Problems / Agents and tools, medium

Agent jobs run twice

Agent jobs are queued and run by workers. When an acknowledgement is lost, the queue redelivers and the job’s side effect (sending an email) happens twice.

Unlock it once for 15 credits; everything inside it is free (runs, changes, Submit, results, hints). Sign in with Google to start; new accounts get free credits.

Your goals

No duplicate side effects.

Test cases

Like a coding problem, a solution has to pass every case, not just the one it was built for. Submit in the lab runs all 6; 2 of them are hidden until then.

  1. As given. The problem’s own traffic, scheduled failures and seed.
  2. Peak hour. 25% more traffic than the problem states, with the same failures.
  3. A slow dependency. The main data store or model answers twice as slowly for part of the run.
  4. A server dies. One replica of the service with the most replicas is killed for part of the run.

The traffic

30 requests a second for 30 seconds: 100% job (writes).

The system

What each component does in this design, and what calls it. The simulator mimics each one from these settings.

ComponentIts job hereSettings
Load balancerLoad balancerTraffic enters here.Calls Agent API.Layer 4 balancers route by IP and port; layer 7 balancers read HTTP and can route by path or header.–
Agent APIApp serviceLoad balancer forwards to it.Calls Agent job queue (publishes).Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s.3 replicas × 500 slots · timeout 30 s
Agent job queueMessage queueAgent API publishes to it.Calls Agent workers.If a consumer does not finish within the visibility timeout, the message is delivered again.–
Agent workersWorkerAgent job queue consumes from it.Calls Email tool.Queues deliver at least once, so a worker can see the same message twice.32 concurrent jobs
Email toolTool / MCP serverAgent workers calls it.Tools give the model actions such as search or database queries; each call is another round trip.200 slots

More agents and tools problems