chore: initialize python virtual environment and dependencies

app.py → server/app.py

@@ -3,7 +3,7 @@ import uvicorn
 from fastapi import FastAPI, HTTPException, Query
 from fastapi.middleware.cors import CORSMiddleware
 
-from .models import CodeReviewAction, CodeReviewState, StepResponse, ResetResponse
+from .server.models import CodeReviewAction, CodeReviewState, StepResponse, ResetResponse
 from .environment import CodeReviewEnvironment
 
 app = FastAPI(

environment.py → server/environment.py

@@ -1,15 +1,14 @@
 from typing import Dict, Any, Tuple, Optional
-from .models import CodeReviewAction, CodeReviewObservation, CodeReviewState
+from .server.models import CodeReviewAction, CodeReviewObservation, CodeReviewState
 
 MAX_STEPS = 3
 
-# ──────────────────────────────────────────────
 # TASK DEFINITIONS
-# ──────────────────────────────────────────────
+
 
 TASKS: Dict[str, dict] = {
 
-    # ── EASY ─────────────────────────────────
+    # EASY 
     "easy": {
         "id": "task_easy_001",
         "difficulty": "easy",
@@ -50,7 +49,7 @@ TASKS: Dict[str, dict] = {
         },
     },
 
-    # ── MEDIUM ────────────────────────────────
+    #MEDIUM 
     "medium": {
         "id": "task_medium_001",
         "difficulty": "medium",
@@ -148,9 +147,9 @@ TASKS: Dict[str, dict] = {
 }
 
 
-# ──────────────────────────────────────────────
+
 # GRADER
-# ──────────────────────────────────────────────
+
 
 def grade_action(action: CodeReviewAction, task: dict) -> Tuple[float, Dict]:
     """
@@ -239,10 +238,8 @@ def grade_action(action: CodeReviewAction, task: dict) -> Tuple[float, Dict]:
 
     return total, {"breakdown": breakdown, "total_score": total, "feedback": feedback}
 
-
-# ──────────────────────────────────────────────
 # ENVIRONMENT
-# ──────────────────────────────────────────────
+
 
 class CodeReviewEnvironment:
     def __init__(self):
@@ -293,7 +290,7 @@ class CodeReviewEnvironment:
             )
         return self._state
 
-    # ── helpers ───────────────────────────────
+    # helpers
 
     def _build_obs(self, step_number: int, previous_feedback: Optional[str]) -> CodeReviewObservation:
         t = self._current_task
@@ -306,4 +303,4 @@ class CodeReviewEnvironment:
             step_number=step_number,
             max_steps=MAX_STEPS,
             previous_feedback=previous_feedback,
-        )
+        )

models.py → server/models.py

@@ -6,7 +6,7 @@ class CodeReviewAction(BaseModel):
     """Action taken by the agent: a structured code review."""
     bug_identified: bool = Field(..., description="Whether a bug was found")
     bug_location: str = Field(..., description="Location of the bug (function, line, variable)")
-    bug_type: str = Field(..., description="Type: off-by-one | logic-error | security-vulnerability | none")
+    bug_type: str = Field(..., description="Type: off-by-one | logic-error | security-vulnerability | null-dereference | none")
     bug_description: str = Field(..., description="Detailed explanation of why this is a bug")
     severity: str = Field(..., description="Severity: none | low | medium | high | critical")
     suggested_fix: str = Field(..., description="The corrected code or a description of how to fix it")
@@ -18,8 +18,8 @@ class CodeReviewObservation(BaseModel):
     language: str = Field(..., description="Programming language")
     task_description: str = Field(..., description="What the code is supposed to do")
     task_id: str = Field(..., description="Unique task identifier")
-    difficulty: str = Field(..., description="easy | medium | hard")
-    step_number: int = Field(..., description="Current step within this episode")
+    difficulty: str = Field(..., description="Level: easy | medium | hard")
+    step_number: int = Field(..., description="Current step number within this episode")
     max_steps: int = Field(..., description="Maximum steps allowed per episode")
     previous_feedback: Optional[str] = Field(None, description="Feedback from previous step if any")