lib/extract.py

@@ -923,36 +923,6 @@ async def extract_cycle(conn, max_workers=None) -> tuple[int, int]:
         except Exception:
             logger.debug("Failed to read source %s", f, exc_info=True)
 
-    # Archive-basename filter: skip queue files whose basename already exists in
-    # inbox/archive/. Research-session commits on agent branches occasionally
-    # re-introduce already-archived queue files when the branch is re-merged,
-    # producing same-source re-extractions every cooldown cycle. The archive
-    # copy is the source of truth — if a file with this basename is in archive,
-    # the source is processed regardless of queue state. Single archive scan
-    # per cycle, cheap (~1k files).
-    #
-    # Assumes basename uniqueness across queue+archive — current naming
-    # convention (date-prefix + topic-slug) makes collisions vanishingly
-    # rare. If short generic names like "notes.md" enter the queue, this
-    # filter silently false-positives.
-    if unprocessed:
-        archive_dir = main / "inbox" / "archive"
-        archived_basenames: set[str] = set()
-        if archive_dir.exists():
-            for af in archive_dir.rglob("*.md"):
-                if af.name.startswith("_"):
-                    continue
-                archived_basenames.add(af.name)
-        if archived_basenames:
-            before = len(unprocessed)
-            unprocessed = [
-                (sp, c, f) for sp, c, f in unprocessed
-                if Path(sp).name not in archived_basenames
-            ]
-            skipped = before - len(unprocessed)
-            if skipped:
-                logger.info("Skipped %d queue source(s) — basename already in inbox/archive/", skipped)
-
     # Don't early-return here — re-extraction sources may exist even when queue is empty
     # (the re-extraction check runs after open-PR filtering below)