feat(agent): scrape linked pages to ground answers in real content

Adds `_fetch_page_content()`, which downloads a URL with a
browser-like User-Agent and uses BeautifulSoup with the lxml
parser to strip scripts, navigation, and other non-content
markup, returning up to 3000 characters of readable text.

The response validator now also compares generated replies
against this scraped text, flagging named entities and claims
that do not appear in the retrieved page content.

Dependencies: adds beautifulsoup4==4.12.3 and pins lxml==5.3.0
for parser compatibility.

venv/lib/python3.11/site-packages/lxml/builder.py

@@ -45,13 +45,6 @@ _QName = ET.QName
 
 from functools import partial
 
-try:
-    from types import GenericAlias as _GenericAlias
-except ImportError:
-    # Python 3.8 - we only need this as return value from "__class_getitem__"
-    def _GenericAlias(cls, item):
-        return f"{cls.__name__}[{item.__name__}]"
-
 try:
     basestring
 except NameError:
@@ -234,10 +227,6 @@ class ElementMaker:
     def __getattr__(self, tag):
         return partial(self, tag)
 
-    # Allow subscripting ElementMaker in type annotations (PEP 560)
-    def __class_getitem__(cls, item):
-        return _GenericAlias(cls, item)
-
 
 # create factory object
 E = ElementMaker()