ops: split RoverPathProfileWorker onto :rover_path queue at 1 slot/pod

The :terrain queue at 3 slots/pod was sized for the lightweight per-QSO
TerrainProfileWorker, but RoverPathProfileWorker now runs the full
PathCompute pipeline (terrain + 9 HRRR profiles + sounding + ionosphere
+ scoring + loss + forecast) — same heap profile as :propagation, which
sits at 1 slot precisely to avoid OOM.

A backfill_paths flood today queued ~200 rover-path jobs. With 4 hot
pods × 3 slots, the cluster stacked 15 concurrent path-computes and
two pods OOM-killed in a loop, taking the libcluster ring with them
(visible as the "unable to connect" warnings on the surviving pods).

New :rover_path queue at 1 slot/pod caps cluster-wide concurrency at
(hot_replicas + 1 backfill), drains the existing 200-job backlog
inside ~30 min, and keeps :terrain free for the cheap workers it was
sized for.

config/config.exs

@@ -74,6 +74,12 @@ config :microwaveprop, Oban,
     enqueue: 1,
     gefs: 2,
     terrain: 4,
+    # RoverPathProfileWorker runs the same full HRRR/terrain/score
+    # /loss/forecast pipeline as the propagation grid chain. Kept on
+    # its own queue at 1 slot/pod so a backfill flood can't stack
+    # multiple heavy path-computes in one BEAM heap (the OOM that
+    # took down hot pods on 2026-05-03).
+    rover_path: 1,
     commercial: 2,
     iemre: 10,
     # 2 slots so PropagationPruneWorker can run alongside the

config/runtime.exs

@@ -172,6 +172,15 @@ if config_env() == :prod do
     # :hrrr queue removed — per-QSO HRRR fetches flow through
     # hrrr_fetch_tasks and the Rust hrrr-point-worker (Phase 3 Stream C).
     terrain: 3,
+    # 1 slot per pod, same reasoning as :propagation. Each
+    # RoverPathProfileWorker job allocates a full path-compute heap
+    # (terrain points + 9 HRRR profiles + sounding + ionosphere +
+    # scoring + loss + forecast); 3 slots × 4 hot pods on the
+    # :terrain queue OOM-killed pods on 2026-05-03 when a backfill
+    # flood landed. Cluster-wide capacity is now (hot replicas + 1
+    # backfill) jobs at a time, which still drains a 200-job
+    # backlog inside ~30 min.
+    rover_path: 1,
     iemre: 3,
     backfill_enqueue: 1,
     admin: 1,

lib/microwaveprop/workers/rover_path_profile_worker.ex

@@ -16,7 +16,7 @@ defmodule Microwaveprop.Workers.RoverPathProfileWorker do
       handed `?rover_path_id=UUID` and renders without recomputing.
   """
   use Oban.Worker,
-    queue: :terrain,
+    queue: :rover_path,
     max_attempts: 5,
     unique: [
       period: 300,