Initial Commit + reset() endpoint

.gitignore

@@ -0,0 +1,28 @@
+# Python / Environment
+.venv/
+__pycache__/
+*.pyc
+
+# Environment Variables / Keys
+.env
+.env.*
+!.env.example
+
+
+# Logging / Tracking Results
+tracking/results.csv
+
+# IDEs
+.vscode/
+.idea/
+openenv_earnings_analyst.egg-info/
+
+# Agents
+.agents/
+.cursor/
+
+.DS_Store
+
+# Huggingface spaces doesn't allow pdfs anywhere in git history
+*.pdf
+*.parquet

.python-version

@@ -0,0 +1 @@
+3.12

README.md

@@ -0,0 +1,255 @@
+---
+title: Earnings Analyst Environment Server
+emoji: 🏑
+colorFrom: pink
+colorTo: pink
+sdk: docker
+pinned: false
+app_port: 8000
+base_path: /web
+tags:
+  - openenv
+---
+
+# Earnings Analyst 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 Earnings Analyst environment is through the `EarningsAnalystEnv` class:
+
+```python
+from earnings_analyst import EarningsAnalystAction, EarningsAnalystEnv
+
+try:
+    # Create environment from Docker image
+    earnings_analystenv = EarningsAnalystEnv.from_docker_image("earnings_analyst-env:latest")
+
+    # Reset
+    result = earnings_analystenv.reset()
+    print(f"Reset: {result.observation.echoed_message}")
+
+    # Send multiple messages
+    messages = ["Hello, World!", "Testing echo", "Final message"]
+
+    for msg in messages:
+        result = earnings_analystenv.step(EarningsAnalystAction(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
+    earnings_analystenv.close()
+```
+
+That's it! The `EarningsAnalystEnv.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 earnings_analyst-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
+**EarningsAnalystAction**: Contains a single field
+- `message` (str) - The message to echo back
+
+### Observation
+**EarningsAnalystObservation**: 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 Earnings Analyst environment server running, you can connect directly:
+
+```python
+from earnings_analyst import EarningsAnalystEnv
+
+# Connect to existing server
+earnings_analystenv = EarningsAnalystEnv(base_url="<ENV_HTTP_URL_HERE>")
+
+# Use as normal
+result = earnings_analystenv.reset()
+result = earnings_analystenv.step(EarningsAnalystAction(message="Hello!"))
+```
+
+Note: When connecting to an existing server, `earnings_analystenv.close()` will NOT stop the server.
+
+### Using the Context Manager
+
+The client supports context manager usage for automatic connection management:
+
+```python
+from earnings_analyst import EarningsAnalystAction, EarningsAnalystEnv
+
+# Connect with context manager (auto-connects and closes)
+with EarningsAnalystEnv(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(EarningsAnalystAction(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(
+    EarningsAnalystEnvironment,  # Pass class, not instance
+    EarningsAnalystAction,
+    EarningsAnalystObservation,
+    max_concurrent_envs=4,  # Allow 4 concurrent sessions
+)
+```
+
+Then multiple clients can connect simultaneously:
+
+```python
+from earnings_analyst import EarningsAnalystAction, EarningsAnalystEnv
+from concurrent.futures import ThreadPoolExecutor
+
+def run_episode(client_id: int):
+    with EarningsAnalystEnv(base_url="http://localhost:8000") as env:
+        result = env.reset()
+        for i in range(10):
+            result = env.step(EarningsAnalystAction(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/earnings_analyst_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
+
+```
+earnings_analyst/
+├── .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              # EarningsAnalystEnv client
+├── models.py              # Action and Observation models
+└── server/
+    ├── __init__.py        # Server module exports
+    ├── earnings_analyst_environment.py  # Core environment logic
+    ├── app.py             # FastAPI application (HTTP + WebSocket endpoints)
+    └── Dockerfile         # Container image definition
+```

__init__.py

@@ -0,0 +1,10 @@
+"""Earnings Analyst Environment."""
+
+from .client import EarningsAnalystEnv
+from .models import EarningsAnalystAction, EarningsAnalystObservation
+
+__all__ = [
+    "EarningsAnalystAction",
+    "EarningsAnalystObservation",
+    "EarningsAnalystEnv",
+]

client.py

@@ -0,0 +1,94 @@
+"""Earnings Analyst 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 EarningsAnalystAction, EarningsAnalystObservation
+
+
+class EarningsAnalystEnv(
+    EnvClient[EarningsAnalystAction, EarningsAnalystObservation, State]
+):
+    """
+    Client for the Earnings Analyst 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 EarningsAnalystEnv(base_url="http://localhost:8000") as client:
+        ...     result = client.reset()
+        ...     print(result.observation.task_instruction)
+        ...
+        ...     result = client.step(EarningsAnalystAction(sentiment="neutral"))
+        ...     print(result.observation.metadata)
+
+    Example with Docker:
+        >>> # Automatically start container and connect
+        >>> client = EarningsAnalystEnv.from_docker_image("earnings_analyst-env:latest")
+        >>> try:
+        ...     result = client.reset()
+        ...     result = client.step(EarningsAnalystAction(sentiment="neutral"))
+        ... finally:
+        ...     client.close()
+    """
+
+    def _step_payload(self, action: EarningsAnalystAction) -> Dict:
+        """
+        Convert EarningsAnalystAction to JSON payload for step message.
+
+        Args:
+            action: EarningsAnalystAction instance
+
+        Returns:
+            Dictionary representation suitable for JSON encoding
+        """
+        return {
+            "sentiment": action.sentiment,
+        }
+
+    def _parse_result(self, payload: Dict) -> StepResult[EarningsAnalystObservation]:
+        """
+        Parse server response into StepResult[EarningsAnalystObservation].
+
+        Args:
+            payload: JSON response data from server
+
+        Returns:
+            StepResult with EarningsAnalystObservation
+        """
+        obs_data = payload.get("observation", {})
+        observation = EarningsAnalystObservation(
+            text_context=obs_data.get("text_context") or {},
+            numerical_context=obs_data.get("numerical_context") or {},
+            task_instruction=obs_data.get("task_instruction", ""),
+            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),
+        )

environment_config.py

@@ -0,0 +1,42 @@
+"""
+Central configuration for all earnings analyst tasks.
+
+Plain data only — no imports from env or dataset loader. Add new tasks here.
+"""
+
+DATASET_ID = "RudrakshNanavaty/earnings-call-data"
+DATASET_FILE = "episodes.parquet"
+
+TASKS = {
+    "sentiment_v1": {
+        "text_cols": [
+            "earnings_transcript",
+            "press_release_8k_body",
+            "press_release_ex991",
+            "press_release_ex992",
+        ],
+        "numerical_cols": [
+            "price_momentum_30d",
+            "price_momentum_90d",
+            "pct_from_52w_high_pt",
+            "avg_volume_20d",
+            "d_minus_1_close",
+        ],
+        "label_col": "sentiment_label",
+        "label_values": [
+            "very bearish",
+            "bearish",
+            "neutral",
+            "bullish",
+            "very bullish",
+        ],
+        "task_instruction": (
+            "Analyse the provided earnings call materials and classify the overall market sentiment.\n\n"
+            "Return a JSON object matching this exact schema:\n"
+            '{"sentiment": "<one of: very bearish | bearish | neutral | bullish | very bullish>"}\n\n'
+            "Do not include any other keys or explanation."
+        ),
+    },
+}
+
+DEFAULT_TASK = "sentiment_v1"

main.py

@@ -0,0 +1,6 @@
+def main():
+    print("Hello from earnings-analyst!")
+
+
+if __name__ == "__main__":
+    main()

models.py

@@ -0,0 +1,34 @@
+"""
+Data models for the Earnings Analyst Environment.
+"""
+
+from openenv.core.env_server.types import Action, Observation
+from pydantic import Field
+
+
+class EarningsAnalystAction(Action):
+    """Action for sentiment classification (and future tasks)."""
+
+    sentiment: str = Field(
+        ...,
+        description=(
+            "Predicted sentiment: one of very bearish, bearish, neutral, bullish, very bullish"
+        ),
+    )
+
+
+class EarningsAnalystObservation(Observation):
+    """Observation bundle: text context, numerical context, and task instruction."""
+
+    text_context: dict[str, str] = Field(
+        default_factory=dict,
+        description="Non-null text fields for the active task (column name -> text)",
+    )
+    numerical_context: dict[str, float] = Field(
+        default_factory=dict,
+        description="Market / numerical features for the active task (column name -> value)",
+    )
+    task_instruction: str = Field(
+        default="",
+        description="Natural language instruction and JSON schema for the agent",
+    )

openenv.yaml

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

pyproject.toml

@@ -0,0 +1,38 @@
+[build-system]
+requires = ["setuptools>=45", "wheel"]
+build-backend = "setuptools.build_meta"
+
+[project]
+name = "openenv-earnings_analyst"
+version = "0.1.0"
+description = "Earnings Analyst environment for OpenEnv"
+requires-python = ">=3.12"
+dependencies = [
+    "datasets>=4.8.4",
+    # Core OpenEnv runtime (provides FastAPI server + HTTP client types)
+    # install from github
+    # "openenv-core[core] @ git+https://github.com/meta-pytorch/OpenEnv.git",
+    "huggingface-hub>=1.10.1",
+    "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 earnings_analyst.server.app
+server = "earnings_analyst.server.app:main"
+
+[tool.setuptools]
+include-package-data = true
+packages = ["earnings_analyst", "earnings_analyst.server"]
+package-dir = { "earnings_analyst" = ".", "earnings_analyst.server" = "server" }

server/Dockerfile

@@ -0,0 +1,74 @@
+# 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=earnings_analyst
+
+# 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
+CMD ["sh", "-c", "cd /app/env && uvicorn server.app:app --host 0.0.0.0 --port 8000"]

server/__init__.py

@@ -0,0 +1,5 @@
+"""Earnings Analyst environment server components."""
+
+from .earnings_analyst_environment import EarningsAnalystEnvironment
+
+__all__ = ["EarningsAnalystEnvironment"]

server/app.py

@@ -0,0 +1,78 @@
+"""
+FastAPI application for the Earnings Analyst Environment.
+
+This module creates an HTTP server that exposes the EarningsAnalystEnvironment
+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
+
+try:
+    from ..models import EarningsAnalystAction, EarningsAnalystObservation
+    from .earnings_analyst_environment import EarningsAnalystEnvironment
+except ModuleNotFoundError:
+    from models import EarningsAnalystAction, EarningsAnalystObservation
+    from server.earnings_analyst_environment import EarningsAnalystEnvironment
+
+
+# Create the app with web interface and README integration
+app = create_app(
+    EarningsAnalystEnvironment,
+    EarningsAnalystAction,
+    EarningsAnalystObservation,
+    env_name="earnings_analyst",
+    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 earnings_analyst.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 earnings_analyst.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/dataset_loader.py

@@ -0,0 +1,20 @@
+"""
+Load the Hugging Face dataset once as a module-level singleton.
+
+No task-specific column lists — see environment_config.TASKS for that.
+"""
+
+from datasets import load_dataset
+
+try:
+    from ..environment_config import DATASET_FILE, DATASET_ID
+except ImportError:
+    from environment_config import DATASET_FILE, DATASET_ID
+
+# Loaded once on first import; all resets share this object.
+# Pin Hub parquet so we never pick up features.parquet / raw_*.parquet from the same repo.
+dataset = load_dataset(
+    DATASET_ID,
+    data_files={"train": DATASET_FILE},
+    split="train",
+)

server/earnings_analyst_environment.py

@@ -0,0 +1,117 @@
+"""
+Earnings Analyst Environment Implementation.
+
+Samples rows from the Hugging Face earnings-call dataset and exposes task-specific
+observations from environment_config.TASKS.
+"""
+
+from __future__ import annotations
+
+import math
+import random
+from typing import Any
+from uuid import uuid4
+
+from openenv.core.env_server.interfaces import Environment
+from openenv.core.env_server.types import State
+
+try:
+    from ..environment_config import DEFAULT_TASK, TASKS
+    from ..models import EarningsAnalystAction, EarningsAnalystObservation
+except ImportError:
+    from environment_config import DEFAULT_TASK, TASKS
+    from models import EarningsAnalystAction, EarningsAnalystObservation
+
+try:
+    from .dataset_loader import dataset
+except ImportError:
+    from server.dataset_loader import dataset
+
+
+def _non_empty_text(value: Any) -> bool:
+    if value is None:
+        return False
+    s = str(value).strip()
+    return bool(s)
+
+
+def _finite_float(value: Any) -> float | None:
+    if value is None:
+        return None
+    try:
+        x = float(value)
+    except (TypeError, ValueError):
+        return None
+    if isinstance(x, float) and math.isnan(x):
+        return None
+    return x
+
+
+class EarningsAnalystEnvironment(Environment):
+    """
+    RL environment over earnings-call rows: reset samples a row and returns
+    text_context, numerical_context, and task_instruction per the active task.
+    """
+
+    SUPPORTS_CONCURRENT_SESSIONS: bool = True
+
+    def __init__(self, task_id: str = DEFAULT_TASK) -> None:
+        if task_id not in TASKS:
+            raise KeyError(
+                f"Unknown task_id={task_id!r}. Valid: {sorted(TASKS.keys())}"
+            )
+        self._cfg = TASKS[task_id]
+        self._state = State(episode_id=str(uuid4()), step_count=0)
+        self._current_row: dict[str, Any] | None = None
+
+    def reset(self) -> EarningsAnalystObservation:
+        """Sample one dataset row and return the agent-visible observation bundle."""
+        self._state = State(episode_id=str(uuid4()), step_count=0)
+        idx = random.randrange(len(dataset))
+        row = dataset[idx]
+        # Normalize to a plain dict for grading and column access
+        self._current_row = dict(row)
+
+        text_context = {
+            col: str(self._current_row[col]).strip()
+            for col in self._cfg["text_cols"]
+            if _non_empty_text(self._current_row.get(col))
+        }
+        numerical_context: dict[str, float] = {}
+        for col in self._cfg["numerical_cols"]:
+            v = _finite_float(self._current_row.get(col))
+            if v is not None:
+                numerical_context[col] = v
+
+        return EarningsAnalystObservation(
+            text_context=text_context,
+            numerical_context=numerical_context,
+            task_instruction=self._cfg["task_instruction"],
+            done=False,
+            reward=0.0,
+        )
+
+    def step(self, action: EarningsAnalystAction) -> EarningsAnalystObservation:  # type: ignore[override]
+        """
+        Execute one step (stub). Scoring against ``sentiment_label`` is a follow-up.
+
+        Args:
+            action: Agent action with predicted ``sentiment``.
+
+        Returns:
+            Terminal observation placeholder; reward grading not implemented yet.
+        """
+        self._state.step_count += 1
+        return EarningsAnalystObservation(
+            text_context={},
+            numerical_context={},
+            task_instruction=self._cfg["task_instruction"],
+            done=True,
+            reward=0.0,
+            metadata={"predicted_sentiment": action.sentiment},
+        )
+
+    @property
+    def state(self) -> State:
+        """Current environment state."""
+        return self._state

server/requirements.txt

@@ -0,0 +1,8 @@
+openenv[core]>=0.2.0
+fastapi>=0.115.0
+uvicorn>=0.24.0
+datasets>=3.0.0
+huggingface-hub>=0.24.0
+
+
+