Problems / Multi-agent and harness, medium
A coding harness runs the test suite in a sandbox every turn. 8 sandboxes, about 1.2 s per run.
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.
Success ≥ 95% of tasks, p99 ≤ 90 s.
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 5; 2 of them are hidden until then.
2 requests a second for 45 seconds: 100% task (writes).
What each component does in this design, and what calls it. The simulator mimics each one from these settings.
| Component | Its job here | Settings |
|---|---|---|
| Load balancerLoad balancer | Traffic 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 service | Load balancer forwards to it.Calls Agent harness.Little's law: throughput ≈ concurrency ÷ latency. 200 slots at 50 ms serve about 4,000 req/s. | 3 replicas × 500 slots · timeout 180 s |
| Agent harnessAgent harness | Agent API calls it.Calls Model, Code sandbox.A harness is everything around the model in an agent: context management, tools, checkpoints, retries and evaluation. | 400 slots · 5 steps |
| ModelLLM endpoint | Agent harness calls it.Latency has two parts: time to the first token, then a steady stream of tokens per second. | 300 streams |
| Code sandboxCode sandbox | Agent harness calls it.Sandboxes run model-written code in an isolated container with limited network and time. | 8 slots |