vesper-wizard 2.3.0 → 2.3.2

package/build/scripts/test-exporter.js

@@ -1,53 +0,0 @@
-import { DataExporter } from "../export/exporter.js";
-import fs from "fs";
-import path from "path";
-async function main() {
-    console.log("=== Vesper Data Exporter Test ===\n");
-    const exporter = new DataExporter();
-    const testDir = path.join(process.cwd(), "test_export");
-    if (!fs.existsSync(testDir))
-        fs.mkdirSync(testDir);
-    const inputFile = path.join(testDir, "input.csv");
-    // Create Dummy Data
-    let csvContent = "id,name,value\n";
-    for (let i = 0; i < 10; i++)
-        csvContent += `${i},item_${i},${Math.random()}\n`;
-    fs.writeFileSync(inputFile, csvContent);
-    console.log(`Created input file: ${inputFile}`);
-    const formats = ["parquet", "jsonl", "arrow"];
-    for (const fmt of formats) {
-        const outputFile = path.join(testDir, `output.${fmt}`);
-        console.log(`\n--- Exporting to ${fmt.toUpperCase()} ---`);
-        try {
-            const result = await exporter.export(inputFile, outputFile, fmt);
-            console.log("Result:", result);
-            if (fs.existsSync(outputFile)) {
-                const stats = fs.statSync(outputFile);
-                console.log(`PASS: File created (${stats.size} bytes)`);
-            }
-            else {
-                console.error("FAIL: Output file not found");
-            }
-        }
-        catch (e) {
-            console.error(`FAIL: Export to ${fmt} failed:`, e);
-        }
-    }
-    // specific Arrow test
-    // specific TFRecord test (might fail if no tensorflow)
-    console.log(`\n--- Exporting to TFRECORD (Optional) ---`);
-    const tfFile = path.join(testDir, "output.tfrecord");
-    try {
-        const result = await exporter.export(inputFile, tfFile, "tfrecord");
-        console.log("Result:", result);
-        if (fs.existsSync(tfFile)) {
-            console.log("PASS: TFRecord file created");
-        }
-    }
-    catch (e) {
-        console.log("SKIP: TFRecord export failed (likely no tensorflow installed):", e.message || e);
-    }
-    // Cleanup
-    // fs.rmSync(testDir, { recursive: true, force: true });
-}
-main().catch(console.error);

package/build/scripts/test-fusion.js

@@ -1,61 +0,0 @@
-import { FusionOrchestrator } from "../fusion/orchestrator.js";
-import * as fs from "fs";
-async function runTest() {
-    const ds1 = {
-        id: "ds1",
-        name: "Dataset 1",
-        source: "huggingface",
-        columns: [
-            { name: "text", type: "string" },
-            { name: "label", type: "int", is_target: true }
-        ],
-        // ... other required fields (using type assertion for brevity in test)
-    };
-    const ds2 = {
-        id: "ds2",
-        name: "Dataset 2",
-        source: "kaggle",
-        columns: [
-            { name: "sentence", type: "string" },
-            { name: "sentiment", type: "string", is_target: true }
-        ],
-    };
-    const config = {
-        target_column: "target",
-        column_aliases: {
-            "text": ["sentence", "content"],
-            "target": ["label", "sentiment", "target"]
-        },
-        type_overrides: {},
-        dedupe_config: {
-            exact: true,
-            fuzzy: true,
-            fuzzy_threshold: 0.6,
-            fuzzy_columns: ["text"]
-        },
-        label_map: {
-            "pos": 1,
-            "neg": 0,
-            "0": 0,
-            "1": 1
-        }
-    };
-    const records = [
-        { datasetId: "ds1", record: { text: "I love this!", label: 1 } },
-        { datasetId: "ds1", record: { text: "This is bad.", label: 0 } },
-        { datasetId: "ds2", record: { sentence: "I love this!", sentiment: "pos" } }, // Exact duplicate (after alignment)
-        { datasetId: "ds2", record: { sentence: "I really love this!", sentiment: "pos" } }, // Fuzzy duplicate
-        { datasetId: "ds2", record: { sentence: "It was okay.", sentiment: "neg" } },
-    ];
-    const orchestrator = new FusionOrchestrator(config);
-    const result = await orchestrator.fuse([ds1, ds2], records);
-    fs.writeFileSync("test-fusion-results.json", JSON.stringify(result, null, 2));
-    console.log("Results written to test-fusion-results.json");
-    if (result.stats.total_output_rows === 3) {
-        console.log("✅ Success: Rows correctly fused and deduplicated.");
-    }
-    else {
-        console.error(`❌ Failure: Expected 3 rows, got ${result.stats.total_output_rows}`);
-    }
-}
-runTest().catch(console.error);

package/build/scripts/test-github.js

@@ -1,27 +0,0 @@
-import { GitHubScraper } from "../metadata/github-scraper.js";
-async function runTest() {
-    console.log("--- Testing GitHub integration ---");
-    const scraper = new GitHubScraper();
-    const query = "covid-19";
-    console.log(`Searching GitHub for: "${query}"...`);
-    const results = await scraper.scrape(query, 5);
-    console.log(`Found ${results.length} datasets.`);
-    if (results.length > 0) {
-        console.log("✅ GitHub Scraper returned results.");
-        console.log("Sample Result:");
-        console.log(JSON.stringify(results[0], null, 2));
-        // Validation
-        const sample = results[0];
-        if (sample.id.startsWith("github:") && sample.source === "github") {
-            console.log("✅ Metadata schema validation passed.");
-        }
-        else {
-            console.error("❌ Metadata schema validation failed.");
-        }
-    }
-    else {
-        console.error("❌ No results found or rate limit hit.");
-    }
-    console.log("--- Test Complete ---");
-}
-runTest().catch(console.error);

package/build/scripts/test-group-split.js

@@ -1,52 +0,0 @@
-import { DataSplitter } from "../splitting/splitter.js";
-import fs from "fs";
-import path from "path";
-async function main() {
-    console.log("=== Vesper Group Split Test ===\n");
-    const splitter = new DataSplitter();
-    const testFile = path.join(process.cwd(), "test_group_split.csv");
-    // Create Dummy Data (100 rows, 10 groups of 10 rows each)
-    let csvContent = "id,group_id,value\n";
-    for (let g = 0; g < 10; g++) {
-        for (let i = 0; i < 10; i++) {
-            csvContent += `${g * 10 + i},group_${g},${Math.random()}\n`;
-        }
-    }
-    fs.writeFileSync(testFile, csvContent);
-    console.log(`Created test file with 10 distinct groups.`);
-    // Test: Group-based Split (60/20/20)
-    const config = {
-        type: "group",
-        ratios: { train: 0.6, val: 0.2, test: 0.2, holdout: 0 },
-        group_column: "group_id",
-        shuffle: true,
-        random_seed: 42
-    };
-    try {
-        const result = await splitter.split(testFile, config);
-        console.log("Stats:", result.stats);
-        // Validation: No group should exist in more than one split
-        console.log("\n--- Group Leakage Validation ---");
-        const report = await splitter.validate(result.paths, { id_column: "group_id" }); // Checking uniqueness of group_id across splits
-        console.log("Validation Report:", report);
-        if (!report.leakage_detected) {
-            console.log("PASS: No group leakage detected.");
-        }
-        else {
-            console.error("FAIL: Groups leaked across splits!");
-        }
-        // Cleanup
-        Object.values(result.paths).forEach(p => {
-            if (fs.existsSync(p))
-                fs.unlinkSync(p);
-        });
-    }
-    catch (e) {
-        console.error("Test execution failed:", e);
-    }
-    finally {
-        if (fs.existsSync(testFile))
-            fs.unlinkSync(testFile);
-    }
-}
-main().catch(console.error);

package/build/scripts/test-hf-download.js

@@ -1,29 +0,0 @@
-import { HFDownloader } from "../ingestion/hf-downloader.js";
-import path from "path";
-import fs from "fs";
-import { fileURLToPath } from "url";
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = path.dirname(__filename);
-const projectRoot = path.join(__dirname, "..", "..");
-async function testHFDownload() {
-    const downloader = new HFDownloader();
-    const repoId = "fka/awesome-chatgpt-prompts";
-    console.log(`Testing HF Download for ${repoId}...`);
-    const bestFile = await downloader.findBestFile(repoId);
-    console.log(`Best file found: ${bestFile}`);
-    if (bestFile) {
-        const testDir = path.join(projectRoot, "data", "test");
-        if (!fs.existsSync(testDir))
-            fs.mkdirSync(testDir, { recursive: true });
-        const targetPath = path.join(testDir, "awesome-prompts.csv");
-        await downloader.download(repoId, bestFile, targetPath, (p) => {
-            process.stdout.write(`\rProgress: ${p}%`);
-        });
-        console.log(`\nDownload complete! Size: ${fs.statSync(targetPath).size} bytes`);
-        console.log(`Location: ${targetPath}`);
-    }
-    else {
-        console.error("No file found!");
-    }
-}
-testHFDownload().catch(console.error);

package/build/scripts/test-holdout-manager.js

@@ -1,61 +0,0 @@
-import { DataSplitter } from "../splitting/splitter.js";
-import fs from "fs";
-import path from "path";
-async function main() {
-    console.log("=== Vesper Holdout Set Manager Test ===\n");
-    const splitter = new DataSplitter();
-    const testFile = path.join(process.cwd(), "test_holdout.csv");
-    // Create Dummy Data (200 rows)
-    let csvContent = "id,label,date\n";
-    for (let i = 0; i < 100; i++)
-        csvContent += `${i},A,2023-01-${(i % 30) + 1}\n`;
-    for (let i = 100; i < 200; i++)
-        csvContent += `${i},B,2023-02-${(i % 28) + 1}\n`;
-    fs.writeFileSync(testFile, csvContent);
-    console.log(`Created test file: ${testFile}`);
-    // Test: 4-way Random Split (70/10/10/10)
-    console.log("\n--- Test: 4-way Random Split (70/10/10/10) ---");
-    const config = {
-        type: "random",
-        ratios: { train: 0.7, val: 0.1, test: 0.1, holdout: 0.1 },
-        shuffle: true,
-        random_seed: 42
-    };
-    try {
-        const result = await splitter.split(testFile, config);
-        console.log("Stats:", result.stats);
-        const expected = { train: 140, val: 20, test: 20, holdout: 20 };
-        if (result.stats.train_rows === expected.train &&
-            result.stats.val_rows === expected.val &&
-            result.stats.test_rows === expected.test &&
-            result.stats.holdout_rows === expected.holdout) {
-            console.log("PASS: 4-way ratios preserved");
-        }
-        else {
-            console.error(`FAIL: Ratios mismatch. Expected ${JSON.stringify(expected)}, got ${JSON.stringify(result.stats)}`);
-        }
-        // Validate Split for Leakage
-        console.log("\n--- Validation Check ---");
-        const report = await splitter.validate(result.paths, { id_column: "id" });
-        console.log("Report:", report);
-        if (!report.leakage_detected) {
-            console.log("PASS: No leakage between 4 splits");
-        }
-        else {
-            console.error("FAIL: Leakage detected!");
-        }
-        // Cleanup
-        Object.values(result.paths).forEach(p => {
-            if (fs.existsSync(p))
-                fs.unlinkSync(p);
-        });
-    }
-    catch (e) {
-        console.error("Test execution failed:", e);
-    }
-    finally {
-        if (fs.existsSync(testFile))
-            fs.unlinkSync(testFile);
-    }
-}
-main().catch(console.error);

package/build/scripts/test-hybrid-search.js

@@ -1,41 +0,0 @@
-import { SearchEngine } from "../search/engine.js";
-import { MetadataStore } from "../metadata/store.js";
-import { VectorStore } from "../search/vector-store.js";
-import { Embedder } from "../search/embedder.js";
-import path from "path";
-async function main() {
-    const dbPath = path.join(process.cwd(), "data", "metadata.db");
-    const vectorPath = path.join(process.cwd(), "data", "vectors.json");
-    const store = new MetadataStore(dbPath);
-    const vectorStore = new VectorStore(vectorPath);
-    const embedder = Embedder.getInstance();
-    await embedder.init();
-    const engine = new SearchEngine(store, vectorStore, embedder);
-    console.log("\n=== Hybrid Search Precision Test ===\n");
-    // Test 1: Financial Forecasting (Drift Check)
-    // Should NOT have crypto in top results if hybrid logic works
-    console.log("Test 1: 'financial forecasting' (Should penalize Crypto)");
-    const results1 = await engine.search("financial forecasting", { limit: 5 });
-    results1.forEach((r, i) => {
-        const score = r.relevance_score;
-        const vector = r.vector_score;
-        const lexical = r.lexical_score;
-        console.log(`  ${i + 1}. [${score}] ${r.name} (Vec: ${vector}, Lex: ${lexical})`);
-        if (r.name.toLowerCase().includes("crypto") || r.description.toLowerCase().includes("bitcoin")) {
-            console.error("     CRITICAL: Crypto found in top results!");
-        }
-    });
-    console.log("");
-    // Test 2: Negative Keywords
-    console.log("Test 2: 'financial forecasting -stock' (Should exclude 'stock')");
-    const results2 = await engine.search("financial forecasting -stock", { limit: 5 });
-    results2.forEach((r, i) => {
-        console.log(`  ${i + 1}. ${r.name}`);
-        if (r.name.toLowerCase().includes("stock") || r.description.toLowerCase().includes("stock")) {
-            console.error("     ERROR: Negative keyword failed!");
-        }
-    });
-    console.log("\nDone.");
-    store.close();
-}
-main().catch(console.error);

package/build/scripts/test-image-analysis.js

@@ -1,50 +0,0 @@
-import { ImageAnalyzer } from "../quality/image-analyzer.js";
-import path from "path";
-import fs from "fs";
-import { execSync } from "child_process";
-async function runTest() {
-    console.log("--- Testing Image Quality Analysis ---");
-    const projectRoot = path.resolve(".");
-    const analyzer = new ImageAnalyzer(projectRoot);
-    // 1. Create a sample image using Python (to avoid external dependencies)
-    const testImageDir = path.join(projectRoot, "data", "test-images");
-    if (!fs.existsSync(testImageDir))
-        fs.mkdirSync(testImageDir, { recursive: true });
-    const imagePath = path.join(testImageDir, "test_v1.png");
-    console.log("Generating test image...");
-    const pythonScript = `
-from PIL import Image, ImageDraw
-import numpy as np
-img = Image.new('RGB', (800, 600), color = (73, 109, 137))
-d = ImageDraw.Draw(img)
-d.text((10,10), "Vesper Test Image", fill=(255,255,0))
-# Add some noise for blur check
-noise = np.random.randint(0, 255, (600, 800, 3), dtype='uint8')
-img_np = np.array(img)
-img_np = (img_np * 0.5 + noise * 0.5).astype('uint8')
-Image.fromarray(img_np).save('${imagePath.replace(/\\/g, "\\\\")}')
-    `;
-    fs.writeFileSync(path.join(testImageDir, "gen_image.py"), pythonScript);
-    execSync(`python "${path.join(testImageDir, "gen_image.py")}"`);
-    // 2. Run Analysis
-    console.log(`Analyzing ${imagePath}...`);
-    try {
-        const report = await analyzer.analyze(imagePath);
-        console.log("Analysis Result:");
-        console.log(`- Format: ${report.individual_results[0].format}`);
-        console.log(`- Resolution: ${report.individual_results[0].width}x${report.individual_results[0].height}`);
-        console.log(`- Blur Score: ${report.individual_results[0].blur_score}`);
-        console.log(`- Is Blurry: ${report.individual_results[0].is_blurry}`);
-        if (report.total_images === 1 && report.average_width === 800) {
-            console.log("\nVERIFICATION_STATUS: PASS");
-        }
-        else {
-            console.log("\nVERIFICATION_STATUS: FAIL - Incorrect stats");
-        }
-    }
-    catch (e) {
-        console.error(`Analysis failed: ${e.message}`);
-        console.log("\nVERIFICATION_STATUS: FAIL");
-    }
-}
-runTest().catch(console.error);

package/build/scripts/test-ingestion-infra.js

@@ -1,39 +0,0 @@
-import { MetadataStore } from "../metadata/store.js";
-import { DataIngestor } from "../ingestion/ingestor.js";
-import path from "path";
-import fs from "fs";
-import { fileURLToPath } from "url";
-const __filename = fileURLToPath(import.meta.url);
-const __dirname = path.dirname(__filename);
-const projectRoot = path.join(__dirname, "..", "..");
-const dbPath = path.join(projectRoot, "data", "test-metadata.db");
-// Clean test DB if exists
-if (fs.existsSync(dbPath))
-    fs.unlinkSync(dbPath);
-const store = new MetadataStore(dbPath);
-const ingestor = new DataIngestor(projectRoot, store);
-async function testInfra() {
-    console.log("--- Testing Ingestion Infrastructure (6.1) ---");
-    const testId = "test/dataset";
-    // 1. Get target path
-    const target = ingestor.getTargetPath(testId);
-    console.log(`Target path: ${target}`);
-    // 2. Register downloading
-    console.log("Registering download start...");
-    store.registerDownload(testId, target, 'downloading');
-    let status = store.getDownloadStatus(testId);
-    console.log("Status after start:", status?.status);
-    // 3. Register completion
-    console.log("Registering completion...");
-    ingestor.completeDownload(testId, target, 1024);
-    status = store.getDownloadStatus(testId);
-    console.log("Status after completion:", status?.status);
-    console.log("Saved path:", status?.local_path);
-    console.log("Size:", status?.size_bytes, "bytes");
-    // 4. Verify directory exists
-    const rawDir = path.join(projectRoot, "data", "raw");
-    console.log(`Raw data dir created: ${fs.existsSync(rawDir)}`);
-    console.log("\nInfrastructure test PASSED!");
-    store.close();
-}
-testInfra().catch(console.error);

package/build/scripts/test-install.js

@@ -1,40 +0,0 @@
-import { InstallService } from "../install/install-service.js";
-import { MetadataStore } from "../metadata/store.js";
-import path from "path";
-import fs from "fs";
-async function runTest() {
-    console.log("--- Testing Automatic Installation ---");
-    const projectRoot = path.resolve(".");
-    const metadataStore = new MetadataStore(path.join(projectRoot, "data", "metadata.db"));
-    const installService = new InstallService(projectRoot, metadataStore);
-    const query = "naruto";
-    const dataset = metadataStore.db.prepare("SELECT * FROM datasets WHERE name LIKE ? LIMIT 1").get(`%${query}%`);
-    if (!dataset) {
-        console.error("Naruto dataset not found in metadata.db. Please run a search first.");
-        return;
-    }
-    console.log(`Found dataset: ${dataset.name}`);
-    // Mock a prepared file
-    const mockFile = path.join(projectRoot, "data", "raw", "naruto_mock.csv");
-    if (!fs.existsSync(path.dirname(mockFile))) {
-        fs.mkdirSync(path.dirname(mockFile), { recursive: true });
-    }
-    fs.writeFileSync(mockFile, "quote,character\nBelieve it!,Naruto\nI will be Hokage,Naruto");
-    console.log(`Installing ${mockFile}...`);
-    const installPath = await installService.install(dataset.id, mockFile);
-    console.log(`✅ Success! Installed to: ${installPath}`);
-    // Verify it exists
-    if (fs.existsSync(installPath)) {
-        console.log("File exists at install location.");
-    }
-    else {
-        console.error("File MISSING from install location!");
-    }
-    // Verify metadata updated
-    const updated = metadataStore.getDataset(dataset.id);
-    const success = updated?.install_path === installPath;
-    console.log(`Updated install_path in metadata: ${updated?.install_path}`);
-    console.log(`VERIFICATION_STATUS: ${success ? "✅ PASS" : "❌ FAIL"}`);
-    console.log("\n--- Test Complete ---");
-}
-runTest().catch(console.error);

package/build/scripts/test-institutional.js

@@ -1,26 +0,0 @@
-import { WorldBankScraper, NASAScraper } from "../metadata/institutional-scrapers.js";
-async function runTest() {
-    console.log("--- Testing Institutional Data Sources ---");
-    const wb = new WorldBankScraper();
-    const nasa = new NASAScraper();
-    console.log('Searching World Bank for: "climate"...');
-    const wbResults = await wb.scrape("climate", 3);
-    console.log(`Found ${wbResults.length} World Bank results.`);
-    if (wbResults.length > 0) {
-        console.log("✅ World Bank Sample:");
-        console.log(` - ID: ${wbResults[0].id}`);
-        console.log(` - Name: ${wbResults[0].name}`);
-        console.log(` - URL: ${wbResults[0].metadata_url}`);
-    }
-    console.log('\nSearching NASA for: "astronomy"...');
-    const nasaResults = await nasa.scrape("astronomy", 3);
-    console.log(`Found ${nasaResults.length} NASA results.`);
-    if (nasaResults.length > 0) {
-        console.log("✅ NASA Sample:");
-        console.log(` - ID: ${nasaResults[0].id}`);
-        console.log(` - Name: ${nasaResults[0].name}`);
-        console.log(` - URL: ${nasaResults[0].metadata_url}`);
-    }
-    console.log("\n--- Test Complete ---");
-}
-runTest().catch(console.error);

package/build/scripts/test-integrity.js

@@ -1,41 +0,0 @@
-import { QualityAnalyzer } from "../quality/analyzer.js";
-import fs from "fs";
-import path from "path";
-async function main() {
-    console.log("=== Vesper Integrity Check Test ===\n");
-    const analyzer = new QualityAnalyzer();
-    const testFile = path.join(process.cwd(), "test_integrity.csv");
-    // Create a CSV with unique IDs but duplicate CONTENT
-    // This simulates a common data issue: exact same review scraped twice with different IDs
-    const csvContent = `id,review,label
-1,"This product involves huge risks.",negative
-2,"Great investment opportunity!",positive
-3,"This product involves huge risks.",negative
-4,"Wait and see.",neutral
-5,"Great investment opportunity!",positive`;
-    fs.writeFileSync(testFile, csvContent);
-    console.log(`Created test file: ${testFile}`);
-    console.log("Expectations:");
-    console.log("  - Duplicate Rows: 0 (because IDs differ)");
-    console.log("  - Text Duplicates: > 0 (because 'review' column has dupes)");
-    try {
-        console.log("\nRunning analyzer...");
-        const report = await analyzer.analyze(testFile);
-        console.log("\n=== Integrity Report ===");
-        console.log(`Duplicate Rows (Exact): ${report.duplicate_rows}`);
-        console.log(`Text Duplicates (Content): ${report.text_duplicates || 0}`);
-        console.log("\nWarnings:", report.warnings);
-        if (report.text_duplicates && report.text_duplicates > 0) {
-            console.log("Test passed! Detected text duplication despite unique IDs.");
-        }
-        else {
-            console.error("Test failed! Did not detect text duplicates.");
-        }
-        // Cleanup
-        fs.unlinkSync(testFile);
-    }
-    catch (error) {
-        console.error("\nTest failed:", error);
-    }
-}
-main().catch(console.error);

package/build/scripts/test-jit.js

@@ -1,42 +0,0 @@
-import { SearchEngine } from "../search/engine.js";
-import { MetadataStore } from "../metadata/store.js";
-import { VectorStore } from "../search/vector-store.js";
-import { Embedder } from "../search/embedder.js";
-import path from "path";
-/**
- * Test JIT fallback with various queries
- */
-async function main() {
-    const dbPath = path.join(process.cwd(), "data", "metadata.db");
-    const vectorPath = path.join(process.cwd(), "data", "vectors.json");
-    const store = new MetadataStore(dbPath);
-    const vectorStore = new VectorStore(vectorPath);
-    const embedder = Embedder.getInstance();
-    await embedder.init();
-    const engine = new SearchEngine(store, vectorStore, embedder);
-    console.log("\n=== JIT Fallback Test Suite ===\n");
-    // Test 1: Query that should have good results (should NOT trigger JIT)
-    console.log("Test 1: Common query (should NOT trigger JIT)");
-    console.log("Query: 'image classification cats dogs'\n");
-    const results1 = await engine.search("image classification cats dogs", { limit: 5 });
-    console.log(`Results: ${results1.length}, Top score: ${results1[0]?.relevance_score || 0}`);
-    console.log("---\n");
-    // Test 2: Very niche query (should trigger JIT)
-    console.log("Test 2: Niche query (SHOULD trigger JIT)");
-    console.log("Query: 'underwater acoustic signal processing dolphins'\n");
-    const results2 = await engine.search("underwater acoustic signal processing dolphins", { limit: 5 });
-    console.log(`Results: ${results2.length}, Top score: ${results2[0]?.relevance_score || 0}`);
-    console.log("---\n");
-    // Test 3: Another niche query
-    console.log("Test 3: Another niche query (SHOULD trigger JIT)");
-    console.log("Query: 'mongolian language morphological analysis'\n");
-    const results3 = await engine.search("mongolian language morphological analysis", { limit: 5 });
-    console.log(`Results: ${results3.length}, Top score: ${results3[0]?.relevance_score || 0}`);
-    console.log("---\n");
-    // Check final dataset count
-    const finalCount = store.getAllDatasets().length;
-    console.log(`\nFinal dataset count: ${finalCount}`);
-    console.log("(Compare with initial 1238 to see if JIT added new datasets)\n");
-    store.close();
-}
-main().catch(console.error);

package/build/scripts/test-job-queue.js

@@ -1,62 +0,0 @@
-import { MetadataStore } from "../metadata/store.js";
-import { JobManager } from "../jobs/manager.js";
-async function runTest() {
-    console.log("--- Initializing Job Queue Test ---");
-    const store = new MetadataStore("data/vesper_test_jobs.db");
-    const manager = JobManager.getInstance(store);
-    manager.setConcurrency(2); // 2 parallel workers
-    const jobsFinished = [];
-    // Listener to simulate job processing
-    manager.on("processJob", async (job, run) => {
-        console.log(`[Worker] Starting Job: ${job.id} (Type: ${job.type}, Priority: ${job.priority})`);
-        await run(async () => {
-            // Simulate variable workload
-            const duration = job.priority === 10 ? 500 : 2000;
-            await new Promise(r => setTimeout(r, duration));
-            // Simulate failure for a specific job to test retries
-            if (job.metadata === "FAIL_ONCE" && job.attempts === 0) {
-                console.log(`[Worker] Simulating failure for job ${job.id}`);
-                throw new Error("Transitory error");
-            }
-            console.log(`[Worker] Finished Job: ${job.id}`);
-            jobsFinished.push(job.id);
-        });
-    });
-    console.log("\n--- Enqueuing Jobs ---");
-    // 1. A slow low-priority job
-    const j1 = manager.createJob("prepare", 0, "slow-1");
-    // 2. A fast high-priority job (Pro user)
-    const j2 = manager.createJob("clean", 10, "pro-1");
-    // 3. Another low-priority job
-    const j3 = manager.createJob("split", 0, "slow-2");
-    // 4. A job that fails once
-    const j4 = manager.createJob("fusion", 5, "FAIL_ONCE");
-    console.log(`Enqueued 4 jobs. Concurrency is 2.`);
-    // Wait for all to finish
-    return new Promise((resolve) => {
-        const check = setInterval(() => {
-            const stats = manager.queue.getStats();
-            if (stats.total === 0 && jobsFinished.includes(j4.id)) {
-                clearInterval(check);
-                console.log("\n--- Test Results ---");
-                console.log("Execution Order:", jobsFinished);
-                const proIndex = jobsFinished.indexOf(j2.id);
-                const slowIndex = jobsFinished.indexOf(j3.id);
-                if (proIndex < slowIndex) {
-                    console.log("✅ Priority verified: Pro job finished before later low-priority jobs.");
-                }
-                else {
-                    console.warn("⚠️ Priority check failed or inconclusive due to parallel timing.");
-                }
-                const j4_final = store.getJob(j4.id);
-                if (j4_final?.attempts === 1) {
-                    console.log("✅ Retry logic verified: Job retried after failure.");
-                }
-                console.log("\n✅ Success: Job queue system verified.");
-                store.close();
-                resolve(null);
-            }
-        }, 1000);
-    });
-}
-runTest().catch(console.error);