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/uri.h

@@ -52,25 +52,14 @@ struct _xmlURI {
  */
 XMLPUBFUN xmlURIPtr
 		xmlCreateURI		(void);
-XMLPUBFUN int
-		xmlBuildURISafe		(const xmlChar *URI,
-					 const xmlChar *base,
-					 xmlChar **out);
 XMLPUBFUN xmlChar *
 		xmlBuildURI		(const xmlChar *URI,
 					 const xmlChar *base);
-XMLPUBFUN int
-		xmlBuildRelativeURISafe	(const xmlChar *URI,
-					 const xmlChar *base,
-					 xmlChar **out);
 XMLPUBFUN xmlChar *
 		xmlBuildRelativeURI	(const xmlChar *URI,
 					 const xmlChar *base);
 XMLPUBFUN xmlURIPtr
 		xmlParseURI		(const char *str);
-XMLPUBFUN int
-		xmlParseURISafe		(const char *str,
-					 xmlURIPtr *uri);
 XMLPUBFUN xmlURIPtr
 		xmlParseURIRaw		(const char *str,
 					 int raw);