openclaw/src/cron/service.failure-alert.test.ts
Evgeny Zislis 4b4ea5df8b
feat(cron): add failure destination support to failed cron jobs (#31059)
* feat(cron): add failure destination support with webhook mode and bestEffort handling

Extends PR #24789 failure alerts with features from PR #29145:
- Add webhook delivery mode for failure alerts (mode: 'webhook')
- Add accountId support for multi-account channel configurations
- Add bestEffort handling to skip alerts when job has bestEffort=true
- Add separate failureDestination config (global + per-job in delivery)
- Add duplicate prevention (prevents sending to same as primary delivery)
- Add CLI flags: --failure-alert-mode, --failure-alert-account-id
- Add UI fields for new options in web cron editor

* fix(cron): merge failureAlert mode/accountId and preserve failureDestination on updates

- Fix mergeCronFailureAlert to merge mode and accountId fields
- Fix mergeCronDelivery to preserve failureDestination on updates
- Fix isSameDeliveryTarget to use 'announce' as default instead of 'none'
  to properly detect duplicates when delivery.mode is undefined

* fix(cron): validate webhook mode requires URL in resolveFailureDestination

When mode is 'webhook' but no 'to' URL is provided, return null
instead of creating an invalid plan that silently fails later.

* fix(cron): fail closed on webhook mode without URL and make failureDestination fields clearable

- sendCronFailureAlert: fail closed when mode is webhook but URL is missing
- mergeCronDelivery: use per-key presence checks so callers can clear
  nested failureDestination fields via cron.update

Note: protocol:check shows missing internalEvents in Swift models - this is
a pre-existing issue unrelated to these changes (upstream sync needed).

* fix(cron): use separate schema for failureDestination and fix type cast

- Create CronFailureDestinationSchema excluding after/cooldownMs fields
- Fix type cast in sendFailureNotificationAnnounce to use CronMessageChannel

* fix(cron): merge global failureDestination with partial job overrides

When job has partial failureDestination config, fall back to global
config for unset fields instead of treating it as a full override.

* fix(cron): avoid forcing announce mode and clear inherited to on mode change

- UI: only include mode in patch if explicitly set to non-default
- delivery.ts: clear inherited 'to' when job overrides mode, since URL
  semantics differ between announce and webhook modes

* fix(cron): preserve explicit to on mode override and always include mode in UI patches

- delivery.ts: preserve job-level explicit 'to' when overriding mode
- UI: always include mode in failureAlert patch so users can switch between announce/webhook

* fix(cron): allow clearing accountId and treat undefined global mode as announce

- UI: always include accountId in patch so users can clear it
- delivery.ts: treat undefined global mode as announce when comparing for clearing inherited 'to'

* Cron: harden failure destination routing and add regression coverage

* Cron: resolve failure destination review feedback

* Cron: drop unrelated timeout assertions from conflict resolution

* Cron: format cron CLI regression test

* Cron: align gateway cron test mock types

---------

Co-authored-by: Tak Hoffman <781889+Takhoffman@users.noreply.github.com>
2026-03-02 09:27:41 -06:00

267 lines
7.4 KiB
TypeScript

import fs from "node:fs/promises";
import os from "node:os";
import path from "node:path";
import { afterEach, beforeEach, describe, expect, it, vi } from "vitest";
import { CronService } from "./service.js";
const noopLogger = {
debug: vi.fn(),
info: vi.fn(),
warn: vi.fn(),
error: vi.fn(),
};
async function makeStorePath() {
const dir = await fs.mkdtemp(path.join(os.tmpdir(), "openclaw-cron-failure-alert-"));
return {
storePath: path.join(dir, "cron", "jobs.json"),
cleanup: async () => {
await fs.rm(dir, { recursive: true, force: true });
},
};
}
describe("CronService failure alerts", () => {
beforeEach(() => {
vi.useFakeTimers();
vi.setSystemTime(new Date("2026-01-01T00:00:00.000Z"));
noopLogger.debug.mockClear();
noopLogger.info.mockClear();
noopLogger.warn.mockClear();
noopLogger.error.mockClear();
});
afterEach(() => {
vi.useRealTimers();
});
it("alerts after configured consecutive failures and honors cooldown", async () => {
const store = await makeStorePath();
const sendCronFailureAlert = vi.fn(async () => undefined);
const runIsolatedAgentJob = vi.fn(async () => ({
status: "error" as const,
error: "wrong model id",
}));
const cron = new CronService({
storePath: store.storePath,
cronEnabled: true,
cronConfig: {
failureAlert: {
enabled: true,
after: 2,
cooldownMs: 60_000,
},
},
log: noopLogger,
enqueueSystemEvent: vi.fn(),
requestHeartbeatNow: vi.fn(),
runIsolatedAgentJob,
sendCronFailureAlert,
});
await cron.start();
const job = await cron.add({
name: "daily report",
enabled: true,
schedule: { kind: "every", everyMs: 60_000 },
sessionTarget: "isolated",
wakeMode: "next-heartbeat",
payload: { kind: "agentTurn", message: "run report" },
delivery: { mode: "announce", channel: "telegram", to: "19098680" },
});
await cron.run(job.id, "force");
expect(sendCronFailureAlert).not.toHaveBeenCalled();
await cron.run(job.id, "force");
expect(sendCronFailureAlert).toHaveBeenCalledTimes(1);
expect(sendCronFailureAlert).toHaveBeenLastCalledWith(
expect.objectContaining({
job: expect.objectContaining({ id: job.id }),
channel: "telegram",
to: "19098680",
text: expect.stringContaining('Cron job "daily report" failed 2 times'),
}),
);
await cron.run(job.id, "force");
expect(sendCronFailureAlert).toHaveBeenCalledTimes(1);
vi.advanceTimersByTime(60_000);
await cron.run(job.id, "force");
expect(sendCronFailureAlert).toHaveBeenCalledTimes(2);
expect(sendCronFailureAlert).toHaveBeenLastCalledWith(
expect.objectContaining({
text: expect.stringContaining('Cron job "daily report" failed 4 times'),
}),
);
cron.stop();
await store.cleanup();
});
it("supports per-job failure alert override when global alerts are disabled", async () => {
const store = await makeStorePath();
const sendCronFailureAlert = vi.fn(async () => undefined);
const runIsolatedAgentJob = vi.fn(async () => ({
status: "error" as const,
error: "timeout",
}));
const cron = new CronService({
storePath: store.storePath,
cronEnabled: true,
cronConfig: {
failureAlert: {
enabled: false,
},
},
log: noopLogger,
enqueueSystemEvent: vi.fn(),
requestHeartbeatNow: vi.fn(),
runIsolatedAgentJob,
sendCronFailureAlert,
});
await cron.start();
const job = await cron.add({
name: "job with override",
enabled: true,
schedule: { kind: "every", everyMs: 60_000 },
sessionTarget: "isolated",
wakeMode: "next-heartbeat",
payload: { kind: "agentTurn", message: "run report" },
failureAlert: {
after: 1,
channel: "telegram",
to: "12345",
cooldownMs: 1,
},
});
await cron.run(job.id, "force");
expect(sendCronFailureAlert).toHaveBeenCalledTimes(1);
expect(sendCronFailureAlert).toHaveBeenLastCalledWith(
expect.objectContaining({
channel: "telegram",
to: "12345",
}),
);
cron.stop();
await store.cleanup();
});
it("respects per-job failureAlert=false and suppresses alerts", async () => {
const store = await makeStorePath();
const sendCronFailureAlert = vi.fn(async () => undefined);
const runIsolatedAgentJob = vi.fn(async () => ({
status: "error" as const,
error: "auth error",
}));
const cron = new CronService({
storePath: store.storePath,
cronEnabled: true,
cronConfig: {
failureAlert: {
enabled: true,
after: 1,
},
},
log: noopLogger,
enqueueSystemEvent: vi.fn(),
requestHeartbeatNow: vi.fn(),
runIsolatedAgentJob,
sendCronFailureAlert,
});
await cron.start();
const job = await cron.add({
name: "disabled alert job",
enabled: true,
schedule: { kind: "every", everyMs: 60_000 },
sessionTarget: "isolated",
wakeMode: "next-heartbeat",
payload: { kind: "agentTurn", message: "run report" },
failureAlert: false,
});
await cron.run(job.id, "force");
await cron.run(job.id, "force");
expect(sendCronFailureAlert).not.toHaveBeenCalled();
cron.stop();
await store.cleanup();
});
it("threads failure alert mode/accountId and skips best-effort jobs", async () => {
const store = await makeStorePath();
const sendCronFailureAlert = vi.fn(async () => undefined);
const runIsolatedAgentJob = vi.fn(async () => ({
status: "error" as const,
error: "temporary upstream error",
}));
const cron = new CronService({
storePath: store.storePath,
cronEnabled: true,
cronConfig: {
failureAlert: {
enabled: true,
after: 1,
mode: "webhook",
accountId: "global-account",
},
},
log: noopLogger,
enqueueSystemEvent: vi.fn(),
requestHeartbeatNow: vi.fn(),
runIsolatedAgentJob,
sendCronFailureAlert,
});
await cron.start();
const normalJob = await cron.add({
name: "normal alert job",
enabled: true,
schedule: { kind: "every", everyMs: 60_000 },
sessionTarget: "isolated",
wakeMode: "next-heartbeat",
payload: { kind: "agentTurn", message: "run report" },
delivery: { mode: "announce", channel: "telegram", to: "19098680" },
});
const bestEffortJob = await cron.add({
name: "best effort alert job",
enabled: true,
schedule: { kind: "every", everyMs: 60_000 },
sessionTarget: "isolated",
wakeMode: "next-heartbeat",
payload: { kind: "agentTurn", message: "run report" },
delivery: {
mode: "announce",
channel: "telegram",
to: "19098680",
bestEffort: true,
},
});
await cron.run(normalJob.id, "force");
expect(sendCronFailureAlert).toHaveBeenCalledTimes(1);
expect(sendCronFailureAlert).toHaveBeenCalledWith(
expect.objectContaining({
mode: "webhook",
accountId: "global-account",
to: undefined,
}),
);
await cron.run(bestEffortJob.id, "force");
expect(sendCronFailureAlert).toHaveBeenCalledTimes(1);
cron.stop();
await store.cleanup();
});
});