fix:minor

Dockerfile

@@ -1,22 +1,13 @@
-FROM python:3.11-slim
+FROM python:3.10
+
+ENV PYTHONUNBUFFERED=1
 
 WORKDIR /app
 
-# Copy requirements first for better caching
-COPY requirements.txt .
+COPY . .
 
-# Install dependencies
 RUN pip install --no-cache-dir -r requirements.txt
 
-# Copy application code
-COPY . .
-
-# Expose port for HuggingFace Spaces
 EXPOSE 7860
 
-# Set environment variables
-ENV PYTHONPATH=/app
-ENV PYTHONUNBUFFERED=1
-
-# Run the application (supports both inference and Space deployment)
 CMD ["python", "app.py"]

README.md

@@ -1,12 +1,6 @@
 ---
-title: Code_man
-emoji: "🚀"
-colorFrom: blue
-colorTo: purple
 sdk: docker
 app_port: 7860
-app_file: app.py
-pinned: false
 ---
 # CodeGuardian Inference Script
 

app.py

@@ -2,9 +2,11 @@
 
 import os
 import sys
+import logging
+
+import uvicorn
 import gradio as gr
 from typing import Dict, Any, Optional, List
-import logging
 
 from fastapi import Body, FastAPI
 from pydantic import BaseModel, ConfigDict, Field
@@ -13,8 +15,7 @@ from pydantic import BaseModel, ConfigDict, Field
 sys.path.insert(0, os.path.dirname(os.path.abspath(__file__)))
 
 from env.environment import CodeGuardianEnv
-from env.models import Action, Observation, AgentState, AgentResponse
-import plotly.graph_objects as go
+from env.models import Action, Observation
 import plotly.express as px
 import pandas as pd
 
@@ -343,21 +344,6 @@ def update_ui():
 # OpenEnv / TRL-style HTTP API — register routes on FastAPI before mounting Gradio at "/".
 
 
-class OpenEnvResetRequest(BaseModel):
-    model_config = ConfigDict(extra="allow")
-
-    seed: Optional[int] = None
-    episode_id: Optional[str] = None
-
-
-class OpenEnvResetResponse(BaseModel):
-    model_config = ConfigDict(extra="forbid")
-
-    observation: Dict[str, Any] = Field(default_factory=dict)
-    reward: float = 0.0
-    done: bool = False
-
-
 class OpenEnvStepRequest(BaseModel):
     model_config = ConfigDict(extra="allow")
 
@@ -374,25 +360,30 @@ class OpenEnvStepResponse(BaseModel):
     done: bool = False
 
 
-app = FastAPI(title="CodeGuardian OpenEnv")
+app = FastAPI()
 
 
-@app.post("/reset", response_model=OpenEnvResetResponse)
-async def openenv_reset(
-    _body: OpenEnvResetRequest = Body(default_factory=OpenEnvResetRequest),
-) -> OpenEnvResetResponse:
-    """OpenEnv reset check: body is always observation {}, reward 0.0, done false; env still resets."""
+@app.post("/reset")
+def reset():
     try:
         obs = space.env.reset()
         space.current_obs = obs
-        logger.info("OpenEnv POST /reset ok (task_id=%s)", getattr(obs, "task_id", None))
+
+        if hasattr(obs, "model_dump"):
+            obs = obs.model_dump()
+
+        return {
+            "observation": obs,
+            "reward": 0.0,
+            "done": False,
+        }
     except Exception as e:
-        logger.error("OpenEnv POST /reset env.reset failed: %s", e, exc_info=True)
-    return OpenEnvResetResponse(
-        observation={},
-        reward=0.0,
-        done=False,
-    )
+        print("RESET ERROR:", e)
+        return {
+            "observation": {},
+            "reward": 0.0,
+            "done": False,
+        }
 
 
 @app.post("/step", response_model=OpenEnvStepResponse)
@@ -550,7 +541,6 @@ demo.queue()
 app = gr.mount_gradio_app(app, demo, path="/")
 
 if __name__ == "__main__":
-    import uvicorn
-
-    PORT = int(os.environ.get("PORT", "7860"))
-    uvicorn.run("app:app", host="0.0.0.0", port=PORT)
+    port = int(os.environ.get("PORT", 7860))
+    print("SERVER STARTED ON PORT", port)
+    uvicorn.run("app:app", host="0.0.0.0", port=port)

requirements.txt

@@ -1,13 +1,10 @@
-# Hugging Face Space / OpenEnv server (required)
 fastapi>=0.110.0
 uvicorn[standard]>=0.27.0
 gradio>=4.0.0
 openai>=1.0.0
-
 pydantic>=2.0.0
+pandas>=2.0.0
+plotly>=5.0.0
 gymnasium>=0.28.0
 numpy>=1.24.0
 python-dotenv>=1.0.0
-flask>=3.0.0
-plotly
-pandas