config file initialize

inference.py

@@ -0,0 +1,63 @@
+import os
+import json
+import argparse
+from typing import Dict, Any, Optional
+import requests
+
+API_BASE_URL = os.environ.get("API_BASE_URL", "https://api.openai.com/v1")
+MODEL_NAME = os.environ.get("MODEL_NAME", "gpt-4")
+API_KEY = os.environ.get("API_KEY", os.environ.get("OPENAI_API_KEY", ""))
+TEMPERATURE = float(os.environ.get("TEMPERATURE", "0.7")) 
+MAX_TOKENS = int(os.environ.get("MAX_TOKENS", "2000"))
+
+FALLBACK_ACTION = '{"action_type": "request_changes", "comments": [], "suggestions": []}'
+
+
+class LLMClient:
+    
+    def __init__(self, base_url: str, api_key: str, model: str):
+        self.base_url = base_url.rstrip('/')
+        self.api_key = api_key
+        self.model = model
+        self.api_type = self._detect_api_type()
+        
+    def _detect_api_type(self) -> str:
+        if "googleapis.com" in self.base_url or "generativelanguage" in self.base_url:
+            return "gemini"
+        elif "openai.com" in self.base_url:
+            return "openai"
+        else:
+            return "openai_compatible"
+    
+    def chat_completion(self, messages: list, temperature: float = 0.7, max_tokens: int = 2000) -> str:
+        if self.api_type == "gemini":
+            return self._gemini_completion(messages, temperature, max_tokens)
+        else:
+            return self._openai_completion(messages, temperature, max_tokens)
+    
+    def _openai_completion(self, messages: list, temperature: float, max_tokens: int) -> str:
+        headers = {
+            "Authorization": f"Bearer {self.api_key}",
+            "Content-Type": "application/json"
+        }
+        
+        payload = {
+            "model": self.model,
+            "messages": messages,
+            "temperature": temperature,
+            "max_tokens": max_tokens
+        }
+        
+        try:
+            response = requests.post(
+                f"{self.base_url}/chat/completions",
+                headers=headers,
+                json=payload,
+                timeout=30
+            )
+            response.raise_for_status()
+            result = response.json()
+            return result["choices"][0]["message"]["content"]
+        except Exception as e:
+            print(f"OpenAI API error: {e}")
+            raise

openenv.yaml

@@ -0,0 +1,56 @@
+name: code-review-agent-env
+version: 1.0.0
+description: |
+  A realistic code review environment where AI agents review pull requests,
+  identify issues, suggest improvements, and make approval decisions.
+  Models real-world software development workflows.
+
+authors:
+  - Ashish <ashishkbaberwal@gmail.com>
+  - Shardul <shardulmd@gmail.com>
+  - Harshit <shakyanitin807@gmail.com>
+tags:
+  - code-review
+  - software-engineering
+  - agent-evaluation
+  - real-world-task
+
+license: MIT
+
+environment:
+  class: environment.env.CodeReviewEnv
+  entry_point: environment.env:CodeReviewEnv
+
+tasks:
+  - id: bug_detection_easy
+    name: "Easy: Detect Division by Zero"
+    difficulty: easy
+    
+  - id: bug_detection_medium
+    name: "Medium: Memory Leak Detection"
+    difficulty: medium
+    
+  - id: bug_detection_hard
+    name: "Hard: SQL Injection Vulnerability"
+    difficulty: hard
+
+observation_space:
+  type: dict
+  description: |
+    Contains code diff, file context, and review status
+
+action_space:
+  type: dict
+  description: |
+    Actions include adding comments, suggesting fixes, approving, or requesting changes
+
+reward_range:
+  min: 0.0
+  max: 1.0
+
+max_episode_steps: 50
+
+requires_api_keys:
+  - API_KEY
+  - API_BASE_URL
+  - MODEL_NAME