Race Conditions in n8n AI Agent Workflows (and the Fix)

Описание и применение

В n8n параллельные выполнения могут привести к двойному бронированию, если AI‑Agent расширяет окно проверки‑действия. Решение: атомарно захватывать ресурс, использовать ключи идемпотентности и повторно проверять состояние перед записью.

Задача

Concurrent executions in n8n can double‑book a resource when an AI Agent node extends the check‑then‑act window, leading to race conditions that are not caught by single‑request testing.

Результат

Implementing an atomic claim, idempotency keys, and a final re‑check eliminates double‑booking in n8n AI Agent workflows, even under high concurrency.

Рабочий процесс

• 1. Claim the slot in a store with a unique constraint (e.g., Postgres INSERT ON CONFLICT DO NOTHING).
• 2. If claim succeeds, generate an idempotency key for the booking action.
• 3. Perform the booking via the tool or API, passing the idempotency key.
• 4. Re‑check the real system (calendar) immediately before the final write; if the slot is no longer free, abort and return a “taken” response.
• 5. If any step fails, route to an error handling path or retry logic.

Доказательства

check shared state (a calendar, a stock count, a CRM record), then act on it, with nothing stopping a second execution from checking in between.

Источник

The fix is to claim before you act, give every business action an idempotency key, and re-check the real system right before the final write.

Источник

INSERT INTO slot_claims (slot_id, execution_id) VALUES ('2026-10-08T15:00', 'EXECUTION_ID') ON CONFLICT (slot_id) DO NOTHING RETURNING slot_id;

Источник