4b9286e4prediction

Predicted finalists exist + come from SF

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 — both Final teams must have won their SF fixture",
  "description": "The 2 teams shown in the Final fixture must each appear as the predicted winner of one of the 2 SF fixtures. Catches bracket-derivation bugs where the Final row gets populated independently of the SF predictions.",
  "priority": "p0",
  "metadata": {
    "category": "prediction",
    "stage": "all"
  },
  "planSteps": [
    {
      "type": "action",
      "description": "Navigate to the homepage and find the Final fixture in the bracket"
    },
    {
      "type": "assertion",
      "description": "Verify both teams in the Final fixture appear as the predicted winner of an SF fixture in the same bracket. (The predicted winner of an SF fixture is the team with the higher predicted score, OR the team listed first if scores are level + suffix indicates penalties)"
    }
  ]
}
View on GitHub →