Feat: Added basic HTMl parsing logic

[sauravpanda]

Comprehensive Browser Agent Updates and HTML Cleaner Utility

• Purpose:
  Enhance the Browser Agent project with new features and an HTML cleaner utility to extract structured data from web content.
• Key Changes:
  • Updated GitHub Actions to streamline the build, lint, and test processes for the Browser Agent project.
  • Introduced a new release workflow that automates versioning and tagging on main branch pushes.
  • Added a new React + TypeScript + Vite demo for the Browser Agent, including components for chat and browsing.
  • Improved README documentation with new model entries and setup instructions for the Browser Agent demo.
  • Updated package version and added Jest for testing with a new configuration.
  • Implemented an HTML cleaner utility with methods to remove specific tags and attributes, extract semantic content, identify interactive elements, preserve heading structure, and extract metadata and schema.org information.
• Impact:
  These changes improve the development workflow, enhance project usability, ensure better testing and deployment practices, and provide a powerful tool for processing and analyzing HTML content.

✨ Generated with love by Kaizen ❤️

Original Description

None

[kaizen-bot]

Consider implementing the following changes to improve the code.

[kaizen-bot]

Comment: Potential performance issue with multiple await calls in a loop.

Solution: Consider using Promise.all for concurrent execution of independent promises where applicable.
!! Make sure the following suggestion is correct before committing it !!

Suggested change

	await this.wait(delay);
	return this.executeWithRetry(fn, attempt + 1);
	await Promise.all([this.wait(delay), this.executeWithRetry(fn, attempt + 1)]);

[kaizen-bot]

🔍 Code Review Summary

❗ Attention Required: This push has potential issues. 🚨

Overview

• Total Feedbacks: 1 (Critical: 1, Refinements: 0)
• Files Affected: 1
• Code Quality: [█████████████████░░░] 85% (Good)

🚨 Critical Issues

security (1 issues)

1. Potential XSS vulnerability due to unescaped HTML content.

---

📁 File: src/core/agent/html-cleaner.ts
🔍 Reasoning:
The innerHTML property is being used to set HTML content directly, which can lead to cross-site scripting (XSS) vulnerabilities if the input is not sanitized properly. This is particularly concerning if the html parameter can be influenced by user input.

💡 Solution:
Use a library or built-in methods to sanitize the HTML before setting it to innerHTML.

Current Code:

tempElement.innerHTML = html;

Suggested Code:

        tempElement.innerHTML = sanitizeHTML(html); // Ensure sanitizeHTML is a function that properly escapes or removes unsafe content.

---

✨ Generated with love by Kaizen ❤️

Useful Commands

• Feedback: Share feedback on kaizens performance with !feedback [your message]
• Ask PR: Reply with !ask-pr [your question]
• Review: Reply with !review
• Update Tests: Reply with !unittest to create a PR with test changes

[kaizen-bot]

Consider implementing the following changes to improve the code.