Hatchet vs Inngest

Hatchet

A durable task waits for a keyed event without holding a worker slot, and resumes from its event log after a restart, in Python, TypeScript, Go or Ruby. Hatchet supplies only the pause and resume. It has no approver inbox, notification channel or record of who answered, and its MCP server cannot push the event.

Inngest

Waits are durable and cost nothing while suspended, with runs up to 30 days on Free and 366 on Business. No reviewer inbox, Slack app or email, so the human side is your code.

Hatchet

1. Put the approval wait in a durable task, and keep API calls, database reads and random values in child tasks, because the code between checkpoints is replayed
2. Add a sleep condition in the same or group as the event condition to set a deadline, and treat the sleep firing first as a timeout
3. Give the event a scope and the wait a lookback window when the answer can arrive before the wait starts. Both must be set together
4. Filter with a CEL expression such as input.user_id == '1234' so one approval key cannot resume another request's task
5. Push the answer with the SDK's event push or POST /api/v1/tenants/{tenant}/events. The MCP server has no tool for it
6. Grant the MCP server one profile with hatchet mcp auth --grant <profile>. It refuses profiles that were not granted

Inngest

1. Use step.waitForSignal() when one run waits for one answer, and waitForEvent only when one answer resumes many runs
2. Register the wait before you send the approval request, or check the external state first, since early events are missed
3. Use a unique approval ID per tool call and match on it, so parallel approvals resolve independently
4. Treat null or undefined as a timeout and decide on purpose whether that rejects, approves or escalates
5. Set an event id when sending the answer, so a retried send is dropped within 24 hours