arcadia-cloud/lib/arcadia_cloud/provisioning.ex

defmodule ArcadiaCloud.Provisioning do
  @moduledoc """
  Context for saga orchestration — provisioning, suspension, offboarding,
  updates, anything that wants compensation-based rollback over Oban.

  Pattern: caller assembles a step list (per template or hand-rolled),
  calls `start_saga/1`, the Runner Oban worker walks the steps,
  persisting results and rolling back on failure.
  """

  import Ecto.Query, warn: false

  alias ArcadiaCloud.Repo
  alias ArcadiaCloud.Provisioning.{SagaRun, SagaStepResult}

  @doc """
  Inserts a saga_runs row + enqueues the Runner job.

  Required:
    :kind            — provision | suspend | offboard | update | rollback | test
    :step_modules    — ordered list of step module atoms or fully-qualified strings
    :inputs          — map of saga inputs (stored in context.__inputs__)

  Optional:
    :deployment_id   — links the saga to a deployment (nil for skyai-internal)
    :triggered_by    — user_id or "system:<reason>"
  """
  def start_saga(opts) when is_list(opts) do
    start_saga(Map.new(opts))
  end

  def start_saga(%{} = attrs) do
    step_modules = Enum.map(attrs[:step_modules] || [], &to_string/1)
    inputs = attrs[:inputs] || %{}

    saga_attrs = %{
      kind: attrs[:kind],
      step_modules: step_modules,
      deployment_id: attrs[:deployment_id],
      triggered_by: attrs[:triggered_by],
      context: %{"__inputs__" => inputs}
    }

    with {:ok, saga} <- create_saga(saga_attrs),
         {:ok, _job} <-
           %{"saga_id" => saga.id}
           |> ArcadiaCloud.Provisioning.Runner.new()
           |> Oban.insert() do
      {:ok, saga}
    end
  end

  def create_saga(attrs) do
    %SagaRun{}
    |> SagaRun.changeset(attrs)
    |> Repo.insert()
  end

  @doc """
  Starts a snapshot saga for a droplet. `droplet_provider_id` is the DO
  numeric droplet id (string). Optional `:snapshot_label` and
  `:triggered_by`.
  """
  def snapshot_droplet(droplet_provider_id, opts \\ []) do
    start_saga(%{
      kind: "provision",
      step_modules: [ArcadiaCloud.Provisioning.Steps.CreateDropletSnapshot],
      inputs: %{
        droplet_provider_id: to_string(droplet_provider_id),
        snapshot_label: opts[:snapshot_label]
      },
      triggered_by: opts[:triggered_by] || "manual"
    })
  end

  def get_saga(id), do: Repo.get(SagaRun, id)
  def get_saga!(id), do: Repo.get!(SagaRun, id)

  def update_saga(%SagaRun{} = saga, attrs) do
    saga
    |> SagaRun.changeset(attrs)
    |> Repo.update()
  end

  def list_sagas(opts \\ []) do
    base = from(s in SagaRun, order_by: [desc: s.inserted_at])

    base
    |> maybe_filter(:status, opts[:status])
    |> maybe_filter(:kind, opts[:kind])
    |> maybe_filter(:deployment_id, opts[:deployment_id])
    |> maybe_limit(opts[:limit])
    |> Repo.all()
  end

  def list_step_results(saga_id) do
    from(r in SagaStepResult,
      where: r.saga_id == ^saga_id,
      order_by: [asc: r.step_idx]
    )
    |> Repo.all()
  end

  def cancel_saga(%SagaRun{} = saga) do
    saga
    |> SagaRun.changeset(%{cancel_requested: true})
    |> Repo.update()
  end

  def upsert_step_result(saga_id, step_idx, attrs) do
    case Repo.get_by(SagaStepResult, saga_id: saga_id, step_idx: step_idx) do
      nil ->
        %SagaStepResult{}
        |> SagaStepResult.changeset(Map.merge(attrs, %{saga_id: saga_id, step_idx: step_idx}))
        |> Repo.insert()

      existing ->
        existing
        |> SagaStepResult.changeset(attrs)
        |> Repo.update()
    end
  end

  defp maybe_filter(q, _f, nil), do: q
  defp maybe_filter(q, field, value), do: from(s in q, where: field(s, ^field) == ^value)

  defp maybe_limit(q, nil), do: q
  defp maybe_limit(q, n), do: from(s in q, limit: ^n)
end