Upload folder using huggingface_hub

Dockerfile

@@ -0,0 +1,81 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+# Multi-stage build using openenv-base
+# This Dockerfile is flexible and works for both:
+# - In-repo environments (with local OpenEnv sources)
+# - Standalone environments (with openenv from PyPI/Git)
+# The build script (openenv build) handles context detection and sets appropriate build args.
+
+ARG BASE_IMAGE=ghcr.io/meta-pytorch/openenv-base:latest
+FROM ${BASE_IMAGE} AS builder
+
+WORKDIR /app
+
+# Ensure git is available (required for installing dependencies from VCS)
+RUN apt-get update && \
+    apt-get install -y --no-install-recommends git && \
+    rm -rf /var/lib/apt/lists/*
+
+# Build argument to control whether we're building standalone or in-repo
+ARG BUILD_MODE=in-repo
+ARG ENV_NAME=code_review_env
+
+# Copy environment code (always at root of build context)
+COPY . /app/env
+
+# For in-repo builds, openenv is already vendored in the build context
+# For standalone builds, openenv will be installed via pyproject.toml
+WORKDIR /app/env
+
+# Ensure uv is available (for local builds where base image lacks it)
+RUN if ! command -v uv >/dev/null 2>&1; then \
+        curl -LsSf https://astral.sh/uv/install.sh | sh && \
+        mv /root/.local/bin/uv /usr/local/bin/uv && \
+        mv /root/.local/bin/uvx /usr/local/bin/uvx; \
+    fi
+    
+# Install dependencies using uv sync
+# If uv.lock exists, use it; otherwise resolve on the fly
+RUN --mount=type=cache,target=/root/.cache/uv \
+    if [ -f uv.lock ]; then \
+        uv sync --frozen --no-install-project --no-editable; \
+    else \
+        uv sync --no-install-project --no-editable; \
+    fi
+
+RUN --mount=type=cache,target=/root/.cache/uv \
+    if [ -f uv.lock ]; then \
+        uv sync --frozen --no-editable; \
+    else \
+        uv sync --no-editable; \
+    fi
+
+# Final runtime stage
+FROM ${BASE_IMAGE}
+
+WORKDIR /app
+
+# Copy the virtual environment from builder
+COPY --from=builder /app/env/.venv /app/.venv
+
+# Copy the environment code
+COPY --from=builder /app/env /app/env
+
+# Set PATH to use the virtual environment
+ENV PATH="/app/.venv/bin:$PATH"
+
+# Set PYTHONPATH so imports work correctly
+ENV PYTHONPATH="/app/env:$PYTHONPATH"
+
+# Health check
+HEALTHCHECK --interval=30s --timeout=3s --start-period=5s --retries=3 \
+    CMD curl -f http://localhost:8000/health || exit 1
+
+# Run the FastAPI server
+# The module path is constructed to work with the /app/env structure
+ENV ENABLE_WEB_INTERFACE=true
+CMD ["sh", "-c", "cd /app/env && uvicorn server.app:app --host 0.0.0.0 --port 8000"]

README.md

@@ -1,10 +1,255 @@
 ---
-title: Code Review Env
-emoji: 🐢
-colorFrom: purple
-colorTo: purple
+title: Code Review Env Environment Server
+emoji: 🎯
+colorFrom: pink
+colorTo: pink
 sdk: docker
 pinned: false
+app_port: 8000
+base_path: /web
+tags:
+  - openenv
 ---
 
-Check out the configuration reference at https://huggingface.co/docs/hub/spaces-config-reference
+# Code Review Env Environment
+
+A simple test environment that echoes back messages. Perfect for testing the env APIs as well as demonstrating environment usage patterns.
+
+## Quick Start
+
+The simplest way to use the Code Review Env environment is through the `CodeReviewEnv` class:
+
+```python
+from code_review_env import CodeReviewAction, CodeReviewEnv
+
+try:
+    # Create environment from Docker image
+    code_review_envenv = CodeReviewEnv.from_docker_image("code_review_env-env:latest")
+
+    # Reset
+    result = code_review_envenv.reset()
+    print(f"Reset: {result.observation.echoed_message}")
+
+    # Send multiple messages
+    messages = ["Hello, World!", "Testing echo", "Final message"]
+
+    for msg in messages:
+        result = code_review_envenv.step(CodeReviewAction(message=msg))
+        print(f"Sent: '{msg}'")
+        print(f"  → Echoed: '{result.observation.echoed_message}'")
+        print(f"  → Length: {result.observation.message_length}")
+        print(f"  → Reward: {result.reward}")
+
+finally:
+    # Always clean up
+    code_review_envenv.close()
+```
+
+That's it! The `CodeReviewEnv.from_docker_image()` method handles:
+- Starting the Docker container
+- Waiting for the server to be ready
+- Connecting to the environment
+- Container cleanup when you call `close()`
+
+## Building the Docker Image
+
+Before using the environment, you need to build the Docker image:
+
+```bash
+# From project root
+docker build -t code_review_env-env:latest -f server/Dockerfile .
+```
+
+## Deploying to Hugging Face Spaces
+
+You can easily deploy your OpenEnv environment to Hugging Face Spaces using the `openenv push` command:
+
+```bash
+# From the environment directory (where openenv.yaml is located)
+openenv push
+
+# Or specify options
+openenv push --namespace my-org --private
+```
+
+The `openenv push` command will:
+1. Validate that the directory is an OpenEnv environment (checks for `openenv.yaml`)
+2. Prepare a custom build for Hugging Face Docker space (enables web interface)
+3. Upload to Hugging Face (ensuring you're logged in)
+
+### Prerequisites
+
+- Authenticate with Hugging Face: The command will prompt for login if not already authenticated
+
+### Options
+
+- `--directory`, `-d`: Directory containing the OpenEnv environment (defaults to current directory)
+- `--repo-id`, `-r`: Repository ID in format 'username/repo-name' (defaults to 'username/env-name' from openenv.yaml)
+- `--base-image`, `-b`: Base Docker image to use (overrides Dockerfile FROM)
+- `--private`: Deploy the space as private (default: public)
+
+### Examples
+
+```bash
+# Push to your personal namespace (defaults to username/env-name from openenv.yaml)
+openenv push
+
+# Push to a specific repository
+openenv push --repo-id my-org/my-env
+
+# Push with a custom base image
+openenv push --base-image ghcr.io/meta-pytorch/openenv-base:latest
+
+# Push as a private space
+openenv push --private
+
+# Combine options
+openenv push --repo-id my-org/my-env --base-image custom-base:latest --private
+```
+
+After deployment, your space will be available at:
+`https://huggingface.co/spaces/<repo-id>`
+
+The deployed space includes:
+- **Web Interface** at `/web` - Interactive UI for exploring the environment
+- **API Documentation** at `/docs` - Full OpenAPI/Swagger interface
+- **Health Check** at `/health` - Container health monitoring
+- **WebSocket** at `/ws` - Persistent session endpoint for low-latency interactions
+
+## Environment Details
+
+### Action
+**CodeReviewAction**: Contains a single field
+- `message` (str) - The message to echo back
+
+### Observation
+**CodeReviewObservation**: Contains the echo response and metadata
+- `echoed_message` (str) - The message echoed back
+- `message_length` (int) - Length of the message
+- `reward` (float) - Reward based on message length (length × 0.1)
+- `done` (bool) - Always False for echo environment
+- `metadata` (dict) - Additional info like step count
+
+### Reward
+The reward is calculated as: `message_length × 0.1`
+- "Hi" → reward: 0.2
+- "Hello, World!" → reward: 1.3
+- Empty message → reward: 0.0
+
+## Advanced Usage
+
+### Connecting to an Existing Server
+
+If you already have a Code Review Env environment server running, you can connect directly:
+
+```python
+from code_review_env import CodeReviewEnv
+
+# Connect to existing server
+code_review_envenv = CodeReviewEnv(base_url="<ENV_HTTP_URL_HERE>")
+
+# Use as normal
+result = code_review_envenv.reset()
+result = code_review_envenv.step(CodeReviewAction(message="Hello!"))
+```
+
+Note: When connecting to an existing server, `code_review_envenv.close()` will NOT stop the server.
+
+### Using the Context Manager
+
+The client supports context manager usage for automatic connection management:
+
+```python
+from code_review_env import CodeReviewAction, CodeReviewEnv
+
+# Connect with context manager (auto-connects and closes)
+with CodeReviewEnv(base_url="http://localhost:8000") as env:
+    result = env.reset()
+    print(f"Reset: {result.observation.echoed_message}")
+    # Multiple steps with low latency
+    for msg in ["Hello", "World", "!"]:
+        result = env.step(CodeReviewAction(message=msg))
+        print(f"Echoed: {result.observation.echoed_message}")
+```
+
+The client uses WebSocket connections for:
+- **Lower latency**: No HTTP connection overhead per request
+- **Persistent session**: Server maintains your environment state
+- **Efficient for episodes**: Better for many sequential steps
+
+### Concurrent WebSocket Sessions
+
+The server supports multiple concurrent WebSocket connections. To enable this,
+modify `server/app.py` to use factory mode:
+
+```python
+# In server/app.py - use factory mode for concurrent sessions
+app = create_app(
+    CodeReviewEnvironment,  # Pass class, not instance
+    CodeReviewAction,
+    CodeReviewObservation,
+    max_concurrent_envs=4,  # Allow 4 concurrent sessions
+)
+```
+
+Then multiple clients can connect simultaneously:
+
+```python
+from code_review_env import CodeReviewAction, CodeReviewEnv
+from concurrent.futures import ThreadPoolExecutor
+
+def run_episode(client_id: int):
+    with CodeReviewEnv(base_url="http://localhost:8000") as env:
+        result = env.reset()
+        for i in range(10):
+            result = env.step(CodeReviewAction(message=f"Client {client_id}, step {i}"))
+        return client_id, result.observation.message_length
+
+# Run 4 episodes concurrently
+with ThreadPoolExecutor(max_workers=4) as executor:
+    results = list(executor.map(run_episode, range(4)))
+```
+
+## Development & Testing
+
+### Direct Environment Testing
+
+Test the environment logic directly without starting the HTTP server:
+
+```bash
+# From the server directory
+python3 server/code_review_env_environment.py
+```
+
+This verifies that:
+- Environment resets correctly
+- Step executes actions properly
+- State tracking works
+- Rewards are calculated correctly
+
+### Running Locally
+
+Run the server locally for development:
+
+```bash
+uvicorn server.app:app --reload
+```
+
+## Project Structure
+
+```
+code_review_env/
+├── .dockerignore         # Docker build exclusions
+├── __init__.py            # Module exports
+├── README.md              # This file
+├── openenv.yaml           # OpenEnv manifest
+├── pyproject.toml         # Project metadata and dependencies
+├── uv.lock                # Locked dependencies (generated)
+├── client.py              # CodeReviewEnv client
+├── models.py              # Action and Observation models
+└── server/
+    ├── __init__.py        # Server module exports
+    ├── code_review_env_environment.py  # Core environment logic
+    ├── app.py             # FastAPI application (HTTP + WebSocket endpoints)
+    └── Dockerfile         # Container image definition
+```

__init__.py

@@ -0,0 +1,16 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""Code Review Env Environment."""
+
+from .client import CodeReviewEnv
+from .models import CodeReviewAction, CodeReviewObservation
+
+__all__ = [
+    "CodeReviewAction",
+    "CodeReviewObservation",
+    "CodeReviewEnv",
+]

baseline.py

@@ -0,0 +1,145 @@
+#!/usr/bin/env python3
+"""
+Standalone baseline inference script.
+Uses OpenAI gpt-4o-mini to review Python code across 3 difficulty levels.
+Saves results to baseline_scores.json.
+"""
+
+import os
+import json
+import requests
+from openai import OpenAI
+
+# Initialize OpenAI client
+api_key = os.getenv("OPENAI_API_KEY")
+if not api_key:
+    raise ValueError("OPENAI_API_KEY environment variable not set")
+
+client = OpenAI(api_key=api_key)
+
+# Server endpoint
+BASE_URL = "http://localhost:8000"
+TASKS = ["easy", "medium", "hard"]
+
+def reset_task(task_id: str) -> dict:
+    """Reset environment for a given task_id."""
+    response = requests.post(
+        f"{BASE_URL}/reset",
+        json={"task_id": task_id}
+    )
+    response.raise_for_status()
+    return response.json()
+
+def step_task(action: dict) -> dict:
+    """Submit action to environment and get observation."""
+    response = requests.post(
+        f"{BASE_URL}/step",
+        json={"action": action}
+    )
+    response.raise_for_status()
+    return response.json()
+
+def review_code(code_snippet: str) -> dict:
+    """Use GPT-4o-mini to review code snippet."""
+    prompt = f"""Review this Python code. Reply as JSON with keys: review (str), bug_type (syntax/logic/security/none), line_number (int), confidence (float)
+
+Code:
+{code_snippet}"""
+
+    response = client.chat.completions.create(
+        model="gpt-4o-mini",
+        messages=[
+            {"role": "user", "content": prompt}
+        ],
+        temperature=0.7
+    )
+    
+    content = response.choices[0].message.content
+    
+    # Try to extract JSON from response
+    try:
+        # First try direct JSON parsing
+        result = json.loads(content)
+    except json.JSONDecodeError:
+        # Try to find JSON in the response text
+        start = content.find('{')
+        end = content.rfind('}') + 1
+        if start != -1 and end > start:
+            result = json.loads(content[start:end])
+        else:
+            raise ValueError(f"Could not parse JSON from response: {content}")
+    
+    return result
+
+def run_baseline():
+    """Run baseline inference on all tasks."""
+    results = {
+        "scores": {},
+        "details": {}
+    }
+    
+    for task_id in TASKS:
+        print(f"\n{'='*60}")
+        print(f"Running task: {task_id}")
+        print('='*60)
+        
+        # Reset environment
+        obs = reset_task(task_id)
+        code_snippet = obs.get("code_snippet", "")
+        print(f"Code snippet:\n{code_snippet}\n")
+        
+        # Get review from GPT-4o-mini
+        print("Calling GPT-4o-mini for review...")
+        review_result = review_code(code_snippet)
+        print(f"Review result: {review_result}")
+        
+        # Prepare action
+        action = {
+            "review": review_result.get("review", ""),
+            "bug_type": review_result.get("bug_type", "none"),
+            "line_number": int(review_result.get("line_number", -1)),
+            "confidence": float(review_result.get("confidence", 0.0))
+        }
+        
+        # Submit action to environment
+        print(f"Submitting action: {action}")
+        step_obs = step_task(action)
+        
+        # Extract score from observation
+        # The step response should have reward/score information
+        score = step_obs.get("cumulative_reward", 0.0)
+        feedback = step_obs.get("previous_feedback", "")
+        
+        print(f"Score: {score}")
+        print(f"Feedback: {feedback}")
+        
+        results["scores"][task_id] = score
+        results["details"][task_id] = {
+            "action": action,
+            "feedback": feedback,
+            "score": score
+        }
+    
+    # Calculate average
+    scores = list(results["scores"].values())
+    average = sum(scores) / len(scores) if scores else 0.0
+    results["average"] = round(average, 4)
+    
+    # Print summary
+    print(f"\n{'='*60}")
+    print("BASELINE RESULTS")
+    print('='*60)
+    for task_id in TASKS:
+        print(f"{task_id:10s}: {results['scores'][task_id]:.4f}")
+    print(f"{'Average':10s}: {results['average']:.4f}")
+    print('='*60 + "\n")
+    
+    # Save to file
+    with open("baseline_scores.json", "w") as f:
+        json.dump(results, f, indent=2)
+    
+    print("Results saved to baseline_scores.json")
+    return results
+
+if __name__ == "__main__":
+    run_baseline()

client.py

@@ -0,0 +1,99 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""Code Review Env Environment Client."""
+
+from typing import Dict
+
+from openenv.core import EnvClient
+from openenv.core.client_types import StepResult
+from openenv.core.env_server.types import State
+
+from .models import CodeReviewAction, CodeReviewObservation
+
+
+class CodeReviewEnv(
+    EnvClient[CodeReviewAction, CodeReviewObservation, State]
+):
+    """
+    Client for the Code Review Env Environment.
+
+    This client maintains a persistent WebSocket connection to the environment server,
+    enabling efficient multi-step interactions with lower latency.
+    Each client instance has its own dedicated environment session on the server.
+
+    Example:
+        >>> # Connect to a running server
+        >>> with CodeReviewEnv(base_url="http://localhost:8000") as client:
+        ...     result = client.reset()
+        ...     print(result.observation.echoed_message)
+        ...
+        ...     result = client.step(CodeReviewAction(message="Hello!"))
+        ...     print(result.observation.echoed_message)
+
+    Example with Docker:
+        >>> # Automatically start container and connect
+        >>> client = CodeReviewEnv.from_docker_image("code_review_env-env:latest")
+        >>> try:
+        ...     result = client.reset()
+        ...     result = client.step(CodeReviewAction(message="Test"))
+        ... finally:
+        ...     client.close()
+    """
+
+    def _step_payload(self, action: CodeReviewAction) -> Dict:
+        """
+        Convert CodeReviewAction to JSON payload for step message.
+
+        Args:
+            action: CodeReviewAction instance
+
+        Returns:
+            Dictionary representation suitable for JSON encoding
+        """
+        return {
+            "message": action.message,
+        }
+
+    def _parse_result(self, payload: Dict) -> StepResult[CodeReviewObservation]:
+        """
+        Parse server response into StepResult[CodeReviewObservation].
+
+        Args:
+            payload: JSON response data from server
+
+        Returns:
+            StepResult with CodeReviewObservation
+        """
+        obs_data = payload.get("observation", {})
+        observation = CodeReviewObservation(
+            echoed_message=obs_data.get("echoed_message", ""),
+            message_length=obs_data.get("message_length", 0),
+            done=payload.get("done", False),
+            reward=payload.get("reward"),
+            metadata=obs_data.get("metadata", {}),
+        )
+
+        return StepResult(
+            observation=observation,
+            reward=payload.get("reward"),
+            done=payload.get("done", False),
+        )
+
+    def _parse_state(self, payload: Dict) -> State:
+        """
+        Parse server response into State object.
+
+        Args:
+            payload: JSON response from state request
+
+        Returns:
+            State object with episode_id and step_count
+        """
+        return State(
+            episode_id=payload.get("episode_id"),
+            step_count=payload.get("step_count", 0),
+        )

models.py

@@ -0,0 +1,44 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""
+Data models for the Code Review Environment.
+Agent receives Python code snippets and must identify bugs.
+"""
+
+from __future__ import annotations
+from typing import Optional
+from openenv.core.env_server.interfaces import Action, Observation, State
+
+
+class ReviewAction(Action):
+    """Action taken by the agent to review a code snippet."""
+    review: str                    # agent's written analysis
+    bug_type: str                  # "syntax" | "logic" | "security" | "none"
+    line_number: int               # which line has the issue, -1 if unknown
+    confidence: float              # agent's confidence 0.0-1.0
+
+
+class ReviewObservation(Observation):
+    """What the agent sees at each step."""
+    code_snippet: str              # the Python code to review
+    task_description: str          # what the agent is asked to do
+    task_id: str                   # "easy" | "medium" | "hard"
+    attempt_number: int            # how many steps taken so far
+    previous_feedback: str         # feedback from last step, empty on reset
+    done: bool                     # whether episode is complete
+
+
+class ReviewState(State):
+    """Internal environment state."""
+    current_task_id: str = "easy"
+    current_snippet: str = ""
+    correct_bug_type: str = ""
+    correct_line_number: int = -1
+    correct_keywords: list = []
+    step_count: int = 0
+    task_episode_id: str = ""
+    cumulative_reward: float = 0.0

openenv.yaml

@@ -0,0 +1,7 @@
+spec_version: 1
+name: code_review_env
+type: space
+runtime: fastapi
+app: server.app:app
+port: 8000
+

openenv_code_review_env.egg-info/PKG-INFO

@@ -0,0 +1,9 @@
+Metadata-Version: 2.4
+Name: openenv-code_review_env
+Version: 0.1.0
+Summary: Code Review Env environment for OpenEnv
+Requires-Python: >=3.10
+Requires-Dist: openenv-core[core]>=0.2.2
+Provides-Extra: dev
+Requires-Dist: pytest>=8.0.0; extra == "dev"
+Requires-Dist: pytest-cov>=4.0.0; extra == "dev"

openenv_code_review_env.egg-info/SOURCES.txt

@@ -0,0 +1,14 @@
+README.md
+pyproject.toml
+./__init__.py
+./client.py
+./models.py
+openenv_code_review_env.egg-info/PKG-INFO
+openenv_code_review_env.egg-info/SOURCES.txt
+openenv_code_review_env.egg-info/dependency_links.txt
+openenv_code_review_env.egg-info/entry_points.txt
+openenv_code_review_env.egg-info/requires.txt
+openenv_code_review_env.egg-info/top_level.txt
+server/__init__.py
+server/app.py
+server/code_review_env_environment.py

openenv_code_review_env.egg-info/dependency_links.txt

@@ -0,0 +1 @@
+

openenv_code_review_env.egg-info/entry_points.txt

@@ -0,0 +1,2 @@
+[console_scripts]
+server = code_review_env.server.app:main

openenv_code_review_env.egg-info/requires.txt

@@ -0,0 +1,5 @@
+openenv-core[core]>=0.2.2
+
+[dev]
+pytest>=8.0.0
+pytest-cov>=4.0.0

openenv_code_review_env.egg-info/top_level.txt

@@ -0,0 +1 @@
+code_review_env

pyproject.toml

@@ -0,0 +1,45 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+[build-system]
+requires = ["setuptools>=45", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "openenv-code_review_env"
+version = "0.1.0"
+description = "Code Review Env environment for OpenEnv"
+requires-python = ">=3.10"
+dependencies = [
+    # Core OpenEnv runtime (provides FastAPI server + HTTP client types)
+    # install from github
+    # "openenv-core[core] @ git+https://github.com/meta-pytorch/OpenEnv.git",
+    "openenv-core[core]>=0.2.2",
+    # Environment-specific dependencies
+    # Add all dependencies needed for your environment here
+    # Examples:
+    # "numpy>=1.19.0",
+    # "torch>=2.0.0",
+    # "gymnasium>=0.29.0",
+    # "openspiel>=1.0.0",
+    # "smolagents>=1.22.0,<2",
+]
+
+[project.optional-dependencies]
+dev = [
+    "pytest>=8.0.0",
+    "pytest-cov>=4.0.0",
+]
+
+[project.scripts]
+# Server entry point - enables running via: uv run --project . server
+# or: python -m code_review_env.server.app
+server = "code_review_env.server.app:main"
+
+[tool.setuptools]
+include-package-data = true
+packages = ["code_review_env", "code_review_env.server"]
+package-dir = { "code_review_env" = ".", "code_review_env.server" = "server" }

server/__init__.py

@@ -0,0 +1,11 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""Code Review Env environment server components."""
+
+from .code_review_env_environment import CodeReviewEnvironment
+
+__all__ = ["CodeReviewEnvironment"]

server/app.py

@@ -0,0 +1,150 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""
+FastAPI server for the Code Review Environment.
+"""
+
+from models import ReviewAction, ReviewObservation
+from server.code_review_env_environment import CodeReviewEnvironment
+from openenv.core.env_server import create_app
+from fastapi import FastAPI, Query
+from fastapi.routing import APIRouter
+
+app = create_app(
+    CodeReviewEnvironment,
+    ReviewAction,
+    ReviewObservation,
+    env_name="code_review_env",
+)
+
+@app.get("/tasks")
+def list_tasks():
+    return {
+        "tasks": [
+            {
+                "task_id": "easy",
+                "description": "Identify syntax/runtime errors in Python code",
+                "difficulty": "easy",
+                "action_schema": {
+                    "review": "string - your analysis",
+                    "bug_type": "string - syntax | logic | security | none",
+                    "line_number": "int - line with the bug, -1 if unknown",
+                    "confidence": "float - your confidence 0.0 to 1.0"
+                }
+            },
+            {
+                "task_id": "medium",
+                "description": "Identify logic bugs in code that runs but produces wrong output",
+                "difficulty": "medium",
+                "action_schema": {
+                    "review": "string - your analysis",
+                    "bug_type": "string - syntax | logic | security | none",
+                    "line_number": "int - line with the bug, -1 if unknown",
+                    "confidence": "float - your confidence 0.0 to 1.0"
+                }
+            },
+            {
+                "task_id": "hard",
+                "description": "Identify security vulnerabilities in Python code",
+                "difficulty": "hard",
+                "action_schema": {
+                    "review": "string - your analysis",
+                    "bug_type": "string - syntax | logic | security | none",
+                    "line_number": "int - line with the bug, -1 if unknown",
+                    "confidence": "float - your confidence 0.0 to 1.0"
+                }
+            }
+        ]
+    }
+
+@app.get("/grader")
+def grader(task_id: str = Query("easy"), episode_id: str = Query(None)):
+    """
+    Run a single task with a perfect answer.
+    Query params: task_id (str), episode_id (str, optional)
+    Returns: {"task_id": str, "score": float, "feedback": str}
+    """
+    env = CodeReviewEnvironment()
+    env.reset(task_id)
+    
+    # Create perfect answer based on task_id
+    if task_id == "easy":
+        action = ReviewAction(
+            review="Line 1 is missing a colon after the function definition. This is a syntax error.",
+            bug_type="syntax",
+            line_number=1,
+            confidence=0.95
+        )
+    elif task_id == "medium":
+        action = ReviewAction(
+            review="Line 5 has an index error: it should be max_val = numbers[i], not numbers[i - 1]. This is a logic bug.",
+            bug_type="logic",
+            line_number=5,
+            confidence=0.95
+        )
+    else:  # hard
+        action = ReviewAction(
+            review="Line 6 has a SQL injection vulnerability because the username is concatenated directly into the query without parameterized statements.",
+            bug_type="security",
+            line_number=6,
+            confidence=0.95
+        )
+    
+    obs = env.step(action)
+    return {
+        "task_id": task_id,
+        "score": env.state.cumulative_reward,
+        "feedback": obs.previous_feedback
+    }
+
+@app.get("/baseline")
+def baseline():
+    """
+    Run all 3 tasks (easy, medium, hard) with perfect hardcoded answers.
+    Returns: {"scores": {"easy": float, "medium": float, "hard": float}, "average": float}
+    """
+    scores = {}
+    
+    for task_id in ["easy", "medium", "hard"]:
+        env = CodeReviewEnvironment()
+        env.reset(task_id)
+        
+        # Create perfect answer based on task_id
+        if task_id == "easy":
+            action = ReviewAction(
+                review="Line 1 is missing a colon after the function definition. This is a syntax error.",
+                bug_type="syntax",
+                line_number=1,
+                confidence=0.95
+            )
+        elif task_id == "medium":
+            action = ReviewAction(
+                review="Line 5 has an index error: it should be max_val = numbers[i], not numbers[i - 1]. This is a logic bug.",
+                bug_type="logic",
+                line_number=5,
+                confidence=0.95
+            )
+        else:  # hard
+            action = ReviewAction(
+                review="Line 6 has a SQL injection vulnerability because the username is concatenated directly into the query without parameterized statements.",
+                bug_type="security",
+                line_number=6,
+                confidence=0.95
+            )
+        
+        obs = env.step(action)
+        scores[task_id] = env.state.cumulative_reward
+    
+    average = sum(scores.values()) / len(scores)
+    return {
+        "scores": scores,
+        "average": round(average, 4)
+    }
+
+if __name__ == "__main__":
+    import uvicorn
+    uvicorn.run(app, host="0.0.0.0", port=8000)

server/code_review_env_environment.py

@@ -0,0 +1,201 @@
+# Copyright (c) Meta Platforms, Inc. and affiliates.
+# All rights reserved.
+#
+# This source code is licensed under the BSD-style license found in the
+# LICENSE file in the root directory of this source tree.
+
+"""
+Code Review Environment — agent finds bugs in Python snippets.
+3 tasks: syntax errors (easy) → logic bugs (medium) → security vulns (hard).
+"""
+
+from __future__ import annotations
+import uuid
+from openenv.core.env_server.interfaces import Environment, Action, Observation
+from models import ReviewAction, ReviewObservation, ReviewState
+# ── Task bank ────────────────────────────────────────────────────────────────
+
+TASKS = {
+    "easy": {
+        "description": (
+            "Review the following Python code and identify any syntax or "
+            "runtime errors. Specify the bug type, the line number where "
+            "the error occurs, and explain what is wrong."
+        ),
+        "snippet": """\
+def calculate_average(numbers)
+    total = 0
+    for num in numbers:
+        total += num
+    return total / len(numbers)
+
+result = calculate_average([10, 20, 30])
+print(result)
+""",
+        "correct_bug_type": "syntax",
+        "correct_line_number": 1,
+        "correct_keywords": ["colon", "missing", "def", "syntax"],
+    },
+    "medium": {
+        "description": (
+            "Review the following Python code. It runs without crashing "
+            "but produces incorrect output. Identify the logic bug, "
+            "the line number, and explain why it is wrong."
+        ),
+        "snippet": """\
+def find_max(numbers):
+    max_val = numbers[0]
+    for i in range(len(numbers)):
+        if numbers[i] > max_val:
+            max_val = numbers[i - 1]
+    return max_val
+
+print(find_max([3, 7, 2, 9, 4]))
+""",
+        "correct_bug_type": "logic",
+        "correct_line_number": 5,
+        "correct_keywords": ["index", "i - 1", "off by one", "wrong", "logic"],
+    },
+    "hard": {
+        "description": (
+            "Review the following Python code for security vulnerabilities. "
+            "Identify the vulnerability type, the line number, and explain "
+            "the security risk it introduces."
+        ),
+        "snippet": """\
+import sqlite3
+
+def get_user(username):
+    conn = sqlite3.connect('users.db')
+    cursor = conn.cursor()
+    query = "SELECT * FROM users WHERE username = '" + username + "'"
+    cursor.execute(query)
+    return cursor.fetchone()
+
+user_input = input("Enter username: ")
+print(get_user(user_input))
+""",
+        "correct_bug_type": "security",
+        "correct_line_number": 6,
+        "correct_keywords": ["sql injection", "injection", "concatenat", "unsanitized", "parameterized"],
+    },
+}
+
+MAX_STEPS = 3
+
+# ── Reward function ───────────────────────────────────────────────────────────
+
+def compute_reward(action: ReviewAction, task: dict, attempt: int) -> tuple[float, str]:
+    """
+    Partial progress reward — not binary.
+    Returns (reward_float, feedback_string).
+    """
+    reward = 0.0
+    feedback_parts = []
+
+    # Bug type match (+1.0)
+    if action.bug_type.lower() == task["correct_bug_type"]:
+        reward += 1.0
+        feedback_parts.append("✓ Correct bug type identified.")
+    else:
+        reward -= 0.3
+        feedback_parts.append(
+            f"✗ Wrong bug type. Got '{action.bug_type}', "
+            f"expected '{task['correct_bug_type']}'."
+        )
+
+    # Line number match (+0.5)
+    if action.line_number == task["correct_line_number"]:
+        reward += 0.5
+        feedback_parts.append("✓ Correct line number.")
+    else:
+        feedback_parts.append(
+            f"✗ Wrong line number. Got {action.line_number}, "
+            f"expected {task['correct_line_number']}."
+        )
+
+    # Keyword quality check (+0.5)
+    review_lower = action.review.lower()
+    matched_keywords = [
+        kw for kw in task["correct_keywords"] if kw in review_lower
+    ]
+    if matched_keywords:
+        reward += 0.5
+        feedback_parts.append(f"✓ Good explanation (matched: {matched_keywords}).")
+    else:
+        feedback_parts.append("✗ Explanation missing key concepts.")
+
+    # Retry penalty
+    if attempt > 1:
+        penalty = 0.1 * (attempt - 1)
+        reward -= penalty
+        feedback_parts.append(f"⚠ Retry penalty: -{penalty:.1f}")
+
+    # Clamp to 0.0-1.0 (max raw = 2.0, normalize)
+    normalized = max(0.0, min(1.0, reward / 2.0))
+    return round(normalized, 4), " ".join(feedback_parts)
+
+
+# ── Environment ───────────────────────────────────────────────────────────────
+
+class CodeReviewEnvironment(Environment):
+    """
+    Code Review Environment.
+    Agent reviews Python snippets across 3 difficulty tasks.
+    """
+
+    def __init__(self):
+        self._state = ReviewState()
+
+    def reset(self, task_id: str = "easy") -> Observation:
+        if task_id not in TASKS:
+            task_id = "easy"
+        task = TASKS[task_id]
+        self._state = ReviewState(
+            current_task_id=task_id,
+            current_snippet=task["snippet"],
+            correct_bug_type=task["correct_bug_type"],
+            correct_line_number=task["correct_line_number"],
+            correct_keywords=task["correct_keywords"],
+            step_count=0,
+            task_episode_id=str(uuid.uuid4()),
+            cumulative_reward=0.0,
+        )
+        return ReviewObservation(
+            code_snippet=task["snippet"],
+            task_description=task["description"],
+            task_id=task_id,
+            attempt_number=0,
+            previous_feedback="",
+            done=False,
+        )
+
+    def step(self, action: Action) -> Observation:
+        if not isinstance(action, ReviewAction):
+            raise ValueError(f"Expected ReviewAction, got {type(action)}")
+
+        self._state.step_count += 1
+        task = TASKS[self._state.current_task_id]
+
+        reward, feedback = compute_reward(
+            action, task, self._state.step_count
+        )
+        self._state.cumulative_reward += reward
+
+        done = (
+            reward >= 0.75  # good enough answer
+            or self._state.step_count >= MAX_STEPS
+        )
+
+        return ReviewObservation(
+            code_snippet=self._state.current_snippet,
+            task_description=task["description"],
+            task_id=self._state.current_task_id,
+            attempt_number=self._state.step_count,
+            previous_feedback=feedback,
+            done=done,
+        )
+
+    @property
+    def state(self) -> ReviewState:
+        return self._state

server/requirements.txt

@@ -0,0 +1,9 @@
+openenv-core>=0.2.3
+fastapi
+uvicorn
+pydantic
+openai
+python-dotenv
+
+
+