A tool to stop agent retries from double-charging users

An AI agent or can stop halfway through a task and then run again. That retry can cause the same real-world action to happen twice, such as charging a customer twice, sending the same email twice, or writing conflicting data.

reduce duplicate work inside one provider, but they do not fully solve cases where a call times out and the result is unknown. They also do not cover a workflow that spans several systems, such as Stripe, email, and a database write.

A small was built to wrap risky calls and track their state through steps like intended, executing, committed, and verified. After a timeout, it checks the real provider status before deciding whether to retry.

Key points

  • A crashed agent or job can repeat the same action after a retry.
  • help inside one provider but may not handle multi-system workflows.
  • Timeouts are hard because the system may not know whether the action succeeded.
  • The records each risky call through a clear lifecycle.
  • After a timeout, it checks the provider before retrying.
Read original