server/tasks/task1/grader.py

"""
grader.py  (Task 1 – Targeted Vulnerability Detection)
-------------------------------------------------------
Deterministic grader. Score range: 0.0 – 1.0

  1.0 – correct function + correct vulnerability keyword
  0.5 – correct function + wrong/unrecognised vulnerability keyword
  0.0 – wrong function name
"""
from __future__ import annotations
from typing import Dict
from utils import SemanticMatcher

class Task1Grader:
    def __init__(self, target_function: str, vulnerability_issue: str) -> None:
        self.target_function = target_function.lower()
        self.vulnerability_issue = vulnerability_issue

    def grade_submission(self, submitted_function: str, submitted_vuln_type: str) -> float:
        if submitted_function.strip().lower() != self.target_function:
            return 0.0
        return 1.0 if SemanticMatcher().match(self.vulnerability_issue, submitted_vuln_type) else 0.5

    def reward_for_score(self, score: float) -> float:
        if score == 1.0: return 5.0
        if score == 0.5: return 1.0
        return -1.5

    def get_canonical_answer(self) -> Dict[str, str]:
        return {"function": self.target_function, "vulnerability": self.vulnerability_issue}