Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .changeset/ordered-barrier-safety-net.md
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
---
'@workflow/core': patch
'workflow': patch
---

Fix a replay-determinism gap where branch wake order — and therefore step correlation ids — could depend on how much of the event log an invocation had loaded, corrupting runs under concurrent replays (CORRUPTED_EVENT_LOG).
1,326 changes: 1,326 additions & 0 deletions packages/core/src/__fixtures__/wrun-41KZYJ92TP-storm-log.json

Large diffs are not rendered by default.

322 changes: 322 additions & 0 deletions packages/core/src/delivery-barrier-dispenser.test.ts
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,322 @@
/**
* Unit coverage for the barrier safety-net dispenser (`ensureBarrierSafetyNet`
* in private.ts) — the pieces of vercel/workflow#3554 that previously only
* end-to-end storm lanes exercised:
*
* 1. End-of-log suspension must not preempt deliveries parked behind an
* unclaimed buffered hook payload. The pass suspends only after the
* parked chain delivered and the woken branch made its follow-up draws
* (the regression surfaced as whole storm runs going dormant/`stuck`).
* 2. With SEVERAL parked segments, chains must wake in log order — the
* dispenser retires heads lowest-first and re-blocks while a woken chain
* drains, so the ULIDs the branches draw next are position-determined,
* not net-timing-determined.
* 3. The dispenser must survive a rejected `promiseQueue`: the registry now
* gates `isDeliveryIdle`, so a silently-dead dispenser would wedge the
* run rather than merely skip a cleanup.
*/
import { WorkflowRuntimeError } from '@workflow/errors';
import { withResolvers } from '@workflow/utils';
import type { Event } from '@workflow/world';
import * as nanoid from 'nanoid';
import { monotonicFactory } from 'ulid';
import { describe, expect, it } from 'vitest';
import { EventsConsumer } from './events-consumer.js';
import { WorkflowSuspension } from './global.js';
import {
isDeliveryIdle,
registerDeliveryBarrier,
type WorkflowOrchestratorContext,
} from './private.js';
import { dehydrateStepReturnValue } from './serialization.js';
import { createUseStep } from './step.js';
import { createStepHydrationCache } from './step-hydration-cache.js';
import { createContext } from './vm/index.js';
import { createCreateHook } from './workflow/hook.js';
import { createSleep } from './workflow/sleep.js';

const CORR_IDS = [
'01K11TFZ62YS0YYFDQ3E8B9YCV',
'01K11TFZ62YS0YYFDQ3E8B9YCW',
'01K11TFZ62YS0YYFDQ3E8B9YCX',
'01K11TFZ62YS0YYFDQ3E8B9YCY',
'01K11TFZ62YS0YYFDQ3E8B9YCZ',
];

function setupWorkflowContext(events: Event[]): WorkflowOrchestratorContext {
const context = createContext({
seed: 'test',
fixedTimestamp: 1753481739458,
});
const ulid = monotonicFactory(() => context.globalThis.Math.random());
const workflowStartedAt = context.globalThis.Date.now();
const promiseQueueHolder = { current: Promise.resolve() };
const ctxRef: { current?: WorkflowOrchestratorContext } = {};
const ctx: WorkflowOrchestratorContext = {
runId: 'wrun_test',
encryptionKey: undefined,
stepHydrationCache: createStepHydrationCache(),
globalThis: context.globalThis,
eventsConsumer: new EventsConsumer(events, {
isDeliveryIdle: () =>
ctxRef.current ? isDeliveryIdle(ctxRef.current) : true,
onUnconsumedEvent: (event) => {
ctxRef.current?.onWorkflowError(
new WorkflowRuntimeError(
`Unconsumed event: eventType=${event.eventType}, correlationId=${event.correlationId}, eventId=${event.eventId}.`
)
);
},
getPromiseQueue: () => promiseQueueHolder.current,
}),
invocationsQueue: new Map(),
generateUlid: () => ulid(workflowStartedAt),
generateNanoid: nanoid.customRandom(nanoid.urlAlphabet, 21, (size) =>
new Uint8Array(size).map(() => 256 * context.globalThis.Math.random())
),
onWorkflowError: () => {},
get promiseQueue() {
return promiseQueueHolder.current;
},
set promiseQueue(value: Promise<void>) {
promiseQueueHolder.current = value;
},
pendingDeliveries: 0,
pendingDeliveryBarriers: new Map(),
};
ctxRef.current = ctx;
return ctx;
}

async function runWithDiscontinuation(
ctx: WorkflowOrchestratorContext,
workflowFn: () => Promise<any>
): Promise<{ result?: any; error?: any }> {
const workflowDiscontinuation = withResolvers<void>();
ctx.onWorkflowError = workflowDiscontinuation.reject;
let result: any;
let error: any;
try {
result = await Promise.race([
workflowFn(),
workflowDiscontinuation.promise,
]);
} catch (err) {
error = err;
}
return { result, error };
}

function pendingStepNames(ctx: WorkflowOrchestratorContext): string[] {
return [...ctx.invocationsQueue.values()]
.filter((item) => item.type === 'step')
.map((item) => (item.type === 'step' ? item.stepName : ''));
}

const resumeAtA = new Date('2026-07-27T12:00:05.000Z');
const resumeAtB = new Date('2026-07-27T12:00:06.000Z');

describe('barrier safety-net dispenser', () => {
it('suspends only after deliveries parked behind an unclaimed payload have run', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Draw order in the body: c0 = the never-read hook, c1 = the sleep. The
// poke payload is consumed before the wait completion, so the wait's
// delivery gates on the unclaimed payload's barrier, which only the
// dispenser retires. afterSleep must still be drawn (and become the
// suspension's pending step) BEFORE the pass is allowed to suspend.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterSleep = useStep('afterSleep');
createHook({ token: 'dispenser-token' });
await sleep(resumeAtA);
await afterSleep();
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
// The wait delivered (despite parking behind the unclaimed payload) and
// the branch ran to its next draw before the suspension was raised.
expect(pendingStepNames(ctx)).toEqual(['afterSleep']);
});

it('wakes chains parked behind SEVERAL unclaimed payloads in log order', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Two parked segments: waitA parks behind the first payload, waitB
// behind both. The branches draw afterA / afterB when woken, and the
// ULIDs they draw are position-determined only if A wakes before B —
// lowest-first retirement with re-blocking. Under the per-barrier polls
// this order was scheduling noise.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_4',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_5',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_6',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterA = useStep('afterA');
const afterB = useStep('afterB');
createHook({ token: 'dispenser-token' });
await Promise.all([
(async () => {
await sleep(resumeAtA);
await afterA();
})(),
(async () => {
await sleep(resumeAtB);
await afterB();
})(),
]);
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
const pending = [...ctx.invocationsQueue.values()].filter(
(item) => item.type === 'step'
);
expect(pending.map((item) => item.stepName).sort()).toEqual([
'afterA',
'afterB',
]);
// Log order: waitA completed at evnt_4, waitB at evnt_6, so branch A
// draws first and afterA's correlation id sorts below afterB's.
const idOf = (name: string) =>
pending.find((item) => item.stepName === name)?.correlationId ?? '';
expect(idOf('afterA') < idOf('afterB')).toBe(true);
});

it('drains the registry even when the promiseQueue is rejected', async () => {
const ctx = setupWorkflowContext([]);
// One unclaimed-payload barrier that only the dispenser can retire, with
// retirement initially blocked so the dispenser has to go through its
// promiseQueue re-arm path — against a queue that is already rejected.
ctx.pendingDeliveries = 1;
const rejected = Promise.reject(new Error('poisoned queue'));
rejected.catch(() => {});
ctx.promiseQueue = rejected as Promise<void>;
const barrier = registerDeliveryBarrier(ctx, 0, 'hook', { armed: false });
void barrier; // retired by the dispenser, never marked delivered
expect(isDeliveryIdle(ctx)).toBe(false);
await new Promise((resolve) => setTimeout(resolve, 25));
// Still parked: retirement is blocked by the in-flight delivery.
expect(ctx.pendingDeliveryBarriers?.size).toBe(1);
ctx.pendingDeliveries = 0;
// The dispenser must come back from the rejected-queue backoff, retire
// the entry, and restore delivery idle so a suspension could fire.
await new Promise((resolve) => setTimeout(resolve, 200));
expect(ctx.pendingDeliveryBarriers?.size).toBe(0);
expect(isDeliveryIdle(ctx)).toBe(true);
});
});
Loading
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { // Add copy buttons to all
 blocks
(function() {
function addCopyButtons() {
document.querySelectorAll('pre code').forEach(function(codeBlock) {
if (codeBlock.parentElement.hasAttribute('data-copy-added')) return;
codeBlock.parentElement.setAttribute('data-copy-added', 'true');
var btn = document.createElement('button');
btn.textContent = 'Copy';
btn.style.cssText = 'position:absolute;top:4px;right:4px;padding:2px 8px;font-size:11px;background:#4ecdc4;border:none;border-radius:4px;color:#1a1a2e;cursor:pointer;opacity:0.7;transition:opacity 0.2s;';
btn.onmouseover = function() { this.style.opacity = '1'; };
btn.onmouseout = function() { this.style.opacity = '0.7'; };
btn.onclick = function() {
navigator.clipboard.writeText(codeBlock.textContent).then(function() {
btn.textContent = 'Copied!';
setTimeout(function() { btn.textContent = 'Copy'; }, 1500);
});
};
codeBlock.parentElement.style.position = 'relative';
codeBlock.parentElement.appendChild(btn);
});
}
addCopyButtons();
// Re-run on dynamic content
var observer = new MutationObserver(addCopyButtons);
observer.observe(document.body, { childList: true, subtree: true });
})();
}
} catch(__e) { console.warn('[Userscript:Add Copy Buttons to Code Blocks]', __e); }
})();
(function(){
try {
var __m = "github.com";
var __re = new RegExp('^' + "github\\.com" + '
Backport #3554: [core] Pin draw order to event-log order: retire delivery barriers through one ordered dispenser by github-actions[bot] · Pull Request #3629 · vercel/workflow · GitHub
Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .changeset/ordered-barrier-safety-net.md
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
---
'@workflow/core': patch
'workflow': patch
---

Fix a replay-determinism gap where branch wake order — and therefore step correlation ids — could depend on how much of the event log an invocation had loaded, corrupting runs under concurrent replays (CORRUPTED_EVENT_LOG).
1,326 changes: 1,326 additions & 0 deletions packages/core/src/__fixtures__/wrun-41KZYJ92TP-storm-log.json

Large diffs are not rendered by default.

322 changes: 322 additions & 0 deletions packages/core/src/delivery-barrier-dispenser.test.ts
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,322 @@
/**
* Unit coverage for the barrier safety-net dispenser (`ensureBarrierSafetyNet`
* in private.ts) — the pieces of vercel/workflow#3554 that previously only
* end-to-end storm lanes exercised:
*
* 1. End-of-log suspension must not preempt deliveries parked behind an
* unclaimed buffered hook payload. The pass suspends only after the
* parked chain delivered and the woken branch made its follow-up draws
* (the regression surfaced as whole storm runs going dormant/`stuck`).
* 2. With SEVERAL parked segments, chains must wake in log order — the
* dispenser retires heads lowest-first and re-blocks while a woken chain
* drains, so the ULIDs the branches draw next are position-determined,
* not net-timing-determined.
* 3. The dispenser must survive a rejected `promiseQueue`: the registry now
* gates `isDeliveryIdle`, so a silently-dead dispenser would wedge the
* run rather than merely skip a cleanup.
*/
import { WorkflowRuntimeError } from '@workflow/errors';
import { withResolvers } from '@workflow/utils';
import type { Event } from '@workflow/world';
import * as nanoid from 'nanoid';
import { monotonicFactory } from 'ulid';
import { describe, expect, it } from 'vitest';
import { EventsConsumer } from './events-consumer.js';
import { WorkflowSuspension } from './global.js';
import {
isDeliveryIdle,
registerDeliveryBarrier,
type WorkflowOrchestratorContext,
} from './private.js';
import { dehydrateStepReturnValue } from './serialization.js';
import { createUseStep } from './step.js';
import { createStepHydrationCache } from './step-hydration-cache.js';
import { createContext } from './vm/index.js';
import { createCreateHook } from './workflow/hook.js';
import { createSleep } from './workflow/sleep.js';

const CORR_IDS = [
'01K11TFZ62YS0YYFDQ3E8B9YCV',
'01K11TFZ62YS0YYFDQ3E8B9YCW',
'01K11TFZ62YS0YYFDQ3E8B9YCX',
'01K11TFZ62YS0YYFDQ3E8B9YCY',
'01K11TFZ62YS0YYFDQ3E8B9YCZ',
];

function setupWorkflowContext(events: Event[]): WorkflowOrchestratorContext {
const context = createContext({
seed: 'test',
fixedTimestamp: 1753481739458,
});
const ulid = monotonicFactory(() => context.globalThis.Math.random());
const workflowStartedAt = context.globalThis.Date.now();
const promiseQueueHolder = { current: Promise.resolve() };
const ctxRef: { current?: WorkflowOrchestratorContext } = {};
const ctx: WorkflowOrchestratorContext = {
runId: 'wrun_test',
encryptionKey: undefined,
stepHydrationCache: createStepHydrationCache(),
globalThis: context.globalThis,
eventsConsumer: new EventsConsumer(events, {
isDeliveryIdle: () =>
ctxRef.current ? isDeliveryIdle(ctxRef.current) : true,
onUnconsumedEvent: (event) => {
ctxRef.current?.onWorkflowError(
new WorkflowRuntimeError(
`Unconsumed event: eventType=${event.eventType}, correlationId=${event.correlationId}, eventId=${event.eventId}.`
)
);
},
getPromiseQueue: () => promiseQueueHolder.current,
}),
invocationsQueue: new Map(),
generateUlid: () => ulid(workflowStartedAt),
generateNanoid: nanoid.customRandom(nanoid.urlAlphabet, 21, (size) =>
new Uint8Array(size).map(() => 256 * context.globalThis.Math.random())
),
onWorkflowError: () => {},
get promiseQueue() {
return promiseQueueHolder.current;
},
set promiseQueue(value: Promise<void>) {
promiseQueueHolder.current = value;
},
pendingDeliveries: 0,
pendingDeliveryBarriers: new Map(),
};
ctxRef.current = ctx;
return ctx;
}

async function runWithDiscontinuation(
ctx: WorkflowOrchestratorContext,
workflowFn: () => Promise<any>
): Promise<{ result?: any; error?: any }> {
const workflowDiscontinuation = withResolvers<void>();
ctx.onWorkflowError = workflowDiscontinuation.reject;
let result: any;
let error: any;
try {
result = await Promise.race([
workflowFn(),
workflowDiscontinuation.promise,
]);
} catch (err) {
error = err;
}
return { result, error };
}

function pendingStepNames(ctx: WorkflowOrchestratorContext): string[] {
return [...ctx.invocationsQueue.values()]
.filter((item) => item.type === 'step')
.map((item) => (item.type === 'step' ? item.stepName : ''));
}

const resumeAtA = new Date('2026-07-27T12:00:05.000Z');
const resumeAtB = new Date('2026-07-27T12:00:06.000Z');

describe('barrier safety-net dispenser', () => {
it('suspends only after deliveries parked behind an unclaimed payload have run', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Draw order in the body: c0 = the never-read hook, c1 = the sleep. The
// poke payload is consumed before the wait completion, so the wait's
// delivery gates on the unclaimed payload's barrier, which only the
// dispenser retires. afterSleep must still be drawn (and become the
// suspension's pending step) BEFORE the pass is allowed to suspend.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterSleep = useStep('afterSleep');
createHook({ token: 'dispenser-token' });
await sleep(resumeAtA);
await afterSleep();
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
// The wait delivered (despite parking behind the unclaimed payload) and
// the branch ran to its next draw before the suspension was raised.
expect(pendingStepNames(ctx)).toEqual(['afterSleep']);
});

it('wakes chains parked behind SEVERAL unclaimed payloads in log order', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Two parked segments: waitA parks behind the first payload, waitB
// behind both. The branches draw afterA / afterB when woken, and the
// ULIDs they draw are position-determined only if A wakes before B —
// lowest-first retirement with re-blocking. Under the per-barrier polls
// this order was scheduling noise.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_4',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_5',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_6',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterA = useStep('afterA');
const afterB = useStep('afterB');
createHook({ token: 'dispenser-token' });
await Promise.all([
(async () => {
await sleep(resumeAtA);
await afterA();
})(),
(async () => {
await sleep(resumeAtB);
await afterB();
})(),
]);
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
const pending = [...ctx.invocationsQueue.values()].filter(
(item) => item.type === 'step'
);
expect(pending.map((item) => item.stepName).sort()).toEqual([
'afterA',
'afterB',
]);
// Log order: waitA completed at evnt_4, waitB at evnt_6, so branch A
// draws first and afterA's correlation id sorts below afterB's.
const idOf = (name: string) =>
pending.find((item) => item.stepName === name)?.correlationId ?? '';
expect(idOf('afterA') < idOf('afterB')).toBe(true);
});

it('drains the registry even when the promiseQueue is rejected', async () => {
const ctx = setupWorkflowContext([]);
// One unclaimed-payload barrier that only the dispenser can retire, with
// retirement initially blocked so the dispenser has to go through its
// promiseQueue re-arm path — against a queue that is already rejected.
ctx.pendingDeliveries = 1;
const rejected = Promise.reject(new Error('poisoned queue'));
rejected.catch(() => {});
ctx.promiseQueue = rejected as Promise<void>;
const barrier = registerDeliveryBarrier(ctx, 0, 'hook', { armed: false });
void barrier; // retired by the dispenser, never marked delivered
expect(isDeliveryIdle(ctx)).toBe(false);
await new Promise((resolve) => setTimeout(resolve, 25));
// Still parked: retirement is blocked by the in-flight delivery.
expect(ctx.pendingDeliveryBarriers?.size).toBe(1);
ctx.pendingDeliveries = 0;
// The dispenser must come back from the rejected-queue backoff, retire
// the entry, and restore delivery idle so a suspension could fire.
await new Promise((resolve) => setTimeout(resolve, 200));
expect(ctx.pendingDeliveryBarriers?.size).toBe(0);
expect(isDeliveryIdle(ctx)).toBe(true);
});
});
Loading
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { // Force GitHub README to respect dark mode (function() { var style = document.createElement('style'); style.textContent = ' .markdown-body { color-scheme: dark light; } .markdown-body pre { background: #161b22 !important; } .markdown-body code { background: rgba(110, 118, 129, 0.4) !important; } .markdown-body table th, .markdown-body table td { border-color: #30363d !important; } .markdown-body img { background: #0d1117; } .markdown-body blockquote { border-left-color: #8b949e; } .markdown-body hr { border-color: #30363d; } '; document.head.appendChild(style); })(); } } catch(__e) { console.warn('[Userscript:GitHub Dark Mode README Fix]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ' Backport #3554: [core] Pin draw order to event-log order: retire delivery barriers through one ordered dispenser by github-actions[bot] · Pull Request #3629 · vercel/workflow · GitHub
Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .changeset/ordered-barrier-safety-net.md
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
---
'@workflow/core': patch
'workflow': patch
---

Fix a replay-determinism gap where branch wake order — and therefore step correlation ids — could depend on how much of the event log an invocation had loaded, corrupting runs under concurrent replays (CORRUPTED_EVENT_LOG).
1,326 changes: 1,326 additions & 0 deletions packages/core/src/__fixtures__/wrun-41KZYJ92TP-storm-log.json

Large diffs are not rendered by default.

322 changes: 322 additions & 0 deletions packages/core/src/delivery-barrier-dispenser.test.ts
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,322 @@
/**
* Unit coverage for the barrier safety-net dispenser (`ensureBarrierSafetyNet`
* in private.ts) — the pieces of vercel/workflow#3554 that previously only
* end-to-end storm lanes exercised:
*
* 1. End-of-log suspension must not preempt deliveries parked behind an
* unclaimed buffered hook payload. The pass suspends only after the
* parked chain delivered and the woken branch made its follow-up draws
* (the regression surfaced as whole storm runs going dormant/`stuck`).
* 2. With SEVERAL parked segments, chains must wake in log order — the
* dispenser retires heads lowest-first and re-blocks while a woken chain
* drains, so the ULIDs the branches draw next are position-determined,
* not net-timing-determined.
* 3. The dispenser must survive a rejected `promiseQueue`: the registry now
* gates `isDeliveryIdle`, so a silently-dead dispenser would wedge the
* run rather than merely skip a cleanup.
*/
import { WorkflowRuntimeError } from '@workflow/errors';
import { withResolvers } from '@workflow/utils';
import type { Event } from '@workflow/world';
import * as nanoid from 'nanoid';
import { monotonicFactory } from 'ulid';
import { describe, expect, it } from 'vitest';
import { EventsConsumer } from './events-consumer.js';
import { WorkflowSuspension } from './global.js';
import {
isDeliveryIdle,
registerDeliveryBarrier,
type WorkflowOrchestratorContext,
} from './private.js';
import { dehydrateStepReturnValue } from './serialization.js';
import { createUseStep } from './step.js';
import { createStepHydrationCache } from './step-hydration-cache.js';
import { createContext } from './vm/index.js';
import { createCreateHook } from './workflow/hook.js';
import { createSleep } from './workflow/sleep.js';

const CORR_IDS = [
'01K11TFZ62YS0YYFDQ3E8B9YCV',
'01K11TFZ62YS0YYFDQ3E8B9YCW',
'01K11TFZ62YS0YYFDQ3E8B9YCX',
'01K11TFZ62YS0YYFDQ3E8B9YCY',
'01K11TFZ62YS0YYFDQ3E8B9YCZ',
];

function setupWorkflowContext(events: Event[]): WorkflowOrchestratorContext {
const context = createContext({
seed: 'test',
fixedTimestamp: 1753481739458,
});
const ulid = monotonicFactory(() => context.globalThis.Math.random());
const workflowStartedAt = context.globalThis.Date.now();
const promiseQueueHolder = { current: Promise.resolve() };
const ctxRef: { current?: WorkflowOrchestratorContext } = {};
const ctx: WorkflowOrchestratorContext = {
runId: 'wrun_test',
encryptionKey: undefined,
stepHydrationCache: createStepHydrationCache(),
globalThis: context.globalThis,
eventsConsumer: new EventsConsumer(events, {
isDeliveryIdle: () =>
ctxRef.current ? isDeliveryIdle(ctxRef.current) : true,
onUnconsumedEvent: (event) => {
ctxRef.current?.onWorkflowError(
new WorkflowRuntimeError(
`Unconsumed event: eventType=${event.eventType}, correlationId=${event.correlationId}, eventId=${event.eventId}.`
)
);
},
getPromiseQueue: () => promiseQueueHolder.current,
}),
invocationsQueue: new Map(),
generateUlid: () => ulid(workflowStartedAt),
generateNanoid: nanoid.customRandom(nanoid.urlAlphabet, 21, (size) =>
new Uint8Array(size).map(() => 256 * context.globalThis.Math.random())
),
onWorkflowError: () => {},
get promiseQueue() {
return promiseQueueHolder.current;
},
set promiseQueue(value: Promise<void>) {
promiseQueueHolder.current = value;
},
pendingDeliveries: 0,
pendingDeliveryBarriers: new Map(),
};
ctxRef.current = ctx;
return ctx;
}

async function runWithDiscontinuation(
ctx: WorkflowOrchestratorContext,
workflowFn: () => Promise<any>
): Promise<{ result?: any; error?: any }> {
const workflowDiscontinuation = withResolvers<void>();
ctx.onWorkflowError = workflowDiscontinuation.reject;
let result: any;
let error: any;
try {
result = await Promise.race([
workflowFn(),
workflowDiscontinuation.promise,
]);
} catch (err) {
error = err;
}
return { result, error };
}

function pendingStepNames(ctx: WorkflowOrchestratorContext): string[] {
return [...ctx.invocationsQueue.values()]
.filter((item) => item.type === 'step')
.map((item) => (item.type === 'step' ? item.stepName : ''));
}

const resumeAtA = new Date('2026-07-27T12:00:05.000Z');
const resumeAtB = new Date('2026-07-27T12:00:06.000Z');

describe('barrier safety-net dispenser', () => {
it('suspends only after deliveries parked behind an unclaimed payload have run', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Draw order in the body: c0 = the never-read hook, c1 = the sleep. The
// poke payload is consumed before the wait completion, so the wait's
// delivery gates on the unclaimed payload's barrier, which only the
// dispenser retires. afterSleep must still be drawn (and become the
// suspension's pending step) BEFORE the pass is allowed to suspend.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterSleep = useStep('afterSleep');
createHook({ token: 'dispenser-token' });
await sleep(resumeAtA);
await afterSleep();
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
// The wait delivered (despite parking behind the unclaimed payload) and
// the branch ran to its next draw before the suspension was raised.
expect(pendingStepNames(ctx)).toEqual(['afterSleep']);
});

it('wakes chains parked behind SEVERAL unclaimed payloads in log order', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Two parked segments: waitA parks behind the first payload, waitB
// behind both. The branches draw afterA / afterB when woken, and the
// ULIDs they draw are position-determined only if A wakes before B —
// lowest-first retirement with re-blocking. Under the per-barrier polls
// this order was scheduling noise.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_4',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_5',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_6',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterA = useStep('afterA');
const afterB = useStep('afterB');
createHook({ token: 'dispenser-token' });
await Promise.all([
(async () => {
await sleep(resumeAtA);
await afterA();
})(),
(async () => {
await sleep(resumeAtB);
await afterB();
})(),
]);
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
const pending = [...ctx.invocationsQueue.values()].filter(
(item) => item.type === 'step'
);
expect(pending.map((item) => item.stepName).sort()).toEqual([
'afterA',
'afterB',
]);
// Log order: waitA completed at evnt_4, waitB at evnt_6, so branch A
// draws first and afterA's correlation id sorts below afterB's.
const idOf = (name: string) =>
pending.find((item) => item.stepName === name)?.correlationId ?? '';
expect(idOf('afterA') < idOf('afterB')).toBe(true);
});

it('drains the registry even when the promiseQueue is rejected', async () => {
const ctx = setupWorkflowContext([]);
// One unclaimed-payload barrier that only the dispenser can retire, with
// retirement initially blocked so the dispenser has to go through its
// promiseQueue re-arm path — against a queue that is already rejected.
ctx.pendingDeliveries = 1;
const rejected = Promise.reject(new Error('poisoned queue'));
rejected.catch(() => {});
ctx.promiseQueue = rejected as Promise<void>;
const barrier = registerDeliveryBarrier(ctx, 0, 'hook', { armed: false });
void barrier; // retired by the dispenser, never marked delivered
expect(isDeliveryIdle(ctx)).toBe(false);
await new Promise((resolve) => setTimeout(resolve, 25));
// Still parked: retirement is blocked by the in-flight delivery.
expect(ctx.pendingDeliveryBarriers?.size).toBe(1);
ctx.pendingDeliveries = 0;
// The dispenser must come back from the rejected-queue backoff, retire
// the entry, and restore delivery idle so a suspension could fire.
await new Promise((resolve) => setTimeout(resolve, 200));
expect(ctx.pendingDeliveryBarriers?.size).toBe(0);
expect(isDeliveryIdle(ctx)).toBe(true);
});
});
Loading
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { // Highlight search terms from Google/DuckDuckGo/Bing referrer (function() { var ref = document.referrer; var terms = []; if (ref.includes('google.com') || ref.includes('duckduckgo.com') || ref.includes('bing.com')) { var url = new URL(ref); var q = url.searchParams.get('q') || url.searchParams.get('p'); if (q) { terms = q.split(/\s+/).filter(function(t) { return t.length > 2; }); } } if (terms.length === 0) return; var style = document.createElement('style'); style.textContent = '.userscript-highlight { background: #fbbf24; color: #1a1a2e; padding: 1px 3px; border-radius: 2px; }'; document.head.appendChild(style); function highlight(node) { if (node.nodeType === 3) { // text node var text = node.textContent; var found = false; terms.forEach(function(term) { var regex = new RegExp('(' + term.replace(/[.*+?^${}()|[\]\\]/g, '\\') + ')', 'gi'); if (regex.test(text)) { found = true; var frag = document.createDocumentFragment(); var parts = text.split(regex); parts.forEach(function(part, i) { if (i % 2 === 0) { frag.appendChild(document.createTextNode(part)); } else { var span = document.createElement('span'); span.className = 'userscript-highlight'; span.textContent = part; frag.appendChild(span); } }); node.parentNode.replaceChild(frag, node); } }); } else if (node.nodeType === 1 && node.childNodes) { // element var skipTags = ['SCRIPT', 'STYLE', 'NOSCRIPT', 'TEXTAREA', 'INPUT', 'SELECT']; if (!skipTags.includes(node.tagName)) { Array.from(node.childNodes).forEach(highlight); } } } highlight(document.body); // Re-highlight on dynamic content var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1 || node.nodeType === 3) highlight(node); }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Highlight Search Terms]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ' Backport #3554: [core] Pin draw order to event-log order: retire delivery barriers through one ordered dispenser by github-actions[bot] · Pull Request #3629 · vercel/workflow · GitHub
Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .changeset/ordered-barrier-safety-net.md
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
---
'@workflow/core': patch
'workflow': patch
---

Fix a replay-determinism gap where branch wake order — and therefore step correlation ids — could depend on how much of the event log an invocation had loaded, corrupting runs under concurrent replays (CORRUPTED_EVENT_LOG).
1,326 changes: 1,326 additions & 0 deletions packages/core/src/__fixtures__/wrun-41KZYJ92TP-storm-log.json

Large diffs are not rendered by default.

322 changes: 322 additions & 0 deletions packages/core/src/delivery-barrier-dispenser.test.ts
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,322 @@
/**
* Unit coverage for the barrier safety-net dispenser (`ensureBarrierSafetyNet`
* in private.ts) — the pieces of vercel/workflow#3554 that previously only
* end-to-end storm lanes exercised:
*
* 1. End-of-log suspension must not preempt deliveries parked behind an
* unclaimed buffered hook payload. The pass suspends only after the
* parked chain delivered and the woken branch made its follow-up draws
* (the regression surfaced as whole storm runs going dormant/`stuck`).
* 2. With SEVERAL parked segments, chains must wake in log order — the
* dispenser retires heads lowest-first and re-blocks while a woken chain
* drains, so the ULIDs the branches draw next are position-determined,
* not net-timing-determined.
* 3. The dispenser must survive a rejected `promiseQueue`: the registry now
* gates `isDeliveryIdle`, so a silently-dead dispenser would wedge the
* run rather than merely skip a cleanup.
*/
import { WorkflowRuntimeError } from '@workflow/errors';
import { withResolvers } from '@workflow/utils';
import type { Event } from '@workflow/world';
import * as nanoid from 'nanoid';
import { monotonicFactory } from 'ulid';
import { describe, expect, it } from 'vitest';
import { EventsConsumer } from './events-consumer.js';
import { WorkflowSuspension } from './global.js';
import {
isDeliveryIdle,
registerDeliveryBarrier,
type WorkflowOrchestratorContext,
} from './private.js';
import { dehydrateStepReturnValue } from './serialization.js';
import { createUseStep } from './step.js';
import { createStepHydrationCache } from './step-hydration-cache.js';
import { createContext } from './vm/index.js';
import { createCreateHook } from './workflow/hook.js';
import { createSleep } from './workflow/sleep.js';

const CORR_IDS = [
'01K11TFZ62YS0YYFDQ3E8B9YCV',
'01K11TFZ62YS0YYFDQ3E8B9YCW',
'01K11TFZ62YS0YYFDQ3E8B9YCX',
'01K11TFZ62YS0YYFDQ3E8B9YCY',
'01K11TFZ62YS0YYFDQ3E8B9YCZ',
];

function setupWorkflowContext(events: Event[]): WorkflowOrchestratorContext {
const context = createContext({
seed: 'test',
fixedTimestamp: 1753481739458,
});
const ulid = monotonicFactory(() => context.globalThis.Math.random());
const workflowStartedAt = context.globalThis.Date.now();
const promiseQueueHolder = { current: Promise.resolve() };
const ctxRef: { current?: WorkflowOrchestratorContext } = {};
const ctx: WorkflowOrchestratorContext = {
runId: 'wrun_test',
encryptionKey: undefined,
stepHydrationCache: createStepHydrationCache(),
globalThis: context.globalThis,
eventsConsumer: new EventsConsumer(events, {
isDeliveryIdle: () =>
ctxRef.current ? isDeliveryIdle(ctxRef.current) : true,
onUnconsumedEvent: (event) => {
ctxRef.current?.onWorkflowError(
new WorkflowRuntimeError(
`Unconsumed event: eventType=${event.eventType}, correlationId=${event.correlationId}, eventId=${event.eventId}.`
)
);
},
getPromiseQueue: () => promiseQueueHolder.current,
}),
invocationsQueue: new Map(),
generateUlid: () => ulid(workflowStartedAt),
generateNanoid: nanoid.customRandom(nanoid.urlAlphabet, 21, (size) =>
new Uint8Array(size).map(() => 256 * context.globalThis.Math.random())
),
onWorkflowError: () => {},
get promiseQueue() {
return promiseQueueHolder.current;
},
set promiseQueue(value: Promise<void>) {
promiseQueueHolder.current = value;
},
pendingDeliveries: 0,
pendingDeliveryBarriers: new Map(),
};
ctxRef.current = ctx;
return ctx;
}

async function runWithDiscontinuation(
ctx: WorkflowOrchestratorContext,
workflowFn: () => Promise<any>
): Promise<{ result?: any; error?: any }> {
const workflowDiscontinuation = withResolvers<void>();
ctx.onWorkflowError = workflowDiscontinuation.reject;
let result: any;
let error: any;
try {
result = await Promise.race([
workflowFn(),
workflowDiscontinuation.promise,
]);
} catch (err) {
error = err;
}
return { result, error };
}

function pendingStepNames(ctx: WorkflowOrchestratorContext): string[] {
return [...ctx.invocationsQueue.values()]
.filter((item) => item.type === 'step')
.map((item) => (item.type === 'step' ? item.stepName : ''));
}

const resumeAtA = new Date('2026-07-27T12:00:05.000Z');
const resumeAtB = new Date('2026-07-27T12:00:06.000Z');

describe('barrier safety-net dispenser', () => {
it('suspends only after deliveries parked behind an unclaimed payload have run', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Draw order in the body: c0 = the never-read hook, c1 = the sleep. The
// poke payload is consumed before the wait completion, so the wait's
// delivery gates on the unclaimed payload's barrier, which only the
// dispenser retires. afterSleep must still be drawn (and become the
// suspension's pending step) BEFORE the pass is allowed to suspend.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterSleep = useStep('afterSleep');
createHook({ token: 'dispenser-token' });
await sleep(resumeAtA);
await afterSleep();
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
// The wait delivered (despite parking behind the unclaimed payload) and
// the branch ran to its next draw before the suspension was raised.
expect(pendingStepNames(ctx)).toEqual(['afterSleep']);
});

it('wakes chains parked behind SEVERAL unclaimed payloads in log order', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Two parked segments: waitA parks behind the first payload, waitB
// behind both. The branches draw afterA / afterB when woken, and the
// ULIDs they draw are position-determined only if A wakes before B —
// lowest-first retirement with re-blocking. Under the per-barrier polls
// this order was scheduling noise.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_4',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_5',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_6',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterA = useStep('afterA');
const afterB = useStep('afterB');
createHook({ token: 'dispenser-token' });
await Promise.all([
(async () => {
await sleep(resumeAtA);
await afterA();
})(),
(async () => {
await sleep(resumeAtB);
await afterB();
})(),
]);
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
const pending = [...ctx.invocationsQueue.values()].filter(
(item) => item.type === 'step'
);
expect(pending.map((item) => item.stepName).sort()).toEqual([
'afterA',
'afterB',
]);
// Log order: waitA completed at evnt_4, waitB at evnt_6, so branch A
// draws first and afterA's correlation id sorts below afterB's.
const idOf = (name: string) =>
pending.find((item) => item.stepName === name)?.correlationId ?? '';
expect(idOf('afterA') < idOf('afterB')).toBe(true);
});

it('drains the registry even when the promiseQueue is rejected', async () => {
const ctx = setupWorkflowContext([]);
// One unclaimed-payload barrier that only the dispenser can retire, with
// retirement initially blocked so the dispenser has to go through its
// promiseQueue re-arm path — against a queue that is already rejected.
ctx.pendingDeliveries = 1;
const rejected = Promise.reject(new Error('poisoned queue'));
rejected.catch(() => {});
ctx.promiseQueue = rejected as Promise<void>;
const barrier = registerDeliveryBarrier(ctx, 0, 'hook', { armed: false });
void barrier; // retired by the dispenser, never marked delivered
expect(isDeliveryIdle(ctx)).toBe(false);
await new Promise((resolve) => setTimeout(resolve, 25));
// Still parked: retirement is blocked by the in-flight delivery.
expect(ctx.pendingDeliveryBarriers?.size).toBe(1);
ctx.pendingDeliveries = 0;
// The dispenser must come back from the rejected-queue backoff, retire
// the entry, and restore delivery idle so a suspension could fire.
await new Promise((resolve) => setTimeout(resolve, 200));
expect(ctx.pendingDeliveryBarriers?.size).toBe(0);
expect(isDeliveryIdle(ctx)).toBe(true);
});
});
Loading
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { // Strip utm_, fbclid, gclid, etc. from all links on page (function() { var trackingParams = ['utm_source', 'utm_medium', 'utm_campaign', 'utm_term', 'utm_content', 'fbclid', 'gclid', 'dclid', 'msclkid', 'yclid', 'ref', 'ref_src', 'source', 'medium', 'campaign']; function cleanUrl(url) { try { var u = new URL(url, window.location.origin); var changed = false; trackingParams.forEach(function(p) { if (u.searchParams.has(p)) { u.searchParams.delete(p); changed = true; } }); return changed ? u.toString() : url; } catch (e) { return url; } } function cleanLinks() { document.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } cleanLinks(); var observer = new MutationObserver(function(mutations) { mutations.forEach(function(m) { m.addedNodes.forEach(function(node) { if (node.nodeType === 1) { if (node.tagName === 'A') cleanLinks(); node.querySelectorAll('a[href]').forEach(function(a) { var clean = cleanUrl(a.href); if (clean !== a.href) a.href = clean; }); } }); }); }); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:Remove Tracking Parameters from Links]', __e); } })(); (function(){ try { var __m = "youtube.com"; var __re = new RegExp('^' + "youtube\\.com" + ' Backport #3554: [core] Pin draw order to event-log order: retire delivery barriers through one ordered dispenser by github-actions[bot] · Pull Request #3629 · vercel/workflow · GitHub
Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .changeset/ordered-barrier-safety-net.md
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
---
'@workflow/core': patch
'workflow': patch
---

Fix a replay-determinism gap where branch wake order — and therefore step correlation ids — could depend on how much of the event log an invocation had loaded, corrupting runs under concurrent replays (CORRUPTED_EVENT_LOG).
1,326 changes: 1,326 additions & 0 deletions packages/core/src/__fixtures__/wrun-41KZYJ92TP-storm-log.json

Large diffs are not rendered by default.

322 changes: 322 additions & 0 deletions packages/core/src/delivery-barrier-dispenser.test.ts
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,322 @@
/**
* Unit coverage for the barrier safety-net dispenser (`ensureBarrierSafetyNet`
* in private.ts) — the pieces of vercel/workflow#3554 that previously only
* end-to-end storm lanes exercised:
*
* 1. End-of-log suspension must not preempt deliveries parked behind an
* unclaimed buffered hook payload. The pass suspends only after the
* parked chain delivered and the woken branch made its follow-up draws
* (the regression surfaced as whole storm runs going dormant/`stuck`).
* 2. With SEVERAL parked segments, chains must wake in log order — the
* dispenser retires heads lowest-first and re-blocks while a woken chain
* drains, so the ULIDs the branches draw next are position-determined,
* not net-timing-determined.
* 3. The dispenser must survive a rejected `promiseQueue`: the registry now
* gates `isDeliveryIdle`, so a silently-dead dispenser would wedge the
* run rather than merely skip a cleanup.
*/
import { WorkflowRuntimeError } from '@workflow/errors';
import { withResolvers } from '@workflow/utils';
import type { Event } from '@workflow/world';
import * as nanoid from 'nanoid';
import { monotonicFactory } from 'ulid';
import { describe, expect, it } from 'vitest';
import { EventsConsumer } from './events-consumer.js';
import { WorkflowSuspension } from './global.js';
import {
isDeliveryIdle,
registerDeliveryBarrier,
type WorkflowOrchestratorContext,
} from './private.js';
import { dehydrateStepReturnValue } from './serialization.js';
import { createUseStep } from './step.js';
import { createStepHydrationCache } from './step-hydration-cache.js';
import { createContext } from './vm/index.js';
import { createCreateHook } from './workflow/hook.js';
import { createSleep } from './workflow/sleep.js';

const CORR_IDS = [
'01K11TFZ62YS0YYFDQ3E8B9YCV',
'01K11TFZ62YS0YYFDQ3E8B9YCW',
'01K11TFZ62YS0YYFDQ3E8B9YCX',
'01K11TFZ62YS0YYFDQ3E8B9YCY',
'01K11TFZ62YS0YYFDQ3E8B9YCZ',
];

function setupWorkflowContext(events: Event[]): WorkflowOrchestratorContext {
const context = createContext({
seed: 'test',
fixedTimestamp: 1753481739458,
});
const ulid = monotonicFactory(() => context.globalThis.Math.random());
const workflowStartedAt = context.globalThis.Date.now();
const promiseQueueHolder = { current: Promise.resolve() };
const ctxRef: { current?: WorkflowOrchestratorContext } = {};
const ctx: WorkflowOrchestratorContext = {
runId: 'wrun_test',
encryptionKey: undefined,
stepHydrationCache: createStepHydrationCache(),
globalThis: context.globalThis,
eventsConsumer: new EventsConsumer(events, {
isDeliveryIdle: () =>
ctxRef.current ? isDeliveryIdle(ctxRef.current) : true,
onUnconsumedEvent: (event) => {
ctxRef.current?.onWorkflowError(
new WorkflowRuntimeError(
`Unconsumed event: eventType=${event.eventType}, correlationId=${event.correlationId}, eventId=${event.eventId}.`
)
);
},
getPromiseQueue: () => promiseQueueHolder.current,
}),
invocationsQueue: new Map(),
generateUlid: () => ulid(workflowStartedAt),
generateNanoid: nanoid.customRandom(nanoid.urlAlphabet, 21, (size) =>
new Uint8Array(size).map(() => 256 * context.globalThis.Math.random())
),
onWorkflowError: () => {},
get promiseQueue() {
return promiseQueueHolder.current;
},
set promiseQueue(value: Promise<void>) {
promiseQueueHolder.current = value;
},
pendingDeliveries: 0,
pendingDeliveryBarriers: new Map(),
};
ctxRef.current = ctx;
return ctx;
}

async function runWithDiscontinuation(
ctx: WorkflowOrchestratorContext,
workflowFn: () => Promise<any>
): Promise<{ result?: any; error?: any }> {
const workflowDiscontinuation = withResolvers<void>();
ctx.onWorkflowError = workflowDiscontinuation.reject;
let result: any;
let error: any;
try {
result = await Promise.race([
workflowFn(),
workflowDiscontinuation.promise,
]);
} catch (err) {
error = err;
}
return { result, error };
}

function pendingStepNames(ctx: WorkflowOrchestratorContext): string[] {
return [...ctx.invocationsQueue.values()]
.filter((item) => item.type === 'step')
.map((item) => (item.type === 'step' ? item.stepName : ''));
}

const resumeAtA = new Date('2026-07-27T12:00:05.000Z');
const resumeAtB = new Date('2026-07-27T12:00:06.000Z');

describe('barrier safety-net dispenser', () => {
it('suspends only after deliveries parked behind an unclaimed payload have run', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Draw order in the body: c0 = the never-read hook, c1 = the sleep. The
// poke payload is consumed before the wait completion, so the wait's
// delivery gates on the unclaimed payload's barrier, which only the
// dispenser retires. afterSleep must still be drawn (and become the
// suspension's pending step) BEFORE the pass is allowed to suspend.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterSleep = useStep('afterSleep');
createHook({ token: 'dispenser-token' });
await sleep(resumeAtA);
await afterSleep();
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
// The wait delivered (despite parking behind the unclaimed payload) and
// the branch ran to its next draw before the suspension was raised.
expect(pendingStepNames(ctx)).toEqual(['afterSleep']);
});

it('wakes chains parked behind SEVERAL unclaimed payloads in log order', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Two parked segments: waitA parks behind the first payload, waitB
// behind both. The branches draw afterA / afterB when woken, and the
// ULIDs they draw are position-determined only if A wakes before B —
// lowest-first retirement with re-blocking. Under the per-barrier polls
// this order was scheduling noise.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_4',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_5',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_6',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterA = useStep('afterA');
const afterB = useStep('afterB');
createHook({ token: 'dispenser-token' });
await Promise.all([
(async () => {
await sleep(resumeAtA);
await afterA();
})(),
(async () => {
await sleep(resumeAtB);
await afterB();
})(),
]);
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
const pending = [...ctx.invocationsQueue.values()].filter(
(item) => item.type === 'step'
);
expect(pending.map((item) => item.stepName).sort()).toEqual([
'afterA',
'afterB',
]);
// Log order: waitA completed at evnt_4, waitB at evnt_6, so branch A
// draws first and afterA's correlation id sorts below afterB's.
const idOf = (name: string) =>
pending.find((item) => item.stepName === name)?.correlationId ?? '';
expect(idOf('afterA') < idOf('afterB')).toBe(true);
});

it('drains the registry even when the promiseQueue is rejected', async () => {
const ctx = setupWorkflowContext([]);
// One unclaimed-payload barrier that only the dispenser can retire, with
// retirement initially blocked so the dispenser has to go through its
// promiseQueue re-arm path — against a queue that is already rejected.
ctx.pendingDeliveries = 1;
const rejected = Promise.reject(new Error('poisoned queue'));
rejected.catch(() => {});
ctx.promiseQueue = rejected as Promise<void>;
const barrier = registerDeliveryBarrier(ctx, 0, 'hook', { armed: false });
void barrier; // retired by the dispenser, never marked delivered
expect(isDeliveryIdle(ctx)).toBe(false);
await new Promise((resolve) => setTimeout(resolve, 25));
// Still parked: retirement is blocked by the in-flight delivery.
expect(ctx.pendingDeliveryBarriers?.size).toBe(1);
ctx.pendingDeliveries = 0;
// The dispenser must come back from the rejected-queue backoff, retire
// the entry, and restore delivery idle so a suspension could fire.
await new Promise((resolve) => setTimeout(resolve, 200));
expect(ctx.pendingDeliveryBarriers?.size).toBe(0);
expect(isDeliveryIdle(ctx)).toBe(true);
});
});
Loading
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { // Auto-enable theater mode on YouTube (function() { function tryTheater() { var btn = document.querySelector('button[aria-label="Theater mode"], ytd-player #player button[title="Theater mode"]'); if (btn && !btn.classList.contains('activated')) { btn.click(); } } // Try immediately tryTheater(); // Try after navigation (SPA) var lastUrl = location.href; setInterval(function() { if (location.href !== lastUrl) { lastUrl = location.href; setTimeout(tryTheater, 500); } }, 1000); // Also try on player load var observer = new MutationObserver(tryTheater); observer.observe(document.body, { childList: true, subtree: true }); })(); } } catch(__e) { console.warn('[Userscript:YouTube Theater Mode Default]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ' Backport #3554: [core] Pin draw order to event-log order: retire delivery barriers through one ordered dispenser by github-actions[bot] · Pull Request #3629 · vercel/workflow · GitHub
Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .changeset/ordered-barrier-safety-net.md
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
---
'@workflow/core': patch
'workflow': patch
---

Fix a replay-determinism gap where branch wake order — and therefore step correlation ids — could depend on how much of the event log an invocation had loaded, corrupting runs under concurrent replays (CORRUPTED_EVENT_LOG).
1,326 changes: 1,326 additions & 0 deletions packages/core/src/__fixtures__/wrun-41KZYJ92TP-storm-log.json

Large diffs are not rendered by default.

322 changes: 322 additions & 0 deletions packages/core/src/delivery-barrier-dispenser.test.ts
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,322 @@
/**
* Unit coverage for the barrier safety-net dispenser (`ensureBarrierSafetyNet`
* in private.ts) — the pieces of vercel/workflow#3554 that previously only
* end-to-end storm lanes exercised:
*
* 1. End-of-log suspension must not preempt deliveries parked behind an
* unclaimed buffered hook payload. The pass suspends only after the
* parked chain delivered and the woken branch made its follow-up draws
* (the regression surfaced as whole storm runs going dormant/`stuck`).
* 2. With SEVERAL parked segments, chains must wake in log order — the
* dispenser retires heads lowest-first and re-blocks while a woken chain
* drains, so the ULIDs the branches draw next are position-determined,
* not net-timing-determined.
* 3. The dispenser must survive a rejected `promiseQueue`: the registry now
* gates `isDeliveryIdle`, so a silently-dead dispenser would wedge the
* run rather than merely skip a cleanup.
*/
import { WorkflowRuntimeError } from '@workflow/errors';
import { withResolvers } from '@workflow/utils';
import type { Event } from '@workflow/world';
import * as nanoid from 'nanoid';
import { monotonicFactory } from 'ulid';
import { describe, expect, it } from 'vitest';
import { EventsConsumer } from './events-consumer.js';
import { WorkflowSuspension } from './global.js';
import {
isDeliveryIdle,
registerDeliveryBarrier,
type WorkflowOrchestratorContext,
} from './private.js';
import { dehydrateStepReturnValue } from './serialization.js';
import { createUseStep } from './step.js';
import { createStepHydrationCache } from './step-hydration-cache.js';
import { createContext } from './vm/index.js';
import { createCreateHook } from './workflow/hook.js';
import { createSleep } from './workflow/sleep.js';

const CORR_IDS = [
'01K11TFZ62YS0YYFDQ3E8B9YCV',
'01K11TFZ62YS0YYFDQ3E8B9YCW',
'01K11TFZ62YS0YYFDQ3E8B9YCX',
'01K11TFZ62YS0YYFDQ3E8B9YCY',
'01K11TFZ62YS0YYFDQ3E8B9YCZ',
];

function setupWorkflowContext(events: Event[]): WorkflowOrchestratorContext {
const context = createContext({
seed: 'test',
fixedTimestamp: 1753481739458,
});
const ulid = monotonicFactory(() => context.globalThis.Math.random());
const workflowStartedAt = context.globalThis.Date.now();
const promiseQueueHolder = { current: Promise.resolve() };
const ctxRef: { current?: WorkflowOrchestratorContext } = {};
const ctx: WorkflowOrchestratorContext = {
runId: 'wrun_test',
encryptionKey: undefined,
stepHydrationCache: createStepHydrationCache(),
globalThis: context.globalThis,
eventsConsumer: new EventsConsumer(events, {
isDeliveryIdle: () =>
ctxRef.current ? isDeliveryIdle(ctxRef.current) : true,
onUnconsumedEvent: (event) => {
ctxRef.current?.onWorkflowError(
new WorkflowRuntimeError(
`Unconsumed event: eventType=${event.eventType}, correlationId=${event.correlationId}, eventId=${event.eventId}.`
)
);
},
getPromiseQueue: () => promiseQueueHolder.current,
}),
invocationsQueue: new Map(),
generateUlid: () => ulid(workflowStartedAt),
generateNanoid: nanoid.customRandom(nanoid.urlAlphabet, 21, (size) =>
new Uint8Array(size).map(() => 256 * context.globalThis.Math.random())
),
onWorkflowError: () => {},
get promiseQueue() {
return promiseQueueHolder.current;
},
set promiseQueue(value: Promise<void>) {
promiseQueueHolder.current = value;
},
pendingDeliveries: 0,
pendingDeliveryBarriers: new Map(),
};
ctxRef.current = ctx;
return ctx;
}

async function runWithDiscontinuation(
ctx: WorkflowOrchestratorContext,
workflowFn: () => Promise<any>
): Promise<{ result?: any; error?: any }> {
const workflowDiscontinuation = withResolvers<void>();
ctx.onWorkflowError = workflowDiscontinuation.reject;
let result: any;
let error: any;
try {
result = await Promise.race([
workflowFn(),
workflowDiscontinuation.promise,
]);
} catch (err) {
error = err;
}
return { result, error };
}

function pendingStepNames(ctx: WorkflowOrchestratorContext): string[] {
return [...ctx.invocationsQueue.values()]
.filter((item) => item.type === 'step')
.map((item) => (item.type === 'step' ? item.stepName : ''));
}

const resumeAtA = new Date('2026-07-27T12:00:05.000Z');
const resumeAtB = new Date('2026-07-27T12:00:06.000Z');

describe('barrier safety-net dispenser', () => {
it('suspends only after deliveries parked behind an unclaimed payload have run', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Draw order in the body: c0 = the never-read hook, c1 = the sleep. The
// poke payload is consumed before the wait completion, so the wait's
// delivery gates on the unclaimed payload's barrier, which only the
// dispenser retires. afterSleep must still be drawn (and become the
// suspension's pending step) BEFORE the pass is allowed to suspend.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterSleep = useStep('afterSleep');
createHook({ token: 'dispenser-token' });
await sleep(resumeAtA);
await afterSleep();
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
// The wait delivered (despite parking behind the unclaimed payload) and
// the branch ran to its next draw before the suspension was raised.
expect(pendingStepNames(ctx)).toEqual(['afterSleep']);
});

it('wakes chains parked behind SEVERAL unclaimed payloads in log order', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Two parked segments: waitA parks behind the first payload, waitB
// behind both. The branches draw afterA / afterB when woken, and the
// ULIDs they draw are position-determined only if A wakes before B —
// lowest-first retirement with re-blocking. Under the per-barrier polls
// this order was scheduling noise.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_4',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_5',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_6',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterA = useStep('afterA');
const afterB = useStep('afterB');
createHook({ token: 'dispenser-token' });
await Promise.all([
(async () => {
await sleep(resumeAtA);
await afterA();
})(),
(async () => {
await sleep(resumeAtB);
await afterB();
})(),
]);
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
const pending = [...ctx.invocationsQueue.values()].filter(
(item) => item.type === 'step'
);
expect(pending.map((item) => item.stepName).sort()).toEqual([
'afterA',
'afterB',
]);
// Log order: waitA completed at evnt_4, waitB at evnt_6, so branch A
// draws first and afterA's correlation id sorts below afterB's.
const idOf = (name: string) =>
pending.find((item) => item.stepName === name)?.correlationId ?? '';
expect(idOf('afterA') < idOf('afterB')).toBe(true);
});

it('drains the registry even when the promiseQueue is rejected', async () => {
const ctx = setupWorkflowContext([]);
// One unclaimed-payload barrier that only the dispenser can retire, with
// retirement initially blocked so the dispenser has to go through its
// promiseQueue re-arm path — against a queue that is already rejected.
ctx.pendingDeliveries = 1;
const rejected = Promise.reject(new Error('poisoned queue'));
rejected.catch(() => {});
ctx.promiseQueue = rejected as Promise<void>;
const barrier = registerDeliveryBarrier(ctx, 0, 'hook', { armed: false });
void barrier; // retired by the dispenser, never marked delivered
expect(isDeliveryIdle(ctx)).toBe(false);
await new Promise((resolve) => setTimeout(resolve, 25));
// Still parked: retirement is blocked by the in-flight delivery.
expect(ctx.pendingDeliveryBarriers?.size).toBe(1);
ctx.pendingDeliveries = 0;
// The dispenser must come back from the rejected-queue backoff, retire
// the entry, and restore delivery idle so a suspension could fire.
await new Promise((resolve) => setTimeout(resolve, 200));
expect(ctx.pendingDeliveryBarriers?.size).toBe(0);
expect(isDeliveryIdle(ctx)).toBe(true);
});
});
Loading
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { // Remove or un-stick sticky/fixed headers that block content (function() { function unstick() { document.querySelectorAll('header, nav, [role="banner"], .header, .navbar, .sticky, .fixed-top, [style*="position: fixed"], [style*="position:sticky"]').forEach(function(el) { if (el.style.position === 'fixed' || el.style.position === 'sticky' || getComputedStyle(el).position === 'fixed' || getComputedStyle(el).position === 'sticky') { el.style.position = 'static'; el.style.top = 'auto'; el.style.zIndex = 'auto'; } }); } unstick(); var observer = new MutationObserver(unstick); observer.observe(document.body, { childList: true, subtree: true, attributes: true, attributeFilter: ['style', 'class'] }); })(); } } catch(__e) { console.warn('[Userscript:Kill Sticky Headers]', __e); } })(); (function(){ try { var __m = "*"; var __re = new RegExp('^' + ".*" + ' Backport #3554: [core] Pin draw order to event-log order: retire delivery barriers through one ordered dispenser by github-actions[bot] · Pull Request #3629 · vercel/workflow · GitHub
Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .changeset/ordered-barrier-safety-net.md
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
---
'@workflow/core': patch
'workflow': patch
---

Fix a replay-determinism gap where branch wake order — and therefore step correlation ids — could depend on how much of the event log an invocation had loaded, corrupting runs under concurrent replays (CORRUPTED_EVENT_LOG).
1,326 changes: 1,326 additions & 0 deletions packages/core/src/__fixtures__/wrun-41KZYJ92TP-storm-log.json

Large diffs are not rendered by default.

322 changes: 322 additions & 0 deletions packages/core/src/delivery-barrier-dispenser.test.ts
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,322 @@
/**
* Unit coverage for the barrier safety-net dispenser (`ensureBarrierSafetyNet`
* in private.ts) — the pieces of vercel/workflow#3554 that previously only
* end-to-end storm lanes exercised:
*
* 1. End-of-log suspension must not preempt deliveries parked behind an
* unclaimed buffered hook payload. The pass suspends only after the
* parked chain delivered and the woken branch made its follow-up draws
* (the regression surfaced as whole storm runs going dormant/`stuck`).
* 2. With SEVERAL parked segments, chains must wake in log order — the
* dispenser retires heads lowest-first and re-blocks while a woken chain
* drains, so the ULIDs the branches draw next are position-determined,
* not net-timing-determined.
* 3. The dispenser must survive a rejected `promiseQueue`: the registry now
* gates `isDeliveryIdle`, so a silently-dead dispenser would wedge the
* run rather than merely skip a cleanup.
*/
import { WorkflowRuntimeError } from '@workflow/errors';
import { withResolvers } from '@workflow/utils';
import type { Event } from '@workflow/world';
import * as nanoid from 'nanoid';
import { monotonicFactory } from 'ulid';
import { describe, expect, it } from 'vitest';
import { EventsConsumer } from './events-consumer.js';
import { WorkflowSuspension } from './global.js';
import {
isDeliveryIdle,
registerDeliveryBarrier,
type WorkflowOrchestratorContext,
} from './private.js';
import { dehydrateStepReturnValue } from './serialization.js';
import { createUseStep } from './step.js';
import { createStepHydrationCache } from './step-hydration-cache.js';
import { createContext } from './vm/index.js';
import { createCreateHook } from './workflow/hook.js';
import { createSleep } from './workflow/sleep.js';

const CORR_IDS = [
'01K11TFZ62YS0YYFDQ3E8B9YCV',
'01K11TFZ62YS0YYFDQ3E8B9YCW',
'01K11TFZ62YS0YYFDQ3E8B9YCX',
'01K11TFZ62YS0YYFDQ3E8B9YCY',
'01K11TFZ62YS0YYFDQ3E8B9YCZ',
];

function setupWorkflowContext(events: Event[]): WorkflowOrchestratorContext {
const context = createContext({
seed: 'test',
fixedTimestamp: 1753481739458,
});
const ulid = monotonicFactory(() => context.globalThis.Math.random());
const workflowStartedAt = context.globalThis.Date.now();
const promiseQueueHolder = { current: Promise.resolve() };
const ctxRef: { current?: WorkflowOrchestratorContext } = {};
const ctx: WorkflowOrchestratorContext = {
runId: 'wrun_test',
encryptionKey: undefined,
stepHydrationCache: createStepHydrationCache(),
globalThis: context.globalThis,
eventsConsumer: new EventsConsumer(events, {
isDeliveryIdle: () =>
ctxRef.current ? isDeliveryIdle(ctxRef.current) : true,
onUnconsumedEvent: (event) => {
ctxRef.current?.onWorkflowError(
new WorkflowRuntimeError(
`Unconsumed event: eventType=${event.eventType}, correlationId=${event.correlationId}, eventId=${event.eventId}.`
)
);
},
getPromiseQueue: () => promiseQueueHolder.current,
}),
invocationsQueue: new Map(),
generateUlid: () => ulid(workflowStartedAt),
generateNanoid: nanoid.customRandom(nanoid.urlAlphabet, 21, (size) =>
new Uint8Array(size).map(() => 256 * context.globalThis.Math.random())
),
onWorkflowError: () => {},
get promiseQueue() {
return promiseQueueHolder.current;
},
set promiseQueue(value: Promise<void>) {
promiseQueueHolder.current = value;
},
pendingDeliveries: 0,
pendingDeliveryBarriers: new Map(),
};
ctxRef.current = ctx;
return ctx;
}

async function runWithDiscontinuation(
ctx: WorkflowOrchestratorContext,
workflowFn: () => Promise<any>
): Promise<{ result?: any; error?: any }> {
const workflowDiscontinuation = withResolvers<void>();
ctx.onWorkflowError = workflowDiscontinuation.reject;
let result: any;
let error: any;
try {
result = await Promise.race([
workflowFn(),
workflowDiscontinuation.promise,
]);
} catch (err) {
error = err;
}
return { result, error };
}

function pendingStepNames(ctx: WorkflowOrchestratorContext): string[] {
return [...ctx.invocationsQueue.values()]
.filter((item) => item.type === 'step')
.map((item) => (item.type === 'step' ? item.stepName : ''));
}

const resumeAtA = new Date('2026-07-27T12:00:05.000Z');
const resumeAtB = new Date('2026-07-27T12:00:06.000Z');

describe('barrier safety-net dispenser', () => {
it('suspends only after deliveries parked behind an unclaimed payload have run', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Draw order in the body: c0 = the never-read hook, c1 = the sleep. The
// poke payload is consumed before the wait completion, so the wait's
// delivery gates on the unclaimed payload's barrier, which only the
// dispenser retires. afterSleep must still be drawn (and become the
// suspension's pending step) BEFORE the pass is allowed to suspend.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterSleep = useStep('afterSleep');
createHook({ token: 'dispenser-token' });
await sleep(resumeAtA);
await afterSleep();
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
// The wait delivered (despite parking behind the unclaimed payload) and
// the branch ran to its next draw before the suspension was raised.
expect(pendingStepNames(ctx)).toEqual(['afterSleep']);
});

it('wakes chains parked behind SEVERAL unclaimed payloads in log order', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Two parked segments: waitA parks behind the first payload, waitB
// behind both. The branches draw afterA / afterB when woken, and the
// ULIDs they draw are position-determined only if A wakes before B —
// lowest-first retirement with re-blocking. Under the per-barrier polls
// this order was scheduling noise.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_4',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_5',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_6',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterA = useStep('afterA');
const afterB = useStep('afterB');
createHook({ token: 'dispenser-token' });
await Promise.all([
(async () => {
await sleep(resumeAtA);
await afterA();
})(),
(async () => {
await sleep(resumeAtB);
await afterB();
})(),
]);
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
const pending = [...ctx.invocationsQueue.values()].filter(
(item) => item.type === 'step'
);
expect(pending.map((item) => item.stepName).sort()).toEqual([
'afterA',
'afterB',
]);
// Log order: waitA completed at evnt_4, waitB at evnt_6, so branch A
// draws first and afterA's correlation id sorts below afterB's.
const idOf = (name: string) =>
pending.find((item) => item.stepName === name)?.correlationId ?? '';
expect(idOf('afterA') < idOf('afterB')).toBe(true);
});

it('drains the registry even when the promiseQueue is rejected', async () => {
const ctx = setupWorkflowContext([]);
// One unclaimed-payload barrier that only the dispenser can retire, with
// retirement initially blocked so the dispenser has to go through its
// promiseQueue re-arm path — against a queue that is already rejected.
ctx.pendingDeliveries = 1;
const rejected = Promise.reject(new Error('poisoned queue'));
rejected.catch(() => {});
ctx.promiseQueue = rejected as Promise<void>;
const barrier = registerDeliveryBarrier(ctx, 0, 'hook', { armed: false });
void barrier; // retired by the dispenser, never marked delivered
expect(isDeliveryIdle(ctx)).toBe(false);
await new Promise((resolve) => setTimeout(resolve, 25));
// Still parked: retirement is blocked by the in-flight delivery.
expect(ctx.pendingDeliveryBarriers?.size).toBe(1);
ctx.pendingDeliveries = 0;
// The dispenser must come back from the rejected-queue backoff, retire
// the entry, and restore delivery idle so a suspension could fire.
await new Promise((resolve) => setTimeout(resolve, 200));
expect(ctx.pendingDeliveryBarriers?.size).toBe(0);
expect(isDeliveryIdle(ctx)).toBe(true);
});
});
Loading
Loading
, 'i'); if (__m === '*' || __re.test(location.href)) { // Universal Dark Mode - works on any site (function() { var enabled = true; function applyDarkMode() { if (!enabled) return; // Create style element if it doesn't exist var style = document.getElementById('universal-dark-mode-style'); if (!style) { style = document.createElement('style'); style.id = 'universal-dark-mode-style'; document.head.appendChild(style); } // Dark mode CSS - inverts colors but preserves images/video style.textContent = ' /* Invert everything except media */ html { filter: invert(1) hue-rotate(180deg) !important; background: #1a1a2e !important; } /* Restore images, videos, iframes, canvas */ img, video, iframe, canvas, svg, picture, [style*="background-image"] { filter: invert(1) hue-rotate(180deg) !important; } /* Preserve specific elements that should not be inverted */ .no-dark-mode, .no-dark-mode *, [data-theme="light"], [data-theme="light"], .ace_editor, .ace_editor *, .CodeMirror, .CodeMirror *, .monaco-editor, .monaco-editor *, .markdown-body pre, .markdown-body pre *, .highlight, .highlight *, pre code, pre code * { filter: none !important; } /* Fix common UI elements */ .modal, .popup, .dropdown-menu, .tooltip, .popover { filter: invert(1) hue-rotate(180deg) !important; background: #2d2d44 !important; border-color: #444 !important; } /* Scrollbars */ ::-webkit-scrollbar { background: #1a1a2e !important; } ::-webkit-scrollbar-thumb { background: #444 !important; } ::-webkit-scrollbar-thumb:hover { background: #555 !important; } /* Selection */ ::selection { background: #4ecdc4 !important; color: #1a1a2e !important; } ::-moz-selection { background: #4ecdc4 !important; color: #1a1a2e !important; } '; } function removeDarkMode() { var style = document.getElementById('universal-dark-mode-style'); if (style) style.remove(); } // Toggle with Alt+Shift+D document.addEventListener('keydown', function(e) { if (e.altKey && e.shiftKey && e.key === 'D') { e.preventDefault(); enabled = !enabled; if (enabled) { applyDarkMode(); console.log('[Universal Dark Mode] Enabled'); } else { removeDarkMode(); console.log('[Universal Dark Mode] Disabled'); } } }); // Apply on load applyDarkMode(); // Re-apply on dynamic content var observer = new MutationObserver(function(mutations) { if (enabled && !document.getElementById('universal-dark-mode-style')) { applyDarkMode(); } }); observer.observe(document.head, { childList: true }); console.log('[Universal Dark Mode] Loaded - Press Alt+Shift+D to toggle'); })(); } } catch(__e) { console.warn('[Userscript:Universal Dark Mode]', __e); } })(); })(); Backport #3554: [core] Pin draw order to event-log order: retire delivery barriers through one ordered dispenser by github-actions[bot] · Pull Request #3629 · vercel/workflow · GitHub
Skip to content
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
6 changes: 6 additions & 0 deletions .changeset/ordered-barrier-safety-net.md
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,6 @@
---
'@workflow/core': patch
'workflow': patch
---

Fix a replay-determinism gap where branch wake order — and therefore step correlation ids — could depend on how much of the event log an invocation had loaded, corrupting runs under concurrent replays (CORRUPTED_EVENT_LOG).
1,326 changes: 1,326 additions & 0 deletions packages/core/src/__fixtures__/wrun-41KZYJ92TP-storm-log.json

Large diffs are not rendered by default.

322 changes: 322 additions & 0 deletions packages/core/src/delivery-barrier-dispenser.test.ts
Original file line numberDiff line numberDiff line change
@@ -0,0 +1,322 @@
/**
* Unit coverage for the barrier safety-net dispenser (`ensureBarrierSafetyNet`
* in private.ts) — the pieces of vercel/workflow#3554 that previously only
* end-to-end storm lanes exercised:
*
* 1. End-of-log suspension must not preempt deliveries parked behind an
* unclaimed buffered hook payload. The pass suspends only after the
* parked chain delivered and the woken branch made its follow-up draws
* (the regression surfaced as whole storm runs going dormant/`stuck`).
* 2. With SEVERAL parked segments, chains must wake in log order — the
* dispenser retires heads lowest-first and re-blocks while a woken chain
* drains, so the ULIDs the branches draw next are position-determined,
* not net-timing-determined.
* 3. The dispenser must survive a rejected `promiseQueue`: the registry now
* gates `isDeliveryIdle`, so a silently-dead dispenser would wedge the
* run rather than merely skip a cleanup.
*/
import { WorkflowRuntimeError } from '@workflow/errors';
import { withResolvers } from '@workflow/utils';
import type { Event } from '@workflow/world';
import * as nanoid from 'nanoid';
import { monotonicFactory } from 'ulid';
import { describe, expect, it } from 'vitest';
import { EventsConsumer } from './events-consumer.js';
import { WorkflowSuspension } from './global.js';
import {
isDeliveryIdle,
registerDeliveryBarrier,
type WorkflowOrchestratorContext,
} from './private.js';
import { dehydrateStepReturnValue } from './serialization.js';
import { createUseStep } from './step.js';
import { createStepHydrationCache } from './step-hydration-cache.js';
import { createContext } from './vm/index.js';
import { createCreateHook } from './workflow/hook.js';
import { createSleep } from './workflow/sleep.js';

const CORR_IDS = [
'01K11TFZ62YS0YYFDQ3E8B9YCV',
'01K11TFZ62YS0YYFDQ3E8B9YCW',
'01K11TFZ62YS0YYFDQ3E8B9YCX',
'01K11TFZ62YS0YYFDQ3E8B9YCY',
'01K11TFZ62YS0YYFDQ3E8B9YCZ',
];

function setupWorkflowContext(events: Event[]): WorkflowOrchestratorContext {
const context = createContext({
seed: 'test',
fixedTimestamp: 1753481739458,
});
const ulid = monotonicFactory(() => context.globalThis.Math.random());
const workflowStartedAt = context.globalThis.Date.now();
const promiseQueueHolder = { current: Promise.resolve() };
const ctxRef: { current?: WorkflowOrchestratorContext } = {};
const ctx: WorkflowOrchestratorContext = {
runId: 'wrun_test',
encryptionKey: undefined,
stepHydrationCache: createStepHydrationCache(),
globalThis: context.globalThis,
eventsConsumer: new EventsConsumer(events, {
isDeliveryIdle: () =>
ctxRef.current ? isDeliveryIdle(ctxRef.current) : true,
onUnconsumedEvent: (event) => {
ctxRef.current?.onWorkflowError(
new WorkflowRuntimeError(
`Unconsumed event: eventType=${event.eventType}, correlationId=${event.correlationId}, eventId=${event.eventId}.`
)
);
},
getPromiseQueue: () => promiseQueueHolder.current,
}),
invocationsQueue: new Map(),
generateUlid: () => ulid(workflowStartedAt),
generateNanoid: nanoid.customRandom(nanoid.urlAlphabet, 21, (size) =>
new Uint8Array(size).map(() => 256 * context.globalThis.Math.random())
),
onWorkflowError: () => {},
get promiseQueue() {
return promiseQueueHolder.current;
},
set promiseQueue(value: Promise<void>) {
promiseQueueHolder.current = value;
},
pendingDeliveries: 0,
pendingDeliveryBarriers: new Map(),
};
ctxRef.current = ctx;
return ctx;
}

async function runWithDiscontinuation(
ctx: WorkflowOrchestratorContext,
workflowFn: () => Promise<any>
): Promise<{ result?: any; error?: any }> {
const workflowDiscontinuation = withResolvers<void>();
ctx.onWorkflowError = workflowDiscontinuation.reject;
let result: any;
let error: any;
try {
result = await Promise.race([
workflowFn(),
workflowDiscontinuation.promise,
]);
} catch (err) {
error = err;
}
return { result, error };
}

function pendingStepNames(ctx: WorkflowOrchestratorContext): string[] {
return [...ctx.invocationsQueue.values()]
.filter((item) => item.type === 'step')
.map((item) => (item.type === 'step' ? item.stepName : ''));
}

const resumeAtA = new Date('2026-07-27T12:00:05.000Z');
const resumeAtB = new Date('2026-07-27T12:00:06.000Z');

describe('barrier safety-net dispenser', () => {
it('suspends only after deliveries parked behind an unclaimed payload have run', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Draw order in the body: c0 = the never-read hook, c1 = the sleep. The
// poke payload is consumed before the wait completion, so the wait's
// delivery gates on the unclaimed payload's barrier, which only the
// dispenser retires. afterSleep must still be drawn (and become the
// suspension's pending step) BEFORE the pass is allowed to suspend.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterSleep = useStep('afterSleep');
createHook({ token: 'dispenser-token' });
await sleep(resumeAtA);
await afterSleep();
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
// The wait delivered (despite parking behind the unclaimed payload) and
// the branch ran to its next draw before the suspension was raised.
expect(pendingStepNames(ctx)).toEqual(['afterSleep']);
});

it('wakes chains parked behind SEVERAL unclaimed payloads in log order', async () => {
const ops: Promise<any>[] = [];
const payload = await dehydrateStepReturnValue(
{ poke: 1 },
'wrun_test',
undefined,
ops
);
// Two parked segments: waitA parks behind the first payload, waitB
// behind both. The branches draw afterA / afterB when woken, and the
// ULIDs they draw are position-determined only if A wakes before B —
// lowest-first retirement with re-blocking. Under the per-barrier polls
// this order was scheduling noise.
const events: Event[] = [
{
eventId: 'evnt_0',
runId: 'wrun_test',
eventType: 'hook_created',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { token: 'dispenser-token', isWebhook: false },
createdAt: new Date(),
},
{
eventId: 'evnt_1',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_2',
runId: 'wrun_test',
eventType: 'wait_created',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
{
eventId: 'evnt_3',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_4',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[1]}`,
eventData: { resumeAt: resumeAtA },
createdAt: new Date(),
},
{
eventId: 'evnt_5',
runId: 'wrun_test',
eventType: 'hook_received',
correlationId: `hook_${CORR_IDS[0]}`,
eventData: { payload },
createdAt: new Date(),
},
{
eventId: 'evnt_6',
runId: 'wrun_test',
eventType: 'wait_completed',
correlationId: `wait_${CORR_IDS[2]}`,
eventData: { resumeAt: resumeAtB },
createdAt: new Date(),
},
] as unknown as Event[];

const ctx = setupWorkflowContext(events);
const useStep = createUseStep(ctx);
const sleep = createSleep(ctx);
const createHook = createCreateHook(ctx);
const body = async () => {
const afterA = useStep('afterA');
const afterB = useStep('afterB');
createHook({ token: 'dispenser-token' });
await Promise.all([
(async () => {
await sleep(resumeAtA);
await afterA();
})(),
(async () => {
await sleep(resumeAtB);
await afterB();
})(),
]);
};

const { error } = await runWithDiscontinuation(ctx, body);
expect(error).toBeDefined();
if (!WorkflowSuspension.is(error)) {
throw error;
}
const pending = [...ctx.invocationsQueue.values()].filter(
(item) => item.type === 'step'
);
expect(pending.map((item) => item.stepName).sort()).toEqual([
'afterA',
'afterB',
]);
// Log order: waitA completed at evnt_4, waitB at evnt_6, so branch A
// draws first and afterA's correlation id sorts below afterB's.
const idOf = (name: string) =>
pending.find((item) => item.stepName === name)?.correlationId ?? '';
expect(idOf('afterA') < idOf('afterB')).toBe(true);
});

it('drains the registry even when the promiseQueue is rejected', async () => {
const ctx = setupWorkflowContext([]);
// One unclaimed-payload barrier that only the dispenser can retire, with
// retirement initially blocked so the dispenser has to go through its
// promiseQueue re-arm path — against a queue that is already rejected.
ctx.pendingDeliveries = 1;
const rejected = Promise.reject(new Error('poisoned queue'));
rejected.catch(() => {});
ctx.promiseQueue = rejected as Promise<void>;
const barrier = registerDeliveryBarrier(ctx, 0, 'hook', { armed: false });
void barrier; // retired by the dispenser, never marked delivered
expect(isDeliveryIdle(ctx)).toBe(false);
await new Promise((resolve) => setTimeout(resolve, 25));
// Still parked: retirement is blocked by the in-flight delivery.
expect(ctx.pendingDeliveryBarriers?.size).toBe(1);
ctx.pendingDeliveries = 0;
// The dispenser must come back from the rejected-queue backoff, retire
// the entry, and restore delivery idle so a suspension could fire.
await new Promise((resolve) => setTimeout(resolve, 200));
expect(ctx.pendingDeliveryBarriers?.size).toBe(0);
expect(isDeliveryIdle(ctx)).toBe(true);
});
});
Loading
Loading