feat: add freshrss openclaw pipeline and clean repo

scripts/run_freshrss_extract.py

@@ -17,7 +17,7 @@ if str(SRC_ROOT) not in sys.path:
     sys.path.insert(0, str(SRC_ROOT))
 
 from summary_mcp.core.pipeline import extract_content
-from summary_mcp.integrations.freshrss import FreshRSSClient, map_entry_to_item
+from summary_mcp.integrations.freshrss import READ_TAG, FreshRSSClient, map_entry_to_item
 from summary_mcp.models.summary_io import ExtractionInput
 
 
@@ -47,6 +47,16 @@ def main() -> None:
     )
     parser.add_argument("--limit", type=int, default=5, 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 entries as read after successful extraction for each item.",
+    )
     parser.add_argument(
         "--raw-output",
         type=Path,
@@ -84,6 +94,7 @@ 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")
@@ -93,6 +104,7 @@ def main() -> None:
     mapped_items = [map_entry_to_item(entry) for entry in entries]
     extraction_results: list[dict[str, Any]] = []
     success_count = 0
+    mark_read_ids: list[str] = []
 
     for item in mapped_items:
         extraction = extract_content(ExtractionInput(item=item))
@@ -104,6 +116,8 @@ def main() -> None:
         )
         if extraction.success:
             success_count += 1
+            if item.external_id:
+                mark_read_ids.append(item.external_id)
 
     _save_json(args.raw_output, payload)
     _save_json(args.items_output, [item.model_dump(mode="json") for item in mapped_items])
@@ -118,10 +132,17 @@ def main() -> None:
         },
     )
 
+    marked_count = 0
+    if args.mark_read and mark_read_ids:
+        client.mark_items_as_read(auth_token=auth_token, item_ids=mark_read_ids)
+        marked_count = len(mark_read_ids)
+
     print(
         f"Saved {len(mapped_items)} mapped items and {success_count} successful extractions to {args.extracted_output}"
     )
+    if args.mark_read:
+        print(f"Marked {marked_count} FreshRSS entries as read")
 
 
 if __name__ == "__main__":
-    main()
+    main()