Close inventory gaps: Spaces buckets (URN-discover), droplet backups, snapshot URN aliases

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>
This commit is contained in:
2026-05-19 22:46:29 +10:00
parent 8bdf500214
commit ea3101ca2f
5 changed files with 150 additions and 6 deletions

View File

@@ -64,17 +64,35 @@ defmodule ArcadiaCloud.Sync.ProjectsWorker do
end)
end
# Kinds with a dedicated sync worker — ProjectsWorker only updates attribution
# for these, never inserts (the worker is the source of truth for richer attrs).
@dedicated_kinds ~w(droplet volume snapshot floating_ip firewall load_balancer dns_zone)
defp attribute_urns(urns, %{id: project_id} = local) do
tenant_id = tenant_id_for(local)
Enum.each(urns, fn %{"urn" => urn} ->
case parse_urn(urn) do
{kind, provider_id} -> update_resource_attribution(kind, provider_id, project_id, tenant_id)
_ -> :skip
{kind, provider_id} ->
attribute_or_discover(kind, provider_id, project_id, tenant_id)
_ ->
:skip
end
end)
end
# For kinds with a dedicated worker, just update attribution. For everything
# else (spaces_bucket, managed_db, k8s_cluster, etc.) insert a minimal
# placeholder so the resource shows up in inventory + cost matching.
defp attribute_or_discover(kind, provider_id, project_id, tenant_id) do
if kind in @dedicated_kinds do
update_resource_attribution(kind, provider_id, project_id, tenant_id)
else
ensure_via_urn(kind, provider_id, project_id, tenant_id)
end
end
defp update_resource_attribution(kind, provider_id, project_id, tenant_id) do
from(r in CloudResource,
where:
@@ -84,6 +102,26 @@ defmodule ArcadiaCloud.Sync.ProjectsWorker do
|> Repo.update_all(set: [cloud_project_id: project_id, tenant_id: tenant_id])
end
defp ensure_via_urn(kind, provider_id, project_id, tenant_id) do
now = DateTime.utc_now() |> DateTime.truncate(:second)
Cloud.upsert_resource(
%{
provider: "digitalocean",
provider_id: provider_id,
kind: kind,
name: provider_id,
status: "active",
cloud_project_id: project_id,
tenant_id: tenant_id,
attrs: %{discovered_via: "urn_membership"},
first_seen_at: now,
last_seen_at: now
},
source: "projects_urn"
)
end
# "do:droplet:567897199" → {"droplet", "567897199"}
defp parse_urn("do:" <> rest) do
case String.split(rest, ":", parts: 2) do
@@ -101,6 +139,8 @@ defmodule ArcadiaCloud.Sync.ProjectsWorker do
defp normalize_kind("floatingip"), do: "floating_ip"
defp normalize_kind("loadbalancer"), do: "load_balancer"
defp normalize_kind("dbaas"), do: "managed_db"
defp normalize_kind("volumesnapshot"), do: "snapshot"
defp normalize_kind("image"), do: "snapshot"
defp normalize_kind(other), do: other
defp tenant_id_for(%{name: "tenant-" <> tenant_uuid}), do: tenant_uuid