Skip to content

Free, Open Source, Self-Hosted WhatsApp API Gateway

fix(message): keep a locally running batch out of the takeover reap

Yudhi Armyndharise9391328ac48
diff --git a/src/modules/message/bulk-message.service.spec.ts b/src/modules/message/bulk-message.service.spec.ts
index 64ea3730a..591f60c87 100644
--- a/src/modules/message/bulk-message.service.spec.ts
+++ b/src/modules/message/bulk-message.service.spec.ts
@@ -135,6 +135,23 @@ describe('BulkMessageService.onApplicationBootstrap', () => {
expect(JSON.stringify(mine.messages)).not.toContain('x'.repeat(64));
});
+ it('reapProcessingBatches leaves alone a PROCESSING batch this process is still running', async () => {
+ // Adopted session: the claim moved here before the engine finished initializing, and a bulk
+ // request routed here in that window started a batch of its own before the reap ran.
+ const running = { id: 'b-live', sessionId: 'sess-a', status: BatchStatus.PROCESSING, messages: [] };
+ const orphan = { id: 'b-dead', sessionId: 'sess-a', status: BatchStatus.PROCESSING, messages: [] };
+ repo.find.mockResolvedValue([running, orphan]);
+ (service as unknown as { processingBatches: Map<string, boolean> }).processingBatches.set('b-live', true);
+
+ const reaped = await service.reapProcessingBatches('sess-a', 'session adopted from a lapsed node');
+
+ expect(reaped).toBe(1);
+ expect(running.status).toBe(BatchStatus.PROCESSING);
+ expect(orphan.status).toBe(BatchStatus.FAILED);
+ expect(repo.save).toHaveBeenCalledTimes(1);
+ expect(repo.save).toHaveBeenCalledWith(orphan);
+ });
+
/**
* A batch is only ever driven by the process holding its session's engine, so on a second replica
* "PROCESSING" does not mean "abandoned". Reaping a peer's batch tells the caller their send
diff --git a/src/modules/message/bulk-message.service.ts b/src/modules/message/bulk-message.service.ts
index 959a0a460..9ea155236 100644
--- a/src/modules/message/bulk-message.service.ts
+++ b/src/modules/message/bulk-message.service.ts
@@ -166,9 +166,15 @@ export class BulkMessageService implements OnApplicationBootstrap {
* Same policy as the boot reaper and for the same reason: the dead node's already-sent messages
* are unknowable, so resuming risks double-sends — FAILED with the payloads stripped is the
* honest terminal state, and the caller can re-issue the batch knowingly.
+ *
+ * A batch this process is running itself is not orphaned: the adoption claims the session before
+ * its engine finishes initializing, so a bulk request routed here in that window starts a batch
+ * that is already PROCESSING by the time the caller reaps. Only the dead holder's batches go.
*/
async reapProcessingBatches(sessionId: string, reason: string): Promise<number> {
- const processing = await this.batchRepository.find({ where: { status: BatchStatus.PROCESSING, sessionId } });
+ const processing = (
+ await this.batchRepository.find({ where: { status: BatchStatus.PROCESSING, sessionId } })
+ ).filter(batch => !this.processingBatches.has(batch.id));
for (const batch of processing) {
await this.failOrphanedBatch(batch);
}