import { parametersSchema as z, defineCustomTool } from "@roo-code/types"
import { spawnSync } from "child_process"

export default defineCustomTool({
  name: "web_fetch",
  description: "Fetch a web page and return its content as clean text. Uses curl + HTML stripping. Lightweight alternative to the WebScraper MCP for simple page fetches.",
  parameters: z.object({
    url: z.string().describe("URL to fetch"),
    maxChars: z.number().optional().describe("Truncate output at this many characters. Default: 15000"),
  }),
  async execute({ url, maxChars }) {
    const limit = maxChars || 15000
    const result = spawnSync("curl", ["-sL", "--max-time", "15", "-H", "User-Agent: Mozilla/5.0 (Macintosh; Intel Mac OS X 10_15_7)", url], {
      encoding: "utf-8",
      timeout: 20000,
      maxBuffer: 5 * 1024 * 1024,
    })

    if (result.status !== 0) {
      return `Error fetching ${url}: ${result.stderr || "curl failed"}`
    }

    let text = result.stdout
      .replace(/<script[\s\S]*?<\/script>/gi, "")
      .replace(/<style[\s\S]*?<\/style>/gi, "")
      .replace(/<[^>]+>/g, " ")
      .replace(/&amp;/g, "&")
      .replace(/&lt;/g, "<")
      .replace(/&gt;/g, ">")
      .replace(/&quot;/g, '"')
      .replace(/&#39;/g, "'")
      .replace(/&nbsp;/g, " ")
      .replace(/\s+/g, " ")
      .trim()

    if (text.length > limit) {
      text = text.substring(0, limit) + `\n... [truncated at ${limit} chars]`
    }

    return text
  },
})