smartagent/ts/smartagent.tools.browser.ts

import * as plugins from './plugins.js';
import * as interfaces from './smartagent.interfaces.js';
import { BaseToolWrapper } from './smartagent.tools.base.js';

/**
 * Browser tool for web page interaction
 * Wraps @push.rocks/smartbrowser (Puppeteer-based)
 */
export class BrowserTool extends BaseToolWrapper {
  public name = 'browser';
  public description =
    'Interact with web pages - take screenshots, generate PDFs, and execute JavaScript on pages';

  public actions: interfaces.IToolAction[] = [
    {
      name: 'screenshot',
      description: 'Take a screenshot of a webpage',
      parameters: {
        type: 'object',
        properties: {
          url: { type: 'string', description: 'URL of the page to screenshot' },
        },
        required: ['url'],
      },
    },
    {
      name: 'pdf',
      description: 'Generate a PDF from a webpage',
      parameters: {
        type: 'object',
        properties: {
          url: { type: 'string', description: 'URL of the page to convert to PDF' },
        },
        required: ['url'],
      },
    },
    {
      name: 'evaluate',
      description:
        'Execute JavaScript code on a webpage and return the result. The script runs in the browser context.',
      parameters: {
        type: 'object',
        properties: {
          url: { type: 'string', description: 'URL of the page to run the script on' },
          script: {
            type: 'string',
            description:
              'JavaScript code to execute. Must be a valid expression or statements that return a value.',
          },
        },
        required: ['url', 'script'],
      },
    },
    {
      name: 'getPageContent',
      description: 'Get the text content and title of a webpage',
      parameters: {
        type: 'object',
        properties: {
          url: { type: 'string', description: 'URL of the page to get content from' },
        },
        required: ['url'],
      },
    },
  ];

  private smartbrowser!: plugins.smartbrowser.SmartBrowser;

  public async initialize(): Promise<void> {
    this.smartbrowser = new plugins.smartbrowser.SmartBrowser();
    await this.smartbrowser.start();
    this.isInitialized = true;
  }

  public async cleanup(): Promise<void> {
    if (this.smartbrowser) {
      await this.smartbrowser.stop();
    }
    this.isInitialized = false;
  }

  public async execute(
    action: string,
    params: Record<string, unknown>
  ): Promise<interfaces.IToolExecutionResult> {
    this.validateAction(action);
    this.ensureInitialized();

    try {
      switch (action) {
        case 'screenshot': {
          const result = await this.smartbrowser.screenshotFromPage(params.url as string);
          return {
            success: true,
            result: {
              url: params.url,
              name: result.name,
              id: result.id,
              bufferBase64: Buffer.from(result.buffer).toString('base64'),
              bufferLength: result.buffer.length,
              type: 'screenshot',
            },
          };
        }

        case 'pdf': {
          const result = await this.smartbrowser.pdfFromPage(params.url as string);
          return {
            success: true,
            result: {
              url: params.url,
              name: result.name,
              id: result.id,
              bufferBase64: Buffer.from(result.buffer).toString('base64'),
              bufferLength: result.buffer.length,
              type: 'pdf',
            },
          };
        }

        case 'evaluate': {
          const script = params.script as string;
          // Create an async function from the script
          // The script should be valid JavaScript that returns a value
          const result = await this.smartbrowser.evaluateOnPage(params.url as string, async () => {
            // This runs in the browser context
            // We need to evaluate the script string dynamically
            // eslint-disable-next-line no-eval
            return eval(script);
          });

          return {
            success: true,
            result: {
              url: params.url,
              script: script.substring(0, 200) + (script.length > 200 ? '...' : ''),
              evaluationResult: result,
            },
          };
        }

        case 'getPageContent': {
          const result = await this.smartbrowser.evaluateOnPage(params.url as string, async () => {
            return {
              title: document.title,
              textContent: document.body?.innerText || '',
              url: window.location.href,
            };
          });

          return {
            success: true,
            result: {
              url: params.url,
              title: result.title,
              textContent:
                result.textContent.length > 10000
                  ? result.textContent.substring(0, 10000) + '... [truncated]'
                  : result.textContent,
              actualUrl: result.url,
            },
          };
        }

        default:
          return {
            success: false,
            error: `Unknown action: ${action}`,
          };
      }
    } catch (error) {
      return {
        success: false,
        error: error instanceof Error ? error.message : String(error),
      };
    }
  }

  public getCallSummary(action: string, params: Record<string, unknown>): string {
    switch (action) {
      case 'screenshot':
        return `Take screenshot of "${params.url}"`;

      case 'pdf':
        return `Generate PDF from "${params.url}"`;

      case 'evaluate': {
        const script = params.script as string;
        const preview = script.length > 100 ? script.substring(0, 100) + '...' : script;
        return `Execute JavaScript on "${params.url}": "${preview}"`;
      }

      case 'getPageContent':
        return `Get text content and title from "${params.url}"`;

      default:
        return `Unknown action: ${action}`;
    }
  }
}