fix(scrape): disk preflight before compose and skippable disk errors

Fail fast when archive or repo paths lack free space (DCE_MIN_FREE_MB),
treat disk-full export failures as skippable channels, and add an offline
disk-space smoke. Smokes default DCE_MIN_FREE_MB=0 so CI stays portable.

scripts/run-all-smokes.sh

@@ -43,6 +43,8 @@ main() {
 
   chmod +x "$REPO_ROOT"/scripts/*.sh "$tests_dir"/*.sh 2>/dev/null || true
 
+  export DCE_MIN_FREE_MB="${DCE_MIN_FREE_MB:-0}"
+
   local script_path failures=0 ran=0
   for script_path in "$tests_dir"/*.sh; do
     [[ -f "$script_path" ]] || continue

scripts/run-discord-scrape.sh

@@ -395,7 +395,7 @@ message_count() {
 is_skippable_channel_export_failure() {
   local log_file=$1
   grep -qiE \
-    "failed: forbidden|failed: not found|Missing Access|403 Forbidden|404 Not Found|Cannot read message history" \
+    "failed: forbidden|failed: not found|Missing Access|403 Forbidden|404 Not Found|Cannot read message history|No space left on device|SQLITE_FULL|ENOSPC|disk full|not enough space" \
     "$log_file"
 }
 
@@ -423,7 +423,7 @@ export_channel_incremental() {
   fi
 
   if is_skippable_channel_export_failure "$export_log"; then
-    log "Skipping channel $channel_id (forbidden or inaccessible)."
+    log "Skipping channel $channel_id (inaccessible or non-fatal export error)."
     cat "$export_log" >&2
     rm -f "$export_log"
     return 2

scripts/tests/archive-disk-space-smoke.sh

@@ -0,0 +1,54 @@
+#!/usr/bin/env bash
+
+set -Eeuo pipefail
+
+REPO_ROOT=$(cd "$(dirname "${BASH_SOURCE[0]}")/../.." && pwd -P)
+VERIFY="$REPO_ROOT/scripts/verify-operator-ready.sh"
+TMP_DIR=$(mktemp -d "${TMPDIR:-/tmp}/dce-disk-smoke.XXXXXX")
+CONFIG_PATH="$TMP_DIR/config.json"
+ENV_PATH="$TMP_DIR/scrape.env"
+
+cleanup() {
+  rm -rf "$TMP_DIR"
+}
+trap cleanup EXIT
+
+mkdir -p "$TMP_DIR/archive/demo"
+printf '{"messages":[{"id":"1"}],"channel":{"id":"111111111111111111"}}\n' \
+  >"$TMP_DIR/archive/demo/Guild - general [111111111111111111].json"
+
+cat >"$CONFIG_PATH" <<JSON
+{
+  "archive_root": "$TMP_DIR/archive",
+  "targets": [
+    {
+      "name": "demo",
+      "kind": "guild",
+      "output_dir": "$TMP_DIR/archive/demo",
+      "enabled": true
+    }
+  ]
+}
+JSON
+
+printf 'DISCORD_TOKEN=dummy\n' >"$ENV_PATH"
+
+set +e
+output=$(
+  DCE_MIN_FREE_MB=999999999 \
+    DCE_REPO_ROOT="$REPO_ROOT" \
+    DCE_CONFIG_FILE="$CONFIG_PATH" \
+    DCE_ENV_FILE="$ENV_PATH" \
+    "$VERIFY" --config "$CONFIG_PATH" 2>&1
+)
+verify_status=$?
+set -e
+
+if (( verify_status != 0 )) && printf '%s\n' "$output" | grep -qi 'Insufficient disk space'; then
+  printf 'archive-disk-space-smoke: ok\n'
+  exit 0
+fi
+
+printf 'ERROR: expected disk space check to fail with high DCE_MIN_FREE_MB (status=%s)\n' "$verify_status" >&2
+printf '%s\n' "$output" >&2
+exit 1

scripts/tests/run-operator-validation-smoke.sh

@@ -58,7 +58,8 @@ EOF
 chmod +x "$FAKE_DOCKER"
 export PATH="$TMP_DIR:$PATH_BACKUP"
 
-DCE_REPO_ROOT="$REPO_ROOT" DCE_CONFIG_FILE="$CONFIG_PATH" DCE_ENV_FILE="$ENV_PATH" DCE_LOG_DIR="$LOG_DIR" \
+DCE_MIN_FREE_MB=0 DCE_REPO_ROOT="$REPO_ROOT" DCE_CONFIG_FILE="$CONFIG_PATH" DCE_ENV_FILE="$ENV_PATH" \
+  DCE_LOG_DIR="$LOG_DIR" \
   "$RUNNER" --dry-run --per-target --config "$CONFIG_PATH" --log-file "$LOG_DIR/validation.log"
 
 grep -q 'Per-target summary: 2 succeeded, 0 failed' "$LOG_DIR/validation.log" || {

scripts/tests/verify-operator-ready-smoke.sh

@@ -47,10 +47,10 @@ EOF
 chmod +x "$FAKE_DOCKER"
 export PATH="$TMP_DIR:$PATH_BACKUP"
 
-DCE_REPO_ROOT="$REPO_ROOT" DCE_CONFIG_FILE="$CONFIG_PATH" DCE_ENV_FILE="$ENV_PATH" \
+DCE_MIN_FREE_MB=0 DCE_REPO_ROOT="$REPO_ROOT" DCE_CONFIG_FILE="$CONFIG_PATH" DCE_ENV_FILE="$ENV_PATH" \
   "$VERIFY" --config "$CONFIG_PATH"
 
-if DCE_REPO_ROOT="$REPO_ROOT" DCE_CONFIG_FILE="$CONFIG_PATH" DCE_ENV_FILE="$ENV_PATH" \
+if DCE_MIN_FREE_MB=0 DCE_REPO_ROOT="$REPO_ROOT" DCE_CONFIG_FILE="$CONFIG_PATH" DCE_ENV_FILE="$ENV_PATH" \
   "$VERIFY" --config "$CONFIG_PATH" --preflight demo 2>/dev/null; then
   printf 'ERROR: preflight should fail without real container/token\n' >&2
   exit 1

scripts/verify-operator-ready.sh

@@ -51,6 +51,30 @@ resolve_compose() {
   die "Install Docker or Podman with compose support."
 }
 
+require_archive_disk_space() {
+  local min_mb=${DCE_MIN_FREE_MB:-1024}
+  local archive_root path avail_kb need_kb
+
+  if (( min_mb <= 0 )); then
+    printf 'disk: check skipped (DCE_MIN_FREE_MB=%s)\n' "$min_mb"
+    return 0
+  fi
+
+  archive_root=$(jq -r '.archive_root // empty' "$CONFIG_PATH")
+  [[ -n "$archive_root" && "$archive_root" != null ]] || die "Config is missing archive_root."
+  need_kb=$((min_mb * 1024))
+
+  for path in "$archive_root" "$REPO_ROOT"; do
+    [[ -e "$path" ]] || continue
+    avail_kb=$(df -Pk "$path" | awk 'NR==2 {print $4}')
+    [[ -n "$avail_kb" && "$avail_kb" =~ ^[0-9]+$ ]] || die "Could not read free space for $path"
+    if (( avail_kb < need_kb )); then
+      die "Insufficient disk space on $(df -Pk "$path" | awk 'NR==2 {print $6}'): $((avail_kb / 1024)) MiB free, need at least ${min_mb} MiB under archive_root ($archive_root). Free space before scraping."
+    fi
+    printf 'disk: %s has %s MiB free (need %s MiB)\n' "$(df -Pk "$path" | awk 'NR==2 {print $6}')" "$((avail_kb / 1024))" "$min_mb"
+  done
+}
+
 check_auth() {
   if [[ -f "$ENV_FILE" ]] && grep -qE '^[[:space:]]*DISCORD_TOKEN=' "$ENV_FILE"; then
     printf 'auth: scrape.env has DISCORD_TOKEN\n'
@@ -100,6 +124,7 @@ main() {
 
   printf 'Operator readiness checks\n'
   printf '=========================\n'
+  require_archive_disk_space
   resolve_compose
   check_auth
   printf 'config: %s\n\n' "$CONFIG_PATH"