commit

environment/models.py

@@ -0,0 +1,49 @@
+from pydantic import BaseModel
+from typing import Optional, Dict, Any, List
+
+
+class Issue(BaseModel):
+    line_number: Optional[int] = None
+    issue_type: str  # "syntax_error", "logic_bug", "security_vulnerability"
+    description: str
+    severity: str = "medium"  # "low", "medium", "high", "critical"
+
+
+class CodeReviewAction(BaseModel):
+    identified_issues: List[Issue] = []
+    suggested_fix: Optional[str] = None  # corrected code as a string
+    explanation: str = ""
+    done: bool = False
+
+
+class CodeReviewObservation(BaseModel):
+    task_id: str
+    task_name: str
+    difficulty: str
+    language: str
+    code_snippet: str
+    context: str
+    step_number: int
+    max_steps: int
+    previous_feedback: Optional[str] = None
+
+
+class StepResult(BaseModel):
+    observation: CodeReviewObservation
+    reward: float
+    done: bool
+    info: Dict[str, Any] = {}
+
+
+class ResetResult(BaseModel):
+    observation: CodeReviewObservation
+    info: Dict[str, Any] = {}
+
+
+class StateResult(BaseModel):
+    task_id: str
+    step_number: int
+    total_reward: float
+    actions_history: List[Dict] = []
+    done: bool
+    initialized: bool