fix(retention): fix branch cache and deduplication bugs

- Convert BRANCH_CACHE from string to associative array
- Add SEEN_REPORTS deduplication to prevent processing duplicate reports
- Initialize BRANCH_COUNTS associative array before use
- Fixes main branch reports being incorrectly deleted

git-pages/files/retention-cleanup.sh

@@ -13,7 +13,7 @@ curl_with_host() {
 
 [ -f "$CONFIG" ] || { echo "ERROR: config missing: $CONFIG" >&2; exit 1; }
 
-BRANCH_CACHE=""
+declare -A BRANCH_CACHE
 branch_exists() {
   local owner="$1" repo="$2" branch="$3" key="${owner}/${repo}/${branch}"
   local status
@@ -21,7 +21,7 @@ branch_exists() {
   [ -z "$GITEA_API_URL" ] && return 0
   [ -z "$GITEA_TOKEN" ] && return 0
 
-  if grep -q "^${key}$" <<< "$BRANCH_CACHE" 2>/dev/null; then
+  if [ "${BRANCH_CACHE[$key]:-}" = "1" ]; then
     return 0
   fi
 
@@ -30,7 +30,7 @@ branch_exists() {
     "${GITEA_API_URL}/api/v1/repos/${owner}/${repo}/branches/${branch}" 2>/dev/null || echo "000")
 
   if [ "$status" = "200" ]; then
-    BRANCH_CACHE="${BRANCH_CACHE}${key}"$'\n'
+    BRANCH_CACHE[$key]=1
     return 0
   fi
   return 1
@@ -79,9 +79,15 @@ fi
 
 echo ""
 echo "=== Phase 1: collect reports ==="
+declare -A SEEN_REPORTS
 declare -a REPORTS
 while IFS= read -r meta_path; do
   report_dir=$(dirname "$meta_path")
+  
+  # Skip duplicates - same report dir already processed
+  [ -z "${SEEN_REPORTS[$report_dir]:-}" ] || continue
+  SEEN_REPORTS[$report_dir]=1
+  
   parse_path "$report_dir"
   meta_content=$(curl_with_host "${PAGES_URL}/${meta_path}" 2>/dev/null || true)
   [ -n "$meta_content" ] || { echo "  WARN: could not fetch $meta_path"; continue; }
@@ -121,6 +127,7 @@ done
 
 echo ""
 echo "=== Phase 3: apply retention rules to remaining reports ==="
+declare -A BRANCH_COUNTS
 if [ "${#KEEP[@]}" -gt 0 ]; then
   IFS=$'\n'
   for entry in $(printf '%s\n' "${KEEP[@]}" | sort -t'|' -k4,4 -k5,5rn); do