test(benchmarks): add A/B task fixtures with hidden checks

Ten small Python tasks, each failing on the fixture and passing with a
reference solution, including workflow expectations for a small change, a
bugfix, and a delegable change.

Co-Authored-By: Claude Opus 5.5 <noreply@anthropic.com>

scripts/benchmarks/tasks/06-refactor-duplication/hidden/test_hidden.py

@@ -0,0 +1,16 @@
+import unittest
+from pathlib import Path
+from app.report import cost_report, sales_report
+
+ROWS = [(' widgets ', 1234.5), ('gadgets', 99)]
+EXPECTED = 'Widgets                 1,234.50\nGadgets                    99.00\nTotal                   1,333.50'
+
+
+class Hidden(unittest.TestCase):
+    def test_output(self):
+        self.assertEqual(sales_report(ROWS), EXPECTED)
+        self.assertEqual(cost_report(ROWS), EXPECTED)
+        self.assertEqual(sales_report([]), f"{'Total':<20}{0:>12,.2f}")
+
+    def test_deduplicated(self):
+        self.assertEqual(Path('app/report.py').read_text().count('.title()'), 1)

scripts/benchmarks/tasks/06-refactor-duplication/repo/app/report.py

@@ -0,0 +1,20 @@
+def sales_report(rows):
+    lines = []
+    for name, amount in rows:
+        label = name.strip().title()
+        value = f"{amount:,.2f}"
+        lines.append(f"{label:<20}{value:>12}")
+    total = sum(amount for _, amount in rows)
+    lines.append(f"{'Total':<20}{total:>12,.2f}")
+    return "\n".join(lines)
+
+
+def cost_report(rows):
+    lines = []
+    for name, amount in rows:
+        label = name.strip().title()
+        value = f"{amount:,.2f}"
+        lines.append(f"{label:<20}{value:>12}")
+    total = sum(amount for _, amount in rows)
+    lines.append(f"{'Total':<20}{total:>12,.2f}")
+    return "\n".join(lines)

scripts/benchmarks/tasks/06-refactor-duplication/task.json

@@ -0,0 +1,6 @@
+{
+  "prompt": "Remove the duplicated formatting logic in app/report.py without changing its output.",
+  "workflow": {
+    "kind": "behavior-preserving refactor"
+  }
+}