Add 5s timeout to code generation exec() — prevents infinite loops

Both compilation and test execution are wrapped with signal.alarm(5).
If generated code runs too long (infinite loop), it times out cleanly
with '❌ Timeout: Code läuft zu lange (Endlosschleife?)'.

NB01 verified: executes headless without errors.

Co-authored-by: Copilot <223556219+Copilot@users.noreply.github.com>

Author: abossard

notebooks/01_evaluation_and_tuning.ipynb

@@ -1138,7 +1138,51 @@
       "   ✅ flatten([1, [2], 3]) → [1, 2, 3]\n",
       "   ✅ flatten([1, [2, [3, [4]]]]) → [1, 2, 3, 4]\n",
       "\n",
-      "📝 Aufgabe: Write a function that counts the frequency of each word in a string and returns \n"
+      "📝 Aufgabe: Write a function that counts the frequency of each word in a string and returns \n",
+      "   Generierter Code:\n",
+      "   │ def word_frequency(string):\n",
+      "   │     # Split the string into words\n",
+      "   │     words = string.split()\n",
+      "   │     # Create a dictionary to store word counts\n",
+      "   │     frequency = {}\n",
+      "   │     # Count the frequency of each word\n",
+      "   │     for word in words:\n",
+      "   │         # Convert to lowercase to count \"Word\" and \"word\" as the same\n",
+      "   │ ... (18 Zeilen)\n",
+      "{'hello': 2, 'world': 1}\n",
+      "   ✅ word_frequency('the cat sat on the mat') → {'the': 2, 'cat': 1, 'sat': 1, 'on': 1, 'mat': 1}\n",
+      "\n",
+      "📝 Aufgabe: Write a function that removes duplicate elements from a list while preserving th\n",
+      "   Generierter Code:\n",
+      "   │ def remove_duplicates(input_list):\n",
+      "   │     seen = set()\n",
+      "   │     result = []\n",
+      "   │     for item in input_list:\n",
+      "   │         if item not in seen:\n",
+      "   │             seen.add(item)\n",
+      "   │             result.append(item)\n",
+      "   │     return result\n",
+      "   │ ... (12 Zeilen)\n",
+      "[1, 2, 3, 4, 5]\n",
+      "   ✅ remove_duplicates([1, 2, 3, 2, 1, 4]) → [1, 2, 3, 4]\n",
+      "\n",
+      "📝 Aufgabe: Write a function that evaluates a mathematical expression string containing inte\n",
+      "   Generierter Code:\n",
+      "   │ def evaluate_expression(expression: str) -> float:\n",
+      "   │     def precedence(op):\n",
+      "   │         if op in ('+', '-'):\n",
+      "   │             return 1\n",
+      "   │         if op in ('*', '/'):\n",
+      "   │             return 2\n",
+      "   │         return 0\n",
+      "   │ \n",
+      "   │ ... (69 Zeilen)\n",
+      "-27.0\n",
+      "   ✅ eval_expr('3 + 4 * 2') → 11.0\n",
+      "   ✅ eval_expr('(1 + 2) * (3 + 4)') → 21.0\n",
+      "   ✅ eval_expr('10 / 3') → 3.3333333333333335\n",
+      "   ✅ eval_expr('2 * 3 + 4 * 5') → 26.0\n",
+      "   ✅ eval_expr('(2 + 3) * (7 - 4) / 5') → 3.0\n"
      ]
     }
    ],
@@ -1210,8 +1254,22 @@
     "    # Generierte Funktion ausführen\n",
     "    gen_ns = {}\n",
     "    try:\n",
+    "        import signal\n",
+    "        def _timeout_handler(signum, frame):\n",
+    "            raise TimeoutError('Code execution took too long (possible infinite loop)')\n",
+    "        old_handler = signal.signal(signal.SIGALRM, _timeout_handler)\n",
+    "        signal.alarm(5)  # 5 second timeout\n",
     "        exec(compile(code, '<generated>', 'exec'), gen_ns)\n",
+    "        signal.alarm(0)  # cancel timeout\n",
+    "        signal.signal(signal.SIGALRM, old_handler)\n",
+    "    except TimeoutError:\n",
+    "        signal.alarm(0)\n",
+    "        print(f\"   ❌ Timeout: Code läuft zu lange (Endlosschleife?)\")\n",
+    "        tasks_error += 1\n",
+    "        print()\n",
+    "        continue\n",
     "    except Exception as e:\n",
+    "        signal.alarm(0)\n",
     "        print(f\"   ❌ Kompilierung fehlgeschlagen: {type(e).__name__}: {e}\")\n",
     "        tasks_error += 1\n",
     "        print()\n",
@@ -1253,8 +1311,11 @@
     "    task_ok = True\n",
     "    for args in test_inputs:\n",
     "        try:\n",
+    "            signal.signal(signal.SIGALRM, _timeout_handler)\n",
+    "            signal.alarm(5)\n",
     "            expected = ref_func(*args)\n",
     "            got = gen_func(*args)\n",
+    "            signal.alarm(0)\n",
     "            # Für Floats: Toleranz-Vergleich\n",
     "            if isinstance(expected, float) and isinstance(got, (int, float)):\n",
     "                match = abs(float(got) - expected) < 1e-6\n",
@@ -1606,4 +1667,4 @@
  },
  "nbformat": 4,
  "nbformat_minor": 5
-}
+}