vesper-wizard 2.3.1 → 2.3.2

package/build/splitting/splitter.js

@@ -1,82 +0,0 @@
-import { spawn } from "child_process";
-import path from "path";
-import fs from "fs";
-export class DataSplitter {
-    pythonPath = "python";
-    scriptPath;
-    constructor(buildDir = process.cwd()) {
-        const homeDir = process.env.HOME || process.env.USERPROFILE || buildDir;
-        const dataRoot = path.join(homeDir, ".vesper");
-        const scriptPath0 = path.resolve(dataRoot, "python", "splitter_engine.py");
-        const scriptPath1 = path.resolve(buildDir, "python", "splitter_engine.py");
-        const scriptPath2 = path.resolve(buildDir, "..", "src", "python", "splitter_engine.py");
-        const scriptPath3 = path.resolve(buildDir, "..", "python", "splitter_engine.py");
-        if (fs.existsSync(scriptPath0)) {
-            this.scriptPath = scriptPath0;
-        }
-        else if (fs.existsSync(scriptPath1)) {
-            this.scriptPath = scriptPath1;
-        }
-        else if (fs.existsSync(scriptPath2)) {
-            this.scriptPath = scriptPath2;
-        }
-        else if (fs.existsSync(scriptPath3)) {
-            this.scriptPath = scriptPath3;
-        }
-        else {
-            this.scriptPath = scriptPath0;
-        }
-        // Detect Python command
-        if (process.platform === "win32") {
-            this.pythonPath = "py";
-        }
-    }
-    /**
-     * Splits a dataset into Train/Val/Test sets based on config
-     */
-    async split(filePath, config) {
-        return this.runPython("split", [filePath, JSON.stringify(config)]);
-    }
-    /**
-     * Validates a split for leakage and distribution
-     */
-    async validate(paths, options) {
-        const config = {
-            paths,
-            id_column: options?.id_column,
-            target_column: options?.target_column
-        };
-        return this.runPython("validate", [JSON.stringify(config)]);
-    }
-    async runPython(action, args) {
-        return new Promise((resolve, reject) => {
-            const process = spawn(this.pythonPath, [this.scriptPath, action, ...args]);
-            let stdout = "";
-            let stderr = "";
-            process.stdout.on("data", (data) => {
-                stdout += data.toString();
-            });
-            process.stderr.on("data", (data) => {
-                stderr += data.toString();
-            });
-            process.on("close", (code) => {
-                if (code !== 0) {
-                    reject(new Error(`Data Splitter (${action}) failed: ${stderr}`));
-                    return;
-                }
-                try {
-                    const result = JSON.parse(stdout);
-                    if (result.error) {
-                        reject(new Error(result.error));
-                    }
-                    else {
-                        resolve(result);
-                    }
-                }
-                catch (e) {
-                    reject(new Error(`Failed to parse output: ${stdout}`));
-                }
-            });
-        });
-    }
-}

package/build/splitting/types.js

@@ -1 +0,0 @@
-export {};

package/build/tools/formatter.js

@@ -1,251 +0,0 @@
-/**
- * Format job status for visual representation
- */
-export function formatJobStatus(job) {
-    const statusMap = {
-        "pending": "PENDING",
-        "queued": "QUEUED",
-        "running": "RUNNING",
-        "completed": "COMPLETED",
-        "failed": "FAILED",
-        "retrying": "RETRYING"
-    };
-    const statusText = statusMap[job.status] || "UNKNOWN";
-    const barWidth = 20;
-    const filledWidth = Math.round((job.progress / 100) * barWidth);
-    const emptyWidth = barWidth - filledWidth;
-    const bar = "█".repeat(filledWidth) + "░".repeat(emptyWidth);
-    let output = `═ Job Status: ${job.type.toUpperCase()} ═\n`;
-    output += `ID: ${job.id}\n`;
-    output += `Status: ${statusText}\n`;
-    output += `Progress: ${bar} ${job.progress}%\n`;
-    output += `Activity: ${job.status_text}\n`;
-    if (job.status === "running" || job.status === "retrying" || job.status === "queued" || job.status === "pending") {
-        output += `Polling hint: check again in 5-10 seconds.\n`;
-    }
-    else {
-        output += `Polling hint: no further polling required.\n`;
-    }
-    if (job.result_url) {
-        output += `\nResult: ${job.result_url}\n`;
-    }
-    if (job.error) {
-        output += `\nERROR:\n`;
-        // Format multi-line errors nicely
-        const errorLines = job.error.split('\n');
-        errorLines.forEach(line => {
-            output += `   ${line}\n`;
-        });
-        output += `\n`;
-    }
-    output += `Updated: ${new Date(job.updated_at).toLocaleTimeString()}\n`;
-    output += "═".repeat(25) + "\n";
-    return output;
-}
-/**
- * Format dataset search results for human-readable display
- */
-export function formatSearchResults(results) {
-    if (results.length === 0) {
-        return "No datasets found matching your query.";
-    }
-    let output = `Found ${results.length} dataset(s):\n\n`;
-    output += "═".repeat(80) + "\n\n";
-    results.forEach((ds, index) => {
-        const relevanceScore = ds.relevance_score || 0;
-        // Source badge and access level
-        const openSources = ["huggingface", "openml", "s3", "uci", "github", "worldbank", "nasa"];
-        const isOpen = openSources.includes(ds.source);
-        const sourceLabel = ds.source.charAt(0).toUpperCase() + ds.source.slice(1);
-        const accessBadge = isOpen ? "Open Access" : "Requires API Key";
-        // Safety indicator
-        let safetyIndicator = "";
-        if (ds.license.category === "safe") {
-            safetyIndicator = "Safe";
-        }
-        else if (ds.license.category === "restricted") {
-            safetyIndicator = "Restricted";
-        }
-        else {
-            safetyIndicator = "Unknown License";
-        }
-        // Header
-        output += `${index + 1}. ${ds.name}\n`;
-        output += `   Source: ${sourceLabel} | ${accessBadge} | ${safetyIndicator}\n`;
-        output += `   Relevance: ${(relevanceScore * 100).toFixed(0)}% | ID: ${ds.id}\n\n`;
-        // Description
-        if (ds.description && ds.description.length > 0) {
-            const shortDesc = ds.description.length > 200
-                ? ds.description.substring(0, 200) + "..."
-                : ds.description;
-            output += `   ${shortDesc}\n\n`;
-        }
-        // Quality warnings
-        if (ds.quality_warnings && ds.quality_warnings.length > 0) {
-            output += `   Quality Warnings:\n`;
-            ds.quality_warnings.forEach(warning => {
-                output += `      • ${warning}\n`;
-            });
-            output += "\n";
-        }
-        // Key stats
-        output += `   Stats:\n`;
-        if (ds.downloads)
-            output += `      Downloads: ${ds.downloads.toLocaleString()}\n`;
-        if (ds.likes)
-            output += `      Likes: ${ds.likes}\n`;
-        if (ds.total_examples)
-            output += `      Examples: ${ds.total_examples.toLocaleString()}\n`;
-        if (ds.total_size_mb)
-            output += `      Size: ${ds.total_size_mb} MB\n`;
-        output += `      Domain: ${ds.domain || "unknown"}\n`;
-        output += `      Task: ${ds.task || "unknown"}\n`;
-        // Data splits
-        if (ds.splits && ds.splits.length > 0) {
-            const splitNames = ds.splits.map(s => s.name).join(", ");
-            output += `      Splits: ${splitNames}\n`;
-        }
-        // License details
-        output += `\n   License: ${ds.license.id || "Unknown"}\n`;
-        if (ds.license.warnings && ds.license.warnings.length > 0) {
-            ds.license.warnings.forEach(warning => {
-                output += `      WARNING: ${warning}\n`;
-            });
-        }
-        if (ds.license.commercial_use !== undefined) {
-            output += `      Commercial use: ${ds.license.commercial_use ? "Yes" : "No"}\n`;
-        }
-        // Download link
-        output += `\n   ${ds.download_url}\n`;
-        output += "\n" + "─".repeat(80) + "\n\n";
-    });
-    return output;
-}
-/**
- * Format detailed dataset info
- */
-export function formatDatasetInfo(ds) {
-    let output = "";
-    // Header
-    output += "═".repeat(80) + "\n";
-    output += `${ds.name}\n`;
-    output += "═".repeat(80) + "\n\n";
-    // Source and safety
-    const openSources = ["huggingface", "openml", "s3", "uci", "github", "worldbank", "nasa"];
-    const isOpen = openSources.includes(ds.source);
-    const sourceLabel = ds.source.charAt(0).toUpperCase() + ds.source.slice(1);
-    const accessBadge = isOpen ? "Open Access" : "Requires API Key";
-    let safetyIndicator = "";
-    if (ds.license.category === "safe") {
-        safetyIndicator = "Safe for use";
-    }
-    else if (ds.license.category === "restricted") {
-        safetyIndicator = "Restricted - Review license carefully";
-    }
-    else {
-        safetyIndicator = "Unknown license - Use with caution";
-    }
-    output += `Source: ${sourceLabel} (${accessBadge})\n`;
-    output += `Safety: ${safetyIndicator}\n`;
-    output += `ID: ${ds.id}\n\n`;
-    if (!isOpen && ds.source === "kaggle") {
-        output += `NOTE: This dataset uses the Kaggle connector. Vesper can access it through server-managed credentials when configured, otherwise a Kaggle key is still required.\n\n`;
-    }
-    if (!isOpen && ds.source === "dataworld") {
-        output += `NOTE: This dataset uses the data.world connector. Vesper can access it through a server-managed token when configured.\n\n`;
-    }
-    // Description
-    if (ds.description) {
-        output += "Description:\n";
-        output += `${ds.description}\n\n`;
-    }
-    // Quality warnings
-    if (ds.quality_warnings && ds.quality_warnings.length > 0) {
-        output += "Quality Warnings:\n";
-        ds.quality_warnings.forEach(warning => {
-            output += `   • ${warning}\n`;
-        });
-        output += "\n";
-    }
-    // Metadata
-    output += "Metadata:\n";
-    output += `   Downloads: ${ds.downloads?.toLocaleString() || "N/A"}\n`;
-    output += `   Likes: ${ds.likes || 0}\n`;
-    output += `   Quality Score: ${ds.quality_score}/100\n`;
-    output += `   Domain: ${ds.domain || "unknown"}\n`;
-    output += `   Task: ${ds.task || "unknown"}\n`;
-    output += `   Languages: ${ds.languages?.join(", ") || "N/A"}\n`;
-    output += `   Last Updated: ${new Date(ds.last_updated).toLocaleDateString()}\n\n`;
-    // Data characteristics
-    output += "Data Characteristics:\n";
-    output += `   Total Examples: ${ds.total_examples?.toLocaleString() || "N/A"}\n`;
-    output += `   Total Size: ${ds.total_size_mb ? ds.total_size_mb + " MB" : "N/A"}\n`;
-    output += `   Structured: ${ds.is_structured ? "Yes" : "No"}\n`;
-    output += `   Has Target Column: ${ds.has_target_column ? "Yes" : "No"}\n`;
-    output += `   Format: ${ds.format || "N/A"}\n\n`;
-    // Splits
-    if (ds.splits && ds.splits.length > 0) {
-        output += "Data Splits:\n";
-        ds.splits.forEach(split => {
-            output += `   • ${split.name}: ${split.num_examples?.toLocaleString() || "?"} examples`;
-            if (split.size_bytes) {
-                output += ` (${(split.size_bytes / (1024 * 1024)).toFixed(2)} MB)`;
-            }
-            output += "\n";
-        });
-        output += "\n";
-    }
-    // Columns
-    if (ds.columns && ds.columns.length > 0) {
-        output += "Columns:\n";
-        ds.columns.slice(0, 10).forEach(col => {
-            const targetMarker = col.is_target ? " [TARGET]" : "";
-            output += `   • ${col.name}${targetMarker}`;
-            if (col.type)
-                output += ` (${col.type})`;
-            output += "\n";
-        });
-        if (ds.columns.length > 10) {
-            output += `   ... and ${ds.columns.length - 10} more columns\n`;
-        }
-        output += "\n";
-    }
-    // License
-    output += "License Information:\n";
-    output += `   License: ${ds.license.id || "Unknown"}\n`;
-    output += `   Category: ${ds.license.category}\n`;
-    output += `   Commercial Use: ${ds.license.commercial_use ? "Allowed" : "Not allowed"}\n`;
-    if (ds.license.warnings && ds.license.warnings.length > 0) {
-        output += `   Warnings:\n`;
-        ds.license.warnings.forEach(warning => {
-            output += `      WARNING: ${warning}\n`;
-        });
-    }
-    if (ds.license.usage_restrictions && ds.license.usage_restrictions.length > 0) {
-        output += `   Restrictions:\n`;
-        ds.license.usage_restrictions.forEach(restriction => {
-            output += `      • ${restriction}\n`;
-        });
-    }
-    output += "\n";
-    // Safety flags
-    output += "Safety Flags:\n";
-    output += `   Safe Source: ${ds.is_safe_source ? "Yes" : "No"}\n`;
-    output += `   Has Personal Data: ${ds.has_personal_data ? "Yes" : "No"}\n`;
-    output += `   Paywalled: ${ds.is_paywalled ? "Yes" : "No"}\n`;
-    output += `   Scraped Web Data: ${ds.is_scraped_web_data ? "Yes" : "No"}\n\n`;
-    // Tags
-    if (ds.tags && ds.tags.length > 0) {
-        output += "Tags:\n";
-        output += `   ${ds.tags.slice(0, 15).join(", ")}`;
-        if (ds.tags.length > 15) {
-            output += ` ... and ${ds.tags.length - 15} more`;
-        }
-        output += "\n\n";
-    }
-    // Download link
-    output += "Download:\n";
-    output += `   ${ds.download_url}\n\n`;
-    output += "═".repeat(80) + "\n";
-    return output;
-}

package/build/utils/downloader.js

@@ -1,52 +0,0 @@
-import fs from "fs";
-import { Readable } from "stream";
-import { finished } from "stream/promises";
-import { retryWithBackoff } from "../metadata/rate-limiter.js";
-export class RobustDownloader {
-    /**
-     * Downloads a file with automatic retries and resume support
-     */
-    async download(url, targetPath, options = {}) {
-        await retryWithBackoff(async () => {
-            let startByte = 0;
-            const headers = { ...(options.headers || {}) };
-            // Handle resume logic
-            if (options.resume && fs.existsSync(targetPath)) {
-                startByte = fs.statSync(targetPath).size;
-                if (startByte > 0) {
-                    headers["Range"] = `bytes=${startByte}-`;
-                    console.error(`[Downloader] Resuming from byte ${startByte}`);
-                }
-            }
-            const response = await fetch(url, { headers });
-            if (response.status === 416) {
-                // Requested range not satisfiable - likely already finished
-                console.error("[Downloader] Range not satisfiable, file might be complete.");
-                return;
-            }
-            if (!response.ok && response.status !== 206) {
-                throw new Error(`Download failed: ${response.statusText} (${response.status})`);
-            }
-            const contentLength = response.headers.get("content-length");
-            const totalSize = (contentLength ? parseInt(contentLength, 10) : 0) + startByte;
-            const reader = response.body;
-            if (!reader)
-                throw new Error("Response body is empty");
-            // Open stream in append mode if resuming
-            const fileStream = fs.createWriteStream(targetPath, { flags: startByte > 0 ? "a" : "w" });
-            const nodeReadable = Readable.fromWeb(reader);
-            let downloadedBytes = startByte;
-            let lastProgressTime = 0;
-            nodeReadable.on("data", (chunk) => {
-                downloadedBytes += chunk.length;
-                // Throttle progress updates
-                const now = Date.now();
-                if (options.onProgress && (now - lastProgressTime > 500 || downloadedBytes === totalSize)) {
-                    options.onProgress(downloadedBytes, totalSize);
-                    lastProgressTime = now;
-                }
-            });
-            await finished(nodeReadable.pipe(fileStream));
-        }, { maxRetries: 5, initialDelay: 2000 });
-    }
-}

package/build/utils/python-runtime.js

@@ -1,130 +0,0 @@
-import { spawn } from "child_process";
-import fs from "fs";
-import os from "os";
-import path from "path";
-function getHomeDir(buildDir) {
-    return os.homedir() || process.env.HOME || process.env.USERPROFILE || buildDir;
-}
-export function getVesperDataRoot(buildDir = process.cwd()) {
-    return path.join(getHomeDir(buildDir), ".vesper");
-}
-export function getManagedPythonPath(buildDir = process.cwd()) {
-    const dataRoot = getVesperDataRoot(buildDir);
-    return process.platform === "win32"
-        ? path.join(dataRoot, ".venv", "Scripts", "python.exe")
-        : path.join(dataRoot, ".venv", "bin", "python");
-}
-function getFallbackPythonCommand() {
-    return process.platform === "win32" ? "py" : "python3";
-}
-export function resolvePythonCommand(buildDir = process.cwd()) {
-    const managedPython = getManagedPythonPath(buildDir);
-    if (fs.existsSync(managedPython)) {
-        return managedPython;
-    }
-    const envPython = process.env.VESPER_PYTHON;
-    if (envPython) {
-        return envPython;
-    }
-    const localCandidates = process.platform === "win32"
-        ? [
-            path.resolve(buildDir, ".venv", "Scripts", "python.exe"),
-            path.resolve(buildDir, "..", ".venv", "Scripts", "python.exe")
-        ]
-        : [
-            path.resolve(buildDir, ".venv", "bin", "python"),
-            path.resolve(buildDir, "..", ".venv", "bin", "python")
-        ];
-    for (const candidate of localCandidates) {
-        if (fs.existsSync(candidate)) {
-            return candidate;
-        }
-    }
-    return getFallbackPythonCommand();
-}
-function runPythonCommand(pythonPath, args, timeoutMs = 300000) {
-    return new Promise((resolve, reject) => {
-        const proc = spawn(pythonPath, args, {
-            env: {
-                ...process.env,
-                PYTHONIOENCODING: "utf-8",
-            },
-        });
-        let stdout = "";
-        let stderr = "";
-        const timer = setTimeout(() => {
-            proc.kill();
-            resolve({ code: 124, stdout, stderr: stderr || `Python command timed out after ${timeoutMs}ms` });
-        }, timeoutMs);
-        proc.stdout.on("data", (data) => {
-            stdout += data.toString();
-        });
-        proc.stderr.on("data", (data) => {
-            stderr += data.toString();
-        });
-        proc.on("close", (code) => {
-            clearTimeout(timer);
-            resolve({ code: code ?? 1, stdout, stderr });
-        });
-        proc.on("error", (error) => {
-            clearTimeout(timer);
-            reject(error);
-        });
-    });
-}
-async function createManagedPythonEnv(buildDir) {
-    const dataRoot = getVesperDataRoot(buildDir);
-    const venvDir = path.join(dataRoot, ".venv");
-    const managedPython = getManagedPythonPath(buildDir);
-    if (fs.existsSync(managedPython)) {
-        return managedPython;
-    }
-    fs.mkdirSync(dataRoot, { recursive: true });
-    const bootstrapAttempts = process.platform === "win32"
-        ? [
-            { command: "py", args: ["-3", "-m", "venv", venvDir] },
-            { command: "python", args: ["-m", "venv", venvDir] },
-        ]
-        : [
-            { command: "python3", args: ["-m", "venv", venvDir] },
-            { command: "python", args: ["-m", "venv", venvDir] },
-        ];
-    let lastError = "";
-    for (const attempt of bootstrapAttempts) {
-        try {
-            const result = await runPythonCommand(attempt.command, attempt.args, 180000);
-            if (result.code === 0 && fs.existsSync(managedPython)) {
-                await runPythonCommand(managedPython, ["-m", "pip", "install", "--disable-pip-version-check", "--upgrade", "pip"], 300000);
-                return managedPython;
-            }
-            lastError = (result.stderr || result.stdout || "Unknown venv creation error").trim();
-        }
-        catch (error) {
-            lastError = error?.message || String(error);
-        }
-    }
-    throw new Error(`Failed to create Vesper Python environment. ${lastError}`.trim());
-}
-export async function ensurePythonPackages(buildDir, requirements) {
-    const pythonPath = await createManagedPythonEnv(buildDir).catch(() => resolvePythonCommand(buildDir));
-    const missing = [];
-    for (const requirement of requirements) {
-        const check = await runPythonCommand(pythonPath, [
-            "-c",
-            `import importlib.util,sys; sys.exit(0 if importlib.util.find_spec(${JSON.stringify(requirement.module)}) else 1)`
-        ], 20000);
-        if (check.code !== 0) {
-            missing.push(requirement);
-        }
-    }
-    if (missing.length === 0) {
-        return pythonPath;
-    }
-    const packages = [...new Set(missing.map(requirement => requirement.packageName))];
-    const install = await runPythonCommand(pythonPath, ["-m", "pip", "install", "--disable-pip-version-check", ...packages], 600000);
-    if (install.code !== 0) {
-        const details = (install.stderr || install.stdout || "Unknown pip install error").trim();
-        throw new Error(`Failed to install Python packages (${packages.join(", ")}). ${details}`);
-    }
-    return pythonPath;
-}

package/build/utils/selector.js

@@ -1,69 +0,0 @@
-import readline from "readline";
-export class Selector {
-    currentIndex = 0;
-    options;
-    title;
-    constructor(title, options) {
-        this.title = title;
-        this.options = options;
-    }
-    render() {
-        // Clear previous lines
-        process.stdout.write("\x1b[?25l"); // Hide cursor
-        readline.cursorTo(process.stdout, 0);
-        // Clear the lines we used before (options + title + blank line)
-        for (let i = 0; i <= this.options.length + 1; i++) {
-            readline.clearLine(process.stdout, 0);
-            process.stdout.write("\x1b[1A"); // Move up one line
-        }
-        readline.clearLine(process.stdout, 0);
-        console.log(`\n${this.title}`);
-        this.options.forEach((opt, idx) => {
-            const isCurrent = idx === this.currentIndex;
-            const checkbox = opt.selected ? "[\x1b[32mX\x1b[0m]" : "[ ]";
-            const cursor = isCurrent ? "\x1b[36m>\x1b[0m " : "  ";
-            const label = isCurrent ? `\x1b[36m${opt.name}\x1b[0m` : opt.name;
-            console.log(`${cursor}${checkbox} ${label}`);
-        });
-        console.log("\x1b[2m(Use arrows to move, Space to toggle, Enter to confirm)\x1b[0m");
-    }
-    async run() {
-        if (this.options.length === 0)
-            return [];
-        readline.emitKeypressEvents(process.stdin);
-        if (process.stdin.isTTY) {
-            process.stdin.setRawMode(true);
-        }
-        // Initial render room (print blank lines to be cleared)
-        console.log("\n".repeat(this.options.length + 1));
-        this.render();
-        return new Promise((resolve) => {
-            const handleKey = (str, key) => {
-                if (key.name === "up") {
-                    this.currentIndex = (this.currentIndex - 1 + this.options.length) % this.options.length;
-                    this.render();
-                }
-                else if (key.name === "down") {
-                    this.currentIndex = (this.currentIndex + 1) % this.options.length;
-                    this.render();
-                }
-                else if (key.name === "space") {
-                    this.options[this.currentIndex].selected = !this.options[this.currentIndex].selected;
-                    this.render();
-                }
-                else if (key.name === "return") {
-                    process.stdin.setRawMode(false);
-                    process.stdin.removeListener("keypress", handleKey);
-                    process.stdout.write("\x1b[?25h"); // Show cursor
-                    console.log("");
-                    resolve(this.options.filter(o => o.selected).map(o => o.value));
-                }
-                else if (key.ctrl && key.name === "c") {
-                    process.stdin.setRawMode(false);
-                    process.exit();
-                }
-            };
-            process.stdin.on("keypress", handleKey);
-        });
-    }
-}

package/mcp-config-template.json

@@ -1,18 +0,0 @@
-{
-    "mcpServers": {
-        "vesper": {
-            "command": "npx",
-            "args": [
-                "-y",
-                "-p",
-                "@vespermcp/mcp-server@latest",
-                "vespermcp"
-            ],
-            "env": {
-                "KAGGLE_USERNAME": "your-kaggle-username",
-                "KAGGLE_KEY": "your-kaggle-api-key",
-                "HF_TOKEN": "your-huggingface-token"
-            }
-        }
-    }
-}