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=sequence_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: Cognitive Primitives Sequence
-emoji: 🦀
-colorFrom: gray
-colorTo: yellow
+title: Sequence Env Environment Server
+emoji: 🎾
+colorFrom: yellow
+colorTo: red
 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
+# Sequence 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 Sequence Env environment is through the `SequenceEnv` class:
+
+```python
+from sequence_env import SequenceAction, SequenceEnv
+
+try:
+    # Create environment from Docker image
+    sequence_envenv = SequenceEnv.from_docker_image("sequence_env-env:latest")
+
+    # Reset
+    result = sequence_envenv.reset()
+    print(f"Reset: {result.observation.echoed_message}")
+
+    # Send multiple messages
+    messages = ["Hello, World!", "Testing echo", "Final message"]
+
+    for msg in messages:
+        result = sequence_envenv.step(SequenceAction(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
+    sequence_envenv.close()
+```
+
+That's it! The `SequenceEnv.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 sequence_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
+**SequenceAction**: Contains a single field
+- `message` (str) - The message to echo back
+
+### Observation
+**SequenceObservation**: 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 Sequence Env environment server running, you can connect directly:
+
+```python
+from sequence_env import SequenceEnv
+
+# Connect to existing server
+sequence_envenv = SequenceEnv(base_url="<ENV_HTTP_URL_HERE>")
+
+# Use as normal
+result = sequence_envenv.reset()
+result = sequence_envenv.step(SequenceAction(message="Hello!"))
+```
+
+Note: When connecting to an existing server, `sequence_envenv.close()` will NOT stop the server.
+
+### Using the Context Manager
+
+The client supports context manager usage for automatic connection management:
+
+```python
+from sequence_env import SequenceAction, SequenceEnv
+
+# Connect with context manager (auto-connects and closes)
+with SequenceEnv(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(SequenceAction(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(
+    SequenceEnvironment,  # Pass class, not instance
+    SequenceAction,
+    SequenceObservation,
+    max_concurrent_envs=4,  # Allow 4 concurrent sessions
+)
+```
+
+Then multiple clients can connect simultaneously:
+
+```python
+from sequence_env import SequenceAction, SequenceEnv
+from concurrent.futures import ThreadPoolExecutor
+
+def run_episode(client_id: int):
+    with SequenceEnv(base_url="http://localhost:8000") as env:
+        result = env.reset()
+        for i in range(10):
+            result = env.step(SequenceAction(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/sequence_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
+
+```
+sequence_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              # SequenceEnv client
+├── models.py              # Action and Observation models
+└── server/
+    ├── __init__.py        # Server module exports
+    ├── sequence_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.
+
+"""Sequence Env Environment."""
+
+from .client import SequenceEnv
+from .models import SequenceAction, SequenceObservation
+
+__all__ = [
+    "SequenceAction",
+    "SequenceObservation",
+    "SequenceEnv",
+]

client.py

@@ -0,0 +1,57 @@
+# 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.
+
+"""Sequence 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 SequenceAction, SequenceObservation
+
+
+class SequenceEnv(EnvClient[SequenceAction, SequenceObservation]):
+    """
+    Client for the Sequence Environment.
+
+    Pattern recognition with 8 rounds of increasing difficulty.
+    """
+
+    def _step_payload(self, action: SequenceAction) -> Dict:
+        """Convert SequenceAction to JSON payload for step message."""
+        return {
+            "answer": action.answer,
+        }
+
+    def _parse_result(self, payload: Dict) -> StepResult[SequenceObservation]:
+        """Parse server response into StepResult[SequenceObservation]."""
+        obs_data = payload.get("observation", {})
+        observation = SequenceObservation(
+            sequence=obs_data.get("sequence", []),
+            round=obs_data.get("round", 0),
+            total_rounds=obs_data.get("total_rounds", 8),
+            correct=obs_data.get("correct"),
+            score=obs_data.get("score", 0),
+            choices=obs_data.get("choices", []),
+            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."""
+        return State(
+            episode_id=payload.get("episode_id"),
+            step_count=payload.get("step_count", 0),
+        )

models.py

@@ -0,0 +1,33 @@
+# 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 Sequence Environment.
+
+Pattern recognition: show 5 numbers following a rule, agent predicts the 6th.
+"""
+
+from typing import List, Optional
+
+from openenv.core.env_server.types import Action, Observation
+from pydantic import Field
+
+
+class SequenceAction(Action):
+    """Action for the Sequence environment - predict the next number."""
+
+    answer: int = Field(..., description="The predicted next number in the sequence")
+
+
+class SequenceObservation(Observation):
+    """Observation from the Sequence environment."""
+
+    sequence: List[int] = Field(default_factory=list, description="The 5 visible numbers")
+    round: int = Field(default=0, description="Current round number (1-8)")
+    total_rounds: int = Field(default=8, description="Total number of rounds")
+    correct: Optional[bool] = Field(default=None, description="Whether the last answer was correct")
+    score: int = Field(default=0, description="Number of correct answers so far")
+    choices: List[int] = Field(default_factory=list, description="4 possible answers including correct one")

openenv.yaml

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

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-sequence_env"
+version = "0.1.0"
+description = "Sequence 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]>=0.2.1",
+    # 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 sequence_env.server.app
+server = "sequence_env.server.app:main"
+
+[tool.setuptools]
+include-package-data = true
+packages = ["sequence_env", "sequence_env.server"]
+package-dir = { "sequence_env" = ".", "sequence_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.
+
+"""Sequence Env environment server components."""
+
+from .sequence_env_environment import SequenceEnvironment
+
+__all__ = ["SequenceEnvironment"]

server/app.py

@@ -0,0 +1,82 @@
+# 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 application for the Sequence Env Environment.
+
+This module creates an HTTP server that exposes the SequenceEnvironment
+over HTTP and WebSocket endpoints, compatible with EnvClient.
+
+Endpoints:
+    - POST /reset: Reset the environment
+    - POST /step: Execute an action
+    - GET /state: Get current environment state
+    - GET /schema: Get action/observation schemas
+    - WS /ws: WebSocket endpoint for persistent sessions
+
+Usage:
+    # Development (with auto-reload):
+    uvicorn server.app:app --reload --host 0.0.0.0 --port 8000
+
+    # Production:
+    uvicorn server.app:app --host 0.0.0.0 --port 8000 --workers 4
+
+    # Or run directly:
+    python -m server.app
+"""
+
+try:
+    from openenv.core.env_server.http_server import create_app
+except Exception as e:  # pragma: no cover
+    raise ImportError(
+        "openenv is required for the web interface. Install dependencies with '\n    uv sync\n'"
+    ) from e
+
+# Import from local models.py (PYTHONPATH includes /app/env in Docker)
+from models import SequenceAction, SequenceObservation
+
+from .sequence_env_environment import SequenceEnvironment
+
+
+# Create the app with web interface and README integration
+app = create_app(
+    SequenceEnvironment,
+    SequenceAction,
+    SequenceObservation,
+    env_name="sequence_env",
+    max_concurrent_envs=1,  # increase this number to allow more concurrent WebSocket sessions
+)
+
+
+def main(host: str = "0.0.0.0", port: int = 8000):
+    """
+    Entry point for direct execution via uv run or python -m.
+
+    This function enables running the server without Docker:
+        uv run --project . server
+        uv run --project . server --port 8001
+        python -m sequence_env.server.app
+
+    Args:
+        host: Host address to bind to (default: "0.0.0.0")
+        port: Port number to listen on (default: 8000)
+
+    For production deployments, consider using uvicorn directly with
+    multiple workers:
+        uvicorn sequence_env.server.app:app --workers 4
+    """
+    import uvicorn
+
+    uvicorn.run(app, host=host, port=port)
+
+
+if __name__ == "__main__":
+    import argparse
+
+    parser = argparse.ArgumentParser()
+    parser.add_argument("--port", type=int, default=8000)
+    args = parser.parse_args()
+    main(port=args.port)

server/requirements.txt

@@ -0,0 +1,6 @@
+openenv[core]>=0.2.0
+fastapi>=0.115.0
+uvicorn>=0.24.0
+
+
+

server/sequence_env_environment.py

@@ -0,0 +1,219 @@
+# 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.
+
+"""
+Sequence Environment Implementation.
+
+Pattern recognition with increasing difficulty. Agent sees 5 numbers and
+must predict the 6th based on the underlying rule.
+"""
+
+import random
+from typing import List, Tuple, Callable
+from uuid import uuid4
+
+from models import SequenceAction, SequenceObservation
+from openenv.core.env_server.interfaces import Environment
+from openenv.core.env_server.types import State
+
+
+class SequenceEnvironment(Environment):
+    """
+    Sequence prediction environment with 8 rounds of increasing difficulty.
+
+    Rules by round:
+    1. Addition (constant difference)
+    2. Multiplication (constant ratio)
+    3. Alternating (two interleaved sequences)
+    4. Squares (n^2)
+    5. Fibonacci-like (sum of previous two)
+    6. Triangular numbers
+    7. Interleaved (two rules combined)
+    8. Compound (rule changes at index)
+    """
+
+    SUPPORTS_CONCURRENT_SESSIONS: bool = True
+    TOTAL_ROUNDS = 8
+
+    def __init__(self):
+        """Initialize the sequence environment."""
+        self._state = State(episode_id=str(uuid4()), step_count=0)
+        self._sequences: List[Tuple[List[int], int]] = []
+        self._current_round: int = 0
+        self._score: int = 0
+        self._last_correct: bool | None = None
+
+    def _generate_addition_sequence(self) -> Tuple[List[int], int]:
+        """Round 1: Arithmetic sequence with constant difference."""
+        start = random.randint(1, 20)
+        diff = random.randint(2, 8)
+        seq = [start + i * diff for i in range(6)]
+        return seq[:5], seq[5]
+
+    def _generate_multiplication_sequence(self) -> Tuple[List[int], int]:
+        """Round 2: Geometric sequence with constant ratio."""
+        start = random.randint(1, 5)
+        ratio = random.randint(2, 3)
+        seq = [start * (ratio ** i) for i in range(6)]
+        return seq[:5], seq[5]
+
+    def _generate_alternating_sequence(self) -> Tuple[List[int], int]:
+        """Round 3: Two interleaved arithmetic sequences."""
+        start1 = random.randint(1, 10)
+        start2 = random.randint(11, 20)
+        diff1 = random.randint(2, 5)
+        diff2 = random.randint(2, 5)
+        seq = []
+        for i in range(6):
+            if i % 2 == 0:
+                seq.append(start1 + (i // 2) * diff1)
+            else:
+                seq.append(start2 + (i // 2) * diff2)
+        return seq[:5], seq[5]
+
+    def _generate_squares_sequence(self) -> Tuple[List[int], int]:
+        """Round 4: Perfect squares."""
+        start = random.randint(1, 5)
+        seq = [(start + i) ** 2 for i in range(6)]
+        return seq[:5], seq[5]
+
+    def _generate_fibonacci_sequence(self) -> Tuple[List[int], int]:
+        """Round 5: Fibonacci-like (sum of previous two)."""
+        a = random.randint(1, 5)
+        b = random.randint(2, 7)
+        seq = [a, b]
+        for _ in range(4):
+            seq.append(seq[-1] + seq[-2])
+        return seq[:5], seq[5]
+
+    def _generate_triangular_sequence(self) -> Tuple[List[int], int]:
+        """Round 6: Triangular numbers (n*(n+1)/2)."""
+        offset = random.randint(0, 3)
+        seq = [(n + offset) * (n + offset + 1) // 2 for n in range(1, 7)]
+        return seq[:5], seq[5]
+
+    def _generate_interleaved_sequence(self) -> Tuple[List[int], int]:
+        """Round 7: Evens are squares, odds are doubles."""
+        start_sq = random.randint(1, 4)
+        start_dbl = random.randint(2, 8)
+        seq = []
+        for i in range(6):
+            if i % 2 == 0:
+                seq.append((start_sq + i // 2) ** 2)
+            else:
+                seq.append(start_dbl * (2 ** (i // 2)))
+        return seq[:5], seq[5]
+
+    def _generate_compound_sequence(self) -> Tuple[List[int], int]:
+        """Round 8: First 3 add, last 3 multiply by 2."""
+        start = random.randint(2, 6)
+        diff = random.randint(2, 4)
+        seq = [start, start + diff, start + 2 * diff]
+        for i in range(3):
+            seq.append(seq[-1] * 2)
+        return seq[:5], seq[5]
+
+    def _generate_all_sequences(self):
+        """Generate all 8 sequences for the episode."""
+        generators = [
+            self._generate_addition_sequence,
+            self._generate_multiplication_sequence,
+            self._generate_alternating_sequence,
+            self._generate_squares_sequence,
+            self._generate_fibonacci_sequence,
+            self._generate_triangular_sequence,
+            self._generate_interleaved_sequence,
+            self._generate_compound_sequence,
+        ]
+        self._sequences = [gen() for gen in generators]
+
+    def _generate_choices(self, correct: int) -> List[int]:
+        """Generate 4 choices including the correct answer."""
+        choices = {correct}
+        while len(choices) < 4:
+            offset = random.choice([-3, -2, -1, 1, 2, 3])
+            wrong = correct + offset * random.randint(1, 5)
+            if wrong > 0:
+                choices.add(wrong)
+        result = list(choices)
+        random.shuffle(result)
+        return result
+
+    def reset(self) -> SequenceObservation:
+        """Reset the environment and generate new sequences."""
+        self._state = State(episode_id=str(uuid4()), step_count=0)
+        self._generate_all_sequences()
+        self._current_round = 0
+        self._score = 0
+        self._last_correct = None
+
+        seq, correct_answer = self._sequences[0]
+        choices = self._generate_choices(correct_answer)
+
+        return SequenceObservation(
+            sequence=seq,
+            round=1,
+            total_rounds=self.TOTAL_ROUNDS,
+            correct=None,
+            score=0,
+            choices=choices,
+            done=False,
+            reward=0.0,
+        )
+
+    def step(self, action: SequenceAction) -> SequenceObservation:  # type: ignore[override]
+        """
+        Execute a step by checking the agent's answer.
+
+        Args:
+            action: SequenceAction with the predicted answer
+
+        Returns:
+            SequenceObservation with the next sequence or final results
+        """
+        self._state.step_count += 1
+
+        _, correct_answer = self._sequences[self._current_round]
+        is_correct = action.answer == correct_answer
+        reward = 1.0 if is_correct else 0.0
+
+        if is_correct:
+            self._score += 1
+        self._last_correct = is_correct
+        self._current_round += 1
+
+        done = self._current_round >= self.TOTAL_ROUNDS
+
+        if done:
+            return SequenceObservation(
+                sequence=[],
+                round=self._current_round,
+                total_rounds=self.TOTAL_ROUNDS,
+                correct=is_correct,
+                score=self._score,
+                choices=[],
+                done=True,
+                reward=reward,
+            )
+
+        next_seq, next_correct = self._sequences[self._current_round]
+        choices = self._generate_choices(next_correct)
+
+        return SequenceObservation(
+            sequence=next_seq,
+            round=self._current_round + 1,
+            total_rounds=self.TOTAL_ROUNDS,
+            correct=is_correct,
+            score=self._score,
+            choices=choices,
+            done=False,
+            reward=reward,
+        )
+
+    @property
+    def state(self) -> State:
+        """Get the current environment state."""
+        return self._state