feat(scrape): harden preflight and cron config for Documents archives

Preflight probes skip forbidden channels when seeded archives exist.
Cron installer passes container config path and supports --config override.
Compose and docs align with append-only ~/Documents scrape workflow.

scripts/run-discord-scrape.sh

@@ -645,26 +645,16 @@ resolve_target_channels() {
   fi
 }
 
-preflight_target() {
-  local target_json=$1
-  local defaults_json=$2
-  local target_name output_dir
-  local probe_channel_id probe_dir probe_output
-  local -a channel_ids
+preflight_probe_channel() {
+  local probe_channel_id=$1
+  local output_dir=$2
+  local probe_dir probe_output probe_log
+  local -a probe_command after_id probe_destination
+  local probe_status=0
 
-  target_name=$(jq -r '.name' <<<"$target_json")
-  output_dir=$(jq -r '.output_dir' <<<"$target_json")
-  bootstrap_channel_map_from_archives "$output_dir"
-
-  mapfile -t channel_ids < <(resolve_target_channels "$target_json" "$defaults_json")
-  if (( ${#channel_ids[@]} == 0 )); then
-    die "Target '$target_name' resolved no channels during preflight."
-  fi
-
-  probe_channel_id="${channel_ids[0]}"
   probe_dir=$(mktemp -d "${TMPDIR:-/tmp}/dce-preflight.${probe_channel_id}.XXXXXX")
   probe_output="$probe_dir/probe.json"
-  local -a probe_command after_id probe_destination
+  probe_log=$(mktemp "${TMPDIR:-/tmp}/dce-preflight-log.${probe_channel_id}.XXXXXX")
 
   probe_destination=$(resolve_destination_path "$output_dir" "$probe_channel_id")
   after_id=""
@@ -683,13 +673,75 @@ preflight_target() {
     probe_command+=(--after "$after_id")
   fi
 
-  if ! "${probe_command[@]}"; then
+  set +e
+  "${probe_command[@]}" >"$probe_log" 2>&1
+  probe_status=$?
+  set -e
+
+  if (( probe_status == 0 )); then
+    rm -f "$probe_log"
     rm -rf "$probe_dir"
-    die "Target '$target_name' failed authenticated preflight on channel '$probe_channel_id'."
+    return 0
   fi
 
+  if is_skippable_channel_export_failure "$probe_log"; then
+    log "Preflight probe skipped channel $probe_channel_id (forbidden or inaccessible)."
+    cat "$probe_log" >&2
+    rm -f "$probe_log"
+    rm -rf "$probe_dir"
+    return 2
+  fi
+
+  cat "$probe_log" >&2
+  rm -f "$probe_log"
   rm -rf "$probe_dir"
-  log "Preflight ok for target '$target_name': ${#channel_ids[@]} channel(s) resolved for $output_dir."
+  return 1
+}
+
+preflight_target() {
+  local target_json=$1
+  local defaults_json=$2
+  local target_name output_dir
+  local probe_channel_id
+  local -a channel_ids seeded_channel_ids
+  local probe_status=0
+  local skipped_channels=0
+  local probed_channels=0
+
+  target_name=$(jq -r '.name' <<<"$target_json")
+  output_dir=$(jq -r '.output_dir' <<<"$target_json")
+  bootstrap_channel_map_from_archives "$output_dir"
+
+  mapfile -t channel_ids < <(resolve_target_channels "$target_json" "$defaults_json")
+  if (( ${#channel_ids[@]} == 0 )); then
+    die "Target '$target_name' resolved no channels during preflight."
+  fi
+
+  for probe_channel_id in "${channel_ids[@]}"; do
+    probed_channels=$((probed_channels + 1))
+    preflight_probe_channel "$probe_channel_id" "$output_dir" || probe_status=$?
+    case "$probe_status" in
+      0)
+        log "Preflight ok for target '$target_name': ${#channel_ids[@]} channel(s) resolved for $output_dir."
+        return 0
+        ;;
+      2)
+        skipped_channels=$((skipped_channels + 1))
+        probe_status=0
+        ;;
+      *)
+        die "Target '$target_name' failed authenticated preflight on channel '$probe_channel_id'."
+        ;;
+    esac
+  done
+
+  mapfile -t seeded_channel_ids < <(load_archive_seed_channel_ids "$output_dir" | sort -u)
+  if (( skipped_channels == probed_channels && ${#seeded_channel_ids[@]} > 0 )); then
+    log "Preflight ok for target '$target_name' with warning: all ${#channel_ids[@]} resolved channel(s) are inaccessible, but ${#seeded_channel_ids[@]} seeded archive(s) exist under $output_dir."
+    return 0
+  fi
+
+  die "Target '$target_name' failed preflight: every resolved channel is inaccessible and no seeded archives exist under $output_dir."
 }
 
 scrape_target() {

scripts/setup-cron.sh

@@ -45,6 +45,7 @@ Options:
   --cron EXPR         Use an explicit five-field cron expression instead of --interval/--at.
   --job-name NAME     Marker name for the installed cron block. Default: discord-scrape
   --log-file PATH     Cron log file. Default: $LOG_FILE
+  --config PATH       Scrape targets JSON. Default: $CONFIG_FILE
   --env-file PATH     Compose env file. Default: $ENV_FILE
   --skip-preflight    Install the cron job without running the authenticated container preflight.
   --dry-run           Print the cron block instead of installing it.
@@ -130,6 +131,22 @@ append_target_args() {
   done
 }
 
+container_config_path() {
+  local config_path=$1
+
+  if [[ "$config_path" == "$REPO_ROOT/config/"* ]]; then
+    printf '/config/%s\n' "$(basename "$config_path")"
+    return 0
+  fi
+
+  if [[ "$config_path" == config/* ]]; then
+    printf '/config/%s\n' "${config_path#config/}"
+    return 0
+  fi
+
+  printf '%s\n' "$config_path"
+}
+
 ensure_target_directories() {
   local selected_targets_json archive_root output_dir
 
@@ -182,6 +199,7 @@ run_preflight() {
     --env-file "$ENV_FILE"
     --compose-file "$COMPOSE_FILE"
     preflight
+    --config "$(container_config_path "$CONFIG_FILE")"
   )
   append_target_args preflight_args
   "${preflight_args[@]}"
@@ -230,6 +248,11 @@ main() {
         LOG_FILE=$2
         shift 2
         ;;
+      --config)
+        [[ $# -ge 2 ]] || die "Missing value for --config."
+        CONFIG_FILE=$2
+        shift 2
+        ;;
       --env-file)
         [[ $# -ge 2 ]] || die "Missing value for --env-file."
         ENV_FILE=$2
@@ -315,6 +338,7 @@ main() {
     --env-file "$ENV_FILE"
     --compose-file "$COMPOSE_FILE"
     scrape
+    --config "$(container_config_path "$CONFIG_FILE")"
   )
   append_target_args scrape_args
   scrape_command=$(printf '%q ' "${scrape_args[@]}")