tools.py

import re
import json
import math
import textwrap
from typing import List, Dict, Any, Optional

import requests
from bs4 import BeautifulSoup
from readability import Document
from ddgs import DDGS


# ---------- Web tools ----------

def web_search(query: str, max_results: int = 5) -> List[Dict[str, str]]:
    """
    DuckDuckGo search.
    Returns: [{title, href, body}, ...]
    """
    results: List[Dict[str, str]] = []
    with DDGS() as ddgs:
        for r in ddgs.text(query, max_results=max_results):
            results.append({
                "title": r.get("title", ""),
                "href": r.get("href", ""),
                "body": r.get("body", ""),
            })
    return results


def fetch_url(url: str, timeout: int = 20) -> str:
    """
    Fetch raw HTML/text from a URL.
    """
    headers = {
        "User-Agent": (
            "Mozilla/5.0 (X11; Linux x86_64) AppleWebKit/537.36 "
            "(KHTML, like Gecko) Chrome/120.0 Safari/537.36"
        )
    }
    resp = requests.get(url, headers=headers, timeout=timeout)
    resp.raise_for_status()
    return resp.text


def extract_main_text(html: str, max_chars: int = 12000) -> str:
    """
    Extract main readable text from HTML, trimming to max_chars.
    """
    try:
        doc = Document(html)
        content_html = doc.summary()
        soup = BeautifulSoup(content_html, "lxml")
        text = soup.get_text(" ", strip=True)
    except Exception:
        soup = BeautifulSoup(html, "lxml")
        text = soup.get_text(" ", strip=True)

    text = re.sub(r"\s+", " ", text).strip()
    if len(text) > max_chars:
        text = text[:max_chars] + "…"
    return text


# ---------- Safe-ish python tool ----------
# This is not a perfect sandbox, but it blocks imports and dangerous builtins.
# For public Spaces, keep it restrictive.

_ALLOWED_BUILTINS = {
    "abs": abs,
    "min": min,
    "max": max,
    "sum": sum,
    "len": len,
    "range": range,
    "round": round,
    "sorted": sorted,
    "enumerate": enumerate,
    "zip": zip,
    "map": map,
    "filter": filter,
    "list": list,
    "dict": dict,
    "set": set,
    "tuple": tuple,
    "str": str,
    "int": int,
    "float": float,
    "bool": bool,
    "json": json,
    "math": math,
}

def python_tool(code: str) -> str:
    """
    Executes small python snippets.
    - No imports
    - Restricted builtins
    - Must set a variable named `result` to return something
    """
    if "import " in code or "__" in code:
        return "Blocked: imports and dunder usage are not allowed."

    local_vars: Dict[str, Any] = {}
    global_vars: Dict[str, Any] = {"__builtins__": _ALLOWED_BUILTINS}

    try:
        exec(code, global_vars, local_vars)
    except Exception as e:
        return f"Python error: {type(e).__name__}: {e}"

    if "result" not in local_vars:
        return "No `result` variable found. Set `result = ...` to return output."

    out = local_vars["result"]
    if isinstance(out, (dict, list, tuple)):
        return json.dumps(out, ensure_ascii=False, indent=2)
    return str(out)