Upload folder using huggingface_hub

README.md

@@ -144,13 +144,24 @@ Install the OpenEnv core package:
 ```bash
 pip install openenv-core
 ```
-# Terminal 1 — install packages
+
+Clone the repo
+```bash
+git clone https://github.com/Ajay-Ganapathy/code_review && cd code_review
+```
+
+Install packages
+```bash
 uv pip install -e .
+```
 
-# Terminal 1 — Run server locally
+`[OPTIONAL]` To run server locally
+```bash
 uv run server --host 0.0.0.0 --port 8000
- 
-# Terminal 2 — run the agent
+```
+
+Run the agent in another terminal
+```bash
 uv run python inference.py
 ```
  

client.py

@@ -113,15 +113,13 @@ class CodeReviewEnv(EnvClient[CodeReviewAction, CodeReviewObservation, State]):
         # Handle reward (reset vs step)
         reward_data = payload.get("reward")
         reward = None
-       
+
         if reward_data is not None:
             try:
                 reward = float(reward_data)
             except Exception:
                 reward = None
-           
 
-      
         return StepResult(
             observation=observation,
             reward=reward,

inference.py

@@ -233,10 +233,7 @@ async def run_episode(client, env):
         reward = result.reward
         done = result.done
 
-
-        log_step(
-            step=step, action=response_text, reward=reward , done=done, error=None
-        )
+        log_step(step=step, action=response_text, reward=reward, done=done, error=None)
         final_score = max(final_score, reward if reward else 0.0)
 
     return final_score

server/app.py

@@ -74,11 +74,11 @@ def main():
     import argparse
 
     parser = argparse.ArgumentParser()
-    host = "0.0.0.0"
+    parser.add_argument("--host" , type=str , default="0.0.0.0")
     parser.add_argument("--port", type=int, default=8000)
     args = parser.parse_args()
 
-    uvicorn.run(app, host=host, port=args.port)
+    uvicorn.run(app, host=args.host, port=args.port)
 
 
 if __name__ == "__main__":

server/code_review_environment.py

@@ -218,7 +218,7 @@ class CodeReviewEnvironment(Environment):
         # print("Obs == " , obs)
 
         rew = CodeReviewReward(score=score, feedback="graded")
-        print("Score == " , type(rew.score) , " --- " , rew.score)
+        print("Score == ", type(rew.score), " --- ", rew.score)
 
         # print("FINAL REWARD TYPE:", type(rew))
         # print("FINAL REWARD:", rew)