batch-extract-50.sh

@@ -42,6 +42,36 @@ git fetch origin main 2>/dev/null
 git checkout -f main 2>/dev/null
 git reset --hard origin/main 2>/dev/null
 
+# Pre-extraction cleanup: remove queue files that already exist in archive
+# This runs on the MAIN worktree (not extract/) so deletions are committed to git.
+# Prevents the "queue duplicate reappears after reset --hard" problem.
+CLEANED=0
+for qfile in $MAIN_REPO/inbox/queue/*.md; do
+    [ -f "$qfile" ] || continue
+    qbase=$(basename "$qfile")
+    if find "$MAIN_REPO/inbox/archive" -name "$qbase" 2>/dev/null | grep -q .; then
+        rm -f "$qfile"
+        CLEANED=$((CLEANED + 1))
+    fi
+done
+if [ "$CLEANED" -gt 0 ]; then
+    echo "[$(date)] Cleaned $CLEANED stale queue duplicates" >> $LOG
+    cd $MAIN_REPO
+    git add -A inbox/queue/ 2>/dev/null
+    git commit -m "pipeline: clean $CLEANED stale queue duplicates
+
+Pentagon-Agent: Epimetheus <3D35839A-7722-4740-B93D-51157F7D5E70>" 2>/dev/null
+    # Push with retry
+    for attempt in 1 2 3; do
+        git pull --rebase origin main 2>/dev/null
+        git push origin main 2>/dev/null && break
+        sleep 2
+    done
+    cd $REPO
+    git fetch origin main 2>/dev/null
+    git reset --hard origin/main 2>/dev/null
+fi
+
 # Get sources in queue
 SOURCES=$(ls inbox/queue/*.md 2>/dev/null | head -$MAX)