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/relaxng.h

@@ -14,9 +14,8 @@
 #include <libxml/xmlerror.h>
 #include <libxml/xmlstring.h>
 #include <libxml/tree.h>
-#include <libxml/parser.h>
 
-#ifdef LIBXML_RELAXNG_ENABLED
+#ifdef LIBXML_SCHEMAS_ENABLED
 
 #ifdef __cplusplus
 extern "C" {
@@ -156,10 +155,6 @@ XMLPUBFUN void
 					 xmlRelaxNGParserCtxtPtr ctxt,
 					 xmlStructuredErrorFunc serror,
 					 void *ctx);
-XMLPUBFUN void
-		    xmlRelaxNGSetResourceLoader	(xmlRelaxNGParserCtxtPtr ctxt,
-						 xmlResourceLoader loader,
-						 void *vctxt);
 XMLPUBFUN xmlRelaxNGPtr
 		    xmlRelaxNGParse		(xmlRelaxNGParserCtxtPtr ctxt);
 XMLPUBFUN void
@@ -219,6 +214,6 @@ XMLPUBFUN int
 }
 #endif
 
-#endif /* LIBXML_RELAXNG_ENABLED */
+#endif /* LIBXML_SCHEMAS_ENABLED */
 
 #endif /* __XML_RELAX_NG__ */