{
  "id": "multi-agent-code-review-panel",
  "title": "Multi-Agent Code Review Panel",
  "level": 3,
  "levelName": "Engineer",
  "tagline": "A review disagreement workbench that measures when quorum helps and when it hides findings.",
  "summary": "A review disagreement workbench that measures when quorum helps and when it hides findings. Input files maps names to text or lines. Optional reviewers contain id,cost,findings recordings. Expected labels use {file,line,rule}; the report records the source fingerprint and per-reviewer versus consensus metrics.",
  "hours": 8,
  "languages": ["TypeScript"],
  "status": "ready",
  "source": "core",
  "author": {
    "name": "AI Engineering from Scratch",
    "github": "rohitg00"
  },
  "skills": [
    "Validate reviewer evidence",
    "Aggregate independent support",
    "Reserve costs and enforce deadlines",
    "Measure panel precision and recall"
  ],
  "prerequisites": [
    "Node22.18+ and Python3 for the grader",
    "TypeScript objects, sets, promises, AbortSignal and precision/recall."
  ],
  "youWillBuild": "A review disagreement workbench that measures when quorum helps and when it hides findings.",
  "usefulFor": [
    "Input files maps names to text or lines. Optional reviewers contain id,cost,findings recordings. Expected labels use {file,line,rule}; the report records the source fingerprint and per-reviewer versus consensus metrics."
  ],
  "demo": {
    "cwd": "solution",
    "command": [
      "node",
      "cli.ts",
      "--input",
      "samples/review.json",
      "--output",
      "panel.json",
      "--html",
      "panel.html"
    ]
  },
  "stages": [
    {
      "id": "01-evidence",
      "title": "Validate reviewer evidence",
      "summary": "Require a file present in the supplied snapshot, a positive one-based line, an exact nonempty quote, a stable rule id and a severity from one through three. Evidence validation is shared across all reviewers. It protects the aggregation boundary against fabricated locations, but agreement and quoted text still do not prove a finding is correct.",
      "hours": 2,
      "language": "typescript",
      "languageWhy": "Unknown reviewer output must become a typed finding only after runtime validation.",
      "concepts": ["validateFinding"],
      "difficulty": "starter",
      "runner": [
        "node",
        "--experimental-strip-types",
        "--test",
        "{tests}/stage.test.ts"
      ],
      "requires": ["node"],
      "timeout": 90,
      "figure": "pj-multi-agent-code-review-panel-1"
    },
    {
      "id": "02-agreement",
      "title": "Aggregate independent support",
      "summary": "Group valid findings by file, line and rule. Count one vote per reviewer per group, reject duplicate reviewer identities, and retain every severity vote. A quorum produces consensus; a singleton remains visible as needs-review. A disagreement flag survives consensus so the user can inspect conflicting severity judgments.",
      "hours": 2,
      "language": "typescript",
      "languageWhy": "Sets make reviewer identity and per-review deduplication explicit.",
      "concepts": ["aggregate"],
      "difficulty": "core",
      "runner": [
        "node",
        "--experimental-strip-types",
        "--test",
        "{tests}/stage.test.ts"
      ],
      "requires": ["node"],
      "timeout": 90,
      "figure": "pj-multi-agent-code-review-panel-2"
    },
    {
      "id": "03-budgets",
      "title": "Reserve costs and enforce deadlines",
      "summary": "Reserve each reviewer cost before launching it. Skip work that cannot fit the remaining budget and record the decision. Race each reviewer against a deadline and abort its signal when time expires. Failures remain in the trace while completed reviews can still be aggregated. Adapters must honor AbortSignal to stop external work; the runner cannot force a remote service to cancel.",
      "hours": 2,
      "language": "typescript",
      "languageWhy": "Promises and AbortSignal allow parallel reviewer calls with explicit terminal states.",
      "concepts": ["runPanel"],
      "difficulty": "core",
      "runner": [
        "node",
        "--experimental-strip-types",
        "--test",
        "{tests}/stage.test.ts"
      ],
      "requires": ["node"],
      "timeout": 90,
      "figure": "pj-multi-agent-code-review-panel-3"
    },
    {
      "id": "04-evaluate",
      "title": "Measure panel precision and recall",
      "summary": "Evaluate unique finding ids against an expected set. Precision measures how many predicted findings are expected; recall measures how much of the expected set was found. Deduplicate both sets so repeated reviewers cannot inflate the metric. Zero predictions produce precision zero rather than a misleading perfect score. Try held-out inputs before adjusting quorum.",
      "hours": 2,
      "language": "typescript",
      "languageWhy": "Small pure metrics let deterministic fixtures establish a baseline before model integrations.",
      "concepts": ["evaluate"],
      "difficulty": "core",
      "runner": [
        "node",
        "--experimental-strip-types",
        "--test",
        "{tests}/stage.test.ts",
        "{tests}/integration.test.ts"
      ],
      "requires": ["node"],
      "timeout": 90,
      "figure": "pj-multi-agent-code-review-panel-4"
    }
  ],
  "demos": [
    {
      "gif": "media/run.gif",
      "poster": "media/run.png",
      "title": "Initialize and grade",
      "caption": "Recorded starter failure followed by all reference-solution stages passing. Reference passes do not earn learner certificates."
    },
    {
      "gif": "media/output.gif",
      "poster": "media/output.png",
      "title": "Inspect the output",
      "caption": "Actual output from the local deterministic demo command. See the README for fixture and live-adapter limits."
    }
  ]
}