Add evaluation report

eval-report.json

@@ -1,7 +1,7 @@
 {
   "adapter": "Taimwe/securecoder-30b-pro",
   "base": "unsloth/Qwen3-Coder-30B-A3B-Instruct",
-  "when": "2026-09-25T10:38:09Z",
+  "when": "2026-09-25T11:02:30Z",
   "sections": [
     {
       "section": "tool_calls",
@@ -12,9 +12,9 @@
     },
     {
       "section": "code_sanity",
-      "n_prompts": 0,
-      "ast_rate": 0.0,
-      "compile_rate": 0.0
+      "n_prompts": 15,
+      "ast_rate": 0.06666666666666667,
+      "compile_rate": 0.06666666666666667
     },
     {
       "section": "security_mcq",
@@ -3639,10 +3639,101 @@
     },
     {
       "section": "code_sanity",
-      "n_prompts": 0,
-      "ast_rate": 0.0,
-      "compile_rate": 0.0,
-      "details": []
+      "n_prompts": 15,
+      "ast_rate": 0.06666666666666667,
+      "compile_rate": 0.06666666666666667,
+      "details": [
+        {
+          "prompt": "Write a Python function `def is_palindrome(s: str) -> bool:`",
+          "ast_ok": null,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n```"
+        },
+        {
+          "prompt": "Write a Python function `def merge_intervals(intervals: list",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\nfrom typing import List\\n\\ndef merge_intervals(intervals: List[List[int]]) -> List[List[int]]:\\n    if not intervals:\\n        return []\\n    \\n    #"
+        },
+        {
+          "prompt": "Write a Python function `def two_sum(nums: list[int], target",
+          "ast_ok": null,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n```"
+        },
+        {
+          "prompt": "Write a Python function `def flatten(nested: list) -> list:`",
+          "ast_ok": true,
+          "compile_ok": true,
+          "reply_first_160": "```python\ndef flatten(nested: list) -> list:\n    result = []\n    for item in nested:\n        if isinstance(item, list):\n            result.extend(flatten(item))"
+        },
+        {
+          "prompt": "Write a Python function `def parse_csv_line(line: str) -> li",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\nimport csv\\n\\ndef parse_csv_line(line: str) -> list[str]:\\n    reader = csv.reader([line], dialect='excel', quoting=csv.QUOTE_MINIMAL)\\n    return ne"
+        },
+        {
+          "prompt": "Write a Python function `def lru_cache(k: int):` returning a",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\nfrom collections import OrderedDict\\ndef lru_cache(k: int):\\n    def decorator(func):\\n        cache = OrderedDict()\\n        def wrapper(*args, **kw"
+        },
+        {
+          "prompt": "Write a Python function `def is_anagram(a: str, b: str) -> b",
+          "ast_ok": null,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n```"
+        },
+        {
+          "prompt": "Write a Python function `def topological_order(graph: dict[s",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\ndef topological_order(graph: dict[str, list[str]]) -> list[str] | None:\\n    # Create a set of all nodes in the graph\\n    nodes = set(graph.keys())\\"
+        },
+        {
+          "prompt": "Write a Python function `def tokenise(s: str) -> list[str]:`",
+          "ast_ok": null,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n```\n"
+        },
+        {
+          "prompt": "Write a Python function `def slugify(text: str) -> str:` pro",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\nfrom unicodedata import normalize\\n\\ndef slugify(text: str) -> str:\\n    # Normalize the text to NFKD form\\n    normalized = normalize('NFKD', text)\\"
+        },
+        {
+          "prompt": "Write a Python function `def read_jsonl(path: str) -> list[d",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\nimport json\\n\\ndef read_jsonl(path: str) -> list[dict]:\\n    with open(path, 'r') as f:\\n        for line in f:\\n            yield json.loads(line)\\n"
+        },
+        {
+          "prompt": "Write a Python function `def binary_search(arr: list[int], t",
+          "ast_ok": null,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n```"
+        },
+        {
+          "prompt": "Write a Python function `def unique_in_order(s: str) -> list",
+          "ast_ok": null,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n    result = []\\n    for i, char in enumerate(s):\\n        if not result or result[-1] != char:\\n            result.append(char)\\n    return result\\n"
+        },
+        {
+          "prompt": "Write a Python function `def safe_eval(expr: str) -> int:` e",
+          "ast_ok": false,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n\\ndef safe_eval(expr: str) -> int:\\n    def tokenize(s):\\n        tokens = []\\n        i = 0\\n        while i < len(s):\\n            if s[i].isdigit("
+        },
+        {
+          "prompt": "Write a Python function `def dedupe_preserve_order(items: li",
+          "ast_ok": null,
+          "compile_ok": null,
+          "reply_first_160": "```python\\n    seen = set()\\n    result = []\\n    for item in items:\\n        if item not in seen:\\n            seen.add(item)\\n            result.append(item)\\"
+        }
+      ]
     },
     {
       "section": "security_mcq",