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/includes/libxml/xinclude.h

@@ -14,9 +14,7 @@
 #define __XML_XINCLUDE_H__
 
 #include <libxml/xmlversion.h>
-#include <libxml/xmlerror.h>
 #include <libxml/tree.h>
-#include <libxml/parser.h>
 
 #ifdef LIBXML_XINCLUDE_ENABLED
 
@@ -117,16 +115,6 @@ XMLPUBFUN xmlXIncludeCtxtPtr
 XMLPUBFUN int
 		xmlXIncludeSetFlags	(xmlXIncludeCtxtPtr ctxt,
 					 int flags);
-XMLPUBFUN void
-		xmlXIncludeSetErrorHandler(xmlXIncludeCtxtPtr ctxt,
-					 xmlStructuredErrorFunc handler,
-					 void *data);
-XMLPUBFUN void
-		xmlXIncludeSetResourceLoader(xmlXIncludeCtxtPtr ctxt,
-					 xmlResourceLoader loader,
-					 void *data);
-XMLPUBFUN int
-		xmlXIncludeGetLastError	(xmlXIncludeCtxtPtr ctxt);
 XMLPUBFUN void
 		xmlXIncludeFreeContext	(xmlXIncludeCtxtPtr ctxt);
 XMLPUBFUN int