test(benchmarks): add concept-search tasks

Three tasks whose target code shares no vocabulary with the prompt, run in a
repository with generated distractor modules.

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

scripts/benchmarks/tasks/13-search-cent-rounding/hidden/test_hidden.py

@@ -0,0 +1,10 @@
+import unittest
+from app.fin.tally import consolidate
+
+
+class Hidden(unittest.TestCase):
+    def test_half_up(self):
+        self.assertEqual(float(consolidate([1.005])), 1.01)
+        self.assertEqual(float(consolidate([2.675])), 2.68)
+        self.assertEqual(float(consolidate([1.0, 0.004])), 1.0)
+        self.assertEqual(float(consolidate([0.1, 0.2])), 0.3)

scripts/benchmarks/tasks/13-search-cent-rounding/repo/app/fin/tally.py

@@ -0,0 +1,3 @@
+def consolidate(lines):
+    """Sum line amounts and return the figure for the document footer."""
+    return round(sum(lines), 2)

scripts/benchmarks/tasks/13-search-cent-rounding/task.json

@@ -0,0 +1,9 @@
+{
+  "prompt": "Invoice totals are sometimes one cent too low, for example 1.005 shows as 1.00. Round half amounts up to the next cent.",
+  "generate": {
+    "filler_modules": 250
+  },
+  "workflow": {
+    "kind": "concept search in a large repository"
+  }
+}