feat: add freshrss openclaw pipeline and clean repo

scripts/pull_freshrss_items.py

@@ -16,7 +16,7 @@ FRESHRSS_OUTPUT_ROOT = OUTPUT_ROOT / "freshrss"
 if str(SRC_ROOT) not in sys.path:
     sys.path.insert(0, str(SRC_ROOT))
 
-from summary_mcp.integrations.freshrss import FreshRSSClient, map_entry_to_item
+from summary_mcp.integrations.freshrss import READ_TAG, FreshRSSClient, map_entry_to_item
 
 
 def _save_json(path: Path, payload: dict[str, Any] | list[Any]) -> None:
@@ -45,6 +45,16 @@ def main() -> None:
     )
     parser.add_argument("--limit", type=int, default=10, help="Maximum number of entries to request")
     parser.add_argument("--continuation", type=str, default=None, help="Continuation token for paging")
+    parser.add_argument(
+        "--include-read",
+        action="store_true",
+        help="Do not exclude items already tagged as read.",
+    )
+    parser.add_argument(
+        "--mark-read",
+        action="store_true",
+        help="Mark fetched entries as read after this script finishes successfully.",
+    )
     parser.add_argument(
         "--raw-output",
         type=Path,
@@ -76,6 +86,7 @@ def main() -> None:
         stream_id=args.stream_id,
         limit=args.limit,
         continuation=args.continuation,
+        exclude_targets=[] if args.include_read else [READ_TAG],
     )
 
     entries = payload.get("items")
@@ -87,8 +98,17 @@ def main() -> None:
     _save_json(args.raw_output, payload)
     _save_json(args.items_output, mapped_items)
 
+    marked_count = 0
+    if args.mark_read:
+        item_ids = [entry.get("external_id") for entry in mapped_items if isinstance(entry.get("external_id"), str)]
+        if item_ids:
+            client.mark_items_as_read(auth_token=auth_token, item_ids=item_ids)
+            marked_count = len(item_ids)
+
     print(f"Saved {len(mapped_items)} mapped items to {args.items_output}")
+    if args.mark_read:
+        print(f"Marked {marked_count} FreshRSS entries as read")
 
 
 if __name__ == "__main__":
-    main()
+    main()