+          total_issues: results.reduce((sum, r) => sum + r.issues.length, 0),
+          issues_by_severity: aggregateIssuesBySeverity(results)
+        }
+      };
+      const outputDir = resolve2(process.cwd(), ".ai-lighthouse");
+      if (!existsSync2(outputDir)) {
+        await mkdir2(outputDir, { recursive: true });
+      }
+      const timestamp = (/* @__PURE__ */ new Date()).toISOString().replace(/:/g, "-").split(".")[0];
+      const baseFilename = `crawl_${new URL(url).hostname}_${timestamp}`;
+      if (options.output === "json") {
+        const jsonPath = join2(outputDir, `${baseFilename}.json`);
+        await writeFile2(jsonPath, JSON.stringify(crawlReport, null, 2));
+        spinner.succeed(chalk3.green("Crawl complete!"));
+        console.log(chalk3.dim(`Report saved to: ${jsonPath}`));
+      } else if (options.output === "html") {
+        const htmlPath = join2(outputDir, `${baseFilename}.html`);
+        const html = generateCrawlHTML(crawlReport);
+        await writeFile2(htmlPath, html);
+        spinner.succeed(chalk3.green("Crawl complete!"));
+        console.log(chalk3.dim(`HTML report saved to: ${htmlPath}`));
+      }
+      console.log("\n" + chalk3.bold("\u{1F310} Crawl Summary"));
+      console.log(`Pages audited: ${chalk3.cyan(crawlReport.total_pages)}`);
+      console.log(`Average overall score: ${chalk3.cyan(crawlReport.summary.avgOverallScore.toFixed(1))}`);
+      console.log(`Average AI readiness: ${chalk3.cyan(crawlReport.summary.avgAIReadinessScore.toFixed(1))}`);
+      console.log(`Total issues found: ${chalk3.yellow(crawlReport.summary.total_issues)}`);
+    } catch (error) {
+      spinner.fail(chalk3.red("Crawl failed"));
+      if (error instanceof Error) {
+        console.error(chalk3.red(error.message));
+      }
+      process.exit(1);
+    }
+  });
+}
+async function parseSitemap(sitemapUrl) {
+  try {
+    const response = await fetch(sitemapUrl);
+    if (!response.ok) {
+      throw new Error(`Failed to fetch sitemap: ${response.statusText}`);
+    }
+    const text = await response.text();
+    const urlMatches = text.match(/<loc>(.*?)<\/loc>/g) || [];
+    return urlMatches.map((match) => match.replace(/<\/?loc>/g, ""));
+  } catch (error) {
+    console.warn(chalk3.yellow(`Could not parse sitemap: ${error}`));
+    return [];
+  }
+}
+async function crawlByDepth(startUrl, maxDepth, maxPages, followExternal) {
+  const visited = /* @__PURE__ */ new Set();
+  const toVisit = [{ url: startUrl, depth: 0 }];
+  const baseHost = new URL(startUrl).host;
+  while (toVisit.length > 0 && visited.size < maxPages) {
+    const { url, depth } = toVisit.shift();
+    if (visited.has(url) || depth > maxDepth) {
+      continue;
+    }
+    visited.add(url);
+    if (depth < maxDepth) {
+      try {
+        const links = await extractLinks(url);
+        for (const link of links) {
+          const linkHost = new URL(link).host;
+          if (followExternal || linkHost === baseHost) {
+            if (!visited.has(link)) {
+              toVisit.push({ url: link, depth: depth + 1 });
+            }
+          }
+        }
+      } catch (error) {
+      }
+    }
+  }
+  return Array.from(visited);
+}
+async function extractLinks(url) {
+  try {
+    const response = await fetch(url);
+    const html = await response.text();
+    const linkMatches = html.match(/href=["'](https?:\/\/[^"']+)["']/g) || [];
+    return linkMatches.map((match) => match.match(/href=["'](https?:\/\/[^"']+)["']/)[1]).filter((link, idx, arr) => arr.indexOf(link) === idx);
+  } catch {
+    return [];
+  }
+}
+function average(numbers) {
+  if (numbers.length === 0) return 0;
+  return numbers.reduce((sum, n) => sum + n, 0) / numbers.length;
+}
+function aggregateIssuesBySeverity(results) {
+  const counts = {
+    critical: 0,
+    high: 0,
+    medium: 0,
+    low: 0,
+    info: 0
+  };
+  for (const result of results) {
+    for (const issue of result.issues) {
+      counts[issue.severity] = (counts[issue.severity] || 0) + 1;
+    }
+  }
+  return counts;
+}
+function generateId() {
+  return `crawl_${Date.now()}_${Math.random().toString(36).substr(2, 9)}`;
+}
+function generateCrawlHTML(report) {
+  return `<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>Crawl Report - ${report.base_url}</title>
+  <style>
+    * { margin: 0; padding: 0; box-sizing: border-box; }
+    body { 
+      font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
+      background: #f5f5f5;
+      padding: 20px;
+    }
+    .container { max-width: 1400px; margin: 0 auto; }
+    .header { background: white; padding: 30px; border-radius: 8px; margin-bottom: 20px; box-shadow: 0 2px 8px rgba(0,0,0,0.1); }
+    h1 { color: #2563eb; margin-bottom: 10px; }
+    .summary { display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 15px; margin-top: 20px; }
+    .stat { background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); color: white; padding: 20px; border-radius: 8px; }
+    .stat-value { font-size: 2em; font-weight: bold; }
+    .stat-label { opacity: 0.9; font-size: 0.9em; }
+    .pages { display: grid; gap: 15px; }
+    .page-card { background: white; padding: 20px; border-radius: 8px; box-shadow: 0 2px 4px rgba(0,0,0,0.1); }
+    .page-url { color: #1e40af; font-weight: 600; margin-bottom: 10px; word-break: break-all; }
+    .page-scores { display: flex; gap: 15px; margin-top: 10px; }
+    .score-badge { background: #dbeafe; color: #1e40af; padding: 5px 12px; border-radius: 4px; font-size: 0.9em; }
+  </style>
+</head>
+<body>
+  <div class="container">
+    <div class="header">
+      <h1>\u{1F310} Crawl Report</h1>
+      <div style="color: #64748b; margin-top: 5px;">${report.base_url}</div>
+      <div style="color: #94a3b8; font-size: 0.85em; margin-top: 5px;">
+        Generated: ${new Date(report.crawled_at).toLocaleString()}
+      </div>
+      
+      <div class="summary">
+        <div class="stat">
+          <div class="stat-label">Pages Audited</div>
+          <div class="stat-value">${report.total_pages}</div>
+        </div>
+        <div class="stat">
+          <div class="stat-label">Avg Overall Score</div>
+          <div class="stat-value">${report.summary.avgOverallScore.toFixed(1)}</div>
+        </div>
+        <div class="stat">
+          <div class="stat-label">Avg AI Readiness</div>
+          <div class="stat-value">${report.summary.avgAIReadinessScore.toFixed(1)}</div>
+        </div>          avg
+        <div class="stat">
+          <div class="stat-label">Total Issues</div>
+          <div class="stat-value">${report.summary.total_issues}</div>
+        </div>
+      </div>
+    </div>
+
+    <div class="pages">
+      ${report.pages.map((page) => `
+        <div class="page-card">
+          <div class="page-url">${page.input.requested_url}</div>
+          <div class="page-scores">
+            <div class="score-badge">Overall: ${page.scores.overall}</div>
+            <div class="score-badge">AI Readiness: ${page.scores.ai_readiness}</div>
+            <div class="score-badge">Issues: ${page.issues.length}</div>
+          </div>
+        </div>
+      `).join("")}
+    </div>
+  </div>
+</body>
+</html>`;
+}
+
+// src/commands/report.ts
+import chalk4 from "chalk";
+import ora3 from "ora";
+import open from "open";
+import { readFile as readFile2, writeFile as writeFile3 } from "fs/promises";
+import { resolve as resolve3 } from "path";
+import { existsSync as existsSync3 } from "fs";
+function reportCommand(program2) {
+  program2.command("report").description("Generate and view reports from saved audit results").argument("<file>", "Path to audit JSON file (e.g., ./last_run.json)").option("--open", "Open the report in browser", false).option("-f, --format <format>", "Output format: html, json, csv", "html").action(async (file, options) => {
+    const spinner = ora3("Loading audit results...").start();
+    try {
+      const filePath = resolve3(process.cwd(), file);
+      if (!existsSync3(filePath)) {
+        throw new Error(`File not found: ${filePath}`);
+      }
+      const jsonContent = await readFile2(filePath, "utf-8");
+      const report = JSON.parse(jsonContent);
+      spinner.text = "Generating report...";
+      const isCrawlReport = "pages" in report && Array.isArray(report.pages);
+      if (options.format === "html") {
+        const htmlPath = filePath.replace(/\.json$/, ".html");
+        const html = isCrawlReport ? generateCrawlHTML2(report) : generateSingleHTML(report);
+        await writeFile3(htmlPath, html);
+        spinner.succeed(chalk4.green("Report generated!"));
+        console.log(chalk4.dim(`HTML saved to: ${htmlPath}`));
+        if (options.open) {
+          spinner.text = "Opening report in browser...";
+          await open(htmlPath);
+          spinner.succeed("Report opened in browser");
+        }
+      } else if (options.format === "json") {
+        spinner.succeed("Report loaded");
+        console.log(JSON.stringify(report, null, 2));
+      } else if (options.format === "csv") {
+        const csvPath = filePath.replace(/\.json$/, ".csv");
+        const csv = generateCSV(report);
+        await writeFile3(csvPath, csv);
+        spinner.succeed(chalk4.green("CSV report generated!"));
+        console.log(chalk4.dim(`CSV saved to: ${csvPath}`));
+      }
+      if (isCrawlReport) {
+        console.log("\n" + chalk4.bold("\u{1F310} Crawl Summary"));
+        console.log(`Pages: ${chalk4.cyan(report.total_pages)}`);
+        console.log(`Avg Score: ${chalk4.cyan(report.summary.avg_overall_score.toFixed(1))}`);
+        console.log(`Total Issues: ${chalk4.yellow(report.summary.total_issues)}`);
+      } else {
+        console.log("\n" + chalk4.bold("\u{1F4CA} Audit Summary"));
+        console.log(`URL: ${chalk4.cyan(report.input.requested_url)}`);
+        console.log(`Overall Score: ${chalk4.cyan(report.scores.overall)}`);
+        console.log(`Issues: ${chalk4.yellow(report.issues.length)}`);
+      }
+    } catch (error) {
+      spinner.fail(chalk4.red("Failed to generate report"));
+      if (error instanceof Error) {
+        console.error(chalk4.red(error.message));
+      }
+      process.exit(1);
+    }
+  });
+}
+function generateSingleHTML(report) {
+  return `<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>AI Lighthouse Report - ${report.input.requested_url}</title>
+  <style>
+    * { margin: 0; padding: 0; box-sizing: border-box; }
+    body { 
+      font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
+      background: #f5f5f5;
+      padding: 20px;
+      line-height: 1.6;
+    }
+    .container { max-width: 1200px; margin: 0 auto; }
+    .header { background: white; padding: 40px; border-radius: 8px; margin-bottom: 20px; box-shadow: 0 2px 8px rgba(0,0,0,0.1); }
+    h1 { color: #2563eb; margin-bottom: 10px; }
+    .scores { display: grid; grid-template-columns: repeat(auto-fit, minmax(180px, 1fr)); gap: 15px; margin: 25px 0; }
+    .score-card { 
+      background: linear-gradient(135deg, #667eea 0%, #764ba2 100%);
+      color: white;
+      padding: 20px;
+      border-radius: 8px;
+      text-align: center;
+    }
+    .score-value { font-size: 2.5em; font-weight: bold; }
+    .score-label { font-size: 0.9em; opacity: 0.9; margin-top: 5px; }
+    .section { background: white; padding: 30px; border-radius: 8px; margin-bottom: 20px; box-shadow: 0 2px 4px rgba(0,0,0,0.1); }
+    .section-title { color: #1e40af; font-size: 1.5em; margin-bottom: 20px; border-bottom: 2px solid #dbeafe; padding-bottom: 10px; }
+    .issues { display: grid; gap: 15px; }
+    .issue { 
+      background: #f8fafc;
+      border-left: 4px solid #cbd5e1;
+      padding: 15px;
+      border-radius: 4px;
+    }
+    .issue.critical { border-left-color: #dc2626; background: #fef2f2; }
+    .issue.high { border-left-color: #ea580c; background: #fff7ed; }
+    .issue.medium { border-left-color: #f59e0b; background: #fffbeb; }
+    .issue-title { font-weight: 600; color: #1e293b; margin-bottom: 8px; font-size: 1.05em; }
+    .issue-meta { font-size: 0.85em; color: #64748b; margin-bottom: 10px; }
+    .issue-fix { color: #0f766e; background: #f0fdfa; padding: 12px; border-radius: 4px; margin-top: 10px; }
+    .entity { background: #f0f9ff; border: 1px solid #bae6fd; padding: 15px; border-radius: 6px; margin-bottom: 15px; }
+    .entity-name { font-weight: 600; color: #0c4a6e; font-size: 1.1em; }
+  </style>
+</head>
+<body>
+  <div class="container">
+    <div class="header">
+      <h1>\u{1F6A8} AI Lighthouse Report</h1>
+      <div style="color: #64748b; margin-top: 5px;">${report.input.requested_url}</div>
+      <div style="color: #94a3b8; font-size: 0.85em; margin-top: 5px;">
+        ${new Date(report.scanned_at).toLocaleString()}
+      </div>
+      
+      <div class="scores">
+        <div class="score-card">
+          <div class="score-value">${report.scores.overall}</div>
+          <div class="score-label">Overall</div>
+        </div>
+        <div class="score-card">
+          <div class="score-value">${report.scores.ai_readiness}</div>
+          <div class="score-label">AI Readiness</div>
+        </div>
+        <div class="score-card">
+          <div class="score-value">${report.scores.crawlability}</div>
+          <div class="score-label">Crawlability</div>
+        </div>
+        <div class="score-card">
+          <div class="score-value">${report.scores.content_clarity}</div>
+          <div class="score-label">Content Clarity</div>
+        </div>
+        <div class="score-card">
+          <div class="score-value">${report.scores.schema_coverage}</div>
+          <div class="score-label">Schema</div>
+        </div>
+      </div>
+    </div>
+
+    ${report.issues.length > 0 ? `
+      <div class="section">
+        <div class="section-title">\u26A0\uFE0F Issues (${report.issues.length})</div>
+        <div class="issues">
+          ${report.issues.map((issue) => `
+            <div class="issue ${issue.severity}">
+              <div class="issue-title">${issue.message}</div>
+              <div class="issue-meta">
+                <span style="text-transform: uppercase; font-weight: 600; color: ${getSeverityColor(issue.severity)}">
+                  ${issue.severity}
+                </span>
+                \xB7 ${issue.category}
+              </div>
+              ${issue.evidence ? `<div style="color: #475569; margin: 10px 0;">${issue.evidence}</div>` : ""}
+              <div class="issue-fix"><strong>\u{1F4A1} Fix:</strong> ${issue.suggested_fix}</div>
+            </div>
+          `).join("")}
+        </div>
+      </div>
+    ` : ""}
+
+    ${report.entities && report.entities.length > 0 ? `
+      <div class="section">
+        <div class="section-title">\u{1F3F7}\uFE0F Detected Entities (${report.entities.length})</div>
+        ${report.entities.map((entity) => `
+          <div class="entity">
+            <div class="entity-name">${entity.name}</div>
+            <div style="color: #0369a1; font-size: 0.9em; margin-top: 3px;">
+              ${entity.type} \xB7 ${entity.source}
+            </div>
+            ${entity.description ? `<div style="margin-top: 10px; color: #334155;">${entity.description}</div>` : ""}
+          </div>
+        `).join("")}
+      </div>
+    ` : ""}
+  </div>
+</body>
+</html>`;
+}
+function generateCrawlHTML2(report) {
+  return `<!DOCTYPE html>
+<html lang="en">
+<head>
+  <meta charset="UTF-8">
+  <meta name="viewport" content="width=device-width, initial-scale=1.0">
+  <title>Crawl Report - ${report.base_url}</title>
+  <style>
+    * { margin: 0; padding: 0; box-sizing: border-box; }
+    body { 
+      font-family: -apple-system, BlinkMacSystemFont, 'Segoe UI', Roboto, sans-serif;
+      background: #f5f5f5;
+      padding: 20px;
+    }
+    .container { max-width: 1400px; margin: 0 auto; }
+    .header { background: white; padding: 30px; border-radius: 8px; margin-bottom: 20px; box-shadow: 0 2px 8px rgba(0,0,0,0.1); }
+    h1 { color: #2563eb; }
+    .summary { display: grid; grid-template-columns: repeat(auto-fit, minmax(200px, 1fr)); gap: 15px; margin-top: 20px; }
+    .stat { background: linear-gradient(135deg, #667eea 0%, #764ba2 100%); color: white; padding: 20px; border-radius: 8px; text-align: center; }
+    .stat-value { font-size: 2em; font-weight: bold; }
+    .pages { display: grid; gap: 15px; }
+    .page-card { background: white; padding: 20px; border-radius: 8px; box-shadow: 0 2px 4px rgba(0,0,0,0.1); }
+    .page-url { color: #1e40af; font-weight: 600; word-break: break-all; margin-bottom: 12px; }
+    .page-scores { display: flex; flex-wrap: wrap; gap: 10px; }
+    .score-badge { background: #dbeafe; color: #1e40af; padding: 6px 12px; border-radius: 4px; font-size: 0.9em; }
+  </style>
+</head>
+<body>
+  <div class="container">
+    <div class="header">
+      <h1>\u{1F310} Multi-Page Crawl Report</h1>
+      <div style="color: #64748b; margin-top: 8px;">${report.base_url}</div>
+      <div style="color: #94a3b8; font-size: 0.85em; margin-top: 5px;">
+        ${new Date(report.crawled_at).toLocaleString()}
+      </div>
+      
+      <div class="summary">
+        <div class="stat">
+          <div class="stat-value">${report.total_pages}</div>
+          <div style="opacity: 0.9; margin-top: 5px;">Pages</div>
+        </div>
+        <div class="stat">
+          <div class="stat-value">${report.summary.avg_overall_score.toFixed(1)}</div>
+          <div style="opacity: 0.9; margin-top: 5px;">Avg Score</div>
+        </div>
+        <div class="stat">
+          <div class="stat-value">${report.summary.avg_ai_readiness.toFixed(1)}</div>
+          <div style="opacity: 0.9; margin-top: 5px;">Avg AI Readiness</div>
+        </div>
+        <div class="stat">
+          <div class="stat-value">${report.summary.total_issues}</div>
+          <div style="opacity: 0.9; margin-top: 5px;">Total Issues</div>
+        </div>
+      </div>
+    </div>
+
+    <div class="pages">
+      ${report.pages.map((page, idx) => `
+        <div class="page-card">
+          <div style="color: #94a3b8; font-size: 0.85em; margin-bottom: 5px;">Page ${idx + 1}</div>
+          <div class="page-url">${page.input.requested_url}</div>
+          <div class="page-scores">
+            <div class="score-badge">Overall: ${page.scores.overall}</div>
+            <div class="score-badge">AI Readiness: ${page.scores.ai_readiness}</div>
+            <div class="score-badge">Crawlability: ${page.scores.crawlability}</div>
+            <div class="score-badge">Issues: ${page.issues.length}</div>
+          </div>
+        </div>
+      `).join("")}
+    </div>
+  </div>
+</body>
+</html>`;
+}
+function generateCSV(report) {
+  const isCrawlReport = "pages" in report && Array.isArray(report.pages);
+  if (isCrawlReport) {
+    const headers = ["Page", "URL", "Overall Score", "AI Readiness", "Crawlability", "Issues"];
+    const rows = report.pages.map((page, idx) => [
+      idx + 1,
+      `"${page.input.requested_url}"`,
+      page.scores.overall,
+      page.scores.ai_readiness,
+      page.scores.crawlability,
+      page.issues.length
+    ]);
+    return [headers.join(","), ...rows.map((r) => r.join(","))].join("\n");
+  } else {
+    const headers = ["ID", "Severity", "Category", "Message", "Fix"];
+    const rows = report.issues.map((issue) => [
+      issue.id,
+      issue.severity,
+      issue.category,
+      `"${issue.message.replace(/"/g, '""')}"`,
+      `"${issue.suggested_fix.replace(/"/g, '""')}"`
+    ]);
+    return [headers.join(","), ...rows.map((r) => r.join(","))].join("\n");
+  }
+}
+function getSeverityColor(severity) {
+  const colors = {
+    critical: "#dc2626",
+    high: "#ea580c",
+    medium: "#f59e0b",
+    low: "#84cc16",
+    info: "#3b82f6"
+  };
+  return colors[severity] || "#64748b";
+}
+
+// src/commands/audit-wizard.ts
+import { render as render2 } from "ink";
+import React11 from "react";
+import { analyzeUrlWithRules as analyzeUrlWithRules3, calculateAIReadiness as calculateAIReadiness2 } from "@ai-lighthouse/scanner";
+function auditWizardCommand(program2) {
+  program2.command("wizard").alias("w").description("Interactive wizard to configure and run an audit").argument("[url]", "Optional URL to audit (will prompt if not provided)").action(async (url) => {
+    const originalConsoleError = console.error;
+    const originalConsoleWarn = console.warn;
+    console.error = () => {
+    };
+    console.warn = () => {
+    };
+    let auditConfig = null;
+    const wizardRender = render2(
+      React11.createElement(SetupWizard, {
+        initialUrl: url,
+        onComplete: (config) => {
+          auditConfig = config;
+        }
+      })
+    );
+    await wizardRender.waitUntilExit();
+    if (!auditConfig) {
+      console.error = originalConsoleError;
+      console.warn = originalConsoleWarn;
+      console.log("\nAudit cancelled.");
+      process.exit(0);
+    }
+    const { clear, rerender } = render2(
+      React11.createElement(AuditReportUI, {
+        url: auditConfig.url,
+        result: {},
+        aiReadiness: {},
+        loading: true,
+        currentStep: "Starting audit..."
+      })
+    );
+    try {
+      const scanOptions = {
+        maxChunkTokens: 1200,
+        chunkingStrategy: "auto",
+        enableChunking: auditConfig.enableChunking,
+        enableExtractability: auditConfig.enableExtractability,
+        enableHallucinationDetection: auditConfig.enableHallucination,
+        enableLLM: auditConfig.enableLlm,
+        minImpactScore: 8,
+        minConfidence: 0.7,
+        maxIssues: 20
+      };
+      if (auditConfig.enableLlm && auditConfig.llmProvider) {
+        scanOptions.llmConfig = {
+          provider: auditConfig.llmProvider,
+          model: auditConfig.llmModel,
+          baseUrl: auditConfig.llmBaseUrl,
+          apiKey: auditConfig.llmApiKey
+        };
+      }
+      rerender(
+        React11.createElement(AuditReportUI, {
+          url: auditConfig.url,
+          result: {},
+          aiReadiness: {},
+          loading: true,
+          currentStep: "Scanning page..."
+        })
+      );
+      const result = await analyzeUrlWithRules3(auditConfig.url, scanOptions);
+      rerender(
+        React11.createElement(AuditReportUI, {
+          url: auditConfig.url,
+          result,
+          aiReadiness: {},
+          loading: true,
+          currentStep: "Calculating AI readiness scores..."
+        })
+      );
+      const aiReadiness = calculateAIReadiness2(result);
+      clear();
+      const finalRender = render2(
+        React11.createElement(AuditReportUI, {
+          url: auditConfig.url,
+          result,
+          aiReadiness,
+          loading: false
+        })
+      );
+      await finalRender.waitUntilExit();
+      console.error = originalConsoleError;
+      console.warn = originalConsoleWarn;
+    } catch (error) {
+      console.error = originalConsoleError;
+      console.warn = originalConsoleWarn;
+      clear();
+      console.log("\n\x1B[1m\x1B[31m\u274C Audit Failed\x1B[0m");
+      console.log("\x1B[31m" + "\u2500".repeat(70) + "\x1B[0m");
+      console.log("\x1B[31m" + (error instanceof Error ? error.message : String(error)) + "\x1B[0m");
+      console.log("\n\x1B[2mPlease check the URL and your configuration.\x1B[0m");
+      process.exit(1);
+    }
+  });
+}
+
+// src/index.ts
+var program = new Command();
+program.name("ai-lighthouse").description("AI Lighthouse - Audit websites for AI readiness and SEO optimization").version("1.0.0");
+auditWizardCommand(program);
 auditCommand(program);
 crawlCommand(program);
 reportCommand(program);