Eric Allam
47ff76d727
## Summary When a runs list query is too expensive to complete, it now fails with a clear, actionable error instead of a generic 500. Previously, a runs list query that exceeded ClickHouse resource limits threw an opaque error. On the public `runs.list` API that surfaced as a retryable 500, so a customer task calling it would keep retrying a query that could never succeed. On the dashboard it rendered as a generic error page with no hint about what to do. ## Fix The ClickHouse client now tags resource-limit failures (memory, time, rows, bytes) with their error type, and the runs repository maps those to a dedicated `RunsListQueryError` (HTTP 422). - `runs.list` API returns 422 with a message telling the user to narrow their `created_at` range, plus an `x-should-retry: false` header so the SDK does not retry it. - The dashboard runs list (and the errors, scheduled, standard-task, agents, and webhooks list views) render a shared error state with the same guidance, so a too-broad time filter is recoverable by the user.
53 lines
1.9 KiB
TypeScript
53 lines
1.9 KiB
TypeScript
import { ClickHouse } from "@internal/clickhouse";
|
|
import { containerTest } from "@internal/testcontainers";
|
|
import { describe, expect, vi } from "vitest";
|
|
import {
|
|
RunsListQueryError,
|
|
RunsRepository,
|
|
} from "~/services/runsRepository/runsRepository.server";
|
|
import {
|
|
createRun,
|
|
insertTaskRunV2Rows,
|
|
seedParents,
|
|
} from "./helpers/apiRunListPresenterTestHelpers";
|
|
|
|
vi.mock("~/db.server", () => ({ prisma: {}, $replica: {} }));
|
|
|
|
vi.setConfig({ testTimeout: 90_000 });
|
|
|
|
describe("runs list query error handling", () => {
|
|
containerTest(
|
|
"a ClickHouse resource-limit error surfaces as RunsListQueryError",
|
|
async ({ clickhouseContainer, prisma }) => {
|
|
const ctx = await seedParents(prisma, "qerr");
|
|
const run = await createRun(prisma, ctx, { friendlyId: "run_qerr" });
|
|
|
|
const seedClient = new ClickHouse({
|
|
url: clickhouseContainer.getConnectionUrl(),
|
|
name: "runs-list-query-error-seed",
|
|
});
|
|
await insertTaskRunV2Rows(seedClient, [{ ...run, createdAt: new Date() }]);
|
|
|
|
const listArgs = {
|
|
page: { size: 10 } as const,
|
|
organizationId: ctx.organizationId,
|
|
projectId: ctx.projectId,
|
|
environmentId: ctx.environmentId,
|
|
};
|
|
|
|
const cappedClient = new ClickHouse({
|
|
url: clickhouseContainer.getConnectionUrl(),
|
|
name: "runs-list-query-error-capped",
|
|
clickhouseSettings: { max_memory_usage: "1" },
|
|
});
|
|
const capped = new RunsRepository({ prisma, clickhouse: cappedClient });
|
|
await expect(capped.listRuns(listArgs)).rejects.toBeInstanceOf(RunsListQueryError);
|
|
await expect(capped.countRuns(listArgs)).rejects.toBeInstanceOf(RunsListQueryError);
|
|
|
|
const ok = new RunsRepository({ prisma, clickhouse: seedClient });
|
|
const result = await ok.listRuns(listArgs);
|
|
expect(result.runs.map((r) => r.friendlyId)).toEqual(["run_qerr"]);
|
|
}
|
|
);
|
|
});
|