retention fix

git-pages/README.md

@@ -171,3 +171,20 @@ Testit käyttävät `<root>/files/retention-lib.sh` -jaettua kirjastoa, jota my
 4. Tarkista `TO_DELETE`-array ja `$output`
 
 **Vaatimukset:** `bats`, `jq`, `date` (GNU date tai BSD date ISO 8601 -tuella).
+
+---
+
+## Retention
+
+Ylläpitoscripti, joka poistaa vanhat raportit git-pagesista retention‑sääntöjen mukaan.
+Ajetaan sidecar‑ tai cronjob‑tilassa Kubernetesissa.
+
+### Air gap -yhteensopimattomuus
+
+Retention‑kontti asentaa tarvitsemansa työkalut (`curl`, `jq`) ajon aikana
+packagemanagerilla (`apt-get` / `apk`). Tämä **ei toimi air gap -ympäristössä**,
+jossa konttirekisteriin tai pakettivarastoihin ei ole verkkoyhteyttä.
+
+**TODO:** Rakenna custom Docker‑image, jossa deps on valmiina:
+`FROM alpine:latest && apk add --no-cache curl jq`.
+Pushaa omaan rekisteriin ja päivitä `values.yaml`:n `retention.image`.

git-pages/files/retention-cleanup.sh

@@ -13,45 +13,8 @@ curl_with_host() {
 
 [ -f "$CONFIG" ] || { echo "ERROR: config missing: $CONFIG" >&2; exit 1; }
 
-declare -A BRANCH_CACHE
+declare -A REPO_BRANCHES_CACHE
-branch_exists() {
+declare -A REPO_STATUS
-  local owner="$1" repo="$2" branch="$3" key="${owner}/${repo}/${branch}"
-  local status attempt
-  
-  [ -z "$GITEA_API_URL" ] && return 0
-  [ -z "$GITEA_TOKEN" ] && return 0
-  
-  if [ "${BRANCH_CACHE[$key]:-}" = "1" ]; then
-    return 0
-  fi
-  
-  # Retry up to 2 times on API errors (hardcoded)
-  for attempt in 1 2 3; do
-    status=$(curl -sS -o /dev/null -w "%{http_code}" \
-      -H "Authorization: token ${GITEA_TOKEN}" \
-      "${GITEA_API_URL}/api/v1/repos/${owner}/${repo}/branches/${branch}" 2>/dev/null || echo "000")
-    
-    if [ "$status" = "200" ]; then
-      BRANCH_CACHE[$key]=1
-      return 0
-    fi
-    
-    if [ "$status" = "404" ]; then
-      return 1
-    fi
-    
-    # API error - retry if not last attempt
-    if [ "$attempt" -lt 3 ]; then
-      sleep 10
-      continue
-    fi
-  done
-  
-  # All retries failed - keep report (fail-safe)
-  echo "  WARN: Gitea API error for ${owner}/${repo}/${branch} (status ${status}) after 3 attempts - KEEPING report"
-  BRANCH_CACHE[$key]=1
-  return 0
-}
 
 SCRIPT_DIR="$(cd "$(dirname "${BASH_SOURCE[0]}")" && pwd)"
 source "$SCRIPT_DIR/retention-lib.sh"
@@ -70,6 +33,7 @@ fi
 echo ""
 echo "=== Phase 1: collect reports ==="
 declare -A SEEN_REPORTS
+declare -A SEEN_ECHO_COMMITS
 declare -a REPORTS
 while IFS= read -r meta_path; do
   report_dir=$(dirname "$meta_path")
@@ -90,34 +54,105 @@ while IFS= read -r meta_path; do
 
   days=$(age_days "$published")
   REPORTS+=("${report_dir}|${OWNER}|${REPO}|${branch}|${days}")
-  echo "  ${OWNER}/${REPO} branch=${branch} age=${days}d"
+
+  commit_dir=$(dirname "$report_dir")
+  if [ -z "${SEEN_ECHO_COMMITS[$commit_dir]:-}" ]; then
+    SEEN_ECHO_COMMITS[$commit_dir]=1
+    echo "  ${commit_dir} branch=${branch} age=${days}d"
+  fi
 done <<< "$META_PATHS"
 
 [ "${#REPORTS[@]}" -eq 0 ] && { echo "No actionable reports"; exit 0; }
 
 echo ""
-echo "=== Phase 2: check branches in Gitea ==="
+echo "=== Phase 2: check branches/repos in Gitea ==="
+if [ -z "$GITEA_API_URL" ] || [ -z "$GITEA_TOKEN" ]; then
+  echo "ERROR: GITEA_API_URL and GITEA_TOKEN must be set" >&2
+  exit 1
+fi
 declare -a TO_DELETE
 declare -a KEEP
+declare -A SEEN_ECHO_BRANCHES
+declare -A SEEN_ECHO_REPO_DELETED
+declare -A UNIQUE_BRANCHES
+declare -A REASON_MAP
+declare -A COMMIT_BRANCH_MAP
+
+# Build commit→branch mapping
+for entry in "${REPORTS[@]}"; do
+  IFS='|' read -r dir _ _ branch _ <<< "$entry"
+  commit_dir=$(dirname "$dir")
+  [ -n "${COMMIT_BRANCH_MAP[$commit_dir]:-}" ] || COMMIT_BRANCH_MAP["$commit_dir"]=$branch
+done
+for entry in "${REPORTS[@]}"; do
+  IFS='|' read -r _ owner repo branch _ <<< "$entry"
+  UNIQUE_BRANCHES["${owner}/${repo}/${branch}"]=1
+done
+TOTAL_BRANCHES=${#UNIQUE_BRANCHES[@]}
+BRANCHES_EXISTING=0
+BRANCH_DELETED_COUNT=0
+REPO_DELETED_COUNT=0
+MAXAGE_DELETED=0
+KEEPMIN_DELETED=0
 for entry in "${REPORTS[@]}"; do
   IFS='|' read -r dir owner repo branch days <<< "$entry"
 
-  if [ -n "$GITEA_API_URL" ] && [ -n "$GITEA_TOKEN" ]; then
+  branch_key="${owner}/${repo}/${branch}"
-    if branch_exists "$owner" "$repo" "$branch"; then
+  if branch_exists "$owner" "$repo" "$branch"; then
-      echo "  BRANCH EXISTS: ${owner}/${repo}/${branch}"
+    if [ -z "${SEEN_ECHO_BRANCHES[$branch_key]:-}" ]; then
-      KEEP+=("${dir}|${owner}|${repo}|${branch}|${days}")
+      SEEN_ECHO_BRANCHES[$branch_key]=1
-    else
+      BRANCHES_EXISTING=$((BRANCHES_EXISTING + 1))
-      echo "  BRANCH DELETED: ${owner}/${repo}/${branch} -> DELETE"
+      echo "  BRANCH EXISTS: ${branch_key}"
-      TO_DELETE+=("$dir")
     fi
-  else
     KEEP+=("${dir}|${owner}|${repo}|${branch}|${days}")
+  else
+    if [ -z "${SEEN_ECHO_BRANCHES[$branch_key]:-}" ]; then
+      SEEN_ECHO_BRANCHES[$branch_key]=1
+      repo_key="${owner}/${repo}"
+      if [ "${REPO_STATUS[$repo_key]:-}" = "deleted" ]; then
+        REPO_DELETED_COUNT=$((REPO_DELETED_COUNT + 1))
+        if [ -z "${SEEN_ECHO_REPO_DELETED[$repo_key]:-}" ]; then
+          SEEN_ECHO_REPO_DELETED[$repo_key]=1
+          echo "  REPO DELETED: ${repo_key} -> DELETE ALL"
+        fi
+        reason="repo deleted"
+      else
+        BRANCH_DELETED_COUNT=$((BRANCH_DELETED_COUNT + 1))
+        echo "  BRANCH DELETED: ${branch_key} -> DELETE"
+        reason="branch deleted"
+      fi
+    fi
+    REASON_MAP["$dir"]="$reason"
+    TO_DELETE+=("$dir")
   fi
 done
 
 echo ""
 echo "=== Phase 3: apply retention rules to remaining reports ==="
+PHASE2_DELETED=${#TO_DELETE[@]}
 apply_retention "$CONFIG"
+PHASE3_DELETED=$(( ${#TO_DELETE[@]} - PHASE2_DELETED ))
+
+fmt_num() {
+  local n="$1" out=""
+  [ -z "$n" ] && { echo "?"; return; }
+  n="${n##0}"  # strip leading zeros
+  while [ "${#n}" -gt 3 ]; do
+    out=" ${n: -3}$out"
+    n="${n:0:${#n}-3}"
+  done
+  echo "${n}${out}"
+}
+
+echo ""
+echo "=== Summary ==="
+echo "  Branches:"
+echo "    existing:          $(fmt_num $BRANCHES_EXISTING)"
+echo "    deleted:           $(fmt_num $BRANCH_DELETED_COUNT)"
+echo "    repo gone:         $(fmt_num $REPO_DELETED_COUNT)"
+echo "  Commits:"
+echo "    deleted by maxAge: $(fmt_num $MAXAGE_DELETED)"
+echo "    deleted by keepMin:$(fmt_num $KEEPMIN_DELETED)"
 
 if [ "${#TO_DELETE[@]}" -eq 0 ]; then
   echo "Nothing to delete"
@@ -142,14 +177,37 @@ echo "Downloading archive.tar..."
 HTTP_CODE=$(curl_with_host -o "$ARCHIVE_FILE" -w "%{http_code}" -sS "${PAGES_URL}/.git-pages/archive.tar")
 
 if [ "$HTTP_CODE" = "200" ] && tar -tf "$ARCHIVE_FILE" >/dev/null 2>&1; then
-  echo "Extracting archive..."
+  OLD_KB=$(du -sk "$ARCHIVE_FILE" 2>/dev/null | awk '{print $1}')
+  echo "Extracting archive (${OLD_KB}kB)..."
   tar -xf "$ARCHIVE_FILE" -C "$SITE_DIR"
 
-  for dir in "${TO_DELETE[@]}"; do
+  declare -A GROUP_SEEN
-    if [ -d "$SITE_DIR/$dir" ]; then
+  declare -A GROUP_LINES
-      echo "  Removing: $dir"
+  for del in "${TO_DELETE[@]}"; do
-      rm -rf "$SITE_DIR/$dir"
+    if [ ! -d "$SITE_DIR/$del" ]; then
+      continue
     fi
+
+    commit_dir=$(dirname "$del")
+    branch="${COMMIT_BRANCH_MAP[$commit_dir]:-?}"
+    reason="${REASON_MAP[$del]:-?}"
+    repo_path="${del%%/reports/*}"
+    commit_hash="${commit_dir##*/}"
+    key="${repo_path}/${branch} | Reason: ${reason}"
+    seen_key="${key}|${commit_hash}"
+
+    if [ -z "${GROUP_SEEN[$seen_key]:-}" ]; then
+      GROUP_SEEN[$seen_key]=1
+      GROUP_LINES["$key"]="${GROUP_LINES[$key]:-} $commit_hash"
+    fi
+
+    rm -rf "$SITE_DIR/$del"
+  done
+  for key in "${!GROUP_LINES[@]}"; do
+    echo "  Removing: ${key}"
+    for hash in ${GROUP_LINES[$key]}; do
+      echo "    commit: ${hash}"
+    done
   done
 else
   echo "archive.tar failed (HTTP ${HTTP_CODE}) - falling back to manifest-based rebuild"
@@ -197,6 +255,7 @@ if [ -z "$(ls -A "$SITE_DIR" 2>/dev/null)" ]; then
 fi
 
 tar -cf "$NEW_TAR" -C "$SITE_DIR" .
+NEW_KB=$(du -sk "$NEW_TAR" 2>/dev/null | awk '{print $1}')
 
 echo "PUT: replacing site contents..."
 HTTP_CODE=$(curl_with_host -X PUT "${PAGES_URL}/" \
@@ -208,6 +267,9 @@ HTTP_CODE=$(curl_with_host -X PUT "${PAGES_URL}/" \
 echo "HTTP ${HTTP_CODE}"
 if [ "$HTTP_CODE" = "200" ] || [ "$HTTP_CODE" = "201" ] || [ "$HTTP_CODE" = "204" ]; then
   echo "Site rebuild completed."
+  if [ -n "${OLD_KB:-}" ]; then
+    echo "  archive size: $(fmt_num $OLD_KB)kB → $(fmt_num $NEW_KB)kB"
+  fi
 else
   echo "ERROR: PUT HTTP ${HTTP_CODE}" >&2
   exit 1

git-pages/files/retention-lib.sh

@@ -23,6 +23,102 @@ read_rule() {
   [ -n "$v" ] && echo "$v" || echo "$default"
 }
 
+# ---------------------------------------------------------------------------
+# Gitea branch/repo checking via git ls-remote
+# Uses global: GITEA_API_URL, GITEA_TOKEN
+# Sets global: REPO_BRANCHES_CACHE, REPO_STATUS
+# ---------------------------------------------------------------------------
+
+# Fetch all branches for a repo (one git ls-remote call per repo).
+# Sets REPO_STATUS[owner/repo].
+# Echos branch list on success.
+# Returns: 0=ok, 1=deleted, 2=cert_error, 3=error (fail-safe keep)
+repo_branches() {
+  local owner="$1" repo="$2" key="${owner}/${repo}"
+  local attempt output
+
+  [ -z "$GITEA_API_URL" ] && return 0
+  [ -z "$GITEA_TOKEN" ] && return 0
+
+  # Check cached status first (avoids re-running git on every report)
+  case "${REPO_STATUS[$key]:-}" in
+    deleted)    return 1 ;;
+    cert_error) return 2 ;;
+    error)      echo "${REPO_BRANCHES_CACHE[$key]:-}"; return 3 ;;
+  esac
+
+  # Cache hit (success with branch list)
+  [ -n "${REPO_BRANCHES_CACHE[$key]:-}" ] && { echo "${REPO_BRANCHES_CACHE[$key]}"; return 0; }
+
+  local git_host
+  git_host=$(echo "$GITEA_API_URL" | sed -E 's|^https?://||' | sed 's|/.*$||')
+  local git_url="https://token:${GITEA_TOKEN}@${git_host}/${owner}/${repo}.git"
+
+  for attempt in 1 2 3; do
+    output=$(git ls-remote --heads "$git_url" 2>&1) && {
+      local branches
+      branches=$(echo "$output" | sed -n 's|.*refs/heads/||p')
+      REPO_BRANCHES_CACHE[$key]="$branches"
+      REPO_STATUS[$key]="ok"
+      echo "$branches"
+      return 0
+    }
+
+    # Repo deleted → no retry
+    if echo "$output" | grep -qiE "fatal:.*(not found|repository.*not|could not read)"; then
+      REPO_BRANCHES_CACHE[$key]="__REPO_DELETED__"
+      REPO_STATUS[$key]="deleted"
+      echo "  REPO DELETED: ${owner}/${repo}" >&2
+      return 1
+    fi
+
+    [ "$attempt" -lt 3 ] && sleep 10
+  done
+
+  # Certificate verification failure → configuration error, stop
+  if echo "$output" | grep -qi "server certificate verification failed"; then
+    REPO_STATUS[$key]="cert_error"
+    echo "[ERROR] git-pages.retention: certificate verification failed for ${owner}/${repo}" >&2
+    echo "[ERROR] git-pages.retention:   check CA certificates or set GIT_SSL_NO_VERIFY=1" >&2
+    echo "[ERROR] git-pages.retention:   git output:" >&2
+    echo "$output" >&2
+    return 2
+  fi
+
+  # Other network errors → fail-safe keep, continue
+  REPO_BRANCHES_CACHE[$key]="__REPO_ERROR__"
+  REPO_STATUS[$key]="error"
+  echo "[WARN] git-pages.retention: cannot reach Gitea for ${owner}/${repo} — keeping all reports" >&2
+  echo "[WARN] git-pages.retention:   git output:" >&2
+  echo "$output" >&2
+  return 3
+}
+
+# Check if a specific branch exists in a repo.
+# Returns 0 (exists), 1 (not found/deleted).
+# Returns 2 (cert error), 3 (network error).
+branch_exists() {
+  local owner="$1" repo="$2" branch="$3"
+  local branches rc
+
+  [ -z "$GITEA_API_URL" ] && return 0
+  [ -z "$GITEA_TOKEN" ] && return 0
+
+  branches=$(repo_branches "$owner" "$repo")
+  rc=$?
+
+  # Return codes from repo_branches propagate through $() subshell:
+  # 0=ok, 1=deleted, 2=cert_error, 3=error
+  case $rc in
+    2) echo "[FATAL] git-pages.retention: cannot reach Gitea (${owner}/${repo}) — check configuration" >&2
+       exit 1 ;;
+    3) return 0 ;;  # network error → fail-safe keep
+    1) return 1 ;;  # repo/branch gone
+  esac
+
+  echo "$branches" | grep -qxF "$branch"
+}
+
 # Phase 3: apply retention rules to KEEP array, populate TO_DELETE
 # Reads from global KEEP array
 # Populates global TO_DELETE array
@@ -30,13 +126,12 @@ read_rule() {
 apply_retention() {
   local config="$1"
   local default_max_age default_keep_min
-  local max_age keep_min key count seen_key commit_dir report_type path
+  local max_age keep_min key count seen_key commit_dir
   local entry dir owner repo branch days
 
   default_max_age=$(jq -r '.branches.default.maxAgeDays // 90' "$config")
   default_keep_min=$(jq -r '.branches.default.keepMin // 5' "$config")
 
-  TO_DELETE=()
   declare -A BRANCH_COUNTS
   declare -A SEEN_COMMITS
   declare -A DELETED_COMMITS
@@ -56,6 +151,8 @@ apply_retention() {
     if [ "$days" -gt "$max_age" ]; then
       echo "  DELETE: ${dir} (age ${days}d > maxAge ${max_age}d, branch ${branch})"
       TO_DELETE+=("$dir")
+      REASON_MAP["$dir"]="maxAgeDays exceed"
+      MAXAGE_DELETED=$((MAXAGE_DELETED + 1))
       continue
     fi
 
@@ -76,9 +173,10 @@ apply_retention() {
     if [ "$count" -gt "$keep_min" ]; then
       if [ -z "${DELETED_COMMITS[$commit_dir]:-}" ]; then
         DELETED_COMMITS[$commit_dir]=1
-        report_type="${dir##*/}"
         echo "  DELETE: ${commit_dir} (kept ${keep_min}/${count} commits, exceeds keepMin, branch ${branch})"
         TO_DELETE+=("$commit_dir")
+        REASON_MAP["$commit_dir"]="keepMin exceed"
+        KEEPMIN_DELETED=$((KEEPMIN_DELETED + 1))
       fi
     fi
   done

git-pages/templates/deployment.yaml

@@ -70,8 +70,15 @@ spec:
               set -euo pipefail
               echo "Retention sidecar: installing deps..."
               apt-get update -qq
-              apt-get install -y --no-install-recommends curl jq python3 >/dev/null
+              apt-get install -y --no-install-recommends curl jq git ca-certificates >/dev/null
               echo "Retention sidecar: ready"
+              # Sleep until 01:00 so retention runs at night
+              now_epoch=$(date +%s)
+              target_epoch=$(date -d "today 01:00:00" +%s)
+              [ "$target_epoch" -le "$now_epoch" ] && target_epoch=$((target_epoch + 86400))
+              sleep_sec=$((target_epoch - now_epoch))
+              echo "Retention sidecar: next run in $((sleep_sec / 3600))h (at 01:00)"
+              sleep $sleep_sec
               while true; do
                 /scripts/retention-cleanup.sh
                 echo "Retention sidecar: next run in 24h"

git-pages/templates/retention-cronjob.yaml

@@ -33,7 +33,7 @@ spec:
                 - |
                   set -euo pipefail
                   apt-get update -qq
-                  apt-get install -y --no-install-recommends curl jq >/dev/null
+                  apt-get install -y --no-install-recommends curl jq git >/dev/null
                   chmod +x /scripts/retention-run.sh /scripts/retention-cleanup.sh
                   /scripts/retention-run.sh
               env:

git-pages/tests/retention.bats

@@ -1,9 +1,12 @@
 #!/usr/bin/env bats
 
 setup() {
-  # Copy the retention lib to a temp location so it's easier to source
-  # (bats runs each test in its own dir)
   source "$(dirname "$BATS_TEST_DIRNAME")/files/retention-lib.sh"
+  declare -gA REPO_BRANCHES_CACHE
+  declare -gA REPO_STATUS
+  declare -gA REASON_MAP
+  MAXAGE_DELETED=0
+  KEEPMIN_DELETED=0
   CONFIG=$(mktemp)
 }
 
@@ -326,3 +329,295 @@ EOF
   apply_retention "$CONFIG"
   [ "${#TO_DELETE[@]}" -eq 0 ]
 }
+
+@test "TO_DELETE preserves Phase 2 entries after apply_retention (no new deletions)" {
+  write_config <<'EOF'
+{"branches":{"default":{"maxAgeDays":365,"keepMin":10}}}
+EOF
+
+  KEEP=(
+    "niko/r/reports/c1/test|niko|r|main|10"
+    "niko/r/reports/c2/test|niko|r|main|5"
+  )
+  TO_DELETE=(
+    "niko/r/reports/abc/branch-gone"
+    "niko/r/reports/def/repo-gone"
+  )
+
+  apply_retention "$CONFIG"
+
+  [ "${#TO_DELETE[@]}" -eq 2 ]
+  [[ "${TO_DELETE[0]}" == "niko/r/reports/abc/branch-gone" ]]
+  [[ "${TO_DELETE[1]}" == "niko/r/reports/def/repo-gone" ]]
+}
+
+@test "TO_DELETE preserves Phase 2 entries AND adds retention deletions" {
+  write_config <<'EOF'
+{"branches":{"default":{"maxAgeDays":365,"keepMin":3}}}
+EOF
+
+  KEEP=(
+    "niko/r/reports/c1/test|niko|r|main|40"
+    "niko/r/reports/c2/test|niko|r|main|30"
+    "niko/r/reports/c3/test|niko|r|main|20"
+    "niko/r/reports/c4/test|niko|r|main|10"
+  )
+  TO_DELETE=(
+    "niko/r/reports/abc/branch-gone"
+  )
+
+  apply_retention "$CONFIG"
+
+  # 1 pre-existing + 1 commit deleted (c1, oldest of 4, keepMin=3)
+  [ "${#TO_DELETE[@]}" -eq 2 ]
+  [[ "${TO_DELETE[0]}" == "niko/r/reports/abc/branch-gone" ]]
+}
+
+# ---------------------------------------------------------------------------
+# branch_exists — mocking REPO_STATUS / REPO_BRANCHES_CACHE
+# ---------------------------------------------------------------------------
+
+@test "branch_exists: branch in list → return 0" {
+  GITEA_API_URL="https://gitea.example.com"
+  GITEA_TOKEN="test-token"
+
+  REPO_BRANCHES_CACHE["owner/repo"]=$'main\nfeature/x'
+  REPO_STATUS["owner/repo"]="ok"
+
+  run branch_exists "owner" "repo" "main"
+  [ "$status" -eq 0 ]
+}
+
+@test "branch_exists: branch not in list → return 1" {
+  GITEA_API_URL="https://gitea.example.com"
+  GITEA_TOKEN="test-token"
+
+  REPO_BRANCHES_CACHE["owner/repo"]=$'main\nfeature/x'
+  REPO_STATUS["owner/repo"]="ok"
+
+  run branch_exists "owner" "repo" "nonexistent"
+  [ "$status" -eq 1 ]
+}
+
+@test "branch_exists: cert error → exit 1 with [FATAL]" {
+  GITEA_API_URL="https://gitea.example.com"
+  GITEA_TOKEN="test"
+
+  REPO_STATUS["owner/repo"]="cert_error"
+
+  run branch_exists "owner" "repo" "any-branch"
+  [ "$status" -eq 1 ]
+  [[ "$output" == *"[FATAL]"* ]]
+}
+
+@test "branch_exists: repo deleted → return 1" {
+  GITEA_API_URL="https://gitea.example.com"
+  GITEA_TOKEN="test-token"
+
+  REPO_BRANCHES_CACHE["owner/repo"]="__REPO_DELETED__"
+  REPO_STATUS["owner/repo"]="deleted"
+
+  run branch_exists "owner" "repo" "any-branch"
+  [ "$status" -eq 1 ]
+}
+
+@test "branch_exists: network error → return 0 (fail-safe keep)" {
+  GITEA_API_URL="https://gitea.example.com"
+  GITEA_TOKEN="test-token"
+
+  REPO_BRANCHES_CACHE["owner/repo"]="__REPO_ERROR__"
+  REPO_STATUS["owner/repo"]="error"
+
+  run branch_exists "owner" "repo" "any-branch"
+  [ "$status" -eq 0 ]
+}
+
+@test "branch_exists: empty GITEA_API_URL → return 0 (skip)" {
+  GITEA_API_URL=""
+  GITEA_TOKEN="test-token"
+
+  run branch_exists "owner" "repo" "any-branch"
+  [ "$status" -eq 0 ]
+}
+
+@test "branch_exists: empty GITEA_TOKEN → return 0 (skip)" {
+  GITEA_API_URL="https://gitea.example.com"
+  GITEA_TOKEN=""
+
+  run branch_exists "owner" "repo" "any-branch"
+  [ "$status" -eq 0 ]
+}
+
+# ---------------------------------------------------------------------------
+# repo_branches — git ls-remote error detection patterns
+# ---------------------------------------------------------------------------
+
+@test "error detection: 'command not found' does NOT trigger repo deleted" {
+  # This must NOT match — "bash: git: command not found" is NOT a repo deletion
+  local msg="bash: git: command not found"
+  run grep -qiE "fatal:.*(not found|repository.*not|could not read)" <<< "$msg"
+  [ "$status" -eq 1 ]
+}
+
+@test "error detection: 'fatal: repo not found' triggers repo deleted" {
+  # This MUST match — genuine git error for deleted/missing repo
+  local msg="fatal: repository 'https://gitea.app/owner/repo.git' not found"
+  run grep -qiE "fatal:.*(not found|repository.*not|could not read)" <<< "$msg"
+  [ "$status" -eq 0 ]
+}
+
+@test "error detection: 'could not read from remote' triggers repo deleted" {
+  local msg="fatal: could not read from remote repository"
+  run grep -qiE "fatal:.*(not found|repository.*not|could not read)" <<< "$msg"
+  [ "$status" -eq 0 ]
+}
+
+# ---------------------------------------------------------------------------
+# git ls-remote integration (real git, temp repo)
+# ---------------------------------------------------------------------------
+
+@test "git ls-remote parsing: lists branches correctly" {
+  local tmpdir=$(mktemp -d)
+
+  git -C "$tmpdir" init -b main source >/dev/null 2>&1
+  git -C "$tmpdir/source" config user.email "test@test"
+  git -C "$tmpdir/source" config user.name "test"
+  git -C "$tmpdir/source" commit --allow-empty -m "init" >/dev/null 2>&1
+  git -C "$tmpdir/source" branch feature/x >/dev/null 2>&1
+  git clone --bare "$tmpdir/source" "$tmpdir/repo.git" >/dev/null 2>&1
+
+  local url="file://$tmpdir/repo.git"
+  local output
+  output=$(git ls-remote --heads "$url" 2>&1)
+  local branches
+  branches=$(echo "$output" | sed -n 's|.*refs/heads/||p')
+
+  echo "$branches" | grep -qxF "main"
+  [ "$?" -eq 0 ]
+
+  echo "$branches" | grep -qxF "feature/x"
+  [ "$?" -eq 0 ]
+
+  ! echo "$branches" | grep -qxF "nonexistent"
+
+  rm -rf "$tmpdir"
+}
+
+# ---------------------------------------------------------------------------
+# repo_branches — retry + error output (using git mock)
+# ---------------------------------------------------------------------------
+
+@test "repo_branches: success returns branches immediately" {
+  local mockdir=$(mktemp -d)
+  cat > "$mockdir/git" << 'SCRIPT'
+#!/usr/bin/env bash
+echo "abc123	refs/heads/main"
+echo "def456	refs/heads/feature/x"
+SCRIPT
+  chmod +x "$mockdir/git"
+  local save_PATH="$PATH"
+  export PATH="$mockdir:$PATH"
+  GITEA_API_URL="https://gitea.example.com"
+  GITEA_TOKEN="test"
+  REPO_BRANCHES_CACHE=()
+  REPO_STATUS=()
+
+  run repo_branches "owner" "repo"
+
+  [ "$status" -eq 0 ]
+  [[ "$output" == *"main"* ]]
+  [[ "$output" == *"feature/x"* ]]
+
+  export PATH="$save_PATH"
+  rm -rf "$mockdir"
+}
+
+@test "repo_branches: retries 3 times on transient error" {
+  local mockdir=$(mktemp -d)
+  cat > "$mockdir/git" << 'SCRIPT'
+#!/usr/bin/env bash
+echo "call" >> "$MOCKDIR/count"
+echo "fatal: unable to access 'https://...'" >&2
+exit 1
+SCRIPT
+  chmod +x "$mockdir/git"
+  # Inject mockdir path into mock script via env var
+  sed -i '' "s|\$MOCKDIR|$mockdir|g" "$mockdir/git"
+  local save_PATH="$PATH"
+  export PATH="$mockdir:$PATH"
+  GITEA_API_URL="https://gitea.example.com"
+  GITEA_TOKEN="test"
+  REPO_BRANCHES_CACHE=()
+  REPO_STATUS=()
+
+  local start=$SECONDS
+  run repo_branches "owner" "repo"
+
+  [ "$status" -eq 3 ]
+  [[ "$output" == *"[WARN] git-pages.retention"* ]]
+  [[ "$output" == *"keeping all reports"* ]]
+  [[ "$output" == *"git output:"* ]]
+  [[ "$output" == *"unable to access"* ]]
+  [ $(cat "$mockdir/count" | wc -l) -eq 3 ]
+  [ $(( SECONDS - start )) -ge 18 ]
+
+  export PATH="$save_PATH"
+  rm -rf "$mockdir"
+}
+
+@test "repo_branches: certificate error → [ERROR] + return 1" {
+  local mockdir=$(mktemp -d)
+  cat > "$mockdir/git" << 'SCRIPT'
+#!/usr/bin/env bash
+echo "call" >> "$MOCKDIR/count"
+echo "fatal: unable to access 'https://gitea.app/owner/repo.git/': server certificate verification failed. CAfile: none CRLfile: none" >&2
+exit 1
+SCRIPT
+  chmod +x "$mockdir/git"
+  sed -i '' "s|\$MOCKDIR|$mockdir|g" "$mockdir/git"
+  local save_PATH="$PATH"
+  export PATH="$mockdir:$PATH"
+  GITEA_API_URL="https://gitea.example.com"
+  GITEA_TOKEN="test"
+  REPO_BRANCHES_CACHE=()
+  REPO_STATUS=()
+
+  run repo_branches "owner" "repo"
+
+  [ "$status" -eq 2 ]
+  [[ "$output" == *"[ERROR]"* ]]
+  [[ "$output" == *"certificate verification"* ]]
+  [[ "$output" == *"git output:"* ]]
+  [[ "$output" == *"unable to access"* ]]
+
+  export PATH="$save_PATH"
+  rm -rf "$mockdir"
+}
+
+@test "repo_branches: repo not found returns immediately (no retry)" {
+  local mockdir=$(mktemp -d)
+  cat > "$mockdir/git" << 'SCRIPT'
+#!/usr/bin/env bash
+echo "call" >> "$MOCKDIR/count"
+echo "fatal: repository 'https://gitea.app/owner/repo.git' not found" >&2
+exit 1
+SCRIPT
+  chmod +x "$mockdir/git"
+  sed -i '' "s|\$MOCKDIR|$mockdir|g" "$mockdir/git"
+  local save_PATH="$PATH"
+  export PATH="$mockdir:$PATH"
+  GITEA_API_URL="https://gitea.example.com"
+  GITEA_TOKEN="test"
+  REPO_BRANCHES_CACHE=()
+  REPO_STATUS=()
+
+  run repo_branches "owner" "repo"
+
+  [ "$status" -eq 1 ]
+  [[ "$output" == *"REPO DELETED"* ]]
+  [[ "$output" != *"[WARN]"* ]]
+  [ $(cat "$mockdir/count" | wc -l) -eq 1 ]
+
+  export PATH="$save_PATH"
+  rm -rf "$mockdir"
+}