tasks/medium_tasks.json

[
  {
    "task_id": "medium_001",
    "difficulty": "medium",
    "query": "SELECT * FROM events ORDER BY created_at DESC;",
    "schema": {
      "events": {
        "id": "BIGINT PRIMARY KEY",
        "event_name": "VARCHAR(255)",
        "payload": "JSON",
        "created_at": "TIMESTAMP INDEX",
        "actor_id": "BIGINT",
        "metadata": "JSON"
      }
    },
    "context": "Show the most recent events on an admin dashboard.",
    "ground_truth_issues": [
      {
        "id": "medium_001_select_star",
        "category": "performance",
        "description": "SELECT * pulls a wide payload when the dashboard only needs a few columns.",
        "severity": 0.3,
        "fix": "SELECT id, event_name, created_at FROM events ORDER BY created_at DESC LIMIT 50;",
        "keywords": [
          "select *", "wide table", "projection", "performance", "star",
          "all columns", "unnecessary columns", "column selection",
          "over-fetching", "wildcard"
        ]
      },
      {
        "id": "medium_001_missing_limit",
        "category": "performance",
        "description": "The dashboard query is missing a LIMIT and can scan far more rows than necessary.",
        "severity": 0.3,
        "fix": "SELECT id, event_name, created_at FROM events ORDER BY created_at DESC LIMIT 50;",
        "keywords": [
          "limit", "unbounded query", "dashboard", "performance", "no limit",
          "missing limit", "unlimited rows", "pagination", "all rows",
          "full scan", "row count"
        ]
      }
    ],
    "max_steps": 5
  },
  {
    "task_id": "medium_002",
    "difficulty": "medium",
    "query": "SELECT c.id, c.name, (SELECT COUNT(*) FROM orders o WHERE o.customer_id = c.id) AS order_count FROM customers c;",
    "schema": {
      "customers": {
        "id": "INT PRIMARY KEY",
        "name": "VARCHAR(255)"
      },
      "orders": {
        "id": "INT PRIMARY KEY",
        "customer_id": "INT INDEX",
        "total": "DECIMAL(10,2)"
      }
    },
    "context": "Show each customer with the number of orders they have placed.",
    "ground_truth_issues": [
      {
        "id": "medium_002_correlated_subquery",
        "category": "performance",
        "description": "The correlated subquery re-counts orders per row and should be rewritten as a join with GROUP BY.",
        "severity": 0.6,
        "fix": "SELECT c.id, c.name, COUNT(o.id) AS order_count FROM customers c LEFT JOIN orders o ON o.customer_id = c.id GROUP BY c.id, c.name;",
        "keywords": [
          "correlated subquery", "group by", "join", "count", "performance",
          "subquery per row", "n+1", "rewrite", "left join", "aggregate",
          "scalar subquery", "dependent subquery"
        ]
      }
    ],
    "max_steps": 6
  },
  {
    "task_id": "medium_003",
    "difficulty": "medium",
    "query": "SELECT DISTINCT email FROM users WHERE email IS NOT NULL;",
    "schema": {
      "users": {
        "id": "INT PRIMARY KEY",
        "email": "VARCHAR(255) UNIQUE",
        "last_login_at": "TIMESTAMP NULL"
      }
    },
    "context": "Export non-null user emails for a CRM sync.",
    "ground_truth_issues": [
      {
        "id": "medium_003_redundant_distinct",
        "category": "performance",
        "description": "DISTINCT is redundant because users.email is already unique.",
        "severity": 0.45,
        "fix": "SELECT email FROM users WHERE email IS NOT NULL;",
        "keywords": [
          "distinct", "unique", "redundant", "email", "performance",
          "unnecessary distinct", "unique constraint", "already unique",
          "duplicate elimination", "deduplication", "wasted sort"
        ]
      }
    ],
    "max_steps": 5
  },
  {
    "task_id": "medium_004",
    "difficulty": "medium",
    "query": "SELECT o.id, o.total, u.name FROM orders o JOIN users u ON u.id = o.user_id WHERE DATE(o.created_at) = '2026-04-10';",
    "schema": {
      "orders": {
        "id": "INT PRIMARY KEY",
        "user_id": "INT INDEX",
        "created_at": "TIMESTAMP INDEX",
        "total": "DECIMAL(10,2)"
      },
      "users": {
        "id": "INT PRIMARY KEY",
        "name": "VARCHAR(255)"
      }
    },
    "context": "List orders placed on a specific date with the user name attached.",
    "ground_truth_issues": [
      {
        "id": "medium_004_function_on_indexed_column",
        "category": "performance",
        "description": "Wrapping created_at with DATE() prevents efficient use of the created_at index.",
        "severity": 0.6,
        "fix": "SELECT o.id, o.total, u.name FROM orders o JOIN users u ON u.id = o.user_id WHERE o.created_at >= '2026-04-10' AND o.created_at < '2026-04-11';",
        "keywords": [
          "date()", "function on column", "index", "range predicate", "performance",
          "sargable", "non-sargable", "prevents index", "full scan",
          "index usage", "function wrapping"
        ]
      }
    ],
    "max_steps": 6
  },
  {
    "task_id": "medium_005",
    "difficulty": "medium",
    "query": "SELECT id, name FROM products WHERE LOWER(name) LIKE '%pro%';",
    "schema": {
      "products": {
        "id": "INT PRIMARY KEY",
        "name": "VARCHAR(255) INDEX",
        "category_id": "INT",
        "price": "DECIMAL(10,2)"
      }
    },
    "context": "Search products whose names contain the text pro.",
    "ground_truth_issues": [
      {
        "id": "medium_005_lower_blocks_index",
        "category": "performance",
        "description": "Applying LOWER(name) on every row prevents the index on name from being used efficiently.",
        "severity": 0.35,
        "fix": "SELECT id, name FROM products WHERE name ILIKE 'pro%';",
        "keywords": [
          "lower", "function on column", "index", "performance", "sargable",
          "non-sargable", "case insensitive", "full scan", "table scan",
          "function wrapping column"
        ]
      },
      {
        "id": "medium_005_leading_wildcard",
        "category": "performance",
        "description": "The leading wildcard in LIKE '%pro%' forces a full scan instead of an index-friendly prefix lookup.",
        "severity": 0.35,
        "fix": "SELECT id, name FROM products WHERE name ILIKE 'pro%';",
        "keywords": [
          "leading wildcard", "%pro%", "full scan", "prefix lookup", "performance",
          "like wildcard", "pattern matching", "index unusable", "table scan",
          "wildcard prefix"
        ]
      }
    ],
    "max_steps": 6
  },
  {
    "task_id": "medium_006",
    "difficulty": "medium",
    "query": "SELECT * FROM events WHERE DATE(created_at) = '2024-01-15';",
    "schema": {
      "events": {
        "id": "INT PRIMARY KEY",
        "name": "VARCHAR(255)",
        "created_at": "TIMESTAMP",
        "INDEX": "idx_created_at ON events(created_at)"
      }
    },
    "context": "Find all events that happened on a specific date.",
    "ground_truth_issues": [
      {
        "id": "medium_006_function_on_index",
        "category": "performance",
        "description": "Using DATE() function on an indexed column prevents index usage. Use a range comparison instead.",
        "severity": 0.7,
        "fix": "SELECT * FROM events WHERE created_at >= '2024-01-15 00:00:00' AND created_at < '2024-01-16 00:00:00';",
        "keywords": [
          "function on column", "date function", "index", "sargable",
          "non-sargable", "prevents index", "range comparison", "full scan",
          "table scan", "index usage", "function wrapping column"
        ]
      },
      {
        "id": "medium_006_star",
        "category": "performance",
        "description": "SELECT * returns all columns when only specific fields may be needed.",
        "severity": 0.2,
        "fix": "SELECT id, name, created_at FROM events WHERE created_at >= '2024-01-15' AND created_at < '2024-01-16';",
        "keywords": [
          "select *", "star", "all columns", "projection", "unnecessary columns",
          "wildcard", "over-fetching", "column selection"
        ]
      }
    ],
    "max_steps": 6
  },
  {
    "task_id": "medium_007",
    "difficulty": "medium",
    "query": "SELECT * FROM products ORDER BY RAND() LIMIT 10;",
    "schema": {
      "products": {
        "id": "INT PRIMARY KEY",
        "name": "VARCHAR(255)",
        "price": "DECIMAL(10,2)",
        "category": "VARCHAR(64)"
      }
    },
    "context": "Show 10 random products on the homepage.",
    "ground_truth_issues": [
      {
        "id": "medium_007_order_rand",
        "category": "performance",
        "description": "ORDER BY RAND() generates a random value for every row in the table, causing a full table scan and sort. Extremely slow on large tables.",
        "severity": 0.8,
        "fix": "SELECT * FROM products WHERE id >= (SELECT FLOOR(RAND() * (SELECT MAX(id) FROM products))) LIMIT 10;",
        "keywords": [
          "order by rand", "random", "full table scan", "sort", "performance",
          "slow", "every row", "random ordering", "rand function",
          "expensive sort", "large table"
        ]
      }
    ],
    "max_steps": 5
  }
]