Optimize routing rules, per-agent model selection, timeout values, cost per task

The runtime configuration your team can adjust without touching code. TuneKit values are loaded by the engine alongside the manifest and override primitive defaults. Below: a sensible starter config inferred from this play's complexity + WAF posture.

{
  "model": "gpt-4o-mini",
  "temperature": 0.1,
  "maxTokens": 1000,
  "retrieval": {
    "topK": 5,
    "chunkSize": 800
  },
  "evaluation": {
    "sampleRate": 0.1,
    "reportingWindow": "P7D"
  },
  "cost": {
    "dailyCapUsd": 10
  }
}