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/xmlreader.h

@@ -14,12 +14,11 @@
 #include <libxml/tree.h>
 #include <libxml/xmlerror.h>
 #include <libxml/xmlIO.h>
-#ifdef LIBXML_RELAXNG_ENABLED
-#include <libxml/relaxng.h>
-#endif
 #ifdef LIBXML_SCHEMAS_ENABLED
+#include <libxml/relaxng.h>
 #include <libxml/xmlschemas.h>
 #endif
+/* for compatibility */
 #include <libxml/parser.h>
 
 #ifdef __cplusplus
@@ -128,8 +127,6 @@ XMLPUBFUN int
 XMLPUBFUN void
             xmlTextReaderSetMaxAmplification(xmlTextReaderPtr reader,
                    unsigned maxAmpl);
-XMLPUBFUN const xmlError *
-            xmlTextReaderGetLastError(xmlTextReaderPtr reader);
 
 /*
  * Iterators
@@ -289,7 +286,7 @@ XMLPUBFUN int
 		    xmlTextReaderNextSibling	(xmlTextReaderPtr reader);
 XMLPUBFUN int
 		    xmlTextReaderIsValid	(xmlTextReaderPtr reader);
-#ifdef LIBXML_RELAXNG_ENABLED
+#ifdef LIBXML_SCHEMAS_ENABLED
 XMLPUBFUN int
 		    xmlTextReaderRelaxNGValidate(xmlTextReaderPtr reader,
 						 const char *rng);
@@ -301,8 +298,6 @@ XMLPUBFUN int
 XMLPUBFUN int
 		    xmlTextReaderRelaxNGSetSchema(xmlTextReaderPtr reader,
 						 xmlRelaxNGPtr schema);
-#endif
-#ifdef LIBXML_SCHEMAS_ENABLED
 XMLPUBFUN int
 		    xmlTextReaderSchemaValidate	(xmlTextReaderPtr reader,
 						 const char *xsd);
@@ -429,11 +424,6 @@ XMLPUBFUN void
 					 xmlTextReaderErrorFunc *f,
 					 void **arg);
 
-XMLPUBFUN void
-	    xmlTextReaderSetResourceLoader(xmlTextReaderPtr reader,
-					   xmlResourceLoader loader,
-					   void *data);
-
 #endif /* LIBXML_READER_ENABLED */
 
 #ifdef __cplusplus