import asyncio

from langchain.tools import ToolRuntime, tool

from deerflow.community.jina_ai.jina_client import JinaClient
from deerflow.config.deer_flow_context import resolve_context
from deerflow.utils.readability import ReadabilityExtractor

readability_extractor = ReadabilityExtractor()


@tool("web_fetch", parse_docstring=True)
async def web_fetch_tool(url: str, runtime: ToolRuntime) -> str:
    """Fetch the contents of a web page at a given URL.
    Only fetch EXACT URLs that have been provided directly by the user or have been returned in results from the web_search and web_fetch tools.
    This tool can NOT access content that requires authentication, such as private Google Docs or pages behind login walls.
    Do NOT add www. to URLs that do NOT have them.
    URLs must include the schema: https://example.com is a valid URL while example.com is an invalid URL.

    Args:
        url: The URL to fetch the contents of.
    """
    jina_client = JinaClient()
    timeout = 10
    tool_config = resolve_context(runtime).app_config.get_tool_config("web_fetch")
    if tool_config is not None and "timeout" in tool_config.model_extra:
        timeout = tool_config.model_extra.get("timeout")
    html_content = await jina_client.crawl(url, return_format="html", timeout=timeout)
    if isinstance(html_content, str) and html_content.startswith("Error:"):
        return html_content
    article = await asyncio.to_thread(readability_extractor.extract_article, html_content)
    return article.to_markdown()[:4096]