feat: migrate npm registry from Verdaccio to Gitea Packages

packages/concept-engine/src/cli.ts

@@ -0,0 +1,149 @@
+#!/usr/bin/env node
+// ============================================================================
+// @mintel/concept-engine — CLI Entry Point
+// Simple commander-based CLI for concept generation.
+// ============================================================================
+
+import { Command } from "commander";
+import * as path from "node:path";
+import * as fs from "node:fs/promises";
+import { existsSync } from "node:fs";
+import { config as dotenvConfig } from "dotenv";
+import { ConceptPipeline } from "./pipeline.js";
+
+// Load .env from monorepo root
+dotenvConfig({ path: path.resolve(process.cwd(), "../../.env") });
+dotenvConfig({ path: path.resolve(process.cwd(), ".env") });
+
+const program = new Command();
+
+program
+    .name("concept")
+    .description("AI-powered project concept generator")
+    .version("1.0.0");
+
+program
+    .command("run")
+    .description("Run the full concept pipeline")
+    .argument("[briefing]", "Briefing text or @path/to/file.txt")
+    .option("--url <url>", "Target website URL")
+    .option("--comments <comments>", "Additional notes")
+    .option("--clear-cache", "Clear crawl cache and re-crawl")
+    .option("--output <dir>", "Output directory", "../../out/concepts")
+    .option("--crawl-dir <dir>", "Crawl data directory", "../../data/crawls")
+    .action(async (briefingArg: string | undefined, options: any) => {
+        const openrouterKey = process.env.OPENROUTER_API_KEY || process.env.OPENROUTER_KEY;
+        if (!openrouterKey) {
+            console.error("❌ OPENROUTER_API_KEY not found in environment.");
+            process.exit(1);
+        }
+
+        let briefing = briefingArg || "";
+
+        // Handle @file references
+        if (briefing.startsWith("@")) {
+            const rawPath = briefing.substring(1);
+            const filePath = rawPath.startsWith("/")
+                ? rawPath
+                : path.resolve(process.cwd(), rawPath);
+            if (!existsSync(filePath)) {
+                console.error(`❌ Briefing file not found: ${filePath}`);
+                process.exit(1);
+            }
+            briefing = await fs.readFile(filePath, "utf8");
+            console.log(`📄 Loaded briefing from: ${filePath}`);
+        }
+
+        // Auto-discover URL from briefing
+        let url = options.url;
+        if (!url && briefing) {
+            const urlMatch = briefing.match(/https?:\/\/[^\s]+/);
+            if (urlMatch) {
+                url = urlMatch[0];
+                console.log(`🔗 Discovered URL in briefing: ${url}`);
+            }
+        }
+
+        if (!briefing && !url) {
+            console.error("❌ Provide a briefing text or --url");
+            process.exit(1);
+        }
+
+        const pipeline = new ConceptPipeline(
+            {
+                openrouterKey,
+                zyteApiKey: process.env.ZYTE_API_KEY,
+                outputDir: path.resolve(process.cwd(), options.output),
+                crawlDir: path.resolve(process.cwd(), options.crawlDir),
+            },
+            {
+                onStepStart: (id, name) => {
+                    // Will be enhanced with Ink spinner later
+                },
+                onStepComplete: (id, result) => {
+                    // Will be enhanced with Ink UI later
+                },
+            },
+        );
+
+        try {
+            await pipeline.run({
+                briefing,
+                url,
+                comments: options.comments,
+                clearCache: options.clearCache,
+            });
+
+            console.log("\n✨ Concept generation complete!");
+        } catch (err) {
+            console.error(`\n❌ Pipeline failed: ${(err as Error).message}`);
+            process.exit(1);
+        }
+    });
+
+program
+    .command("analyze")
+    .description("Only crawl and analyze a website (no LLM)")
+    .argument("<url>", "Website URL to analyze")
+    .option("--crawl-dir <dir>", "Crawl data directory", "../../data/crawls")
+    .option("--clear-cache", "Clear existing crawl cache")
+    .action(async (url: string, options: any) => {
+        const { crawlSite } = await import("./scraper.js");
+        const { analyzeSite } = await import("./analyzer.js");
+
+        if (options.clearCache) {
+            const { clearCrawlCache } = await import("./scraper.js");
+            const domain = new URL(url).hostname;
+            await clearCrawlCache(path.resolve(process.cwd(), options.crawlDir), domain);
+        }
+
+        const pages = await crawlSite(url, {
+            zyteApiKey: process.env.ZYTE_API_KEY,
+            crawlDir: path.resolve(process.cwd(), options.crawlDir),
+        });
+
+        const domain = new URL(url).hostname;
+        const profile = analyzeSite(pages, domain);
+
+        console.log("\n📊 Site Profile:");
+        console.log(`  Domain: ${profile.domain}`);
+        console.log(`  Total Pages: ${profile.totalPages}`);
+        console.log(`  Navigation: ${profile.navigation.map((n) => n.label).join(", ")}`);
+        console.log(`  Features: ${profile.existingFeatures.join(", ") || "none"}`);
+        console.log(`  Services: ${profile.services.join(", ") || "none"}`);
+        console.log(`  External Domains: ${profile.externalDomains.join(", ") || "none"}`);
+        console.log(`  Company: ${profile.companyInfo.name || "unbekannt"}`);
+        console.log(`  Tax ID: ${profile.companyInfo.taxId || "unbekannt"}`);
+        console.log(`  Colors: ${profile.colors.join(", ")}`);
+        console.log(`  Images Found: ${profile.images.length}`);
+        console.log(`  Social: ${Object.entries(profile.socialLinks).map(([k, v]) => `${k}`).join(", ") || "none"}`);
+
+        const outputPath = path.join(
+            path.resolve(process.cwd(), options.crawlDir),
+            domain.replace(/\./g, "-"),
+            "_site_profile.json",
+        );
+        console.log(`\n📦 Full profile saved to: ${outputPath}`);
+    });
+
+program.parse();