fix: stop tagging all macro_news articles as macro_event — default to article, let extractor reclassify. Also reduced fetch limit to 20 and cadence to 30min

2026-04-16 18:09:50 +00:00
parent f83577480f
commit 513310abba
1 changed files with 7 additions and 2 deletions
@@ -209,12 +209,17 @@ async def persist_broker_event(


 def _resolve_document_type(source_type: str) -> str:
-    """Map source_type to a document_type value."""
+    """Map source_type to a document_type value.
+
+    Note: macro_news articles default to 'article' — the extractor
+    reclassifies them as 'macro_event' only if the content is truly
+    about macro/global events (not company-specific news).
+    """
    mapping = {
        "news_api": "article",
        "filings_api": "filing",
        "web_scrape": "press_release",
-        "macro_news": "macro_event",
+        "macro_news": "article",
    }
    return mapping.get(source_type, "article")