Two patterns added: 1. ProjectsWorker now does URN-discover for kinds without a dedicated sync worker (spaces_bucket, managed_db, k8s_cluster, etc.). For these, it inserts a minimal placeholder row when the URN points to something not yet in inventory. Kinds with dedicated workers (droplet, snapshot, volume, etc.) still get attribution-only — the worker is source of truth for richer attrs. Implemented by splitting attribute_or_discover/4 on a @dedicated_kinds whitelist. 2. New BackupsWorker pulls /v2/droplets/:id/backups for each active droplet. DO automated backups aren't in /v2/snapshots; they live per droplet. Cron: hourly at :41. Kind="droplet_backup". URN normalization extended for two more aliases DO emits: "volumesnapshot" → snapshot (was creating a duplicate row) "image" → snapshot (DO droplet snapshots show as do:image:id) Billing.find_resource/1 gets a kind-specific clause for droplet_backup that matches to the parent droplet by name, since invoice lines for backups read "<droplet-name> (Weekly Backup Services)" — the line is a per-droplet subscription, not a per-backup-snapshot fee. Live verified on the same April 2026 invoice: - 6 Spaces buckets discovered via URN (account has 6, only 1 visible in the invoice as the $5 subscription line — that's account-level so it can't tie to a specific bucket, expected). - 4 droplet backups discovered via BackupsWorker; the git.sky-ai.com backup line now matches (repo.sky-ai.com backup line can't match — that droplet was destroyed). - Of 16 unmatched lines: 11 are destroyed historic resources, 1 is GST, 1 is the account-level Spaces subscription, 3 are likely tiny snapshot name variances. Effectively ~100% of currently-existing billable resources match. Co-Authored-By: Claude Opus 4.7 (1M context) <noreply@anthropic.com>
85 lines
2.2 KiB
Elixir
85 lines
2.2 KiB
Elixir
defmodule ArcadiaCloud.Sync.BackupsWorker do
|
|
@moduledoc """
|
|
Sync of DO automated droplet backups.
|
|
|
|
Backups are not exposed via /v2/snapshots — they live under each
|
|
droplet at /v2/droplets/:id/backups. We iterate every active droplet
|
|
in inventory and pull its backups, normalizing them as
|
|
kind="droplet_backup" with the parent droplet_id in attrs.
|
|
"""
|
|
|
|
use Oban.Worker, queue: :cloud_sync_full, max_attempts: 3
|
|
|
|
import Ecto.Query
|
|
|
|
alias ArcadiaCloud.Cloud
|
|
alias ArcadiaCloud.Cloud.CloudResource
|
|
alias ArcadiaCloud.DigitalOcean.Client
|
|
alias ArcadiaCloud.Repo
|
|
|
|
@kind "droplet_backup"
|
|
@provider "digitalocean"
|
|
|
|
@impl Oban.Worker
|
|
def perform(_job) do
|
|
now = DateTime.utc_now() |> DateTime.truncate(:second)
|
|
droplets = list_active_droplets()
|
|
|
|
Enum.each(droplets, fn d ->
|
|
case Client.list_droplet_backups(d.provider_id) do
|
|
{:ok, backups} ->
|
|
Enum.each(backups, fn b ->
|
|
Cloud.upsert_resource(normalize(b, d, now))
|
|
end)
|
|
|
|
{:error, _} ->
|
|
# Soft-fail per droplet; mark_stale below handles disappearances.
|
|
:skip
|
|
end
|
|
end)
|
|
|
|
Cloud.mark_stale(@kind, now)
|
|
:ok
|
|
end
|
|
|
|
defp list_active_droplets do
|
|
from(r in CloudResource,
|
|
where:
|
|
r.provider == ^@provider and r.kind == "droplet" and is_nil(r.deleted_at) and
|
|
r.status != "archived",
|
|
select: %{id: r.id, provider_id: r.provider_id, cloud_project_id: r.cloud_project_id,
|
|
tenant_id: r.tenant_id}
|
|
)
|
|
|> Repo.all()
|
|
end
|
|
|
|
defp normalize(b, droplet, now) do
|
|
region =
|
|
case b["regions"] do
|
|
[first | _] when is_binary(first) -> first
|
|
_ -> nil
|
|
end
|
|
|
|
%{
|
|
provider: @provider,
|
|
provider_id: to_string(b["id"]),
|
|
kind: @kind,
|
|
name: b["name"] || "backup-#{b["id"]}",
|
|
region: region,
|
|
status: "active",
|
|
tags: [],
|
|
cloud_project_id: droplet.cloud_project_id,
|
|
tenant_id: droplet.tenant_id,
|
|
attrs: %{
|
|
droplet_id: droplet.provider_id,
|
|
size_gigabytes: b["size_gigabytes"],
|
|
min_disk_size: b["min_disk_size"],
|
|
regions: b["regions"],
|
|
do_created_at: b["created_at"]
|
|
},
|
|
first_seen_at: now,
|
|
last_seen_at: now
|
|
}
|
|
end
|
|
end
|