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.
This commit is contained in:
2026-10-26 16:48:29 -03:00
parent 9eed02645b
commit 723ca1506b
231 changed files with 20508 additions and 5330 deletions
@@ -13,6 +13,7 @@
#include <libxml/xmlversion.h>
#ifdef LIBXML_REGEXP_ENABLED
#ifdef LIBXML_AUTOMATA_ENABLED
#include <libxml/xmlstring.h>
@@ -39,31 +40,24 @@ typedef xmlAutomataState *xmlAutomataStatePtr;
/*
* Building API
*/
XML_DEPRECATED
XMLPUBFUN xmlAutomataPtr
xmlNewAutomata (void);
XML_DEPRECATED
XMLPUBFUN void
xmlFreeAutomata (xmlAutomataPtr am);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataGetInitState (xmlAutomataPtr am);
XML_DEPRECATED
XMLPUBFUN int
xmlAutomataSetFinalState (xmlAutomataPtr am,
xmlAutomataStatePtr state);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataNewState (xmlAutomataPtr am);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataNewTransition (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
const xmlChar *token,
void *data);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataNewTransition2 (xmlAutomataPtr am,
xmlAutomataStatePtr from,
@@ -71,7 +65,6 @@ XMLPUBFUN xmlAutomataStatePtr
const xmlChar *token,
const xmlChar *token2,
void *data);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataNewNegTrans (xmlAutomataPtr am,
xmlAutomataStatePtr from,
@@ -80,7 +73,6 @@ XMLPUBFUN xmlAutomataStatePtr
const xmlChar *token2,
void *data);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataNewCountTrans (xmlAutomataPtr am,
xmlAutomataStatePtr from,
@@ -89,7 +81,6 @@ XMLPUBFUN xmlAutomataStatePtr
int min,
int max,
void *data);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataNewCountTrans2 (xmlAutomataPtr am,
xmlAutomataStatePtr from,
@@ -99,7 +90,6 @@ XMLPUBFUN xmlAutomataStatePtr
int min,
int max,
void *data);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataNewOnceTrans (xmlAutomataPtr am,
xmlAutomataStatePtr from,
@@ -108,7 +98,6 @@ XMLPUBFUN xmlAutomataStatePtr
int min,
int max,
void *data);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataNewOnceTrans2 (xmlAutomataPtr am,
xmlAutomataStatePtr from,
@@ -118,39 +107,32 @@ XMLPUBFUN xmlAutomataStatePtr
int min,
int max,
void *data);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataNewAllTrans (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
int lax);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataNewEpsilon (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataNewCountedTrans (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
int counter);
XML_DEPRECATED
XMLPUBFUN xmlAutomataStatePtr
xmlAutomataNewCounterTrans (xmlAutomataPtr am,
xmlAutomataStatePtr from,
xmlAutomataStatePtr to,
int counter);
XML_DEPRECATED
XMLPUBFUN int
xmlAutomataNewCounter (xmlAutomataPtr am,
int min,
int max);
XML_DEPRECATED
XMLPUBFUN struct _xmlRegexp *
xmlAutomataCompile (xmlAutomataPtr am);
XML_DEPRECATED
XMLPUBFUN int
xmlAutomataIsDeterminist (xmlAutomataPtr am);
@@ -158,6 +140,7 @@ XMLPUBFUN int
}
#endif
#endif /* LIBXML_AUTOMATA_ENABLED */
#endif /* LIBXML_REGEXP_ENABLED */
#endif /* __XML_AUTOMATA_H__ */