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/xpath.h

@@ -26,10 +26,15 @@
 #include <libxml/xmlerror.h>
 #include <libxml/tree.h>
 #include <libxml/hash.h>
+#endif /* LIBXML_XPATH_ENABLED */
 
+#if defined(LIBXML_XPATH_ENABLED) || defined(LIBXML_SCHEMAS_ENABLED)
 #ifdef __cplusplus
 extern "C" {
 #endif
+#endif /* LIBXML_XPATH_ENABLED or LIBXML_SCHEMAS_ENABLED */
+
+#ifdef LIBXML_XPATH_ENABLED
 
 typedef struct _xmlXPathContext xmlXPathContext;
 typedef xmlXPathContext *xmlXPathContextPtr;
@@ -99,15 +104,22 @@ typedef enum {
     XPATH_BOOLEAN = 2,
     XPATH_NUMBER = 3,
     XPATH_STRING = 4,
+#ifdef LIBXML_XPTR_LOCS_ENABLED
+    XPATH_POINT = 5,
+    XPATH_RANGE = 6,
+    XPATH_LOCATIONSET = 7,
+#endif
     XPATH_USERS = 8,
     XPATH_XSLT_TREE = 9  /* An XSLT value tree, non modifiable */
 } xmlXPathObjectType;
 
+#ifndef LIBXML_XPTR_LOCS_ENABLED
 /** DOC_DISABLE */
 #define XPATH_POINT 5
 #define XPATH_RANGE 6
 #define XPATH_LOCATIONSET 7
 /** DOC_ENABLE */
+#endif
 
 typedef struct _xmlXPathObject xmlXPathObject;
 typedef xmlXPathObject *xmlXPathObjectPtr;
@@ -401,11 +413,8 @@ struct _xmlXPathParserContext {
  * Objects and Nodesets handling
  */
 
-XML_DEPRECATED
 XMLPUBVAR double xmlXPathNAN;
-XML_DEPRECATED
 XMLPUBVAR double xmlXPathPINF;
-XML_DEPRECATED
 XMLPUBVAR double xmlXPathNINF;
 
 /* These macros may later turn into functions */
@@ -506,10 +515,6 @@ XMLPUBFUN xmlXPathContextPtr
 		    xmlXPathNewContext		(xmlDocPtr doc);
 XMLPUBFUN void
 		    xmlXPathFreeContext		(xmlXPathContextPtr ctxt);
-XMLPUBFUN void
-		    xmlXPathSetErrorHandler(xmlXPathContextPtr ctxt,
-					    xmlStructuredErrorFunc handler,
-					    void *context);
 XMLPUBFUN int
 		    xmlXPathContextSetCache(xmlXPathContextPtr ctxt,
 				            int active,
@@ -552,7 +557,8 @@ XMLPUBFUN int
 						 xmlXPathContextPtr ctxt);
 XMLPUBFUN void
 		    xmlXPathFreeCompExpr	(xmlXPathCompExprPtr comp);
-
+#endif /* LIBXML_XPATH_ENABLED */
+#if defined(LIBXML_XPATH_ENABLED) || defined(LIBXML_SCHEMAS_ENABLED)
 XML_DEPRECATED
 XMLPUBFUN void
 		    xmlXPathInit		(void);
@@ -565,5 +571,5 @@ XMLPUBFUN int
 }
 #endif
 
-#endif /* LIBXML_XPATH_ENABLED */
+#endif /* LIBXML_XPATH_ENABLED or LIBXML_SCHEMAS_ENABLED*/
 #endif /* ! __XML_XPATH_H__ */