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/xpathInternals.h

@@ -22,12 +22,6 @@
 extern "C" {
 #endif
 
-/*
- * Backward compatibility
- */
-#define valuePush xmlXPathValuePush
-#define valuePop xmlXPathValuePop
-
 /************************************************************************
  *									*
  *			Helpers						*
@@ -484,10 +478,11 @@ XMLPUBFUN xmlXPathParserContextPtr
 XMLPUBFUN void
 		xmlXPathFreeParserContext	(xmlXPathParserContextPtr ctxt);
 
+/* TODO: remap to xmlXPathValuePop and Push. */
 XMLPUBFUN xmlXPathObjectPtr
-		xmlXPathValuePop		(xmlXPathParserContextPtr ctxt);
+		valuePop			(xmlXPathParserContextPtr ctxt);
 XMLPUBFUN int
-		xmlXPathValuePush		(xmlXPathParserContextPtr ctxt,
+		valuePush			(xmlXPathParserContextPtr ctxt,
 						 xmlXPathObjectPtr value);
 
 XMLPUBFUN xmlXPathObjectPtr
@@ -521,7 +516,6 @@ XMLPUBFUN void
 
 XMLPUBFUN void
 		xmlXPathRoot			(xmlXPathParserContextPtr ctxt);
-XML_DEPRECATED
 XMLPUBFUN void
 		xmlXPathEvalExpr		(xmlXPathParserContextPtr ctxt);
 XMLPUBFUN xmlChar *