Merge repaired plugin scheduling into tool health migration

Co-Authored-By: Paperclip <noreply@paperclip.ing>
This commit is contained in:
DottaandPaperclip committed 2026-10-24 23:59:10 -05:00
commit 17f3eaf806
14 files changed
+302 -66

No files matched your search

@@ -282,6 +282,68 @@ const support = external ? { supported: true } : await getEmbeddedPostgresTestSu
draining = false; await seeded(approval.id); await quiet();
});
it("backs off persistent projection failures without forgetting the owed membership", async () => {
const service = approvalQueueSeedingService(db);
await service.sweep();
const approval = await pending();
service.request(new Set([companyId]));
await db.execute(sql`create function approval_queue_fail() returns trigger language plpgsql as $$ begin raise exception 'projection unavailable'; end $$`);
await db.execute(sql`create trigger approval_queue_fail before insert on decision_queue_items for each row execute function approval_queue_fail()`);
const transactions = vi.spyOn(db, "transaction");
try {
for (let second = 0; second < 120; second++) {
service.request(new Set([companyId]));
await service.sweep().catch(() => undefined);
await vi.advanceTimersByTimeAsync(1000);
}
expect(transactions.mock.calls.length).toBeLessThanOrEqual(8);
expect(transactions.mock.calls.length).toBeGreaterThan(1);
expect(await memberships()).toEqual([]);
expect(await service.next()).not.toBeNull();
} finally {
transactions.mockRestore();
await db.execute(sql`drop trigger approval_queue_fail on decision_queue_items`);
}
await vi.advanceTimersByTimeAsync(60_000);
await service.sweep();
expect(await memberships()).toEqual([expect.objectContaining({ sourceId: approval.id })]);
expect(await service.next()).toBeNull();
});
it("keeps backoff SQL-quiet while another company's committed work proceeds", async () => {
const service = approvalQueueSeedingService(db), sweep = service.sweep;
let running = false;
service.sweep = async signal => { running = true; try { await sweep(signal); } finally { running = false; } };
await start(service); await quiet();
await db.execute(sql`create function approval_queue_fail() returns trigger language plpgsql as $$ begin
if new.company_id::text = TG_ARGV[0] then raise exception 'projection unavailable'; end if; return new; end $$`);
await db.execute(sql`create trigger approval_queue_fail before insert on decision_queue_items for each row execute function approval_queue_fail(${sql.raw("'" + companyId + "'")})`);
const approval = await pending();
for (let count = 1; count <= 7; count++) {
await vi.waitFor(async () => { await vi.advanceTimersByTimeAsync(1000); expect(errors.length).toBeGreaterThanOrEqual(count); }, { timeout: 5000 });
await vi.waitFor(() => expect(running).toBe(false));
}
const reads = vi.spyOn(db, "select"), writes = vi.spyOn(db, "transaction");
await vi.advanceTimersByTimeAsync(30_000);
expect(reads).not.toHaveBeenCalled(); expect(writes).not.toHaveBeenCalled();
reads.mockRestore(); writes.mockRestore();
const otherId = randomUUID();
await db.insert(companies).values({ id: otherId, name: "Healthy tenant", issuePrefix: `H${otherId.slice(0, 6)}` });
const [otherIssue] = await db.insert(issues).values({ companyId: otherId, title: "Other PR", status: "todo" }).returning();
await workProductService(db).createForIssue(otherIssue.id, otherId, { type: "pull_request", provider: "github", title: "Other PR", status: "open" });
const otherApproval = await approvalRecords(db).create(otherId, { type: "request_board_approval", payload: {} });
await issueApprovalService(db).link(otherIssue.id, otherApproval.id);
await vi.waitFor(async () => {
await vi.advanceTimersByTimeAsync(1000);
expect(await db.select().from(decisionQueueItems).where(eq(decisionQueueItems.companyId, otherId)))
.toEqual([expect.objectContaining({ sourceId: otherApproval.id })]);
}, { timeout: 5000 });
expect(await memberships()).toEqual([]);
await db.execute(sql`drop trigger approval_queue_fail on decision_queue_items`); errors.length = 0;
await vi.advanceTimersByTimeAsync(60_000);
await seeded(approval.id); await quiet();
});
it("drains multiple pages without duplicating memberships or audit events", async () => {
const target = await issue(); await product(target.id);
const rows = await db.insert(approvals).values(Array.from({ length: 101 }, () => ({ companyId, type: "request_board_approval", payload: {} }))).returning();
@@ -309,6 +371,7 @@ const support = external ? { supported: true } : await getEmbeddedPostgresTestSu
await db.execute(sql`create trigger approval_queue_fail before insert on decision_queue_items for each row execute function approval_queue_fail(${sql.raw("'" + last + "'")})`);
const service = approvalQueueSeedingService(db);
await expect(service.sweep()).rejects.toThrow("Approval queue seeding failed");
await vi.advanceTimersByTimeAsync(1000);
await service.sweep(); expect((await memberships()).map(row => row.sourceId)).toEqual([last]);
await db.execute(sql`drop trigger approval_queue_fail on decision_queue_items`);
await service.sweep(); expect(await memberships()).toHaveLength(101); expect(await service.next()).toBeNull();
@@ -1,3 +1,4 @@
import { finishServiceShutdown } from "../shutdown.js";
import { EventEmitter } from "node:events";
import { randomUUID } from "node:crypto";
import { afterAll, afterEach, beforeAll, beforeEach, describe, expect, it, vi } from "vitest";
@@ -61,7 +62,11 @@ const support = external ? { supported: true } : await getEmbeddedPostgresTestSu
}, { timeout: 5000 });
}
async function quiet() {
await settled(); expect(coordinator!.nextWakeAt()).toBeNull();
await vi.waitFor(async () => {
await vi.advanceTimersByTimeAsync(1000);
expect(idleWorkSnapshot().active).toBe(0);
expect(coordinator!.nextWakeAt()).toBeNull();
}, { timeout: 5000 });
const reads = vi.spyOn(db, "select"), writes = vi.spyOn(db, "transaction"), executes = vi.spyOn(db, "execute");
await vi.advanceTimersByTimeAsync(180_000);
expect(reads).not.toHaveBeenCalled(); expect(writes).not.toHaveBeenCalled(); expect(executes).not.toHaveBeenCalled();
@@ -80,6 +85,23 @@ const support = external ? { supported: true } : await getEmbeddedPostgresTestSu
}
it("does not query repeatedly after an empty startup reconciliation", async () => { await start(); await quiet(); });
it("bounds full refreshes while many job status writes arrive sequentially", async () => {
await pluginJobStore(db).syncJobDeclarations(pluginId, Array.from({ length: 40 }, (_, i) => ({ jobKey: `manual-${i}`, schedule: "" })));
const jobs = await db.select().from(pluginJobs).where(eq(pluginJobs.pluginId, pluginId));
await start(); await quiet();
const reads = vi.spyOn(db, "select");
for (const job of jobs.slice(0, 15)) {
const run = await pluginJobStore(db).createRun({ jobId: job.id, pluginId, trigger: "manual" });
await pluginJobStore(db).markRunning(run.id);
await pluginJobStore(db).completeRun(run.id, { status: "succeeded" });
await vi.advanceTimersByTimeAsync(1100);
}
expect(reads.mock.calls.length).toBeLessThanOrEqual(1);
reads.mockRestore();
await quiet();
expect(await runs()).toHaveLength(15);
expect(rpc).not.toHaveBeenCalled();
});
it("keeps configured manual-only and invalid schedules quiet", async () => {
await job("manual", ""); await job("invalid", "not cron"); await start(); await quiet(); expect(rpc).not.toHaveBeenCalled();
});
@@ -147,7 +169,7 @@ const support = external ? { supported: true } : await getEmbeddedPostgresTestSu
await db.execute(sql`create function plugin_settlement_failure() returns trigger language plpgsql as $$ begin if new.status in ('succeeded', 'failed') then raise exception 'settlement unavailable'; end if; return new; end $$`);
await db.execute(sql`create trigger plugin_settlement_failure before update on plugin_job_runs for each row execute function plugin_settlement_failure()`);
await due(); await start();
await vi.waitFor(() => expect(errors.length).toBeGreaterThan(0)); expect(rpc).toHaveBeenCalledTimes(1);
await vi.waitFor(async () => { await vi.advanceTimersByTimeAsync(1000); expect(errors.length).toBeGreaterThan(0); }, { timeout: 5000 }); expect(rpc).toHaveBeenCalledTimes(1);
await db.execute(sql`drop trigger plugin_settlement_failure on plugin_job_runs`); errors.length = 0;
await completed(); expect(rpc).toHaveBeenCalledTimes(1);
});
@@ -155,7 +177,7 @@ const support = external ? { supported: true } : await getEmbeddedPostgresTestSu
await db.execute(sql`create function plugin_settlement_failure() returns trigger language plpgsql as $$ begin if new.status in ('succeeded', 'failed') then raise exception 'settlement unavailable'; end if; return new; end $$`);
await db.execute(sql`create trigger plugin_settlement_failure before update on plugin_job_runs for each row execute function plugin_settlement_failure()`);
await due(); await start();
await vi.waitFor(() => expect(errors.length).toBeGreaterThan(0));
await vi.waitFor(async () => { await vi.advanceTimersByTimeAsync(1000); expect(errors.length).toBeGreaterThan(0); }, { timeout: 5000 });
draining = true;
await coordinator!.stop();
await db.execute(sql`drop trigger plugin_settlement_failure on plugin_job_runs`); errors.length = 0;
@@ -163,11 +185,28 @@ const support = external ? { supported: true } : await getEmbeddedPostgresTestSu
expect((await runs())[0].status).toBe("succeeded");
expect(rpc).toHaveBeenCalledTimes(1);
});
it("finishes service cleanup and retries a failed settlement before closing the pool", async () => {
await db.execute(sql`create function plugin_settlement_failure() returns trigger language plpgsql as $$ begin if new.status in ('succeeded', 'failed') then raise exception 'settlement unavailable'; end if; return new; end $$`);
await db.execute(sql`create trigger plugin_settlement_failure before update on plugin_job_runs for each row execute function plugin_settlement_failure()`);
await due(); await start();
await vi.waitFor(async () => { await vi.advanceTimersByTimeAsync(1000); expect(errors.length).toBeGreaterThan(0); }, { timeout: 5000 });
draining = true; await coordinator!.stop(); errors.length = 0;
const cleanup = vi.fn(async () => {
expect((await runs())[0].status).toBe("running");
await db.execute(sql`drop trigger plugin_settlement_failure on plugin_job_runs`);
});
const stop = vi.fn(() => scheduler!.stop());
await finishServiceShutdown(stop, cleanup);
expect(cleanup).toHaveBeenCalledOnce();
expect(stop).toHaveBeenCalledTimes(2);
expect((await runs())[0].status).toBe("succeeded");
expect(rpc).toHaveBeenCalledTimes(1);
});
it("reports shutdown persistence failure and retains the result for another stop attempt", async () => {
await db.execute(sql`create function plugin_settlement_failure() returns trigger language plpgsql as $$ begin if new.status in ('succeeded', 'failed') then raise exception 'settlement unavailable'; end if; return new; end $$`);
await db.execute(sql`create trigger plugin_settlement_failure before update on plugin_job_runs for each row execute function plugin_settlement_failure()`);
await due(); await start();
await vi.waitFor(() => expect(errors.length).toBeGreaterThan(0));
await vi.waitFor(async () => { await vi.advanceTimersByTimeAsync(1000); expect(errors.length).toBeGreaterThan(0); }, { timeout: 5000 });
draining = true; await coordinator!.stop(); errors.length = 0;
try {
await expect(scheduler!.stop()).rejects.toThrow("Plugin job completion persistence failed during shutdown");
@@ -183,7 +222,7 @@ const support = external ? { supported: true } : await getEmbeddedPostgresTestSu
await db.execute(sql`create trigger plugin_settlement_failure before update on plugin_job_runs for each row execute function plugin_settlement_failure(${sql.raw("'" + blocked.id + "'")})`);
try {
await start();
await vi.waitFor(() => expect(errors.length).toBeGreaterThan(0));
await vi.waitFor(async () => { await vi.advanceTimersByTimeAsync(1000); expect(errors.length).toBeGreaterThan(0); }, { timeout: 5000 });
const independent = await due("independent");
await vi.waitFor(async () => {
await vi.advanceTimersByTimeAsync(1000);
@@ -244,7 +283,11 @@ const support = external ? { supported: true } : await getEmbeddedPostgresTestSu
it("does no SQL while waiting for a future configured deadline", async () => {
const row = await job(); const at = new Date(Date.now() + 600_000);
await pluginJobStore(db).updateRunTimestamps(row.id, new Date(0), at);
await start(); await settled(); expect(coordinator!.nextWakeAt()).toBe(at.getTime());
await start();
await vi.waitFor(async () => {
await vi.advanceTimersByTimeAsync(1000);
expect(coordinator!.nextWakeAt()).toBe(at.getTime());
}, { timeout: 5000 });
const reads = vi.spyOn(db, "select"), writes = vi.spyOn(db, "transaction");
await vi.advanceTimersByTimeAsync(180_000);
expect(reads).not.toHaveBeenCalled(); expect(writes).not.toHaveBeenCalled();
@@ -254,7 +297,11 @@ const support = external ? { supported: true } : await getEmbeddedPostgresTestSu
const row = await job(); const at = new Date(Date.now() + 600_000);
await pluginJobStore(db).updateRunTimestamps(row.id, new Date(0), at);
await start(); await settled(); await scheduler!.stop(); await coordinator!.stop();
await start(); await settled(); expect(coordinator!.nextWakeAt()).toBe(at.getTime());
await start();
await vi.waitFor(async () => {
await vi.advanceTimersByTimeAsync(1000);
expect(coordinator!.nextWakeAt()).toBe(at.getTime());
}, { timeout: 5000 });
await vi.advanceTimersByTimeAsync(at.getTime() - Date.now()); await completed(); expect(rpc).toHaveBeenCalledTimes(1);
});
it("rechecks a paused definition after waiting for its lock", async () => {
@@ -331,7 +331,7 @@ vi.mock("../services/join-request-retention.js", async importOriginal => ({
vi.mock("../services/approval-queue-seeding-work.js", async importOriginal => ({
...await importOriginal<typeof import("../services/approval-queue-seeding-work.js")>(),
approvalQueueSeedingService: vi.fn(() => ({ sweep: vi.fn(async () => undefined), next: vi.fn(async () => null) })),
approvalQueueSeedingService: vi.fn(() => ({ sweep: vi.fn(async () => undefined), next: vi.fn(() => null), request: vi.fn() })),
}));
vi.mock("../services/approval-retention.js", async importOriginal => ({
@@ -545,7 +545,10 @@ describe("startServer feedback export wiring", () => {
if (enabled) {
const service = vi.mocked(approvalQueueSeedingService).mock.results.at(-1)!.value;
await registration![1].run(new AbortController().signal);
expect(service.sweep).toHaveBeenCalled(); expect(service.next).toHaveBeenCalled();
expect(service.sweep).toHaveBeenCalled();
expect(registration![1].nextRunAt()).toBeNull();
expect(await registration![1].hasPending()).toBe(false);
expect(service.next).toHaveBeenCalled();
}
});
+3 -5
View File
@@ -1,3 +1,4 @@
import { finishServiceShutdown } from "./shutdown.js";
import { promptInjectionPreventionRoutes } from "./routes/prompt-injection-prevention.js";
import { voiceSessionRoutes, voiceWebhookRoutes } from "./routes/voice-sessions.js";
import { eq } from "drizzle-orm";
@@ -1455,10 +1456,7 @@ export async function createApp(
let appServicesShutdown: Promise<void> | null = null;
const shutdownAppServices = (): Promise<void> => {
if (appServicesShutdown) return appServicesShutdown;
appServicesShutdown = (async () => {
// The scheduler tick queries the database. Stop it here, inside the
// awaited teardown, so no tick runs after the caller ends the pool.
await scheduler.stop();
appServicesShutdown = finishServiceShutdown(() => scheduler.stop(), async () => {
await agentLifecycle.stop();
await publicMcpEvents?.stop();
await dotMcpEvents?.stop();
@@ -1493,7 +1491,7 @@ export async function createApp(
// caller stops the database and the provider. A lease release that
// fails stays a durable record for the startup reaper.
await setupTokenLoginService?.shutdown();
})();
});
return appServicesShutdown;
};
app.locals.paperclipShutdown = shutdownAppServices;
@@ -1,6 +1,7 @@
import { and, asc, eq, gt, sql, type SQL } from "drizzle-orm";
import { approvals, companies, issues, type Db } from "@paperclipai/db";
import { approvals, companies, issues, issueWorkProducts, type Db } from "@paperclipai/db";
import { executionIssueCondition } from "./issue-visibility.js";
import { pullRequestSeedProductCondition } from "./decision-queue-seed-rules.js";
import { decisionQueueService } from "./decision-queues.js";
import type { createDeliveryWorkCoordinator } from "./delivery-work-coordinator.js";
import { DELIVERY_QUEUES } from "./delivery-work-notifications.js";
@@ -10,12 +11,12 @@ const linkedIssue = sql<string>`(select linked.issue_id from issue_approvals lin
order by linked.issue_id limit 1)`;
export function approvalQueueSeedingService(db: Db) {
const pending = new Map<string | undefined, { cursor?: string; generation: number }>([[undefined, { generation: 0 }]]);
const pending = new Map<string | undefined, { cursor?: string; generation: number; failures: number; retryAt: number }>([[undefined, { generation: 0, failures: 0, retryAt: 0 }]]);
function request(companyIds: ReadonlySet<string> | undefined) {
for (const companyId of companyIds ?? []) {
const existing = pending.get(companyId);
if (existing) existing.generation++;
else pending.set(companyId, { generation: 0 });
else pending.set(companyId, { generation: 0, failures: 0, retryAt: 0 });
}
}
function candidates(database: Db, companyId: string | undefined, condition?: SQL) {
@@ -24,47 +25,56 @@ export function approvalQueueSeedingService(db: Db) {
.where(and(eq(approvals.status, "pending"), eq(companies.status, "active"), companyId === undefined ? undefined : eq(approvals.companyId, companyId), condition,
sql`exists (select 1 from ${issues} where ${issues.id} = ${linkedIssue}
and ${issues.companyId} = ${approvals.companyId} and ${executionIssueCondition()}
and exists (select 1 from issue_work_products product where product.company_id = ${approvals.companyId}
and product.issue_id = ${issues.id} and product.type = 'pull_request'))`,
and exists (select 1 from ${issueWorkProducts} where ${pullRequestSeedProductCondition(approvals.companyId)}
and ${issueWorkProducts.issueId} = ${issues.id}))`,
sql`not exists (select 1 from decision_queues queue where queue.company_id = ${approvals.companyId} and queue.key = 'prs'
and (not queue.seed_rules_enabled or exists (select 1 from decision_queue_items item where item.queue_id = queue.id
and item.company_id = ${approvals.companyId} and item.source_kind = 'approval' and item.source_id = ${approvals.id}::text)))`,
)).orderBy(asc(approvals.id));
}
async function sweep(signal?: AbortSignal) {
const scope = pending.entries().next().value;
const scope = [...pending.entries()].find(([, state]) => state.retryAt <= Date.now());
if (!scope) return;
const [companyId, state] = scope;
const generation = state.generation;
const rows = await candidates(db, companyId, state.cursor ? gt(approvals.id, state.cursor) : undefined).limit(100);
const errors: unknown[] = [];
for (const row of rows) {
if (signal?.aborted) break;
try {
await db.transaction(async tx => {
const database = tx as unknown as Db;
const [current] = await candidates(database, row.companyId, eq(approvals.id, row.id)).for("update", { of: approvals });
if (!current) return;
await decisionQueueService(database).materializeSeedSources(current.companyId, [{
sourceKind: "approval", sourceId: current.id, issueId: current.issueId,
}]);
});
} catch (error) { errors.push(error); }
state.cursor = row.id;
try {
const generation = state.generation;
const rows = await candidates(db, companyId, state.cursor ? gt(approvals.id, state.cursor) : undefined).limit(100);
const errors: unknown[] = [];
for (const row of rows) {
if (signal?.aborted) break;
try {
await db.transaction(async tx => {
const database = tx as unknown as Db;
const [current] = await candidates(database, row.companyId, eq(approvals.id, row.id)).for("update", { of: approvals });
if (!current) return;
await decisionQueueService(database).materializeSeedSources(current.companyId, [{
sourceKind: "approval", sourceId: current.id, issueId: current.issueId,
}]);
});
} catch (error) { errors.push(error); }
state.cursor = row.id;
}
if (rows.length < 100) state.cursor = undefined;
const remaining = await candidates(db, companyId).limit(1);
if (!signal?.aborted && generation === state.generation && remaining.length === 0) pending.delete(companyId);
if (errors.length === 1) throw errors[0];
if (errors.length) throw new AggregateError(errors, "Approval queue seeding failed");
state.retryAt = 0;
} catch (error) {
state.failures = Math.min(state.failures + 1, 7);
state.retryAt = Date.now() + Math.min(60_000, 1_000 * 2 ** (state.failures - 1));
throw error;
} finally {
if (pending.has(companyId)) {
pending.delete(companyId);
pending.set(companyId, state);
}
}
if (rows.length < 100) state.cursor = undefined;
const remaining = await candidates(db, companyId).limit(1);
if (!signal?.aborted && generation === state.generation && remaining.length === 0) {
pending.delete(companyId);
} else {
pending.delete(companyId);
pending.set(companyId, state);
}
if (errors.length === 1) throw errors[0];
if (errors.length) throw new AggregateError(errors, "Approval queue seeding failed");
}
async function next() {
return pending.size ? Date.now() : null;
function next() {
let earliest: number | null = null;
for (const state of pending.values()) earliest = earliest === null ? state.retryAt : Math.min(earliest, state.retryAt);
return earliest;
}
return { sweep, next, request };
}
@@ -75,19 +85,20 @@ export function registerApprovalQueueSeedingWork(
canRun: () => boolean,
) {
let earliest = 0;
let next: number | null = null;
return coordinator.register(DELIVERY_QUEUES.approvalQueueSeeding, {
retryMs: 1_000,
pausePassiveMaintenance: true,
onSettled: service.request,
run: async signal => {
if (!canRun()) return;
if (Date.now() < earliest) { next = earliest; return; }
if (Date.now() < earliest) return;
earliest = Date.now() + 1_000;
await service.sweep(signal);
next = await service.next();
},
hasPending: async () => (await service.next()) !== null,
nextRunAt: () => next,
hasPending: async () => (service.next() ?? Infinity) <= Date.now(),
nextRunAt: () => {
const next = service.next();
return next === null ? null : Math.max(earliest, next);
},
});
}
@@ -0,0 +1,6 @@
import { and, eq, type SQLWrapper } from "drizzle-orm";
import { issueWorkProducts } from "@paperclipai/db";
export function pullRequestSeedProductCondition(companyId: string | SQLWrapper) {
return and(eq(issueWorkProducts.companyId, companyId), eq(issueWorkProducts.type, "pull_request"));
}
+2 -2
View File
@@ -1,3 +1,4 @@
import { pullRequestSeedProductCondition } from "./decision-queue-seed-rules.js";
import { notifyApprovalQueueWork } from "./approval-work-notifications.js";
import { and, desc, eq, inArray, isNull, sql } from "drizzle-orm";
import type { Db } from "@paperclipai/db";
@@ -402,8 +403,7 @@ export function decisionQueueService(db: Db) {
.select({ issueId: issueWorkProducts.issueId })
.from(issueWorkProducts)
.where(and(
eq(issueWorkProducts.companyId, companyId),
eq(issueWorkProducts.type, "pull_request"),
pullRequestSeedProductCondition(companyId),
inArray(issueWorkProducts.issueId, issueIds),
)).then((rows) => rows.map((row) => row.issueId)));
+1 -1
View File
@@ -45,7 +45,7 @@ function nextCron(schedule: string, now: Date): Date | null {
}
export function createPluginJobScheduler(options: PluginJobSchedulerOptions): PluginJobScheduler {
const { db, jobStore, workerManager, tickIntervalMs = 1_000,
const { db, jobStore, workerManager, tickIntervalMs = 30_000,
jobTimeoutMs = 5 * 60_000, maxConcurrentJobs = 10 } = options;
const log = logger.child({ service: "plugin-job-scheduler" });
const activeJobs = new Set<string>();
+2 -5
View File
@@ -1,3 +1,4 @@
import { finishServiceShutdown } from "../shutdown.js";
/**
* PluginLoader — discovery, installation, and runtime activation of plugins.
*
@@ -2143,11 +2144,7 @@ export function pluginLoader(
const { workerManager, jobScheduler } = runtimeServices;
// 1. Stop the job scheduler tick loop
await jobScheduler.stop();
// 2. Stop all worker processes
await workerManager.stopAll();
await finishServiceShutdown(() => jobScheduler.stop(), () => workerManager.stopAll());
log.info("plugin-loader: all plugins shut down");
},
+24
View File
@@ -5,6 +5,7 @@ import {
coordinateHeartbeatSchedulerShutdown,
drainRunExecutionFinalizersForShutdown,
finalizeServerShutdown,
finishServiceShutdown,
loadWithoutCoordinatedShutdownSignalHooks,
} from "./shutdown.js";
@@ -523,3 +524,26 @@ describe("coordinateHeartbeatSchedulerShutdown", () => {
});
});
});
describe("service shutdown failure isolation", () => {
it("awaits remaining cleanup before reporting a scheduler failure", async () => {
const failure = new Error("plugin result could not be saved");
const gate = deferred();
const cleanup = vi.fn(() => gate.promise);
let finished = false;
const stopping = finishServiceShutdown(async () => { throw failure; }, cleanup)
.then(() => { finished = true; return undefined; }, error => { finished = true; return error; });
try {
await vi.waitFor(() => expect(cleanup).toHaveBeenCalledOnce());
expect(finished).toBe(false);
} finally { gate.resolve(); }
expect(await stopping).toBe(failure);
});
it("reports both failures after attempting cleanup", async () => {
const stopFailure = new Error("scheduler failure"), cleanupFailure = new Error("worker failure");
const cleanup = vi.fn(async () => { throw cleanupFailure; });
await expect(finishServiceShutdown(async () => { throw stopFailure; }, cleanup))
.rejects.toMatchObject({ errors: [stopFailure, cleanupFailure] });
expect(cleanup).toHaveBeenCalledOnce();
});
});
+15
View File
@@ -272,3 +272,18 @@ export async function coordinateHeartbeatSchedulerShutdown<
waitedForSchedulerIdle: true,
};
}
export async function finishServiceShutdown(
stop: () => Promise<void>,
cleanup: () => Promise<void>,
): Promise<void> {
const failures: unknown[] = [];
let retryStop = false;
try { await stop(); } catch { retryStop = true; }
try { await cleanup(); } catch (error) { failures.push(error); }
if (retryStop) {
try { await stop(); } catch (error) { failures.unshift(error); }
}
if (failures.length === 1) throw failures[0];
if (failures.length > 1) throw new AggregateError(failures, "Service shutdown failed");
}