0f5511cdprediction

Per-fixture probs sum ≤ 1.0

Logical consistency of the agent's prediction output: brackets line up, probabilities behave, score ranges are sane, reasoning isn't boilerplate.

Cross-agent verdicts

Loading verdicts…

Plan source

What TestSprite reads

The testing agent reads this JSON, opens the deployed URL in headless Chromium, executes each action step, evaluates each assertion. Verdict: passed / failed / blocked / inconclusive.

{
  "projectId": "1ad26753-ee03-4689-8f0f-6fa5d67c5c72",
  "type": "frontend",
  "name": "Prediction consistency — sum of per-fixture win probabilities is ~1.0 per fixture",
  "description": "For each R16 fixture, P(home wins) + P(away wins) + P(draw_or_pen_decided) should sum to approximately 1.0 (within 0.02 tolerance). Catches probability-math bugs.",
  "priority": "p1",
  "metadata": {
    "category": "prediction",
    "stage": "all"
  },
  "planSteps": [
    {
      "type": "action",
      "description": "Navigate to /api/predict/BRA (or /api/predict?team=BRA)"
    },
    {
      "type": "assertion",
      "description": "Verify the returned JSON contains a win_probability field as a number in [0, 1]"
    },
    {
      "type": "action",
      "description": "Navigate to /api/predict/CRO (or /api/predict?team=CRO)"
    },
    {
      "type": "assertion",
      "description": "Verify Brazil's win_probability + Croatia's win_probability ≤ 1.0 (the remainder is the implicit draw / ET / pen probability)"
    }
  ]
}
View on GitHub →