{
  "id": "retry-storm-lab",
  "title": "Retry Storm Lab",
  "tagline": "Watch many reasonable retries combine into an overloaded service.",
  "summary": "Help SDK authors choose retry behavior when many clients fail together. Replay concurrent clients against a deterministic service model, compare bounded backoff and jitter with a shared retry budget, then run the same policy against a local HTTP fixture. Export amplification and recovery timelines with a reusable client policy.",
  "level": 3,
  "source": "core",
  "status": "ready",
  "hours": 8,
  "languages": [
    "Go",
    "TypeScript"
  ],
  "author": {
    "name": "AI Engineering from Scratch",
    "github": "rohitg00"
  },
  "youWillBuild": "Retry policy library, deterministic workload replay and amplification timeline",
  "prerequisiteProjects": [
    "llm-gateway-with-fallbacks",
    "agent-budget-planner"
  ],
  "demo": {
    "command": [
      "python3",
      "demo.py"
    ],
    "cwd": "solution"
  },
  "stages": [
    {
      "id": "01-deterministic-service",
      "title": "Model concurrent failures with a deterministic clock",
      "summary": "Make aggregate retry load visible in a discrete event replay.",
      "hours": 2,
      "language": "go",
      "difficulty": "starter",
      "concepts": [
        "discrete clock",
        "capacity",
        "amplification"
      ],
      "timeout": 120,
      "figure": "pj-retry-storm-lab-1"
    },
    {
      "id": "02-bounded-jitter",
      "title": "Compare bounded backoff and jitter",
      "summary": "Spread scheduled retries with a reproducible client-specific sequence.",
      "hours": 2,
      "language": "go",
      "difficulty": "core",
      "concepts": [
        "exponential backoff",
        "full jitter",
        "seed"
      ],
      "timeout": 120,
      "figure": "pj-retry-storm-lab-2"
    },
    {
      "id": "03-shared-budget",
      "title": "Enforce shared retry budgets and server delays",
      "summary": "Bound aggregate attempts across clients, not just each individual request.",
      "hours": 2,
      "language": "go",
      "difficulty": "core",
      "concepts": [
        "shared budget",
        "Retry-After",
        "mutex"
      ],
      "timeout": 120,
      "figure": "pj-retry-storm-lab-3"
    },
    {
      "id": "04-local-http-replay",
      "title": "Replay against a local HTTP service",
      "summary": "Exercise actual HTTP requests and verify the exported counters independently.",
      "hours": 2,
      "language": "go+typescript",
      "difficulty": "core",
      "concepts": [
        "context cancellation",
        "loopback fixture",
        "receipt validation"
      ],
      "timeout": 120,
      "figure": "pj-retry-storm-lab-4",
      "runners": [
        {
          "language": "go"
        },
        {
          "language": "typescript"
        }
      ]
    }
  ],
  "demos": [
    {
      "gif": "media/run.gif",
      "poster": "media/run.png",
      "title": "Initialize and grade",
      "caption": "Recorded starter failure followed by every reference stage passing."
    },
    {
      "gif": "media/output.gif",
      "poster": "media/output.png",
      "title": "Inspect actual output",
      "caption": "Recorded local command output. See the README for input and scope."
    }
  ]
}