prop/test/microwaveprop/weather/era5_client_test.exs
Graham McIntire 14a2284321
Handle CDS "rejected" status + widen submit cap headroom
CDS returns status="rejected" (distinct from "failed") when a submit
is rate-limited past the 150-job per-user cap. The poll worker's
interpret_status_body treated this as an unknown status → generic
retryable error → 10 retries → discarded. 102 jobs hit this path
overnight.

Fix:
  * Era5Client.check_status/1 now returns {:rejected, reason} (and
    treats "dismissed" the same way — that's the status a manually
    deleted job transitions to).
  * Era5PollWorker handles :rejected exactly like :not_found: drop the
    DB row, clean up the sibling CDS job, re-enqueue the submit, and
    discard the current Oban job so it doesn't burn attempts retrying
    a terminal state.
  * Widened Era5SubmitWorker cap headroom from 10 → 30 (effective
    ceiling 120 not 140). The race between concurrent workers all
    passing the count check simultaneously meant we were reaching 141
    in-flight against the 150 hard cap; 30 slots of headroom tolerates
    a ~15-worker race before clipping CDS's ceiling.

Refactored handle_row/1 into handle_row + handle_non_both_done with a
leg_outcome/1 tag helper so the cross-product of leg statuses collapses
to a single pair match (credo complexity limit).
2026-04-14 08:26:42 -05:00

210 lines
7.3 KiB
Elixir

defmodule Microwaveprop.Weather.Era5ClientTest do
# async: false — tests mutate the global ERA5_CDS_API_KEY env var to match
# production's lookup path. Running concurrently with Era5BatchClientTest
# (which *deletes* the env var to exercise the missing-key error path)
# leaks state in both directions.
use ExUnit.Case, async: false
alias Microwaveprop.Weather.Era5Client
setup do
# A real key — stubs don't care about value, only presence.
System.put_env("ERA5_CDS_API_KEY", "test-key")
on_exit(fn -> System.delete_env("ERA5_CDS_API_KEY") end)
:ok
end
describe "submit_job/2" do
test "returns {:ok, job_id} when CDS accepts the request" do
Req.Test.stub(Era5Client, fn conn ->
assert conn.method == "POST"
assert String.ends_with?(conn.request_path, "/reanalysis-era5-single-levels/execution")
Req.Test.json(conn, %{"jobID" => "cds-job-123", "status" => "accepted"})
end)
assert {:ok, "cds-job-123"} =
Era5Client.submit_job("reanalysis-era5-single-levels", %{"foo" => "bar"})
end
test "returns {:error, _} when CDS returns 400" do
Req.Test.stub(Era5Client, fn conn ->
conn
|> Plug.Conn.put_resp_content_type("application/json")
|> Plug.Conn.resp(400, ~s({"detail":"bad request"}))
end)
assert {:error, reason} = Era5Client.submit_job("reanalysis-era5-single-levels", %{})
assert reason =~ "HTTP 400"
end
test "returns {:error, _} when API key is missing" do
System.delete_env("ERA5_CDS_API_KEY")
assert {:error, reason} = Era5Client.submit_job("reanalysis-era5-single-levels", %{})
assert reason =~ "ERA5_CDS_API_KEY"
end
end
describe "check_status/1" do
test "returns :running while CDS job is accepted" do
Req.Test.stub(Era5Client, fn conn ->
assert conn.method == "GET"
assert String.ends_with?(conn.request_path, "/jobs/cds-job-123")
Req.Test.json(conn, %{"status" => "accepted"})
end)
assert :running = Era5Client.check_status("cds-job-123")
end
test "returns :running while CDS job is running" do
Req.Test.stub(Era5Client, fn conn ->
Req.Test.json(conn, %{"status" => "running"})
end)
assert :running = Era5Client.check_status("cds-job-123")
end
test "returns {:done, {:url, href}} when CDS job completes with an asset href" do
Req.Test.stub(Era5Client, fn conn ->
case conn.request_path do
"/api/retrieve/v1/jobs/cds-job-123" ->
Req.Test.json(conn, %{"status" => "successful"})
"/api/retrieve/v1/jobs/cds-job-123/results" ->
Req.Test.json(conn, %{
"asset" => %{"value" => %{"href" => "https://example.com/file.grib"}}
})
end
end)
assert {:done, {:url, "https://example.com/file.grib"}} =
Era5Client.check_status("cds-job-123")
end
test "returns {:failed, _} when CDS reports the job failed" do
Req.Test.stub(Era5Client, fn conn ->
assert conn.request_path == "/api/retrieve/v1/jobs/cds-job-123"
Req.Test.json(conn, %{"status" => "failed", "message" => "input out of range"})
end)
assert {:failed, reason} = Era5Client.check_status("cds-job-123")
assert reason =~ "input out of range"
end
test "returns :not_found when CDS returns 404 for the job" do
# 404 means the CDS job was deleted or never existed. This is terminal —
# retrying will always 404 — so callers should treat it as a distinct
# state from the generic {:error, _} retryable bucket.
Req.Test.stub(Era5Client, fn conn ->
conn
|> Plug.Conn.put_resp_content_type("application/json")
|> Plug.Conn.resp(
404,
~s({"detail":"job cds-job-123 deleted","status":404,"title":"job not found"})
)
end)
assert :not_found = Era5Client.check_status("cds-job-123")
end
test "returns {:rejected, reason} when CDS marks the job as rejected" do
# CDS rejects submits when the user's in-flight queue is over the cap
# (150 jobs). The rejected job still gets a jobID and a GET /jobs/:id
# returns a body with status=rejected. This is terminal — re-polling
# will never transition to successful — so callers should treat it
# like {:failed, _} and re-submit the tile-month.
Req.Test.stub(Era5Client, fn conn ->
Req.Test.json(conn, %{
"jobID" => "cds-job-123",
"status" => "rejected",
"metadata" => %{"origin" => "api"}
})
end)
assert {:rejected, reason} = Era5Client.check_status("cds-job-123")
assert is_binary(reason)
end
end
describe "delete_job/1" do
test "sends DELETE to the CDS jobs endpoint and returns :ok on 204" do
test_pid = self()
Req.Test.stub(Era5Client, fn conn ->
send(test_pid, {:delete_request, conn.method, conn.request_path})
Plug.Conn.resp(conn, 204, "")
end)
assert :ok = Era5Client.delete_job("cds-job-123")
assert_received {:delete_request, "DELETE", "/api/retrieve/v1/jobs/cds-job-123"}
end
test "also treats 200/202/404 as success (CDS sometimes returns 200 or the job may already be gone)" do
for status <- [200, 202, 404] do
Req.Test.stub(Era5Client, fn conn -> Plug.Conn.resp(conn, status, "") end)
assert :ok = Era5Client.delete_job("cds-job-#{status}")
end
end
test "returns {:error, _} for unexpected statuses" do
Req.Test.stub(Era5Client, fn conn -> Plug.Conn.resp(conn, 500, "server error") end)
assert {:error, reason} = Era5Client.delete_job("cds-job-500")
assert reason =~ "HTTP 500"
end
end
describe "download_source_to_file/3" do
test "writes a {:body, binary} source directly to the target path" do
path = Path.join(System.tmp_dir!(), "era5_test_#{System.unique_integer([:positive])}.grib")
try do
assert :ok = Era5Client.download_source_to_file({:body, "grib-payload"}, nil, path)
assert File.read!(path) == "grib-payload"
after
File.rm(path)
end
end
test "streams a {:url, href} source through Req into the target path" do
Req.Test.stub(Era5Client, fn conn ->
assert conn.method == "GET"
conn
|> Plug.Conn.put_resp_content_type("application/octet-stream")
|> Plug.Conn.resp(200, "streamed-grib-data")
end)
path = Path.join(System.tmp_dir!(), "era5_test_#{System.unique_integer([:positive])}.grib")
try do
assert :ok =
Era5Client.download_source_to_file(
{:url, "https://example.com/file.grib"},
"test-key",
path
)
assert File.read!(path) == "streamed-grib-data"
after
File.rm(path)
end
end
test "removes partial file and returns {:error, _} on HTTP error" do
Req.Test.stub(Era5Client, fn conn ->
Plug.Conn.resp(conn, 503, "")
end)
path = Path.join(System.tmp_dir!(), "era5_test_#{System.unique_integer([:positive])}.grib")
assert {:error, reason} =
Era5Client.download_source_to_file(
{:url, "https://example.com/file.grib"},
"test-key",
path
)
assert reason =~ "HTTP 503"
refute File.exists?(path)
end
end
end